system

Abstract

We provide the system. [Solution] A means of generating fraud situations using a generation algorithm, A means for presenting the generated fraud situation to a communication device, A means of recognizing voice input from users in real time and converting it into text, A means for generating a fraudster's response using a machine learning model based on the said document, A means of analyzing user response history and providing improvement feedback to users, A means of implementing an interactive fraud training application on a user's communication device, A data processing device that includes a data processing device.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, fraud damages such as remittance fraud and phishing fraud have been increasing, and there is a problem that especially the elderly and young people are likely to be victimized. Along with this, the importance of crime prevention education to prevent fraud damages has been increasing, but with the current educational methods, there are limitations in effectively enhancing the response ability due to the difference in Internet literacy and the complexity of the modus operandi of fraudsters. Therefore, there is a demand for providing a new crime prevention education system that improves the response ability to fraud through a more realistic experience.

Means for Solving the Problems

[0005] This invention provides a system that enables interactive training by generating diverse fraud scenarios using a generation algorithm and presenting them to the user's terminal. It features a function that automatically generates fraudster responses based on the user's responses using a technology that recognizes and converts voice input from the user in real time. Furthermore, it provides a means to intuitively and practically improve the ability to deal with fraud by analyzing the user's response history and providing appropriate improvement feedback.

[0006] A "generative algorithm" is a computational method that creates data or information based on specific conditions or rules.

[0007] A "fraud scenario" is a story or situational setting that simulates a certain type of fraud.

[0008] A "user terminal" is a device that allows a human to access and operate a computer system through an interface.

[0009] "Voice input" is a method of providing information to a device using voice.

[0010] "Converting to text" is the process of changing audio information into digital text information.

[0011] An "AI model" is a data processing structure created to analyze data using artificial intelligence technology and perform a specific task.

[0012] "Response history" refers to a record of the answers and selections a user has made in the past.

[0013] "Improvement feedback" is information that informs users of areas for improvement in their actions and choices, thereby encouraging better results.

[0014] "Interactive training" is an educational method in which participants acquire knowledge and skills through active involvement. [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] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

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

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

[0018] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of 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, a RAM (Random Access Memory) with a reference number is a memory in which information is temporarily stored and is used as a work memory by the processor.

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

[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 provides an educational system to improve users' ability to respond to fraud. The system consists of a server and user terminals and conducts fraud training in an interactive manner that encourages active user participation.

[0037] The server first generates fraud scenarios using a generation algorithm. These scenarios mimic specific fraud methods and situations, and are designed to be intuitively understandable to the user. The generated scenarios are immediately delivered to the user's terminal.

[0038] On the user's terminal, the received fraud scenario is presented to the user in an interactive format. Through voice output and text display, the user chooses how to respond based on the presented scenario. At this time, the server converts the user's voice response into text in real time and uses an AI model to generate the fraudster's reaction to that response.

[0039] Users can test their judgment within a scenario by selecting from options or freely entering answers. The server analyzes the user's response history in detail, generating personalized feedback based on that analysis. This feedback includes specific advice on how the user can improve.

[0040] For example, if a user attempts a wire fraud scenario and makes a wrong choice, the server provides feedback on how that choice could be exploited by the fraudster. This allows the user to make better decisions in subsequent training sessions.

[0041] In this way, the present invention provides effective training for users to develop practical and continuous resistance to fraud. In particular, by creating an environment where the elderly and young people can learn while having fun, it realizes social value in preventing fraud.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server generates fraud scenarios using a generation algorithm based on past fraud case data stored in the database. Multiple patterns are available to reflect a variety of fraud methods.

[0045] Step 2:

[0046] The server sends the generated fraud scenario to the user's device. The user's device then transforms this scenario into an interactive UI and presents it to the user. This UI includes audio output and text display, allowing the user to understand the situation within the scenario.

[0047] Step 3:

[0048] The user reads the presented scenario and responds using voice or by selecting options. The user's response is recorded on the device using the voice input function and immediately sent to the server.

[0049] Step 4:

[0050] The server converts the received user's voice data into text and analyzes it using an AI model. Based on this analysis, it generates the scammer's next response and sends it back to the user's device.

[0051] Step 5:

[0052] The user's device receives a new scammer response from the server and presents it to the user. The user repeats this process, advancing the scenario.

[0053] Step 6:

[0054] The server analyzes the user's response history to assess their ability to handle fraud. Based on this assessment, it generates feedback for improvement and sends it to the user's device.

[0055] Step 7:

[0056] The user's device presents feedback from the server to the user. Based on this, the user reflects on their own response capabilities and learns how to deal with fraud.

[0057] Step 8:

[0058] Users can then choose to use the feedback to move on to the next training session or to challenge themselves with more practical applications.

[0059] (Example 1)

[0060] 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."

