system

Abstract

Provide a system. 【Solution means】 Data processing means for collecting and analyzing fraud method data, Scenario generation means for generating fraud scenarios based on the collected data, Presentation means for interactively presenting the generated fraud scenarios to the user, Response recording means for recording and analyzing interactive user responses, Feedback generation means for generating feedback based on the user's response results, Feedback presentation means for providing the generated feedback to the user, Update means for periodically obtaining new fraud data and updating the generated scenarios, A system including the above.

Description

Technical Field

[0004] , ,

[0005] , , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, fraud victims have been increasing, and there is a problem that especially those with insufficient fraud literacy, such as the elderly, are likely to be victimized. Conventional fraud prevention education remains at general information provision and is often insufficient to cultivate specific coping abilities in actual fraud situations. Therefore, there is a need for a method to provide practical and individualized fraud prevention education.

Means for Solving the Problems

[0005] This invention provides a data processing means for collecting and analyzing fraudulent method data, and a means for generating fraud scenarios based on the collected data, thereby constructing a system that allows users to simulate realistic fraud experiences. Furthermore, by customizing the generated scenarios based on user profiles and presenting them interactively, it enables education tailored to individual risk levels. In addition, by recording and analyzing user responses and providing accurate feedback, it enhances the ability to respond in actual fraud situations. By including an update means for updating the system in response to the evolution of fraudulent methods, the educational effect can be continuously maintained.

[0006] "Data processing means" refers to methods for collecting data related to fraudulent practices and analyzing that data to extract useful information.

[0007] A "scenario generation method" is a means for generating a scenario that simulates a fraud situation based on collected and analyzed data.

[0008] A "presentation method" is a means of interactively presenting a generated fraud scenario to the user, providing an experience that closely resembles a real fraud situation.

[0009] A "response recording means" is a method for recording the user's reactions and choices to a presented scenario, and for later analysis.

[0010] A "feedback generation method" is a means of evaluating learning outcomes based on the user's response results and generating areas for improvement and advice.

[0011] A "feedback presentation method" is a means of presenting generated feedback information to the user in an easy-to-understand manner to enhance the educational effect.

[0012] "Update methods" refer to the means of incorporating newly collected fraud data and updating the system's scenarios and educational content to match the current situation.

[0013] "Customization methods" refer to means of optimizing and individually addressing generated scenarios based on the user's individual information (age, past training results, etc.).

[0014] "Difficulty adjustment mechanism" refers to a means of adjusting the difficulty level of a scenario according to the user's abilities and experience, thereby providing an appropriate learning environment. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

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

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

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

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

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

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

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention is a fraud prevention education system that utilizes multimodal AI technology to provide users with realistic fraud scenarios. Specific embodiments of this invention are described below.

[0037] First, the server collects the latest data on fraudulent methods and analyzes it using data processing tools. This analysis helps understand patterns in fraudulent methods and extracts information useful for user education. Based on the information obtained, the server uses scenario generation tools to generate a variety of fraud scenarios. Each scenario incorporates fraudulent methods and characteristics and mimics real-life situations that users may face.

[0038] Meanwhile, the terminal receives fraud scenarios provided by the server and presents them interactively to the user using presentation tools. Based on information in the user profile, the scenarios are optimized for each individual and customized to suit their age, past training results, and other factors.

[0039] The user acts according to the presented fraud scenario and learns what consequences their responses will have. During this process, the device uses response recording devices to record the user's reactions in detail and sends this data to a server for later analysis.

[0040] The server uses the obtained user response data to activate a feedback generation mechanism and evaluate the user's actions. This feedback includes not only whether the choices were correct or incorrect, but also a detailed explanation of why those choices were appropriate or inappropriate. The feedback is provided to the user through a feedback presentation mechanism and contributes to strengthening their response capabilities.

[0041] Furthermore, the servers utilize various update mechanisms to regularly reflect information on the latest fraudulent tactics in the system. This ensures that users always receive training that is up-to-date.

[0042] As a concrete example, a simulation for the elderly involves a "telephone scam impersonating a bank." The server generates this scenario and plays the audio to the user through their terminal, recreating the typical approach of a scammer. The user experiences the situation of receiving a phone call in a simulated manner, making choices while considering how to respond. They can deepen their learning by receiving immediate feedback on the results.

[0043] In this configuration, this embodiment provides a system that effectively improves practical defenses against fraud. Furthermore, by using the obtained data to optimize training according to the individual needs of users, a more effective educational environment is realized.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server collects data on the latest fraud techniques from external sources and stores it in a database. These sources include news articles, expert reports, and user reports. The server uses multimodal AI to analyze the collected data and identify fraud patterns and trends.

[0047] Step 2:

[0048] The server designs fraud scenarios based on the analysis results. Using scenario generation tools, it creates scenarios that mimic actual fraud situations, including voice messages, text messages, and images. During this process, the scenarios are customized according to the user's age, skill level, and past performance.

[0049] Step 3:

[0050] The device receives a customized scenario based on the user profile and initiates interactive training. The device presents the scenario through audio playback, screen displays, and choice-based presentations, encouraging active user participation. Users make choices according to the scenario, and these are reflected in real time.

[0051] Step 4:

[0052] Users choose their actions based on the situation presented. For example, in a phone scam scenario, users can choose to "hang up," "continue asking questions," or "check with the bank."

[0053] Step 5:

[0054] The device records the user's responses and quickly sends them to the server. The transmitted response data is used for subsequent evaluation and feedback generation.

[0055] Step 6:

[0056] The server analyzes the received response data and evaluates the appropriateness of the user's choices. Based on this, it uses a feedback generation mechanism to construct feedback for the user. This feedback includes specific areas for improvement and success stories.

[0057] Step 7:

[0058] The device presents the generated feedback to the user. Through this feedback, the user can understand the strengths and weaknesses of their actions and use this information to improve future training sessions.

[0059] Step 8:

[0060] The server updates the system to incorporate the latest fraud techniques, keeping the scenarios always up-to-date. This allows users to continuously develop the skills to adapt to new situations.

[0061] (Example 1)

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

[0063] In response to the increasingly diverse fraud methods of today, there is a need to provide effective education tailored to individual users to improve their ability to defend against fraud. However, conventional systems have struggled to incorporate the latest information on fraud methods and situations in real time and provide personalized education. As a result, there is a challenge in that users cannot be trained to respond immediately when they actually face a fraud situation.

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

[0065] In this invention, the server includes data analysis means for collecting and analyzing fraudulent scheme information, scenario generation means for generating fraud scenarios based on the collected information, and scenario presentation means for interactively presenting the generated fraud scenarios to the user. This allows for the provision of education based on the latest fraudulent schemes to the user at all times, and enables the presentation of scenarios and adjustment of difficulty levels to meet individual needs.

[0066] "Fraudulent scheme information" refers to detailed information about fraudulent methods, techniques, and patterns, and is data used to understand the characteristics and trends of fraud by analyzing it.

[0067] "Data analysis means" refers to methods and apparatus for collecting information on fraudulent practices, processing that information using statistical analysis and machine learning, and extracting useful insights.

[0068] "Scenario generation means" refers to a method and apparatus for automatically generating fraud scenarios that are easy for users to understand and realistically set up, based on analyzed data.

[0069] A "scenario presentation means" is a method and apparatus that interactively presents a generated fraud scenario to a user, allowing them to simulate and experience an actual fraud situation.

[0070] "Response recording means" refers to a method and apparatus for recording the actions and choices made by a user in response to a scenario and storing that data for later analysis.

[0071] "Feedback generation means" refers to a method and apparatus for analyzing recorded user response results and automatically generating feedback that includes evaluations and suggestions for improvement regarding the response.

[0072] A "feedback presentation means" is a method and apparatus for providing generated feedback to the user visually or audibly and linking it to subsequent learning.

[0073] "Information update means" refers to methods and devices that regularly acquire the latest fraud techniques and reflect them in the system's database and scenarios to ensure that up-to-date education is always provided.

[0074] "Personalization means" are methods and devices for customizing scenarios based on the user's characteristics and past performance to provide the most suitable learning experience.

[0075] "Adaptive control means" refers to a method and apparatus for dynamically adjusting the difficulty level of fraud scenarios based on the user's age and past performance.

[0076] "Generation means" refers to a method and apparatus for constructing scenarios using a generative AI model and creating highly novel fraud scenarios.

[0077] This invention provides a sophisticated and personalized educational environment for users by utilizing data analysis technology and generative AI models as a fraud prevention education system. The following describes specific embodiments of this invention.

[0078] The server collects information on fraudulent practices from the internet and dedicated databases. Using programming languages ​​such as Python and APIs, this information is converted into a data frame format, and statistical methods and machine learning techniques are used through data analysis to extract patterns in fraudulent practices. Through this analysis, the characteristics of fraud are identified, and information that can be used for education is extracted.

[0079] Based on the analyzed data, the server generates fraud scenarios using a generative AI model. For example, using a GPT-based model, it can construct specific scenarios by inputting prompts such as, "Generate a phone fraud scenario that an elderly person might encounter." This allows for realistic training that improves users' ability to respond effectively.

[0080] The device presents the user with fraud scenarios received from the server. It provides a visually and audibly interactive experience using voice output devices and displays. The device references the user's profile and customizes the scenario based on their age and past training results.

[0081] Users act based on the presented scenarios and make choices according to the system's instructions. The user's responses are recorded by the terminal, and this data is sent to the server. This data is analyzed by the server using a feedback generation system, which then generates feedback including detailed explanations. This feedback is provided to the user via the terminal, facilitating reflection on learning outcomes and understanding areas for improvement.

[0082] As described above, this invention utilizes the latest information on fraudulent methods and provides users with a personalized learning experience and detailed feedback to create an effective fraud prevention education environment.

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

[0084] Step 1:

[0085] The server retrieves information on fraudulent practices from the internet and dedicated databases. It uses an internet connection and APIs or web scraping tools as input. The data is formatted into a data frame using Python or a database management system. The output is a well-organized set of fraudulent practice information. Specifically, it collects reports and warnings about fraud cases and stores them as a dataset.

[0086] Step 2:

[0087] The server processes the collected fraud scheme information using data analysis tools. The input is the fraud scheme data obtained in Step 1. The server analyzes the data using machine learning algorithms and statistical models to extract patterns of fraud schemes. This data processing produces a model that shows the characteristics and trends of fraud schemes as output. Specifically, it applies clustering and classification methods to reveal the characteristics of the fraud.

[0088] Step 3:

[0089] The server generates fraud scenarios using a generative AI model. The input is the characteristics and trends of fraudulent methods obtained in step 2. A prompt is input to the generative AI model, for example, "Generate a telephone fraud scenario that elderly people might encounter," and the system generates a scenario. The output is the text data of the scenario. Specifically, a natural language processing model such as GPT-4(registered trademark) is used to create a detailed fraud scenario.

[0090] Step 4:

[0091] The terminal receives the fraud scenario sent from the server and presents it to the user. The input is the fraud scenario obtained in step 3. The terminal interactively displays and plays the scenario using its display and audio playback functions. This output is the fraud scenario presented visually and audibly. The terminal refers to the user profile and adjusts the scenario to suit the user's attributes.

[0092] Step 5:

[0093] The user reacts to the presented fraud scenario and selects a response using various input functions. The input is the scenario presented by the terminal. The user's selection is recorded by the terminal and saved as a log. This output is the user's selection log. Specifically, the user makes selections through screen touches or voice responses.

[0094] Step 6:

[0095] The terminal sends user response data to the server. The input is the user selection log recorded in step 5. The server receives this for analysis and prepares for the next feedback generation process. This output is an analyzable user response dataset.

[0096] Step 7:

[0097] The server analyzes user response data and generates feedback. The input is the user response data obtained in step 6. Using the feedback generation mechanism, detailed feedback including results and areas for improvement is created. This output is the feedback information provided to the user. Specifically, based on the data analysis results, it explains why the choice was appropriate or inappropriate.

[0098] Step 8:

[0099] The device presents the generated feedback to the user. The input is the feedback information generated in step 7. The device displays and plays the feedback using visual and auditory means. This output is the feedback provided to the user. Upon receiving the feedback, the user can strengthen their ability to respond for future learning.

[0100] (Application Example 1)

[0101] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0102] Fraudulent tactics are becoming more sophisticated every day, and there is a growing need to provide users with practical defenses to combat the increasing frequency of fraudulent activities. However, many current systems only provide static information and do not offer an environment where users can actively learn how to deal with fraud. In particular, in today's society where fraudulent methods are rapidly evolving, there is a challenge in that it is difficult for users to keep up-to-date with the latest knowledge and effectively counter fraud.

[0103] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0104] In this invention, the server includes data analysis means for aggregating and analyzing information on fraudulent methods, situation generation means for forming a fraudulent situation based on the aggregated information, and display means for displaying the formed fraudulent situation to the user in an interactive format. This provides users with an opportunity to interactively learn about the latest fraudulent methods and countermeasures, enabling a rapid and practical improvement in defensive capabilities.

[0105] "Data analysis methods" refer to means of aggregating information related to fraudulent practices and understanding the characteristics and patterns of fraud through various analyses.

[0106] A "situation generation method" is a means of creating realistic scenarios by forming fraud situations that users may encounter, based on aggregated data.

[0107] A "display method" is a means of interactively presenting a generated fraud scenario to the user and prompting the user to respond.

[0108] A "response recording means" is a means for recording the user's interactive responses in detail and for analyzing that data later.

[0109] An "evaluation generation means" is a means for evaluating the user's response results, determining the correctness of their actions, and generating detailed feedback.

[0110] A "means of providing evaluation" refers to a method of providing users with the generated feedback and suggesting areas for improvement and ways to make improvements.

[0111] "Update methods" refer to measures to regularly acquire information on new fraudulent techniques and keep the fraud situation within the system up to date.

[0112] A "mobile device version of a display means" is a mobile display means equipped with communication functions and a user interface, capable of providing users with practical training in fraud prevention.

[0113] The system for implementing this invention is a fraud prevention education system that utilizes multimodal AI technology. The system consists of a server and terminals, each with a clearly defined role.

[0114] First, the server aggregates the latest information on fraudulent methods and analyzes that data using data analysis tools. The software used here includes TENSORFLOW® for data analysis. The server then uses the analyzed data to create various fraud scenarios using a scenario generation tool. The generated scenarios accurately reproduce the characteristics of the fraud and mimic situations that users might actually face.

[0115] The device receives fraud scenarios provided by the server and presents them interactively to the user through a display mechanism. The display utilizes a smartphone user interface and leverages React Native. The device also meticulously records the user's responses obtained through the dialogue using a corresponding recording mechanism. This data is then sent back to the server for later analysis.

[0116] Based on the user's choices in response to the provided scenario, the server activates an evaluation generation mechanism. The displayed evaluation includes the context of the user's choices and explains why a particular action is appropriate or inappropriate. The generated evaluation is provided to the user through an evaluation presentation mechanism to help refine their choices.

[0117] In operating this system, the server regularly acquires new fraud information and keeps the system up-to-date through update mechanisms. This allows users to constantly learn about new fraud methods and countermeasures.

[0118] A concrete example is "a scenario in which an elderly person simulates a phone scam." The server generates this scenario and reproduces the typical approach of a scammer through audio playback. The user simulates the situation of receiving a call and makes choices while considering how to respond. The user receives immediate feedback on the results, allowing them to deepen their learning.