[0061] In modern society, fraudulent methods are becoming increasingly sophisticated, raising the risk of many people becoming victims. In particular, there is a need for effective training methods to prevent fraud, especially for users who lack sufficient knowledge and skills to deal with such scams. Current educational methods do not encourage interactive participation from users, making it difficult to adequately improve practical response capabilities.

[0062] 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.

[0063] In this invention, the server includes means for generating fraud scenarios using a generation program, means for recognizing voice input from a user in real time and converting it into text information, and means for generating a fraudster's response using a generation AI model based on the text information. This makes it possible for users to effectively and interactively improve their ability to respond to fraud through scenarios that are based on actual fraud situations.

[0064] A "generator program" is software that includes algorithms for automatically creating fraud scenarios.

[0065] A "fraud scenario" is a hypothetical scenario that simulates the methods and circumstances of fraudulent activities and is provided to users for training purposes.

[0066] A "user terminal" is a computer device that receives fraud scenarios sent from the server and presents them to the user.

[0067] "Voice input" refers to the words or sounds that a user speaks into a device, and the medium through which this is captured by the system.

[0068] "Textual information" refers to information obtained by converting voice input into text format, and serves as the basis for analysis by generative AI models.

[0069] A "generative AI model" is an artificial intelligence model used to analyze input data and generate a specific output, such as the response of a con artist.

[0070] "Fraudster responses" refer to the actions and words of a virtual fraudster, generated by a generative AI model and presented in real time in response to the user's responses.

[0071] "Interactive methods" refer to interaction functions that allow users to directly select or input responses to the system, thereby testing their decision-making abilities within a scenario.

[0072] This invention is an educational system aimed at improving users' ability to respond to fraud. The system mainly consists of a server and user terminals.

[0073] The server first generates fraud scenarios using a generation program. These fraud scenarios are created using a generative AI model and natural language processing technology, simulating fraudulent methods and situations. The generated scenarios are sent to the user's terminal in JSON format. A concrete example is a scenario simulating a phishing email.

[0074] The user terminal interactively presents the received fraud scenario. The terminal features text display and audio output capabilities and is designed for intuitive user understanding. For example, it uses speech synthesis technology to play the scenario aloud while displaying the corresponding text on the screen.

[0075] Based on the presented scenario, users either click on an option or enter their answer via free text. If voice input is used, the device sends it back to the server. The server uses speech recognition technology to convert this into text, and then uses a generative AI model based on this text to generate a scammer's reaction. Through this interaction, users can experience a situation similar to a real scam and learn how to respond appropriately.

[0076] The responses provided by users are analyzed by the server. Based on the collected data, the server creates personalized improvement guidance for users and provides specific advice for the next training session. This allows users to deepen their understanding of fraud and develop effective response skills.

[0077] An example of a prompt might be, "Guide the best response for a user who has received a phishing email and is required to respond." Based on this prompt, the generative AI model generates new scenarios and responses to further improve user feedback.

[0078] The present invention, configured in this manner, is a system that helps users enhance their practical skills against fraud and contribute to a safer social life.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The server generates fraud scenarios using a generation program. It receives prompts and past scenario data as input and uses natural language processing and generative AI models to generate new fraud scenarios. The generated scenarios mimic fraudulent methods and situations, with a phishing email scenario being a concrete example of output.

[0082] Step 2:

[0083] The server sends the generated fraud scenario to the user's device. The output scenario is converted to JSON format and transferred to the device. The user's device receives this data and prepares for the next step.

[0084] Step 3:

[0085] The user terminal presents the received fraud scenario in an interactive format. It takes scenario data in JSON format as input and presents the scenario to the user using text display and audio playback technologies. Specifically, it displays text on the screen and presents information through speech synthesis.

[0086] Step 4:

[0087] Users make selections based on the presented scenario or freely enter answers. In the case of voice input, the device receives voice data as input and sends it to the server. During this process, the user's choices and voice commands are recorded and prepared for the next step.

[0088] Step 5:

[0089] The server converts the audio data received from the user into text in real time. Using speech recognition software, it transcribes the speech into text and supplies this text as input to a generative AI model. The output is the fraudster's response based on the generative AI model.

[0090] Step 6:

[0091] The server uses a generative AI model to generate responses from fraudsters and sends them to the user's terminal. The AI ​​model analyzes the input text and generates an appropriate response. This response is provided to the terminal as output, enabling the next interaction.

[0092] Step 7:

[0093] The user's device displays the scammer's response received from the server. The system then presents the user with further options and facilitates interaction for the next step. Specifically, new text or audio responses are presented.

[0094] Step 8:

[0095] The server analyzes the user's entire response history to generate improvement guidance. It uses the user's response history data as input and analyzes the data using machine learning algorithms. The output provides specific feedback on how the user should improve their behavior.

[0096] (Application Example 1)

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

[0098] This invention aims to solve the problem of providing an interactive educational system that helps users acquire the skills to effectively respond to actual fraud situations in order to prevent fraud from occurring.