[0119] An example of a prompt for a generative AI model is: "Create a typical scenario of a phone scam targeting the elderly, in a format that provides feedback on what actions the user should take."

[0120] In this way, the entire system works in coordination, enabling users to develop practical and adaptive fraud prevention capabilities.

[0121] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0122] Step 1:

[0123] The server collects the latest information on fraud techniques from the internet and cybersecurity reports. The input is external data resources, and the output is aggregated fraud technique data. Data analysis tools are used to analyze this data and extract fundamental information for understanding fraud patterns and characteristics.

[0124] Step 2:

[0125] The server utilizes the analyzed data to generate specific fraud scenarios using a situation generation mechanism. The input is the analyzed data, and the output is a fraud scenario for simulation. Using a generation AI model, realistic and challenging fraud situations are created, mimicking situations that users may encounter.

[0126] Step 3:

[0127] The terminal presents the user with fraud scenarios received from the server. The input is generated scenario data, and the output is an interactive display for the user. A smartphone user interface is used as the display method, allowing the user to directly engage with these scenarios.

[0128] Step 4:

[0129] The user responds to presented fraud scenarios. The input is the interactive scenario presented to the user, and the output is the user's response data. By interactively selecting and manipulating options on the device, the user visually learns how to respond.

[0130] Step 5:

[0131] The terminal records the user's response using a corresponding recording device and sends it to the server. The input is the user's response data, and the output is the transmission of data to the server for analysis. This prepares the data for subsequent feedback generation.

[0132] Step 6:

[0133] The server analyzes the received user response data using an evaluation generation mechanism and creates feedback for the user. The input is the user's response data, and the output is feedback information. The feedback is constructed using a generation AI model, providing detailed information about the background of the choice and areas for improvement.

[0134] Step 7:

[0135] Using an evaluation presentation mechanism, the terminal displays the generated feedback to the user. The input is the generated feedback information, and the output is the display to the user. Through this feedback, the user can review and improve their own response skills.

[0136] Step 8:

[0137] The server regularly collects new fraud information through update mechanisms, keeping the system up-to-date. Input consists of new data from external data resources, while output consists of updated fraud technique data. This ensures the freshness and effectiveness of the scenarios, providing users with the latest countermeasures at all times.

[0138] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0139] This invention provides an interactive educational system that combines multimodal AI technology and an emotion engine to improve users' ability to protect themselves from fraud. Specific embodiments of this invention are described below.

[0140] The server first collects the latest data on fraud techniques and analyzes it to extract useful information. Based on this, it uses a scenario generation system to generate scenarios that mimic a wide range of fraud situations. At this time, the scenarios are individually customized based on the user profile, and appropriate training is provided according to the user's experience and skill level.

[0141] The device interactively presents the received scenario and begins training the user. It encourages user participation and provides a comprehensive simulation experience combining voice, text, images, and other elements.

[0142] The crucial role here is that of the emotion engine. The device collects and analyzes emotional data in real time from the user's facial expressions, tone of voice, and other factors. This emotional data is used to understand the user's stress level and concentration level. For example, if the user is anxious or confused, the system senses this situation and provides appropriate support.

[0143] The server meticulously records user responses using a response recording mechanism that incorporates emotional data, and uses this data for subsequent evaluation and feedback generation. The feedback generation mechanism takes emotional data into consideration and adjusts the content of the feedback to ensure the user has a better learning experience.

[0144] The feedback is presented via the device and serves as a guide for users to take specific actions for self-improvement. This enhances the learning effect, and users can use the feedback to prepare for the next simulation.

[0145] This emotion-driven adaptive learning process aims to improve the ability to effectively understand and counter fraud scenarios. Furthermore, the server regularly incorporates new fraud data and updates the system, ensuring users are always trained to adapt to the latest situations. In this way, emotion recognition provides the most effective learning support for users.

[0146] The following describes the processing flow.

[0147] Step 1:

[0148] The server collects data on the latest fraud techniques from a variety of sources on the internet. This includes raw data from news, forums, and expert reports. The collected data is stored in a database.

[0149] Step 2:

[0150] The server analyzes accumulated data using natural language processing technology to extract current trends and characteristics of fraudulent methods. Based on these analysis results, it constructs fraud scenarios that users are likely to encounter.

[0151] Step 3:

[0152] The server references each user's profile information (age, skill level, past training data, etc.) and individually customizes the fraud scenarios it generates. This ensures that training scenarios with appropriate difficulty and content are prepared for each user.

[0153] Step 4:

[0154] The device presents the user with a pre-prepared fraud scenario. It offers an interactive experience through the presentation methods, allowing the user to actively participate. Various media are used, including voice instructions, text messages, and images.

[0155] Step 5:

[0156] The user chooses actions according to the presented fraud scenario. The scenario presents options, and the simulation progresses as the user selects the appropriate action.

[0157] Step 6:

[0158] The device activates an emotion engine that collects the user's facial expressions and voice tone in real time, acquiring the user's emotional data. The analyzed emotional data is used to understand the user's situation.

[0159] Step 7:

[0160] The server analyzes user selection and sentiment data sent from the terminal. This allows it to evaluate the appropriateness of the user's chosen actions and understand the user's stress levels and learning progress from the sentiment data.

[0161] Step 8:

[0162] The server uses feedback generation mechanisms to construct appropriate feedback based on the analysis results obtained. This feedback includes specific advice regarding the user's choices and emotional support based on sentiment data.

[0163] Step 9:

[0164] The device presents the generated feedback to the user. By receiving the feedback, the user can learn how to improve their responses and what to pay attention to in the next training session.

[0165] Step 10:

[0166] The server regularly acquires the latest information on fraudulent methods and updates the system-wide scenarios and learning content. This ensures that users are always trained on the most up-to-date fraudulent techniques.

[0167] (Example 2)

[0168] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0169] In modern society, fraudulent methods are becoming increasingly sophisticated and diverse. Consequently, it is crucial for users to develop the ability to recognize and defend against fraud based on their own judgment. However, existing countermeasures are limited to providing uniform information and lack interactive support tailored to the individual characteristics and emotional states of users. Therefore, providing a learning environment optimized for each individual user is a key challenge.

[0170] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0171] In this invention, the server includes information processing means for collecting and analyzing fraudulent scheme information, situation generation means for generating fraudulent situations based on the collected information, and emotion analysis means for analyzing the user's emotional state and providing situation-appropriate support. This makes it possible to provide an interactive learning experience optimized for each individual user and effectively improve fraud prevention capabilities.

[0172] "Information processing means" refers to technical means for collecting data related to fraudulent methods, analyzing that data, and extracting useful information.

[0173] A "situation generation means" is a technical means for imitating or creating specific fraud situations based on collected and analyzed information on fraudulent methods.

[0174] A "presentation means" is a technical means for showing the generated fraud situation to the user and enabling interactive communication with the user.

[0175] A "response recording means" is a technical means for recording interactive responses by users and evaluating user behavior by analyzing that data.

[0176] An "evaluation generation means" is a technical means for generating an evaluation based on the user's response results and clearly indicating areas for improvement and learning points.

[0177] An "evaluation presentation means" is a technical means that transmits generated evaluation information to the user, enabling the user to understand the effectiveness of their own learning and apply that understanding to their next actions.

[0178] "Update methods" refer to technical means for regularly acquiring the latest fraud information and keeping the system's status and data up-to-date at all times.

[0179] "Emotional analysis tools" are technical tools that collect emotional data such as a user's facial expressions and tone of voice, and analyze it in order to provide appropriate support according to the situation.

[0180] "Optimization methods" refer to technical means that customize fraud situations individually based on user characteristic information to provide a more effective learning experience.

[0181] A "complexity adjustment mechanism" is a technical means for appropriately adjusting the difficulty and complexity of fraud scenarios based on the user's characteristics and past learning results.

[0182] This invention is an interactive learning system for improving users' ability to deal with cyber fraud. First, the server collects the latest information on fraudulent methods from the internet and various databases. In this process, data analysis is performed using, for example, NLTK, a Python library that uses natural language processing technology, to analyze fraud patterns.

[0183] The server then uses a generative AI model to construct a fraud scenario. Specifically, it uses a general generative model and generates a fraud scenario by taking the prompt "Create a scenario based on the latest fraud techniques" as input.

[0184] The terminal receives this scenario sent from the server and presents it to the user in an interactive format. The terminal uses technologies such as HTML5 and JavaScript® to present content combining audio, text, and images to the user and provide a comprehensive anti-fraud experience. This allows the user to consider countermeasures in real time against a virtual fraud scenario.

[0185] As a key component, the device incorporates an emotion analysis engine. The device collects the user's facial expressions and voice tone through its camera and microphone, and uses this data to analyze the user's emotions in real time, leveraging machine learning libraries such as TensorFlow. This allows the system to provide immediate support if the user experiences anxiety or confusion.

[0186] The server generates evaluation information and feedback based on user response and sentiment data obtained from the terminal. This allows users to receive specific advice on areas for improvement and skills to strengthen. The system regularly incorporates new fraud information, ensuring that it is always up-to-date and able to respond to users effectively.

[0187] This system will allow users to deepen their understanding of fraud and significantly improve their ability to take practical countermeasures.

[0188] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0189] Step 1:

[0190] The server collects the latest information on fraudulent methods from the internet and specific databases. It uses web scraping techniques to extract data, which is then used as input. Next, it performs text analysis using natural language processing techniques to extract useful information about fraud trends and specific methods as output. This process prepares the fraud data for the system's next use.

[0191] Step 2:

[0192] The server generates fraud scenarios based on collected and analyzed fraud data. During this process, it uses a generation AI model and is prompted with the message, "Create a scenario based on the latest fraud techniques." The AI ​​model outputs a text scenario that mimics a specific fraud scene, and this scenario forms the basis for subsequent processing.

[0193] Step 3:

[0194] The server receives user profile data (e.g., age, work history, past training history) as input and customizes the generated scenarios based on this data. Using machine learning libraries such as Scikit-learn, it clusters the user's profile and adjusts the difficulty and content of the scenarios to best suit the user before outputting them.

[0195] Step 4:

[0196] The device receives a customized scenario sent from the server and presents it interactively to the user. Using HTML5 and JavaScript technologies, the device generates interactive content combining audio, text, and images, allowing the user to experience a real-life fraud scenario. User input consists of choices and actions within the scenario, and the results determine the next development of the scenario.

[0197] Step 5:

[0198] The device acquires the user's facial expressions and voice as input through its camera and microphone, and analyzes their emotions in real time. This utilizes machine learning platforms such as TensorFlow. The output of the emotion analysis serves as support information when the user shows anxiety or confusion, and is used to provide appropriate guidance and advice.

[0199] Step 6:

[0200] The server takes user interaction data and emotion data received from the terminal as input to record responses and generate evaluations. This generates feedback based on the user's behavior and emotions, and the evaluation is output as specific actions that the user can use for self-improvement. The feedback is provided to the user through the terminal.

[0201] Step 7:

[0202] The server periodically acquires new fraud information and uses this information to update the system. New fraud data is input here, and based on this, scenarios are regenerated, making it possible to always provide users with the latest fraud prevention training as output.

[0203] (Application Example 2)

[0204] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0205] As fraudulent methods become more diverse and sophisticated, there are limits to how effectively individual users can improve their fraud prevention capabilities. Furthermore, traditional education systems fail to optimize training to take into account the emotional changes of users, resulting in insufficient learning efficiency.

[0206] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0207] In this invention, the server includes information processing means for collecting and analyzing fraud method data, situation generation means for generating fraud situations based on the collected information, and presentation means for interactively presenting the generated fraud situations to the user. This enables adaptive optimization of training content based on the user's emotional data, resulting in more effective learning support.

[0208] "Information processing means" refers to devices or systems that have the function of collecting and analyzing data related to fraudulent methods.

[0209] A "situation generation means" is a device or system that creates a fraudulent situation based on collected information.

[0210] A "presentation means" refers to a device or system for interactively displaying the generated fraud situation to the user.

[0211] A "response recording means" is a device or system for recording and analyzing a user's interactive responses.

[0212] A "feedback generation means" is a device or system that has the function of creating feedback based on the user's response.

[0213] A "feedback presentation means" is a device or system for providing generated feedback to the user.

[0214] An "update mechanism" is a device or system that has the function of regularly acquiring new fraud information and improving the situation generated based on that information.

[0215] "Emotional analysis tools" refer to devices or systems used to collect and analyze users' emotional data.

[0216] An "adaptive feedback mechanism" is a device or system that has the function of adjusting the content of feedback based on analyzed emotional data.

[0217] The system of this invention consists of a server and a terminal to improve users' ability to protect themselves from fraud. First, the server collects data on fraudulent methods and analyzes it using a data analysis tool based on Python. Based on this analysis, it generates fraud scenarios. The scenarios are created using generative AI models such as TensorFlow or PyTorch and are customized based on the user's profile.

[0218] The generated fraud scenarios are presented to the user via a device. The user experiences interactive training combining voice, text, and images on a device such as a smartphone or tablet. The device uses OpenCV to analyze the user's facial expressions and Librosa to analyze their voice tone, collecting emotional data in real time.

[0219] The collected emotional data is sent to a server and analyzed by an adaptive feedback system. The data obtained is used to measure the user's stress level and concentration, and to adjust the feedback accordingly. The feedback provides specific actions to enhance the user's learning effectiveness and is used to improve future scenario engagement.

[0220] As a concrete example, when a user is working on a phone scam scenario, if the emotion analysis system detects an anxious expression, the device will instruct the user, "Don't worry, let's try again." At this point, the system will clarify which part caused the user anxiety and suggest ways to improve.

[0221] As an example of a prompt, it is possible to ask the generative AI model a question such as, "How would the system provide support if the user expressed anxiety or confusion in a specific fraud scenario?" and have it determine the appropriate support method.

[0222] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0223] Step 1:

[0224] The server collects data on fraudulent practices from external databases and the internet. This data is preprocessed using a Python-based analysis tool to extract useful information. The input is raw fraud data, and the output is analyzed fraudulent practice information. The data is then filtered and classified to organize the information according to its intended use.

[0225] Step 2:

[0226] The server generates fraud scenarios based on analyzed fraud technique information. Since a generative AI model is used, the input is fraud technique information. The output is an interactive fraud scenario. The model is trained using TensorFlow and automatically generates scenarios tailored to the user's experience and profile.

[0227] Step 3:

[0228] The terminal presents the user with a fraud scenario received from the server. Audio, text, and images are presented to allow the user to access the scenario visually and aurally. The input is the generated fraud scenario, and the output is the user's actions and responses. In this step, the scenario progresses through an interactive user interface.

[0229] Step 4:

[0230] The device acquires key emotional data from the user's facial expressions and voice. It uses OpenCV to extract facial features and Librosa to analyze voice tone. The input is real-time facial and voice data from the user, and the output is emotional information read from the facial expressions.

[0231] Step 5:

[0232] The server receives emotional data transmitted from the terminal and analyzes it through an adaptive feedback mechanism. The input is emotional information obtained from the user, and the output is the analysis results for feedback generation. In this step, the user's stress level and concentration level are evaluated to prepare for generating adaptive feedback in the next step.

[0233] Step 6:

[0234] The server generates and provides feedback to the user based on the analysis results. Adaptive feedback mechanisms consider emotional information and create specific feedback to encourage improvement. The input is the analysis results, and the output is feedback information. The feedback is presented to the user in an interactive format and functions as guiding advice for future scenarios.

[0235] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0236] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0237] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0238] [Second Embodiment]

[0239] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0240] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0241] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0242] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0243] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0244] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0245] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0246] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0247] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0248] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0249] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0250] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0251] This invention is a fraud prevention education system that utilizes multimodal AI technology to provide users with realistic fraud scenarios. Specific embodiments of this invention are described below.

[0252] First, the server collects the latest data on fraudulent methods and analyzes it using data processing tools. This analysis helps understand patterns in fraudulent methods and extracts information useful for user education. Based on the information obtained, the server uses scenario generation tools to generate a variety of fraud scenarios. Each scenario incorporates fraudulent methods and characteristics and mimics real-life situations that users may face.

[0253] Meanwhile, the terminal receives fraud scenarios provided by the server and presents them interactively to the user using presentation tools. Based on information in the user profile, the scenarios are optimized for each individual and customized to suit their age, past training results, and other factors.

[0254] The user acts according to the presented fraud scenario and learns what consequences their responses will have. During this process, the device uses response recording devices to record the user's reactions in detail and sends this data to a server for later analysis.

[0255] The server uses the obtained user response data to activate a feedback generation mechanism and evaluate the user's actions. This feedback includes not only whether the choices were correct or incorrect, but also a detailed explanation of why those choices were appropriate or inappropriate. The feedback is provided to the user through a feedback presentation mechanism and contributes to strengthening their response capabilities.

[0256] Furthermore, the servers utilize various update mechanisms to regularly reflect information on the latest fraudulent tactics in the system. This ensures that users always receive training that is up-to-date.

[0257] As a concrete example, a simulation for the elderly involves a "telephone scam impersonating a bank." The server generates this scenario and plays the audio to the user through their terminal, recreating the typical approach of a scammer. The user experiences the situation of receiving a phone call in a simulated manner, making choices while considering how to respond. They can deepen their learning by receiving immediate feedback on the results.

[0258] In this configuration, this embodiment provides a system that effectively improves practical defenses against fraud. Furthermore, by using the obtained data to optimize training according to the individual needs of users, a more effective educational environment is realized.

[0259] The following describes the processing flow.

[0260] Step 1:

[0261] The server collects data on the latest fraud techniques from external sources and stores it in a database. These sources include news articles, expert reports, and user reports. The server uses multimodal AI to analyze the collected data and identify fraud patterns and trends.

[0262] Step 2:

[0263] The server designs fraud scenarios based on the analysis results. Using scenario generation tools, it creates scenarios that mimic actual fraud situations, including voice messages, text messages, and images. During this process, the scenarios are customized according to the user's age, skill level, and past performance.

[0264] Step 3:

[0265] The device receives a customized scenario based on the user profile and initiates interactive training. The device presents the scenario through audio playback, screen displays, and choice-based presentations, encouraging active user participation. Users make choices according to the scenario, and these are reflected in real time.

[0266] Step 4:

[0267] Users choose their actions based on the situation presented. For example, in a phone scam scenario, users can choose to "hang up," "continue asking questions," or "check with the bank."

[0268] Step 5:

[0269] The device records the user's responses and quickly sends them to the server. The transmitted response data is used for subsequent evaluation and feedback generation.

[0270] Step 6:

[0271] The server analyzes the received response data and evaluates the appropriateness of the user's choices. Based on this, it uses a feedback generation mechanism to construct feedback for the user. This feedback includes specific areas for improvement and success stories.

[0272] Step 7:

[0273] The device presents the generated feedback to the user. Through this feedback, the user can understand the strengths and weaknesses of their actions and use this information to improve future training sessions.

[0274] Step 8:

[0275] The server updates the system to incorporate the latest fraud techniques, keeping the scenarios always up-to-date. This allows users to continuously develop the skills to adapt to new situations.

[0276] (Example 1)

[0277] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0278] In response to the increasingly diverse fraud methods of today, there is a need to provide effective education tailored to individual users to improve their ability to defend against fraud. However, conventional systems have struggled to incorporate the latest information on fraud methods and situations in real time and provide personalized education. As a result, there is a challenge in that users cannot be trained to respond immediately when they actually face a fraud situation.

[0279] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Example 1 is realized by the following means.

[0280] In this invention, the server includes data analysis means for collecting and analyzing fraud method information, scenario generation means for generating a fraud scenario based on the collected information, and scenario presentation means for interactively presenting the generated fraud scenario to the user. Thereby, it is possible to always provide education based on the latest fraud methods to the user, and to present scenarios according to individual needs and adjust the difficulty level.

[0281] "Fraud method information" is detailed information on fraud techniques, methods, and patterns, and is data for understanding the characteristics and trends of fraud by analyzing them.

[0282] "Data analysis means" is a method and apparatus for collecting fraud method information, processing the information using statistical analysis or machine learning, and extracting useful insights.

[0283] "Scenario generation means" is a method and apparatus for automatically generating a fraud scenario that is easy for the user to understand and is realistically set based on the analyzed data.

[0284] "Scenario presentation means" is a method and apparatus for interactively presenting the generated fraud scenario to the user and simulating the experience of an actual fraud situation.

[0285] "Response recording means" is a method and apparatus for recording the actions and selections made by the user with respect to the scenario and storing the data for later analysis.

[0286] "Feedback generation means" is a method and apparatus for analyzing the recorded response results of the user and automatically generating feedback including an evaluation of the response and points for improvement.

[0287] A "feedback presentation means" is a method and apparatus for providing generated feedback to the user visually or audibly and linking it to subsequent learning.

[0288] "Information update means" refers to methods and devices that regularly acquire the latest fraud techniques and reflect them in the system's database and scenarios to ensure that up-to-date education is always provided.

[0289] "Personalization means" are methods and devices for customizing scenarios based on the user's characteristics and past performance to provide the most suitable learning experience.

[0290] "Adaptive control means" refers to a method and apparatus for dynamically adjusting the difficulty level of fraud scenarios based on the user's age and past performance.

[0291] "Generation means" refers to a method and apparatus for constructing scenarios using a generative AI model and creating highly novel fraud scenarios.

[0292] This invention provides a sophisticated and personalized educational environment for users by utilizing data analysis technology and generative AI models as a fraud prevention education system. The following describes specific embodiments of this invention.

[0293] The server collects information on fraudulent practices from the internet and dedicated databases. Using programming languages ​​such as Python and APIs, this information is converted into a data frame format, and statistical methods and machine learning techniques are used through data analysis to extract patterns in fraudulent practices. Through this analysis, the characteristics of fraud are identified, and information that can be used for education is extracted.

[0294] Based on the analyzed data, the server generates fraud scenarios using a generative AI model. For example, using a GPT-based model, it can construct specific scenarios by inputting prompts such as, "Generate a phone fraud scenario that an elderly person might encounter." This allows for realistic training that improves users' ability to respond effectively.

[0295] The device presents the user with fraud scenarios received from the server. It provides a visually and audibly interactive experience using voice output devices and displays. The device references the user's profile and customizes the scenario based on their age and past training results.

[0296] Users act based on the presented scenarios and make choices according to the system's instructions. The user's responses are recorded by the terminal, and this data is sent to the server. This data is analyzed by the server using a feedback generation system, which then generates feedback including detailed explanations. This feedback is provided to the user via the terminal, facilitating reflection on learning outcomes and understanding areas for improvement.

[0297] As described above, this invention utilizes the latest information on fraudulent methods and provides users with a personalized learning experience and detailed feedback to create an effective fraud prevention education environment.

[0298] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0299] Step 1:

[0300] The server retrieves information on fraudulent practices from the internet and dedicated databases. It uses an internet connection and APIs or web scraping tools as input. The data is formatted into a data frame using Python or a database management system. The output is a well-organized set of fraudulent practice information. Specifically, it collects reports and warnings about fraud cases and stores them as a dataset.

[0301] Step 2:

[0302] The server processes the collected fraud method information using data analysis means. The input is the fraud method data obtained in Step 1. The server analyzes the data using machine learning algorithms and statistical models to extract the patterns of fraud methods. Through this data processing, a model indicating the characteristics and trends of fraud methods is obtained as the output. As specific operations, clustering and classification methods are applied to clarify the characteristics of fraud.

[0303] Step 3:

[0304] The server generates fraud scenarios using a generative AI model. The input is the characteristics and trends of fraud methods obtained in Step 2. A prompt sentence is input into the generative AI model, and scenarios are generated with an instruction such as "Please generate a phone fraud scenario encountered by the elderly". This output is the text data of the scenario. As specific operations, natural language processing models such as GPT-4 are utilized to create detailed fraud scenarios.

[0305] Step 4:

[0306] The terminal receives the fraud scenario sent from the server and presents it to the user. The input is the fraud scenario obtained in Step 3. The terminal interactively displays and plays back the scenario using a display and audio playback function. This output is the fraud scenario presented visually and audibly. The terminal refers to the user profile and adjusts the scenario according to the attributes of the user.

[0307] Step 5:

[0308] The user reacts to the presented fraud scenario and selects a response using various input functions. The input is the scenario presented by the terminal. The user's selection is recorded by the terminal and saved as a log. This output is the user's selection log. Specifically, the user makes selections through screen touches or voice responses.

[0309] Step 6:

[0310] The terminal sends user response data to the server. The input is the user selection log recorded in step 5. The server receives this for analysis and prepares for the next feedback generation process. This output is an analyzable user response dataset.

[0311] Step 7:

[0312] The server analyzes user response data and generates feedback. The input is the user response data obtained in step 6. Using the feedback generation mechanism, detailed feedback including results and areas for improvement is created. This output is the feedback information provided to the user. Specifically, based on the data analysis results, it explains why the choice was appropriate or inappropriate.

[0313] Step 8:

[0314] The device presents the generated feedback to the user. The input is the feedback information generated in step 7. The device displays and plays the feedback using visual and auditory means. This output is the feedback provided to the user. Upon receiving the feedback, the user can strengthen their ability to respond for future learning.

[0315] (Application Example 1)

[0316] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0317] Fraudulent tactics are becoming more sophisticated every day, and there is a growing need to provide users with practical defenses to combat the increasing frequency of fraudulent activities. However, many current systems only provide static information and do not offer an environment where users can actively learn how to deal with fraud. In particular, in today's society where fraudulent methods are rapidly evolving, there is a challenge in that it is difficult for users to keep up-to-date with the latest knowledge and effectively counter fraud.

[0318] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0319] In this invention, the server includes data analysis means for aggregating and analyzing information on fraudulent methods, situation generation means for forming a fraudulent situation based on the aggregated information, and display means for displaying the formed fraudulent situation to the user in an interactive format. This provides users with an opportunity to interactively learn about the latest fraudulent methods and countermeasures, enabling a rapid and practical improvement in defensive capabilities.

[0320] "Data analysis methods" refer to means of aggregating information related to fraudulent practices and understanding the characteristics and patterns of fraud through various analyses.

[0321] A "situation generation method" is a means of creating realistic scenarios by forming fraud situations that users may encounter, based on aggregated data.

[0322] A "display method" is a means of interactively presenting a generated fraud scenario to the user and prompting the user to respond.

[0323] A "response recording means" is a means for recording the user's interactive responses in detail and for analyzing that data later.

[0324] An "evaluation generation means" is a means for evaluating the user's response results, determining the correctness of their actions, and generating detailed feedback.

[0325] A "means of providing evaluation" refers to a method of providing users with the generated feedback and suggesting areas for improvement and ways to make improvements.

[0326] "Update methods" refer to measures to regularly acquire information on new fraudulent techniques and keep the fraud situation within the system up to date.

[0327] A "mobile device version of a display means" is a mobile display means equipped with communication functions and a user interface, capable of providing users with practical training in fraud prevention.

[0328] The system for implementing this invention is a fraud prevention education system that utilizes multimodal AI technology. The system consists of a server and terminals, each with a clearly defined role.

[0329] First, the server aggregates the latest information on fraudulent methods and analyzes that data using data analysis tools. The software used here includes TensorFlow for data analysis. The server then uses the analyzed data to create various fraud scenarios using a scenario generation tool. The generated scenarios accurately reproduce the characteristics of the fraud and mimic situations that users might actually face.

[0330] The device receives fraud scenarios provided by the server and presents them interactively to the user through a display mechanism. The display utilizes a smartphone user interface and leverages React Native. The device also meticulously records the user's responses obtained through the dialogue using a corresponding recording mechanism. This data is then sent back to the server for later analysis.

[0331] Based on the user's choices in response to the provided scenario, the server activates an evaluation generation mechanism. The displayed evaluation includes the context of the user's choices and explains why a particular action is appropriate or inappropriate. The generated evaluation is provided to the user through an evaluation presentation mechanism to help refine their choices.

[0332] In operating this system, the server regularly acquires new fraud information and keeps the system up-to-date through update mechanisms. This allows users to constantly learn about new fraud methods and countermeasures.

[0333] A concrete example is "a scenario in which an elderly person simulates a phone scam." The server generates this scenario and reproduces the typical approach of a scammer through audio playback. The user simulates the situation of receiving a call and makes choices while considering how to respond. The user receives immediate feedback on the results, allowing them to deepen their learning.

[0334] An example of a prompt for a generative AI model is: "Create a typical scenario of a phone scam targeting the elderly, in a format that provides feedback on what actions the user should take."

[0335] In this way, the entire system works in coordination, enabling users to develop practical and adaptive fraud prevention capabilities.

[0336] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0337] Step 1:

[0338] The server collects the latest information on fraud techniques from the internet and cybersecurity reports. The input is external data resources, and the output is aggregated fraud technique data. Data analysis tools are used to analyze this data and extract fundamental information for understanding fraud patterns and characteristics.

[0339] Step 2:

[0340] The server utilizes the analyzed data to generate specific fraud scenarios using a situation generation mechanism. The input is the analyzed data, and the output is a fraud scenario for simulation. Using a generation AI model, realistic and challenging fraud situations are created, mimicking situations that users may encounter.

[0341] Step 3:

[0342] The terminal presents the user with fraud scenarios received from the server. The input is generated scenario data, and the output is an interactive display for the user. A smartphone user interface is used as the display method, allowing the user to directly engage with these scenarios.

[0343] Step 4:

[0344] The user responds to presented fraud scenarios. The input is the interactive scenario presented to the user, and the output is the user's response data. By interactively selecting and manipulating options on the device, the user visually learns how to respond.

[0345] Step 5:

[0346] The terminal records the user's response using a corresponding recording device and sends it to the server. The input is the user's response data, and the output is the transmission of data to the server for analysis. This prepares the data for subsequent feedback generation.

[0347] Step 6:

[0348] The server analyzes the received user response data using an evaluation generation mechanism and creates feedback for the user. The input is the user's response data, and the output is feedback information. The feedback is constructed using a generation AI model, providing detailed information about the background of the choice and areas for improvement.

[0349] Step 7:

[0350] Using an evaluation presentation mechanism, the terminal displays the generated feedback to the user. The input is the generated feedback information, and the output is the display to the user. Through this feedback, the user can review and improve their own response skills.

[0351] Step 8:

[0352] The server regularly collects new fraud information through update mechanisms, keeping the system up-to-date. Input consists of new data from external data resources, while output consists of updated fraud technique data. This ensures the freshness and effectiveness of the scenarios, providing users with the latest countermeasures at all times.

[0353] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0354] This invention provides an interactive educational system that combines multimodal AI technology and an emotion engine to improve users' ability to protect themselves from fraud. Specific embodiments of this invention are described below.

[0355] The server first collects the latest data on fraud techniques and analyzes it to extract useful information. Based on this, it uses a scenario generation system to generate scenarios that mimic a wide range of fraud situations. At this time, the scenarios are individually customized based on the user profile, and appropriate training is provided according to the user's experience and skill level.

[0356] The device interactively presents the received scenario and begins training the user. It encourages user participation and provides a comprehensive simulation experience combining voice, text, images, and other elements.

[0357] The crucial role here is that of the emotion engine. The device collects and analyzes emotional data in real time from the user's facial expressions, tone of voice, and other factors. This emotional data is used to understand the user's stress level and concentration level. For example, if the user is anxious or confused, the system senses this situation and provides appropriate support.

[0358] The server meticulously records user responses using a response recording mechanism that incorporates emotional data, and uses this data for subsequent evaluation and feedback generation. The feedback generation mechanism takes emotional data into consideration and adjusts the content of the feedback to ensure the user has a better learning experience.

[0359] The feedback is presented via the device and serves as a guide for users to take specific actions for self-improvement. This enhances the learning effect, and users can use the feedback to prepare for the next simulation.

[0360] This emotion-driven adaptive learning process aims to improve the ability to effectively understand and counter fraud scenarios. Furthermore, the server regularly incorporates new fraud data and updates the system, ensuring users are always trained to adapt to the latest situations. In this way, emotion recognition provides the most effective learning support for users.

[0361] The following describes the processing flow.

[0362] Step 1:

[0363] The server collects data on the latest fraud techniques from a variety of sources on the internet. This includes raw data from news, forums, and expert reports. The collected data is stored in a database.

[0364] Step 2:

[0365] The server analyzes accumulated data using natural language processing technology to extract current trends and characteristics of fraudulent methods. Based on these analysis results, it constructs fraud scenarios that users are likely to encounter.

[0366] Step 3:

[0367] The server references each user's profile information (age, skill level, past training data, etc.) and individually customizes the fraud scenarios it generates. This ensures that training scenarios with appropriate difficulty and content are prepared for each user.

[0368] Step 4:

[0369] The device presents the user with a pre-prepared fraud scenario. It offers an interactive experience through the presentation methods, allowing the user to actively participate. Various media are used, including voice instructions, text messages, and images.

[0370] Step 5:

[0371] The user chooses actions according to the presented fraud scenario. The scenario presents options, and the simulation progresses as the user selects the appropriate action.

[0372] Step 6:

[0373] The device activates an emotion engine that collects the user's facial expressions and voice tone in real time, acquiring the user's emotional data. The analyzed emotional data is used to understand the user's situation.

[0374] Step 7:

[0375] The server analyzes user selection and sentiment data sent from the terminal. This allows it to evaluate the appropriateness of the user's chosen actions and understand the user's stress levels and learning progress from the sentiment data.

[0376] Step 8:

[0377] The server uses feedback generation mechanisms to construct appropriate feedback based on the analysis results obtained. This feedback includes specific advice regarding the user's choices and emotional support based on sentiment data.

[0378] Step 9:

[0379] The device presents the generated feedback to the user. By receiving the feedback, the user can learn how to improve their responses and what to pay attention to in the next training session.

[0380] Step 10:

[0381] The server regularly acquires the latest information on fraudulent methods and updates the system-wide scenarios and learning content. This ensures that users are always trained on the most up-to-date fraudulent techniques.

[0382] (Example 2)

[0383] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0384] In modern society, fraudulent methods are becoming increasingly sophisticated and diverse. Consequently, it is crucial for users to develop the ability to recognize and defend against fraud based on their own judgment. However, existing countermeasures are limited to providing uniform information and lack interactive support tailored to the individual characteristics and emotional states of users. Therefore, providing a learning environment optimized for each individual user is a key challenge.

[0385] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0386] In this invention, the server includes information processing means for collecting and analyzing fraudulent scheme information, situation generation means for generating fraudulent situations based on the collected information, and emotion analysis means for analyzing the user's emotional state and providing situation-appropriate support. This makes it possible to provide an interactive learning experience optimized for each individual user and effectively improve fraud prevention capabilities.

[0387] "Information processing means" refers to technical means for collecting data related to fraudulent methods, analyzing that data, and extracting useful information.

[0388] A "situation generation means" is a technical means for imitating or creating specific fraud situations based on collected and analyzed information on fraudulent methods.

[0389] A "presentation means" is a technical means for showing the generated fraud situation to the user and enabling interactive communication with the user.

[0390] A "response recording means" is a technical means for recording interactive responses by users and evaluating user behavior by analyzing that data.

[0391] An "evaluation generation means" is a technical means for generating an evaluation based on the user's response results and clearly indicating areas for improvement and learning points.

[0392] An "evaluation presentation means" is a technical means that transmits generated evaluation information to the user, enabling the user to understand the effectiveness of their own learning and apply that understanding to their next actions.

[0393] "Update methods" refer to technical means for regularly acquiring the latest fraud information and keeping the system's status and data up-to-date at all times.

[0394] "Emotional analysis tools" are technical tools that collect emotional data such as a user's facial expressions and tone of voice, and analyze it in order to provide appropriate support according to the situation.

[0395] "Optimization methods" refer to technical means that customize fraud situations individually based on user characteristic information to provide a more effective learning experience.

[0396] A "complexity adjustment mechanism" is a technical means for appropriately adjusting the difficulty and complexity of fraud scenarios based on the user's characteristics and past learning results.

[0397] This invention is an interactive learning system for improving users' ability to deal with cyber fraud. First, the server collects the latest information on fraudulent methods from the internet and various databases. In this process, data analysis is performed using, for example, NLTK, a Python library that uses natural language processing technology, to analyze fraud patterns.

[0398] The server then uses a generative AI model to construct a fraud scenario. Specifically, it uses a general generative model and generates a fraud scenario by taking the prompt "Create a scenario based on the latest fraud techniques" as input.

[0399] The terminal receives this scenario sent from the server and presents it to the user in an interactive format. The terminal uses technologies such as HTML5 and JavaScript to present content that combines audio, text, and images to the user, providing a comprehensive anti-fraud experience. This allows the user to consider countermeasures in real time against a virtual fraud scenario.

[0400] As a key component, the device incorporates an emotion analysis engine. The device collects the user's facial expressions and voice tone through its camera and microphone, and uses this data to analyze the user's emotions in real time, leveraging machine learning libraries such as TensorFlow. This allows the system to provide immediate support if the user experiences anxiety or confusion.

[0401] The server generates evaluation information and feedback based on user response and sentiment data obtained from the terminal. This allows users to receive specific advice on areas for improvement and skills to strengthen. The system regularly incorporates new fraud information, ensuring that it is always up-to-date and able to respond to users effectively.

[0402] This system will allow users to deepen their understanding of fraud and significantly improve their ability to take practical countermeasures.

[0403] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0404] Step 1:

[0405] The server collects the latest information on fraudulent methods from the internet and specific databases. It uses web scraping techniques to extract data, which is then used as input. Next, it performs text analysis using natural language processing techniques to extract useful information about fraud trends and specific methods as output. This process prepares the fraud data for the system's next use.

[0406] Step 2:

[0407] The server generates fraud scenarios based on collected and analyzed fraud data. During this process, it uses a generation AI model and is prompted with the message, "Create a scenario based on the latest fraud techniques." The AI ​​model outputs a text scenario that mimics a specific fraud scene, and this scenario forms the basis for subsequent processing.

[0408] Step 3:

[0409] The server receives user profile data (e.g., age, work history, past training history) as input and customizes the generated scenarios based on this data. Using machine learning libraries such as Scikit-learn, it clusters the user's profile and adjusts the difficulty and content of the scenarios to best suit the user before outputting them.

[0410] Step 4:

[0411] The device receives a customized scenario sent from the server and presents it interactively to the user. Using HTML5 and JavaScript technologies, the device generates interactive content combining audio, text, and images, allowing the user to experience a real-life fraud scenario. User input consists of choices and actions within the scenario, and the results determine the next development of the scenario.

[0412] Step 5:

[0413] The device acquires the user's facial expressions and voice as input through its camera and microphone, and analyzes their emotions in real time. This utilizes machine learning platforms such as TensorFlow. The output of the emotion analysis serves as support information when the user shows anxiety or confusion, and is used to provide appropriate guidance and advice.

[0414] Step 6:

[0415] The server takes user interaction data and emotion data received from the terminal as input to record responses and generate evaluations. This generates feedback based on the user's behavior and emotions, and the evaluation is output as specific actions that the user can use for self-improvement. The feedback is provided to the user through the terminal.

[0416] Step 7:

[0417] The server periodically acquires new fraud information and uses this information to update the system. New fraud data is input here, and based on this, scenarios are regenerated, making it possible to always provide users with the latest fraud prevention training as output.

[0418] (Application Example 2)

[0419] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0420] As fraudulent methods become more diverse and sophisticated, there are limits to how effectively individual users can improve their fraud prevention capabilities. Furthermore, traditional education systems fail to optimize training to take into account the emotional changes of users, resulting in insufficient learning efficiency.

[0421] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0422] In this invention, the server includes information processing means for collecting and analyzing fraud method data, situation generation means for generating fraud situations based on the collected information, and presentation means for interactively presenting the generated fraud situations to the user. This enables adaptive optimization of training content based on the user's emotional data, resulting in more effective learning support.

[0423] "Information processing means" refers to devices or systems that have the function of collecting and analyzing data related to fraudulent methods.

[0424] A "situation generation means" is a device or system that creates a fraudulent situation based on collected information.

[0425] A "presentation means" refers to a device or system for interactively displaying the generated fraud situation to the user.

[0426] A "response recording means" is a device or system for recording and analyzing a user's interactive responses.

[0427] A "feedback generation means" is a device or system that has the function of creating feedback based on the user's response.

[0428] A "feedback presentation means" is a device or system for providing generated feedback to the user.

[0429] An "update mechanism" is a device or system that has the function of regularly acquiring new fraud information and improving the situation generated based on that information.

[0430] "Emotional analysis tools" refer to devices or systems used to collect and analyze users' emotional data.

[0431] An "adaptive feedback mechanism" is a device or system that has the function of adjusting the content of feedback based on analyzed emotional data.

[0432] The system of this invention consists of a server and a terminal to improve users' ability to protect themselves from fraud. First, the server collects data on fraudulent methods and analyzes it using a data analysis tool based on Python. Based on this analysis, it generates fraud scenarios. The scenarios are created using generative AI models such as TensorFlow or PyTorch and are customized based on the user's profile.

[0433] The generated fraud scenarios are presented to the user via a device. The user experiences interactive training combining voice, text, and images on a device such as a smartphone or tablet. The device uses OpenCV to analyze the user's facial expressions and Librosa to analyze their voice tone, collecting emotional data in real time.

[0434] The collected emotional data is sent to a server and analyzed by an adaptive feedback system. The data obtained is used to measure the user's stress level and concentration, and to adjust the feedback accordingly. The feedback provides specific actions to enhance the user's learning effectiveness and is used to improve future scenario engagement.

[0435] As a concrete example, when a user is working on a phone scam scenario, if the emotion analysis system detects an anxious expression, the device will instruct the user, "Don't worry, let's try again." At this point, the system will clarify which part caused the user anxiety and suggest ways to improve.

[0436] As an example of a prompt, it is possible to ask the generative AI model a question such as, "How would the system provide support if the user expressed anxiety or confusion in a specific fraud scenario?" and have it determine the appropriate support method.

[0437] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0438] Step 1:

[0439] The server collects data on fraudulent practices from external databases and the internet. This data is preprocessed using a Python-based analysis tool to extract useful information. The input is raw fraud data, and the output is analyzed fraudulent practice information. The data is then filtered and classified to organize the information according to its intended use.

[0440] Step 2:

[0441] The server generates fraud scenarios based on analyzed fraud technique information. Since a generative AI model is used, the input is fraud technique information. The output is an interactive fraud scenario. The model is trained using TensorFlow and automatically generates scenarios tailored to the user's experience and profile.

[0442] Step 3:

[0443] The terminal presents the user with a fraud scenario received from the server. Audio, text, and images are presented to allow the user to access the scenario visually and aurally. The input is the generated fraud scenario, and the output is the user's actions and responses. In this step, the scenario progresses through an interactive user interface.

[0444] Step 4:

[0445] The device acquires key emotional data from the user's facial expressions and voice. It uses OpenCV to extract facial features and Librosa to analyze voice tone. The input is real-time facial and voice data from the user, and the output is emotional information read from the facial expressions.

[0446] Step 5:

[0447] The server receives emotional data transmitted from the terminal and analyzes it through an adaptive feedback mechanism. The input is emotional information obtained from the user, and the output is the analysis results for feedback generation. In this step, the user's stress level and concentration level are evaluated to prepare for generating adaptive feedback in the next step.

[0448] Step 6:

[0449] The server generates and provides feedback to the user based on the analysis results. Adaptive feedback mechanisms consider emotional information and create specific feedback to encourage improvement. The input is the analysis results, and the output is feedback information. The feedback is presented to the user in an interactive format and functions as guiding advice for future scenarios.

[0450] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0451] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0452] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0453] [Third Embodiment]

[0454] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0455] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0456] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0457] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0458] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0459] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0460] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0461] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0462] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0463] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0464] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0465] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0466] This invention is a fraud prevention education system that utilizes multimodal AI technology to provide users with realistic fraud scenarios. Specific embodiments of this invention are described below.

[0467] First, the server collects the latest data on fraudulent methods and analyzes it using data processing tools. This analysis helps understand patterns in fraudulent methods and extracts information useful for user education. Based on the information obtained, the server uses scenario generation tools to generate a variety of fraud scenarios. Each scenario incorporates fraudulent methods and characteristics and mimics real-life situations that users may face.

[0468] Meanwhile, the terminal receives fraud scenarios provided by the server and presents them interactively to the user using presentation tools. Based on information in the user profile, the scenarios are optimized for each individual and customized to suit their age, past training results, and other factors.

[0469] The user acts according to the presented fraud scenario and learns what consequences their responses will have. During this process, the device uses response recording devices to record the user's reactions in detail and sends this data to a server for later analysis.

[0470] The server uses the obtained user response data to activate a feedback generation mechanism and evaluate the user's actions. This feedback includes not only whether the choices were correct or incorrect, but also a detailed explanation of why those choices were appropriate or inappropriate. The feedback is provided to the user through a feedback presentation mechanism and contributes to strengthening their response capabilities.

[0471] Furthermore, the servers utilize various update mechanisms to regularly reflect information on the latest fraudulent tactics in the system. This ensures that users always receive training that is up-to-date.

[0472] As a concrete example, a simulation for the elderly involves a "telephone scam impersonating a bank." The server generates this scenario and plays the audio to the user through their terminal, recreating the typical approach of a scammer. The user experiences the situation of receiving a phone call in a simulated manner, making choices while considering how to respond. They can deepen their learning by receiving immediate feedback on the results.

[0473] In this configuration, this embodiment provides a system that effectively improves practical defenses against fraud. Furthermore, by using the obtained data to optimize training according to the individual needs of users, a more effective educational environment is realized.

[0474] The following describes the processing flow.

[0475] Step 1:

[0476] The server collects data on the latest fraud techniques from external sources and stores it in a database. These sources include news articles, expert reports, and user reports. The server uses multimodal AI to analyze the collected data and identify fraud patterns and trends.

[0477] Step 2:

[0478] The server designs fraud scenarios based on the analysis results. Using scenario generation tools, it creates scenarios that mimic actual fraud situations, including voice messages, text messages, and images. During this process, the scenarios are customized according to the user's age, skill level, and past performance.

[0479] Step 3:

[0480] The device receives a customized scenario based on the user profile and initiates interactive training. The device presents the scenario through audio playback, screen displays, and choice-based presentations, encouraging active user participation. Users make choices according to the scenario, and these are reflected in real time.

[0481] Step 4:

[0482] Users choose their actions based on the situation presented. For example, in a phone scam scenario, users can choose to "hang up," "continue asking questions," or "check with the bank."

[0483] Step 5:

[0484] The device records the user's responses and quickly sends them to the server. The transmitted response data is used for subsequent evaluation and feedback generation.

[0485] Step 6:

[0486] The server analyzes the received response data and evaluates the appropriateness of the user's choices. Based on this, it uses a feedback generation mechanism to construct feedback for the user. This feedback includes specific areas for improvement and success stories.

[0487] Step 7:

[0488] The device presents the generated feedback to the user. Through this feedback, the user can understand the strengths and weaknesses of their actions and use this information to improve future training sessions.

[0489] Step 8:

[0490] The server updates the system to incorporate the latest fraud techniques, keeping the scenarios always up-to-date. This allows users to continuously develop the skills to adapt to new situations.

[0491] (Example 1)

[0492] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0493] In response to the increasingly diverse fraud methods of today, there is a need to provide effective education tailored to individual users to improve their ability to defend against fraud. However, conventional systems have struggled to incorporate the latest information on fraud methods and situations in real time and provide personalized education. As a result, there is a challenge in that users cannot be trained to respond immediately when they actually face a fraud situation.

[0494] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0495] In this invention, the server includes data analysis means for collecting and analyzing fraudulent scheme information, scenario generation means for generating fraud scenarios based on the collected information, and scenario presentation means for interactively presenting the generated fraud scenarios to the user. This allows for the provision of education based on the latest fraudulent schemes to the user at all times, and enables the presentation of scenarios and adjustment of difficulty levels to meet individual needs.

[0496] "Fraudulent scheme information" refers to detailed information about fraudulent methods, techniques, and patterns, and is data used to understand the characteristics and trends of fraud by analyzing it.

[0497] "Data analysis means" refers to methods and apparatus for collecting information on fraudulent practices, processing that information using statistical analysis and machine learning, and extracting useful insights.

[0498] "Scenario generation means" refers to a method and apparatus for automatically generating fraud scenarios that are easy for users to understand and realistically set up, based on analyzed data.

[0499] A "scenario presentation means" is a method and apparatus that interactively presents a generated fraud scenario to a user, allowing them to simulate and experience an actual fraud situation.

[0500] "Response recording means" refers to a method and apparatus for recording the actions and choices made by a user in response to a scenario and storing that data for later analysis.

[0501] "Feedback generation means" refers to a method and apparatus for analyzing recorded user response results and automatically generating feedback that includes evaluations and suggestions for improvement regarding the response.

[0502] A "feedback presentation means" is a method and apparatus for providing generated feedback to the user visually or audibly and linking it to subsequent learning.

[0503] "Information update means" refers to methods and devices that regularly acquire the latest fraud techniques and reflect them in the system's database and scenarios to ensure that up-to-date education is always provided.

[0504] "Personalization means" are methods and devices for customizing scenarios based on the user's characteristics and past performance to provide the most suitable learning experience.

[0505] "Adaptive control means" refers to a method and apparatus for dynamically adjusting the difficulty level of fraud scenarios based on the user's age and past performance.

[0506] "Generation means" refers to a method and apparatus for constructing scenarios using a generative AI model and creating highly novel fraud scenarios.

[0507] This invention provides a sophisticated and personalized educational environment for users by utilizing data analysis technology and generative AI models as a fraud prevention education system. The following describes specific embodiments of this invention.

[0508] The server collects information on fraudulent practices from the internet and dedicated databases. Using programming languages ​​such as Python and APIs, this information is converted into a data frame format, and statistical methods and machine learning techniques are used through data analysis to extract patterns in fraudulent practices. Through this analysis, the characteristics of fraud are identified, and information that can be used for education is extracted.

[0509] Based on the analyzed data, the server generates fraud scenarios using a generative AI model. For example, using a GPT-based model, it can construct specific scenarios by inputting prompts such as, "Generate a phone fraud scenario that an elderly person might encounter." This allows for realistic training that improves users' ability to respond effectively.

[0510] The device presents the user with fraud scenarios received from the server. It provides a visually and audibly interactive experience using voice output devices and displays. The device references the user's profile and customizes the scenario based on their age and past training results.

[0511] Users act based on the presented scenarios and make choices according to the system's instructions. The user's responses are recorded by the terminal, and this data is sent to the server. This data is analyzed by the server using a feedback generation system, which then generates feedback including detailed explanations. This feedback is provided to the user via the terminal, facilitating reflection on learning outcomes and understanding areas for improvement.

[0512] As described above, this invention utilizes the latest information on fraudulent methods and provides users with a personalized learning experience and detailed feedback to create an effective fraud prevention education environment.

[0513] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0514] Step 1:

[0515] The server retrieves information on fraudulent practices from the internet and dedicated databases. It uses an internet connection and APIs or web scraping tools as input. The data is formatted into a data frame using Python or a database management system. The output is a well-organized set of fraudulent practice information. Specifically, it collects reports and warnings about fraud cases and stores them as a dataset.

[0516] Step 2:

[0517] The server processes the collected fraud scheme information using data analysis tools. The input is the fraud scheme data obtained in Step 1. The server analyzes the data using machine learning algorithms and statistical models to extract patterns of fraud schemes. This data processing produces a model that shows the characteristics and trends of fraud schemes as output. Specifically, it applies clustering and classification methods to reveal the characteristics of the fraud.

[0518] Step 3:

[0519] The server generates fraud scenarios using a generative AI model. The input is the characteristics and trends of fraudulent methods obtained in step 2. A prompt is input to the generative AI model, for example, "Generate a telephone fraud scenario that elderly people might encounter," and the system generates a scenario. The output is the text data of the scenario. Specifically, a natural language processing model such as GPT-4 is used to create a detailed fraud scenario.

[0520] Step 4:

[0521] The terminal receives the fraud scenario sent from the server and presents it to the user. The input is the fraud scenario obtained in step 3. The terminal interactively displays and plays the scenario using its display and audio playback functions. This output is the fraud scenario presented visually and audibly. The terminal refers to the user profile and adjusts the scenario to suit the user's attributes.

[0522] Step 5:

[0523] The user reacts to the presented fraud scenario and selects a response using various input functions. The input is the scenario presented by the terminal. The user's selection is recorded by the terminal and saved as a log. This output is the user's selection log. Specifically, the user makes selections through screen touches or voice responses.

[0524] Step 6:

[0525] The terminal sends user response data to the server. The input is the user selection log recorded in step 5. The server receives this for analysis and prepares for the next feedback generation process. This output is an analyzable user response dataset.

[0526] Step 7:

[0527] The server analyzes user response data and generates feedback. The input is the user response data obtained in step 6. Using the feedback generation mechanism, detailed feedback including results and areas for improvement is created. This output is the feedback information provided to the user. Specifically, based on the data analysis results, it explains why the choice was appropriate or inappropriate.

[0528] Step 8:

[0529] The device presents the generated feedback to the user. The input is the feedback information generated in step 7. The device displays and plays the feedback using visual and auditory means. This output is the feedback provided to the user. Upon receiving the feedback, the user can strengthen their ability to respond for future learning.

[0530] (Application Example 1)

[0531] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0532] Fraudulent tactics are becoming more sophisticated every day, and there is a growing need to provide users with practical defenses to combat the increasing frequency of fraudulent activities. However, many current systems only provide static information and do not offer an environment where users can actively learn how to deal with fraud. In particular, in today's society where fraudulent methods are rapidly evolving, there is a challenge in that it is difficult for users to keep up-to-date with the latest knowledge and effectively counter fraud.

[0533] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0534] In this invention, the server includes data analysis means for aggregating and analyzing information on fraudulent methods, situation generation means for forming a fraudulent situation based on the aggregated information, and display means for displaying the formed fraudulent situation to the user in an interactive format. This provides users with an opportunity to interactively learn about the latest fraudulent methods and countermeasures, enabling a rapid and practical improvement in defensive capabilities.

[0535] "Data analysis methods" refer to means of aggregating information related to fraudulent practices and understanding the characteristics and patterns of fraud through various analyses.

[0536] A "situation generation method" is a means of creating realistic scenarios by forming fraud situations that users may encounter, based on aggregated data.

[0537] A "display method" is a means of interactively presenting a generated fraud scenario to the user and prompting the user to respond.

[0538] A "response recording means" is a means for recording the user's interactive responses in detail and for analyzing that data later.

[0539] An "evaluation generation means" is a means for evaluating the user's response results, determining the correctness of their actions, and generating detailed feedback.

[0540] A "means of providing evaluation" refers to a method of providing users with the generated feedback and suggesting areas for improvement and ways to make improvements.

[0541] "Update methods" refer to measures to regularly acquire information on new fraudulent techniques and keep the fraud situation within the system up to date.

[0542] A "mobile device version of a display means" is a mobile display means equipped with communication functions and a user interface, capable of providing users with practical training in fraud prevention.

[0543] The system for implementing this invention is a fraud prevention education system that utilizes multimodal AI technology. The system consists of a server and terminals, each with a clearly defined role.

[0544] First, the server aggregates the latest information on fraudulent methods and analyzes that data using data analysis tools. The software used here includes TensorFlow for data analysis. The server then uses the analyzed data to create various fraud scenarios using a scenario generation tool. The generated scenarios accurately reproduce the characteristics of the fraud and mimic situations that users might actually face.

[0545] The device receives fraud scenarios provided by the server and presents them interactively to the user through a display mechanism. The display utilizes a smartphone user interface and leverages React Native. The device also meticulously records the user's responses obtained through the dialogue using a corresponding recording mechanism. This data is then sent back to the server for later analysis.

[0546] Based on the user's choices in response to the provided scenario, the server activates an evaluation generation mechanism. The displayed evaluation includes the context of the user's choices and explains why a particular action is appropriate or inappropriate. The generated evaluation is provided to the user through an evaluation presentation mechanism to help refine their choices.

[0547] In operating this system, the server regularly acquires new fraud information and keeps the system up-to-date through update mechanisms. This allows users to constantly learn about new fraud methods and countermeasures.

[0548] A concrete example is "a scenario in which an elderly person simulates a phone scam." The server generates this scenario and reproduces the typical approach of a scammer through audio playback. The user simulates the situation of receiving a call and makes choices while considering how to respond. The user receives immediate feedback on the results, allowing them to deepen their learning.

[0549] An example of a prompt for a generative AI model is: "Create a typical scenario of a phone scam targeting the elderly, in a format that provides feedback on what actions the user should take."

[0550] In this way, the entire system works in coordination, enabling users to develop practical and adaptive fraud prevention capabilities.

[0551] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0552] Step 1:

[0553] The server collects the latest information on fraud techniques from the internet and cybersecurity reports. The input is external data resources, and the output is aggregated fraud technique data. Data analysis tools are used to analyze this data and extract fundamental information for understanding fraud patterns and characteristics.

[0554] Step 2:

[0555] The server utilizes the analyzed data to generate specific fraud scenarios using a situation generation mechanism. The input is the analyzed data, and the output is a fraud scenario for simulation. Using a generation AI model, realistic and challenging fraud situations are created, mimicking situations that users may encounter.

[0556] Step 3:

[0557] The terminal presents the user with fraud scenarios received from the server. The input is generated scenario data, and the output is an interactive display for the user. A smartphone user interface is used as the display method, allowing the user to directly engage with these scenarios.

[0558] Step 4:

[0559] The user responds to presented fraud scenarios. The input is the interactive scenario presented to the user, and the output is the user's response data. By interactively selecting and manipulating options on the device, the user visually learns how to respond.

[0560] Step 5:

[0561] The terminal records the user's response using a corresponding recording device and sends it to the server. The input is the user's response data, and the output is the transmission of data to the server for analysis. This prepares the data for subsequent feedback generation.

[0562] Step 6:

[0563] The server analyzes the received user response data using an evaluation generation mechanism and creates feedback for the user. The input is the user's response data, and the output is feedback information. The feedback is constructed using a generation AI model, providing detailed information about the background of the choice and areas for improvement.

[0564] Step 7:

[0565] Using an evaluation presentation mechanism, the terminal displays the generated feedback to the user. The input is the generated feedback information, and the output is the display to the user. Through this feedback, the user can review and improve their own response skills.

[0566] Step 8:

[0567] The server regularly collects new fraud information through update mechanisms, keeping the system up-to-date. Input consists of new data from external data resources, while output consists of updated fraud technique data. This ensures the freshness and effectiveness of the scenarios, providing users with the latest countermeasures at all times.

[0568] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0569] This invention provides an interactive educational system that combines multimodal AI technology and an emotion engine to improve users' ability to protect themselves from fraud. Specific embodiments of this invention are described below.

[0570] The server first collects the latest data on fraud techniques and analyzes it to extract useful information. Based on this, it uses a scenario generation system to generate scenarios that mimic a wide range of fraud situations. At this time, the scenarios are individually customized based on the user profile, and appropriate training is provided according to the user's experience and skill level.

[0571] The device interactively presents the received scenario and begins training the user. It encourages user participation and provides a comprehensive simulation experience combining voice, text, images, and other elements.

[0572] The crucial role here is that of the emotion engine. The device collects and analyzes emotional data in real time from the user's facial expressions, tone of voice, and other factors. This emotional data is used to understand the user's stress level and concentration level. For example, if the user is anxious or confused, the system senses this situation and provides appropriate support.

[0573] The server meticulously records user responses using a response recording mechanism that incorporates emotional data, and uses this data for subsequent evaluation and feedback generation. The feedback generation mechanism takes emotional data into consideration and adjusts the content of the feedback to ensure the user has a better learning experience.

[0574] The feedback is presented via the device and serves as a guide for users to take specific actions for self-improvement. This enhances the learning effect, and users can use the feedback to prepare for the next simulation.

[0575] This emotion-driven adaptive learning process aims to improve the ability to effectively understand and counter fraud scenarios. Furthermore, the server regularly incorporates new fraud data and updates the system, ensuring users are always trained to adapt to the latest situations. In this way, emotion recognition provides the most effective learning support for users.

[0576] The following describes the processing flow.

[0577] Step 1:

[0578] The server collects data on the latest fraud techniques from a variety of sources on the internet. This includes raw data from news, forums, and expert reports. The collected data is stored in a database.

[0579] Step 2:

[0580] The server analyzes accumulated data using natural language processing technology to extract current trends and characteristics of fraudulent methods. Based on these analysis results, it constructs fraud scenarios that users are likely to encounter.

[0581] Step 3:

[0582] The server references each user's profile information (age, skill level, past training data, etc.) and individually customizes the fraud scenarios it generates. This ensures that training scenarios with appropriate difficulty and content are prepared for each user.

[0583] Step 4:

[0584] The device presents the user with a pre-prepared fraud scenario. It offers an interactive experience through the presentation methods, allowing the user to actively participate. Various media are used, including voice instructions, text messages, and images.

[0585] Step 5:

[0586] The user chooses actions according to the presented fraud scenario. The scenario presents options, and the simulation progresses as the user selects the appropriate action.

[0587] Step 6:

[0588] The device activates an emotion engine that collects the user's facial expressions and voice tone in real time, acquiring the user's emotional data. The analyzed emotional data is used to understand the user's situation.

[0589] Step 7:

[0590] The server analyzes user selection and sentiment data sent from the terminal. This allows it to evaluate the appropriateness of the user's chosen actions and understand the user's stress levels and learning progress from the sentiment data.

[0591] Step 8:

[0592] The server uses feedback generation mechanisms to construct appropriate feedback based on the analysis results obtained. This feedback includes specific advice regarding the user's choices and emotional support based on sentiment data.

[0593] Step 9:

[0594] The device presents the generated feedback to the user. By receiving the feedback, the user can learn how to improve their responses and what to pay attention to in the next training session.

[0595] Step 10:

[0596] The server regularly acquires the latest information on fraudulent methods and updates the system-wide scenarios and learning content. This ensures that users are always trained on the most up-to-date fraudulent techniques.

[0597] (Example 2)

[0598] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0599] In modern society, fraudulent methods are becoming increasingly sophisticated and diverse. Consequently, it is crucial for users to develop the ability to recognize and defend against fraud based on their own judgment. However, existing countermeasures are limited to providing uniform information and lack interactive support tailored to the individual characteristics and emotional states of users. Therefore, providing a learning environment optimized for each individual user is a key challenge.

[0600] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0601] In this invention, the server includes information processing means for collecting and analyzing fraudulent scheme information, situation generation means for generating fraudulent situations based on the collected information, and emotion analysis means for analyzing the user's emotional state and providing situation-appropriate support. This makes it possible to provide an interactive learning experience optimized for each individual user and effectively improve fraud prevention capabilities.

[0602] "Information processing means" refers to technical means for collecting data related to fraudulent methods, analyzing that data, and extracting useful information.

[0603] A "situation generation means" is a technical means for imitating or creating specific fraud situations based on collected and analyzed information on fraudulent methods.

[0604] A "presentation means" is a technical means for showing the generated fraud situation to the user and enabling interactive communication with the user.

[0605] A "response recording means" is a technical means for recording interactive responses by users and evaluating user behavior by analyzing that data.

[0606] An "evaluation generation means" is a technical means for generating an evaluation based on the user's response results and clearly indicating areas for improvement and learning points.

[0607] An "evaluation presentation means" is a technical means that transmits generated evaluation information to the user, enabling the user to understand the effectiveness of their own learning and apply that understanding to their next actions.

[0608] "Update methods" refer to technical means for regularly acquiring the latest fraud information and keeping the system's status and data up-to-date at all times.

[0609] "Emotional analysis tools" are technical tools that collect emotional data such as a user's facial expressions and tone of voice, and analyze it in order to provide appropriate support according to the situation.

[0610] "Optimization methods" refer to technical means that customize fraud situations individually based on user characteristic information to provide a more effective learning experience.

[0611] A "complexity adjustment mechanism" is a technical means for appropriately adjusting the difficulty and complexity of fraud scenarios based on the user's characteristics and past learning results.

[0612] This invention is an interactive learning system for improving users' ability to deal with cyber fraud. First, the server collects the latest information on fraudulent methods from the internet and various databases. In this process, data analysis is performed using, for example, NLTK, a Python library that uses natural language processing technology, to analyze fraud patterns.

[0613] The server then uses a generative AI model to construct a fraud scenario. Specifically, it uses a general generative model and generates a fraud scenario by taking the prompt "Create a scenario based on the latest fraud techniques" as input.

[0614] The terminal receives this scenario sent from the server and presents it to the user in an interactive format. The terminal uses technologies such as HTML5 and JavaScript to present content that combines audio, text, and images to the user, providing a comprehensive anti-fraud experience. This allows the user to consider countermeasures in real time against a virtual fraud scenario.

[0615] As a key component, the device incorporates an emotion analysis engine. The device collects the user's facial expressions and voice tone through its camera and microphone, and uses this data to analyze the user's emotions in real time, leveraging machine learning libraries such as TensorFlow. This allows the system to provide immediate support if the user experiences anxiety or confusion.

[0616] The server generates evaluation information and feedback based on user response and sentiment data obtained from the terminal. This allows users to receive specific advice on areas for improvement and skills to strengthen. The system regularly incorporates new fraud information, ensuring that it is always up-to-date and able to respond to users effectively.

[0617] This system will allow users to deepen their understanding of fraud and significantly improve their ability to take practical countermeasures.

[0618] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0619] Step 1:

[0620] The server collects the latest information on fraudulent methods from the internet and specific databases. It uses web scraping techniques to extract data, which is then used as input. Next, it performs text analysis using natural language processing techniques to extract useful information about fraud trends and specific methods as output. This process prepares the fraud data for the system's next use.

[0621] Step 2:

[0622] The server generates fraud scenarios based on collected and analyzed fraud data. During this process, it uses a generation AI model and is prompted with the message, "Create a scenario based on the latest fraud techniques." The AI ​​model outputs a text scenario that mimics a specific fraud scene, and this scenario forms the basis for subsequent processing.

[0623] Step 3:

[0624] The server receives user profile data (e.g., age, work history, past training history) as input and customizes the generated scenarios based on this data. Using machine learning libraries such as Scikit-learn, it clusters the user's profile and adjusts the difficulty and content of the scenarios to best suit the user before outputting them.

[0625] Step 4:

[0626] The device receives a customized scenario sent from the server and presents it interactively to the user. Using HTML5 and JavaScript technologies, the device generates interactive content combining audio, text, and images, allowing the user to experience a real-life fraud scenario. User input consists of choices and actions within the scenario, and the results determine the next development of the scenario.

[0627] Step 5:

[0628] The device acquires the user's facial expressions and voice as input through its camera and microphone, and analyzes their emotions in real time. This utilizes machine learning platforms such as TensorFlow. The output of the emotion analysis serves as support information when the user shows anxiety or confusion, and is used to provide appropriate guidance and advice.

[0629] Step 6:

[0630] The server takes user interaction data and emotion data received from the terminal as input to record responses and generate evaluations. This generates feedback based on the user's behavior and emotions, and the evaluation is output as specific actions that the user can use for self-improvement. The feedback is provided to the user through the terminal.

[0631] Step 7:

[0632] The server periodically acquires new fraud information and uses this information to update the system. New fraud data is input here, and based on this, scenarios are regenerated, making it possible to always provide users with the latest fraud prevention training as output.

[0633] (Application Example 2)

[0634] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0635] As fraudulent methods become more diverse and sophisticated, there are limits to how effectively individual users can improve their fraud prevention capabilities. Furthermore, traditional education systems fail to optimize training to take into account the emotional changes of users, resulting in insufficient learning efficiency.

[0636] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0637] In this invention, the server includes information processing means for collecting and analyzing fraud method data, situation generation means for generating fraud situations based on the collected information, and presentation means for interactively presenting the generated fraud situations to the user. This enables adaptive optimization of training content based on the user's emotional data, resulting in more effective learning support.

[0638] "Information processing means" refers to devices or systems that have the function of collecting and analyzing data related to fraudulent methods.

[0639] A "situation generation means" is a device or system that creates a fraudulent situation based on collected information.

[0640] A "presentation means" refers to a device or system for interactively displaying the generated fraud situation to the user.

[0641] A "response recording means" is a device or system for recording and analyzing a user's interactive responses.

[0642] A "feedback generation means" is a device or system that has the function of creating feedback based on the user's response.

[0643] A "feedback presentation means" is a device or system for providing generated feedback to the user.

[0644] An "update mechanism" is a device or system that has the function of regularly acquiring new fraud information and improving the situation generated based on that information.

[0645] "Emotional analysis tools" refer to devices or systems used to collect and analyze users' emotional data.

[0646] An "adaptive feedback mechanism" is a device or system that has the function of adjusting the content of feedback based on analyzed emotional data.

[0647] The system of this invention consists of a server and a terminal to improve users' ability to protect themselves from fraud. First, the server collects data on fraudulent methods and analyzes it using a data analysis tool based on Python. Based on this analysis, it generates fraud scenarios. The scenarios are created using generative AI models such as TensorFlow or PyTorch and are customized based on the user's profile.

[0648] The generated fraud scenarios are presented to the user via a device. The user experiences interactive training combining voice, text, and images on a device such as a smartphone or tablet. The device uses OpenCV to analyze the user's facial expressions and Librosa to analyze their voice tone, collecting emotional data in real time.

[0649] The collected emotional data is sent to a server and analyzed by an adaptive feedback system. The data obtained is used to measure the user's stress level and concentration, and to adjust the feedback accordingly. The feedback provides specific actions to enhance the user's learning effectiveness and is used to improve future scenario engagement.

[0650] As a concrete example, when a user is working on a phone scam scenario, if the emotion analysis system detects an anxious expression, the device will instruct the user, "Don't worry, let's try again." At this point, the system will clarify which part caused the user anxiety and suggest ways to improve.

[0651] As an example of a prompt, it is possible to ask the generative AI model a question such as, "How would the system provide support if the user expressed anxiety or confusion in a specific fraud scenario?" and have it determine the appropriate support method.

[0652] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0653] Step 1:

[0654] The server collects data on fraudulent practices from external databases and the internet. This data is preprocessed using a Python-based analysis tool to extract useful information. The input is raw fraud data, and the output is analyzed fraudulent practice information. The data is then filtered and classified to organize the information according to its intended use.

[0655] Step 2:

[0656] The server generates fraud scenarios based on analyzed fraud technique information. Since a generative AI model is used, the input is fraud technique information. The output is an interactive fraud scenario. The model is trained using TensorFlow and automatically generates scenarios tailored to the user's experience and profile.

[0657] Step 3:

[0658] The terminal presents the user with a fraud scenario received from the server. Audio, text, and images are presented to allow the user to access the scenario visually and aurally. The input is the generated fraud scenario, and the output is the user's actions and responses. In this step, the scenario progresses through an interactive user interface.

[0659] Step 4:

[0660] The device acquires key emotional data from the user's facial expressions and voice. It uses OpenCV to extract facial features and Librosa to analyze voice tone. The input is real-time facial and voice data from the user, and the output is emotional information read from the facial expressions.

[0661] Step 5:

[0662] The server receives emotional data transmitted from the terminal and analyzes it through an adaptive feedback mechanism. The input is emotional information obtained from the user, and the output is the analysis results for feedback generation. In this step, the user's stress level and concentration level are evaluated to prepare for generating adaptive feedback in the next step.

[0663] Step 6:

[0664] The server generates and provides feedback to the user based on the analysis results. Adaptive feedback mechanisms consider emotional information and create specific feedback to encourage improvement. The input is the analysis results, and the output is feedback information. The feedback is presented to the user in an interactive format and functions as guiding advice for future scenarios.

[0665] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0666] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0667] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0668] [Fourth Embodiment]

[0669] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0670] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0671] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0672] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0673] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0674] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0675] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0676] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0677] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0678] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0679] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0680] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0681] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0682] This invention is a fraud prevention education system that utilizes multimodal AI technology to provide users with realistic fraud scenarios. Specific embodiments of this invention are described below.

[0683] First, the server collects the latest data on fraudulent methods and analyzes it using data processing tools. This analysis helps understand patterns in fraudulent methods and extracts information useful for user education. Based on the information obtained, the server uses scenario generation tools to generate a variety of fraud scenarios. Each scenario incorporates fraudulent methods and characteristics and mimics real-life situations that users may face.

[0684] Meanwhile, the terminal receives fraud scenarios provided by the server and presents them interactively to the user using presentation tools. Based on information in the user profile, the scenarios are optimized for each individual and customized to suit their age, past training results, and other factors.

[0685] The user acts according to the presented fraud scenario and learns what consequences their responses will have. During this process, the device uses response recording devices to record the user's reactions in detail and sends this data to a server for later analysis.

[0686] The server uses the obtained user response data to activate a feedback generation mechanism and evaluate the user's actions. This feedback includes not only whether the choices were correct or incorrect, but also a detailed explanation of why those choices were appropriate or inappropriate. The feedback is provided to the user through a feedback presentation mechanism and contributes to strengthening their response capabilities.

[0687] Furthermore, the servers utilize various update mechanisms to regularly reflect information on the latest fraudulent tactics in the system. This ensures that users always receive training that is up-to-date.

[0688] As a concrete example, a simulation for the elderly involves a "telephone scam impersonating a bank." The server generates this scenario and plays the audio to the user through their terminal, recreating the typical approach of a scammer. The user experiences the situation of receiving a phone call in a simulated manner, making choices while considering how to respond. They can deepen their learning by receiving immediate feedback on the results.

[0689] In this configuration, this embodiment provides a system that effectively improves practical defenses against fraud. Furthermore, by using the obtained data to optimize training according to the individual needs of users, a more effective educational environment is realized.

[0690] The following describes the processing flow.

[0691] Step 1:

[0692] The server collects data on the latest fraud techniques from external sources and stores it in a database. These sources include news articles, expert reports, and user reports. The server uses multimodal AI to analyze the collected data and identify fraud patterns and trends.

[0693] Step 2:

[0694] The server designs fraud scenarios based on the analysis results. Using scenario generation tools, it creates scenarios that mimic actual fraud situations, including voice messages, text messages, and images. During this process, the scenarios are customized according to the user's age, skill level, and past performance.

[0695] Step 3:

[0696] The device receives a customized scenario based on the user profile and initiates interactive training. The device presents the scenario through audio playback, screen displays, and choice-based presentations, encouraging active user participation. Users make choices according to the scenario, and these are reflected in real time.

[0697] Step 4:

[0698] Users choose their actions based on the situation presented. For example, in a phone scam scenario, users can choose to "hang up," "continue asking questions," or "check with the bank."

[0699] Step 5:

[0700] The device records the user's responses and quickly sends them to the server. The transmitted response data is used for subsequent evaluation and feedback generation.

[0701] Step 6:

[0702] The server analyzes the received response data and evaluates the appropriateness of the user's choices. Based on this, it uses a feedback generation mechanism to construct feedback for the user. This feedback includes specific areas for improvement and success stories.

[0703] Step 7:

[0704] The device presents the generated feedback to the user. Through this feedback, the user can understand the strengths and weaknesses of their actions and use this information to improve future training sessions.

[0705] Step 8:

[0706] The server updates the system to incorporate the latest fraud techniques, keeping the scenarios always up-to-date. This allows users to continuously develop the skills to adapt to new situations.

[0707] (Example 1)

[0708] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0709] In response to the increasingly diverse fraud methods of today, there is a need to provide effective education tailored to individual users to improve their ability to defend against fraud. However, conventional systems have struggled to incorporate the latest information on fraud methods and situations in real time and provide personalized education. As a result, there is a challenge in that users cannot be trained to respond immediately when they actually face a fraud situation.

[0710] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0711] In this invention, the server includes data analysis means for collecting and analyzing fraudulent scheme information, scenario generation means for generating fraud scenarios based on the collected information, and scenario presentation means for interactively presenting the generated fraud scenarios to the user. This allows for the provision of education based on the latest fraudulent schemes to the user at all times, and enables the presentation of scenarios and adjustment of difficulty levels to meet individual needs.

[0712] "Fraudulent scheme information" refers to detailed information about fraudulent methods, techniques, and patterns, and is data used to understand the characteristics and trends of fraud by analyzing it.

[0713] "Data analysis means" refers to methods and apparatus for collecting information on fraudulent practices, processing that information using statistical analysis and machine learning, and extracting useful insights.

[0714] "Scenario generation means" refers to a method and apparatus for automatically generating fraud scenarios that are easy for users to understand and realistically set up, based on analyzed data.

[0715] A "scenario presentation means" is a method and apparatus that interactively presents a generated fraud scenario to a user, allowing them to simulate and experience an actual fraud situation.

[0716] "Response recording means" refers to a method and apparatus for recording the actions and choices made by a user in response to a scenario and storing that data for later analysis.

[0717] "Feedback generation means" refers to a method and apparatus for analyzing recorded user response results and automatically generating feedback that includes evaluations and suggestions for improvement regarding the response.

[0718] A "feedback presentation means" is a method and apparatus for providing generated feedback to the user visually or audibly and linking it to subsequent learning.

[0719] "Information update means" refers to methods and devices that regularly acquire the latest fraud techniques and reflect them in the system's database and scenarios to ensure that up-to-date education is always provided.

[0720] "Personalization means" are methods and devices for customizing scenarios based on the user's characteristics and past performance to provide the most suitable learning experience.

[0721] "Adaptive control means" refers to a method and apparatus for dynamically adjusting the difficulty level of fraud scenarios based on the user's age and past performance.

[0722] "Generation means" refers to a method and apparatus for constructing scenarios using a generative AI model and creating highly novel fraud scenarios.

[0723] This invention provides a sophisticated and personalized educational environment for users by utilizing data analysis technology and generative AI models as a fraud prevention education system. The following describes specific embodiments of this invention.

[0724] The server collects information on fraudulent practices from the internet and dedicated databases. Using programming languages ​​such as Python and APIs, this information is converted into a data frame format, and statistical methods and machine learning techniques are used through data analysis to extract patterns in fraudulent practices. Through this analysis, the characteristics of fraud are identified, and information that can be used for education is extracted.

[0725] Based on the analyzed data, the server generates fraud scenarios using a generative AI model. For example, using a GPT-based model, it can construct specific scenarios by inputting prompts such as, "Generate a phone fraud scenario that an elderly person might encounter." This allows for realistic training that improves users' ability to respond effectively.

[0726] The device presents the user with fraud scenarios received from the server. It provides a visually and audibly interactive experience using voice output devices and displays. The device references the user's profile and customizes the scenario based on their age and past training results.

[0727] Users act based on the presented scenarios and make choices according to the system's instructions. The user's responses are recorded by the terminal, and this data is sent to the server. This data is analyzed by the server using a feedback generation system, which then generates feedback including detailed explanations. This feedback is provided to the user via the terminal, facilitating reflection on learning outcomes and understanding areas for improvement.

[0728] As described above, this invention utilizes the latest information on fraudulent methods and provides users with a personalized learning experience and detailed feedback to create an effective fraud prevention education environment.

[0729] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0730] Step 1:

[0731] The server retrieves information on fraudulent practices from the internet and dedicated databases. It uses an internet connection and APIs or web scraping tools as input. The data is formatted into a data frame using Python or a database management system. The output is a well-organized set of fraudulent practice information. Specifically, it collects reports and warnings about fraud cases and stores them as a dataset.

[0732] Step 2:

[0733] The server processes the collected fraud scheme information using data analysis tools. The input is the fraud scheme data obtained in Step 1. The server analyzes the data using machine learning algorithms and statistical models to extract patterns of fraud schemes. This data processing produces a model that shows the characteristics and trends of fraud schemes as output. Specifically, it applies clustering and classification methods to reveal the characteristics of the fraud.

[0734] Step 3:

[0735] The server generates fraud scenarios using a generative AI model. The input is the characteristics and trends of fraudulent methods obtained in step 2. A prompt is input to the generative AI model, for example, "Generate a telephone fraud scenario that elderly people might encounter," and the system generates a scenario. The output is the text data of the scenario. Specifically, a natural language processing model such as GPT-4 is used to create a detailed fraud scenario.

[0736] Step 4:

[0737] The terminal receives the fraud scenario sent from the server and presents it to the user. The input is the fraud scenario obtained in step 3. The terminal interactively displays and plays the scenario using its display and audio playback functions. This output is the fraud scenario presented visually and audibly. The terminal refers to the user profile and adjusts the scenario to suit the user's attributes.

[0738] Step 5:

[0739] The user reacts to the presented fraud scenario and selects a response using various input functions. The input is the scenario presented by the terminal. The user's selection is recorded by the terminal and saved as a log. This output is the user's selection log. Specifically, the user makes selections through screen touches or voice responses.

[0740] Step 6:

[0741] The terminal sends user response data to the server. The input is the user selection log recorded in step 5. The server receives this for analysis and prepares for the next feedback generation process. This output is an analyzable user response dataset.

[0742] Step 7:

[0743] The server analyzes user response data and generates feedback. The input is the user response data obtained in step 6. Using the feedback generation mechanism, detailed feedback including results and areas for improvement is created. This output is the feedback information provided to the user. Specifically, based on the data analysis results, it explains why the choice was appropriate or inappropriate.

[0744] Step 8:

[0745] The device presents the generated feedback to the user. The input is the feedback information generated in step 7. The device displays and plays the feedback using visual and auditory means. This output is the feedback provided to the user. Upon receiving the feedback, the user can strengthen their ability to respond for future learning.

[0746] (Application Example 1)

[0747] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0748] Fraudulent tactics are becoming more sophisticated every day, and there is a growing need to provide users with practical defenses to combat the increasing frequency of fraudulent activities. However, many current systems only provide static information and do not offer an environment where users can actively learn how to deal with fraud. In particular, in today's society where fraudulent methods are rapidly evolving, there is a challenge in that it is difficult for users to keep up-to-date with the latest knowledge and effectively counter fraud.

[0749] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0750] In this invention, the server includes data analysis means for aggregating and analyzing information on fraudulent methods, situation generation means for forming a fraudulent situation based on the aggregated information, and display means for displaying the formed fraudulent situation to the user in an interactive format. This provides users with an opportunity to interactively learn about the latest fraudulent methods and countermeasures, enabling a rapid and practical improvement in defensive capabilities.

[0751] "Data analysis methods" refer to means of aggregating information related to fraudulent practices and understanding the characteristics and patterns of fraud through various analyses.

[0752] A "situation generation method" is a means of creating realistic scenarios by forming fraud situations that users may encounter, based on aggregated data.

[0753] A "display method" is a means of interactively presenting a generated fraud scenario to the user and prompting the user to respond.

[0754] A "response recording means" is a means for recording the user's interactive responses in detail and for analyzing that data later.

[0755] An "evaluation generation means" is a means for evaluating the user's response results, determining the correctness of their actions, and generating detailed feedback.

[0756] A "means of providing evaluation" refers to a method of providing users with the generated feedback and suggesting areas for improvement and ways to make improvements.

[0757] "Update methods" refer to measures to regularly acquire information on new fraudulent techniques and keep the fraud situation within the system up to date.

[0758] A "mobile device version of a display means" is a mobile display means equipped with communication functions and a user interface, capable of providing users with practical training in fraud prevention.

[0759] The system for implementing this invention is a fraud prevention education system that utilizes multimodal AI technology. The system consists of a server and terminals, each with a clearly defined role.

[0760] First, the server aggregates the latest information on fraudulent methods and analyzes that data using data analysis tools. The software used here includes TensorFlow for data analysis. The server then uses the analyzed data to create various fraud scenarios using a scenario generation tool. The generated scenarios accurately reproduce the characteristics of the fraud and mimic situations that users might actually face.

[0761] The device receives fraud scenarios provided by the server and presents them interactively to the user through a display mechanism. The display utilizes a smartphone user interface and leverages React Native. The device also meticulously records the user's responses obtained through the dialogue using a corresponding recording mechanism. This data is then sent back to the server for later analysis.

[0762] Based on the user's choices in response to the provided scenario, the server activates an evaluation generation mechanism. The displayed evaluation includes the context of the user's choices and explains why a particular action is appropriate or inappropriate. The generated evaluation is provided to the user through an evaluation presentation mechanism to help refine their choices.

[0763] In operating this system, the server regularly acquires new fraud information and keeps the system up-to-date through update mechanisms. This allows users to constantly learn about new fraud methods and countermeasures.

[0764] A concrete example is "a scenario in which an elderly person simulates a phone scam." The server generates this scenario and reproduces the typical approach of a scammer through audio playback. The user simulates the situation of receiving a call and makes choices while considering how to respond. The user receives immediate feedback on the results, allowing them to deepen their learning.

[0765] An example of a prompt for a generative AI model is: "Create a typical scenario of a phone scam targeting the elderly, in a format that provides feedback on what actions the user should take."

[0766] In this way, the entire system works in coordination, enabling users to develop practical and adaptive fraud prevention capabilities.

[0767] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0768] Step 1:

[0769] The server collects the latest information on fraud techniques from the internet and cybersecurity reports. The input is external data resources, and the output is aggregated fraud technique data. Data analysis tools are used to analyze this data and extract fundamental information for understanding fraud patterns and characteristics.

[0770] Step 2:

[0771] The server utilizes the analyzed data to generate specific fraud scenarios using a situation generation mechanism. The input is the analyzed data, and the output is a fraud scenario for simulation. Using a generation AI model, realistic and challenging fraud situations are created, mimicking situations that users may encounter.

[0772] Step 3:

[0773] The terminal presents the user with fraud scenarios received from the server. The input is generated scenario data, and the output is an interactive display for the user. A smartphone user interface is used as the display method, allowing the user to directly engage with these scenarios.

[0774] Step 4:

[0775] The user responds to presented fraud scenarios. The input is the interactive scenario presented to the user, and the output is the user's response data. By interactively selecting and manipulating options on the device, the user visually learns how to respond.

[0776] Step 5:

[0777] The terminal records the user's response using a corresponding recording device and sends it to the server. The input is the user's response data, and the output is the transmission of data to the server for analysis. This prepares the data for subsequent feedback generation.

[0778] Step 6:

[0779] The server analyzes the received user response data using an evaluation generation mechanism and creates feedback for the user. The input is the user's response data, and the output is feedback information. The feedback is constructed using a generation AI model, providing detailed information about the background of the choice and areas for improvement.

[0780] Step 7:

[0781] Using an evaluation presentation mechanism, the terminal displays the generated feedback to the user. The input is the generated feedback information, and the output is the display to the user. Through this feedback, the user can review and improve their own response skills.

[0782] Step 8:

[0783] The server regularly collects new fraud information through update mechanisms, keeping the system up-to-date. Input consists of new data from external data resources, while output consists of updated fraud technique data. This ensures the freshness and effectiveness of the scenarios, providing users with the latest countermeasures at all times.

[0784] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0785] This invention provides an interactive educational system that combines multimodal AI technology and an emotion engine to improve users' ability to protect themselves from fraud. Specific embodiments of this invention are described below.

[0786] The server first collects the latest data on fraud techniques and analyzes it to extract useful information. Based on this, it uses a scenario generation system to generate scenarios that mimic a wide range of fraud situations. At this time, the scenarios are individually customized based on the user profile, and appropriate training is provided according to the user's experience and skill level.

[0787] The device interactively presents the received scenario and begins training the user. It encourages user participation and provides a comprehensive simulation experience combining voice, text, images, and other elements.

[0788] The crucial role here is that of the emotion engine. The device collects and analyzes emotional data in real time from the user's facial expressions, tone of voice, and other factors. This emotional data is used to understand the user's stress level and concentration level. For example, if the user is anxious or confused, the system senses this situation and provides appropriate support.

[0789] The server meticulously records user responses using a response recording mechanism that incorporates emotional data, and uses this data for subsequent evaluation and feedback generation. The feedback generation mechanism takes emotional data into consideration and adjusts the content of the feedback to ensure the user has a better learning experience.

[0790] The feedback is presented via the device and serves as a guide for users to take specific actions for self-improvement. This enhances the learning effect, and users can use the feedback to prepare for the next simulation.

[0791] This emotion-driven adaptive learning process aims to improve the ability to effectively understand and counter fraud scenarios. Furthermore, the server regularly incorporates new fraud data and updates the system, ensuring users are always trained to adapt to the latest situations. In this way, emotion recognition provides the most effective learning support for users.

[0792] The following describes the processing flow.

[0793] Step 1:

[0794] The server collects data on the latest fraud techniques from a variety of sources on the internet. This includes raw data from news, forums, and expert reports. The collected data is stored in a database.

[0795] Step 2:

[0796] The server analyzes accumulated data using natural language processing technology to extract current trends and characteristics of fraudulent methods. Based on these analysis results, it constructs fraud scenarios that users are likely to encounter.

[0797] Step 3:

[0798] The server references each user's profile information (age, skill level, past training data, etc.) and individually customizes the fraud scenarios it generates. This ensures that training scenarios with appropriate difficulty and content are prepared for each user.

[0799] Step 4:

[0800] The device presents the user with a pre-prepared fraud scenario. It offers an interactive experience through the presentation methods, allowing the user to actively participate. Various media are used, including voice instructions, text messages, and images.

[0801] Step 5:

[0802] The user chooses actions according to the presented fraud scenario. The scenario presents options, and the simulation progresses as the user selects the appropriate action.

[0803] Step 6:

[0804] The device activates an emotion engine that collects the user's facial expressions and voice tone in real time, acquiring the user's emotional data. The analyzed emotional data is used to understand the user's situation.

[0805] Step 7:

[0806] The server analyzes user selection and sentiment data sent from the terminal. This allows it to evaluate the appropriateness of the user's chosen actions and understand the user's stress levels and learning progress from the sentiment data.

[0807] Step 8:

[0808] The server uses feedback generation mechanisms to construct appropriate feedback based on the analysis results obtained. This feedback includes specific advice regarding the user's choices and emotional support based on sentiment data.

[0809] Step 9:

[0810] The device presents the generated feedback to the user. By receiving the feedback, the user can learn how to improve their responses and what to pay attention to in the next training session.

[0811] Step 10:

[0812] The server regularly acquires the latest information on fraudulent methods and updates the system-wide scenarios and learning content. This ensures that users are always trained on the most up-to-date fraudulent techniques.

[0813] (Example 2)

[0814] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0815] In modern society, fraudulent methods are becoming increasingly sophisticated and diverse. Consequently, it is crucial for users to develop the ability to recognize and defend against fraud based on their own judgment. However, existing countermeasures are limited to providing uniform information and lack interactive support tailored to the individual characteristics and emotional states of users. Therefore, providing a learning environment optimized for each individual user is a key challenge.

[0816] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0817] In this invention, the server includes information processing means for collecting and analyzing fraudulent scheme information, situation generation means for generating fraudulent situations based on the collected information, and emotion analysis means for analyzing the user's emotional state and providing situation-appropriate support. This makes it possible to provide an interactive learning experience optimized for each individual user and effectively improve fraud prevention capabilities.

[0818] "Information processing means" refers to technical means for collecting data related to fraudulent methods, analyzing that data, and extracting useful information.

[0819] A "situation generation means" is a technical means for imitating or creating specific fraud situations based on collected and analyzed information on fraudulent methods.

[0820] A "presentation means" is a technical means for showing the generated fraud situation to the user and enabling interactive communication with the user.

[0821] A "response recording means" is a technical means for recording interactive responses by users and evaluating user behavior by analyzing that data.

[0822] An "evaluation generation means" is a technical means for generating an evaluation based on the user's response results and clearly indicating areas for improvement and learning points.

[0823] An "evaluation presentation means" is a technical means that transmits generated evaluation information to the user, enabling the user to understand the effectiveness of their own learning and apply that understanding to their next actions.

[0824] "Update methods" refer to technical means for regularly acquiring the latest fraud information and keeping the system's status and data up-to-date at all times.

[0825] "Emotional analysis tools" are technical tools that collect emotional data such as a user's facial expressions and tone of voice, and analyze it in order to provide appropriate support according to the situation.

[0826] "Optimization methods" refer to technical means that customize fraud situations individually based on user characteristic information to provide a more effective learning experience.

[0827] A "complexity adjustment mechanism" is a technical means for appropriately adjusting the difficulty and complexity of fraud scenarios based on the user's characteristics and past learning results.

[0828] This invention is an interactive learning system for improving users' ability to deal with cyber fraud. First, the server collects the latest information on fraudulent methods from the internet and various databases. In this process, data analysis is performed using, for example, NLTK, a Python library that uses natural language processing technology, to analyze fraud patterns.

[0829] The server then uses a generative AI model to construct a fraud scenario. Specifically, it uses a general generative model and generates a fraud scenario by taking the prompt "Create a scenario based on the latest fraud techniques" as input.

[0830] The terminal receives this scenario sent from the server and presents it to the user in an interactive format. The terminal uses technologies such as HTML5 and JavaScript to present content that combines audio, text, and images to the user, providing a comprehensive anti-fraud experience. This allows the user to consider countermeasures in real time against a virtual fraud scenario.

[0831] As a key component, the device incorporates an emotion analysis engine. The device collects the user's facial expressions and voice tone through its camera and microphone, and uses this data to analyze the user's emotions in real time, leveraging machine learning libraries such as TensorFlow. This allows the system to provide immediate support if the user experiences anxiety or confusion.

[0832] The server generates evaluation information and feedback based on user response and sentiment data obtained from the terminal. This allows users to receive specific advice on areas for improvement and skills to strengthen. The system regularly incorporates new fraud information, ensuring that it is always up-to-date and able to respond to users effectively.

[0833] This system will allow users to deepen their understanding of fraud and significantly improve their ability to take practical countermeasures.

[0834] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0835] Step 1:

[0836] The server collects the latest information on fraudulent methods from the internet and specific databases. It uses web scraping techniques to extract data, which is then used as input. Next, it performs text analysis using natural language processing techniques to extract useful information about fraud trends and specific methods as output. This process prepares the fraud data for the system's next use.

[0837] Step 2:

[0838] The server generates fraud scenarios based on collected and analyzed fraud data. During this process, it uses a generation AI model and is prompted with the message, "Create a scenario based on the latest fraud techniques." The AI ​​model outputs a text scenario that mimics a specific fraud scene, and this scenario forms the basis for subsequent processing.

[0839] Step 3:

[0840] The server receives user profile data (e.g., age, work history, past training history) as input and customizes the generated scenarios based on this data. Using machine learning libraries such as Scikit-learn, it clusters the user's profile and adjusts the difficulty and content of the scenarios to best suit the user before outputting them.

[0841] Step 4:

[0842] The device receives a customized scenario sent from the server and presents it interactively to the user. Using HTML5 and JavaScript technologies, the device generates interactive content combining audio, text, and images, allowing the user to experience a real-life fraud scenario. User input consists of choices and actions within the scenario, and the results determine the next development of the scenario.

[0843] Step 5:

[0844] The device acquires the user's facial expressions and voice as input through its camera and microphone, and analyzes their emotions in real time. This utilizes machine learning platforms such as TensorFlow. The output of the emotion analysis serves as support information when the user shows anxiety or confusion, and is used to provide appropriate guidance and advice.

[0845] Step 6:

[0846] The server takes user interaction data and emotion data received from the terminal as input to record responses and generate evaluations. This generates feedback based on the user's behavior and emotions, and the evaluation is output as specific actions that the user can use for self-improvement. The feedback is provided to the user through the terminal.

[0847] Step 7:

[0848] The server periodically acquires new fraud information and uses this information to update the system. New fraud data is input here, and based on this, scenarios are regenerated, making it possible to always provide users with the latest fraud prevention training as output.

[0849] (Application Example 2)

[0850] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0851] As fraudulent methods become more diverse and sophisticated, there are limits to how effectively individual users can improve their fraud prevention capabilities. Furthermore, traditional education systems fail to optimize training to take into account the emotional changes of users, resulting in insufficient learning efficiency.

[0852] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0853] In this invention, the server includes information processing means for collecting and analyzing fraud method data, situation generation means for generating fraud situations based on the collected information, and presentation means for interactively presenting the generated fraud situations to the user. This enables adaptive optimization of training content based on the user's emotional data, resulting in more effective learning support.

[0854] "Information processing means" refers to devices or systems that have the function of collecting and analyzing data related to fraudulent methods.

[0855] A "situation generation means" is a device or system that creates a fraudulent situation based on collected information.

[0856] A "presentation means" refers to a device or system for interactively displaying the generated fraud situation to the user.

[0857] A "response recording means" is a device or system for recording and analyzing a user's interactive responses.

[0858] A "feedback generation means" is a device or system that has the function of creating feedback based on the user's response.

[0859] A "feedback presentation means" is a device or system for providing generated feedback to the user.

[0860] An "update mechanism" is a device or system that has the function of regularly acquiring new fraud information and improving the situation generated based on that information.

[0861] "Emotional analysis tools" refer to devices or systems used to collect and analyze users' emotional data.

[0862] An "adaptive feedback mechanism" is a device or system that has the function of adjusting the content of feedback based on analyzed emotional data.

[0863] The system of this invention consists of a server and a terminal to improve users' ability to protect themselves from fraud. First, the server collects data on fraudulent methods and analyzes it using a data analysis tool based on Python. Based on this analysis, it generates fraud scenarios. The scenarios are created using generative AI models such as TensorFlow or PyTorch and are customized based on the user's profile.

[0864] The generated fraud scenarios are presented to the user via a device. The user experiences interactive training combining voice, text, and images on a device such as a smartphone or tablet. The device uses OpenCV to analyze the user's facial expressions and Librosa to analyze their voice tone, collecting emotional data in real time.

[0865] The collected emotional data is sent to a server and analyzed by an adaptive feedback system. The data obtained is used to measure the user's stress level and concentration, and to adjust the feedback accordingly. The feedback provides specific actions to enhance the user's learning effectiveness and is used to improve future scenario engagement.

[0866] As a concrete example, when a user is working on a phone scam scenario, if the emotion analysis system detects an anxious expression, the device will instruct the user, "Don't worry, let's try again." At this point, the system will clarify which part caused the user anxiety and suggest ways to improve.

[0867] As an example of a prompt, it is possible to ask the generative AI model a question such as, "How would the system provide support if the user expressed anxiety or confusion in a specific fraud scenario?" and have it determine the appropriate support method.

[0868] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0869] Step 1:

[0870] The server collects data on fraudulent practices from external databases and the internet. This data is preprocessed using a Python-based analysis tool to extract useful information. The input is raw fraud data, and the output is analyzed fraudulent practice information. The data is then filtered and classified to organize the information according to its intended use.

[0871] Step 2:

[0872] The server generates fraud scenarios based on analyzed fraud technique information. Since a generative AI model is used, the input is fraud technique information. The output is an interactive fraud scenario. The model is trained using TensorFlow and automatically generates scenarios tailored to the user's experience and profile.

[0873] Step 3:

[0874] The terminal presents the user with a fraud scenario received from the server. Audio, text, and images are presented to allow the user to access the scenario visually and aurally. The input is the generated fraud scenario, and the output is the user's actions and responses. In this step, the scenario progresses through an interactive user interface.

[0875] Step 4:

[0876] The device acquires key emotional data from the user's facial expressions and voice. It uses OpenCV to extract facial features and Librosa to analyze voice tone. The input is real-time facial and voice data from the user, and the output is emotional information read from the facial expressions.

[0877] Step 5:

[0878] The server receives emotional data transmitted from the terminal and analyzes it through an adaptive feedback mechanism. The input is emotional information obtained from the user, and the output is the analysis results for feedback generation. In this step, the user's stress level and concentration level are evaluated to prepare for generating adaptive feedback in the next step.

[0879] Step 6:

[0880] The server generates and provides feedback to the user based on the analysis results. Adaptive feedback mechanisms consider emotional information and create specific feedback to encourage improvement. The input is the analysis results, and the output is feedback information. The feedback is presented to the user in an interactive format and functions as guiding advice for future scenarios.

[0881] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0882] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0883] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0884] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0885] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0886] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0887] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0888] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0889] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0890] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0891] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0892] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0893] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0894] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0895] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0896] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0897] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0898] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0899] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0900] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0901] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0902] The following is further disclosed regarding the embodiments described above.

[0903] (Claim 1)

[0904] A data processing method for collecting and analyzing fraudulent methods data,

[0905] A scenario generation method for generating fraud scenarios based on collected data,

[0906] A presentation method that interactively presents a generated fraud scenario to the user,

[0907] A response recording means for recording and analyzing interactive user responses,

[0908] A feedback generation means that generates feedback based on the user's response results,

[0909] A feedback presentation means that provides the generated feedback to the user,

[0910] A means of updating the generated scenarios by regularly acquiring new fraud data,

[0911] A system that includes this.

[0912] (Claim 2)

[0913] The system according to claim 1, further comprising a customization means for customizing fraud scenarios based on user information.

[0914] (Claim 3)

[0915] The system according to claim 1, further comprising difficulty adjustment means for adjusting the difficulty of fraud scenarios based on the user's age and past performance.

[0916] "Example 1"

[0917] (Claim 1)

[0918] Data analysis tools for collecting and analyzing fraudulent methods,

[0919] A scenario generation method for generating fraud scenarios based on collected information,

[0920] A scenario presentation method that interactively presents generated fraud scenarios to users,

[0921] A response recording means for recording and evaluating interactive user responses,

[0922] A feedback generation means that generates feedback based on the user's response results,

[0923] A feedback presentation means that presents the generated feedback to the user,

[0924] A means of updating information that regularly acquires new fraud information and updates the generated scenarios,

[0925] Personalization methods that customize fraud scenarios based on user data,

[0926] Adaptive control means that adjusts the difficulty level of the scenario based on the user's characteristics and past performance,

[0927] A system that includes this.

[0928] (Claim 2)

[0929] The system according to claim 1, further comprising a feedback analysis means for analyzing user reactions and generating feedback including detailed explanations accordingly.

[0930] (Claim 3)

[0931] The system according to claim 1, further comprising a generation means for constructing fraud scenarios using a generation AI model.

[0932] "Application Example 1"

[0933] (Claim 1)

[0934] A data analysis tool that collects and analyzes information on fraudulent methods,

[0935] A means for generating a situation that forms a fraud situation based on aggregated information,

[0936] A display means that shows the fraud situation that has been created to the user in a dialogue format,

[0937] A means for recording and analyzing user interactions in an interactive format,

[0938] An evaluation generation means that generates an evaluation based on the user's response results,

[0939] A means for providing the generated evaluation to the user,

[0940] A means of updating information on new scams and the generated situation,

[0941] A mobile device version of a presentation means equipped with communication functions and a user interface, which provides practical training in fraud prevention,

[0942] A system that includes this.

[0943] (Claim 2)

[0944] The system according to claim 1, further comprising an optimization means for optimizing fraud situations based on user information.

[0945] (Claim 3)

[0946] The system according to claim 1, further comprising an adjustment means for adjusting the difficulty level of a fraud situation based on the user's age or past performance.

[0947] "Example 2 of combining an emotion engine"

[0948] (Claim 1)

[0949] Information processing tools for collecting and analyzing fraudulent methods,

[0950] A situation generation means that generates a fraud situation based on collected information,

[0951] A presentation method that presents the generated fraud situation to the user in a dialogue format,

[0952] A response recording means for recording and analyzing user dialogue responses,

[0953] An evaluation generation means that generates evaluation information based on the user's response results,

[0954] An evaluation presentation means that provides the generated evaluation information to the user,

[0955] A means of updating the generated situation by regularly acquiring new fraud information,

[0956] An emotional analysis tool that analyzes the emotional state of users and provides support according to the situation,

[0957] A system that includes this.

[0958] (Claim 2)

[0959] The system according to claim 1, further comprising an optimization means for optimizing fraud situations based on user characteristic information.

[0960] (Claim 3)

[0961] The system according to claim 1, further comprising complexity adjustment means for adjusting the complexity of fraud situations based on user characteristics and past results.

[0962] "Application example 2 when combining with an emotional engine"

[0963] (Claim 1)

[0964] Information processing means for collecting and analyzing fraud method data,

[0965] A situation generation means that generates a fraud situation based on collected information,

[0966] A presentation method that interactively presents the generated fraud situation to the user,

[0967] A response recording means for recording and analyzing interactive user responses,

[0968] A feedback generation means that generates feedback based on the user's response results,

[0969] A feedback presentation means that provides the generated feedback to the user,

[0970] A means of updating the generated situation by regularly acquiring new fraud information,

[0971] A means of sentiment analysis that collects and analyzes sentiment data,

[0972] Adaptive feedback means that adjusts the content of feedback based on emotional data,

[0973] A system that includes this.

[0974] (Claim 2)

[0975] The system according to claim 1, further comprising a customization means for customizing fraud situations based on user information.

[0976] (Claim 3)

[0977] The system according to claim 1, further comprising a difficulty adjustment means for adjusting the difficulty of fraud situations based on the user's age and past performance. [Explanation of symbols]

[0978] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A data processing method for collecting and analyzing fraudulent methods data, A scenario generation method for generating fraud scenarios based on collected data, A presentation method that interactively presents a generated fraud scenario to the user, A response recording means for recording and analyzing interactive user responses, A feedback generation means that generates feedback based on the user's response results, A feedback presentation means that provides the generated feedback to the user, A means of updating the generated scenarios by regularly acquiring new fraud data, A system that includes this.

2. The system according to claim 1, further comprising a customization means for customizing fraud scenarios based on user information.

3. The system according to claim 1, further comprising difficulty adjustment means for adjusting the difficulty of fraud scenarios based on the user's age and past performance.

Images