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

[0100] In this invention, the server includes means for generating fraud scenarios using a generation algorithm, means for presenting the generated fraud scenarios to a communication device, and means for implementing an interactive fraud training application on the user's communication device. This allows users to learn while experiencing fraud scenarios similar to reality and strengthen their ability to defend against actual fraud.

[0101] A "generative algorithm" is a set of calculations used to automatically create fraudulent situations for a specific purpose.

[0102] A "fraud scenario" is a simulation that imitates fraudulent methods and situations, and is used for user education and training.

[0103] A "communication device" is a hardware device that has the function of sending and receiving data, and is used by users to access interactive content.

[0104] A "document" is a text format converted from voice input, used to provide information visually.

[0105] A "machine learning model" is a form of artificial intelligence that makes predictions and judgments based on data, and in this invention, it is used to generate the responses of a con artist.

[0106] An "interactive fraud training application" is interactive educational software designed to help users improve their ability to respond to fraud through the application.

[0107] A "data processing device" is a computer system that has the functions of receiving, processing, and outputting information, and constitutes the entire system of the present invention.

[0108] This invention is a system for developing users' ability to effectively respond to fraud. This system consists of a server and a communication device for the user.

[0109] The server uses a generation algorithm to create a virtual fraud scenario for the user to experience. For example, in a "telephone fraud" scenario, it generates a scenario in the voice of a fraudster, making suspicious requests to the user. This generated fraud scenario is presented to the user's communication device through an interactive fraud training application.

[0110] The user's communication device has the ability to recognize the user's voice input in real time and convert it into text. Speech recognition technologies such as Google® Speech-to-Text API are used for this process. The converted text is sent to a server, where a machine learning model (a generative AI model in this system) generates a fraudster's response and provides the user with the following scenario.

[0111] Furthermore, the server analyzes the user's response history in detail and generates personalized feedback based on that history. This feedback includes specific guidance on how the user can improve, helping them prepare for the next training session.

[0112] For example, in a scenario where a user is told over the phone that they "need money," if they decide it's "suspicious" and choose to hang up, the machine learning model will evaluate that action positively and provide feedback such as "contact the police after hanging up."

[0113] This system allows you to use prompts like this: "Choose the appropriate course of action to take when someone calls you and says, 'I need money.' Then, explain, with specific examples, why that choice is the best."

[0114] Through this invention, users can confidently develop their resistance to fraud and create a safer living environment.

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] The server creates fraud scenarios using a generation algorithm. Parameters such as the type and difficulty of the fraud are provided as input. Based on this data, the algorithm constructs fraud scenarios, and a virtual fraud scenario is obtained as output.

[0118] Step 2:

[0119] The server sends the generated fraud situation to the user's communication device. It receives fraud situation data as input and converts it into a format that can be distributed to the communication device. This converted data is then sent to the communication device as output.

[0120] Step 3:

[0121] The communication device presents the received fraud scenario to the user through an interactive fraud training application. This includes audio and text displays. The user experiences the presented fraud scenario and chooses an action based on the content.

[0122] Step 4:

[0123] The voice input spoken by the user is recognized in real time by the communication device and converted into text. The input is voice data, which is processed into text using the Google Speech-to-Text API. The output is the user's response in text format.

[0124] Step 5:

[0125] The server receives user responses in text format and uses a generative AI model to generate scammer responses based on them. The input for this step is the user's response text, which is parsed and processed by the AI ​​model, and the output is the scammer's next scenario.

[0126] Step 6:

[0127] The server collects and analyzes the user's response history and generates personalized improvement feedback. The input consists of data on the user's past choices and responses. Using data analysis techniques, the server evaluates the user's decisions and generates specific advice for improvement as output.

[0128] Step 7:

[0129] The feedback is sent to the user's communication device and presented to the user through the application. This allows the user to understand the correctness of their judgment and areas for improvement, and use this information to improve their next training session.

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

[0131] The system according to the present invention provides an interactive training environment that combines an emotion engine to enhance users' ability to respond to fraud. This system consists of a server, terminals, and diverse input data from users.

[0132] First, the server uses a generation algorithm to create fraud scenarios from a large amount of fraud data. These scenarios include various fraud methods and situations. The created fraud scenarios are immediately delivered to the user's device and presented to the user in an interactive format.

[0133] The device uses speech recognition technology to convert the user's voice responses into text. This text data is sent to a server and analyzed by an AI model. The scammer's response is generated based on this analysis and sent back to the device, where it is presented to the user. Throughout this interaction, an emotion engine recognizes the user's emotions from their voice and facial expressions, and makes dynamic adjustments according to the user's psychological state.

[0134] In particular, the scammer's reactions are adjusted in real time based on the user's emotions. For example, if the user is feeling anxious, the scammer's tone and content can be changed to provide a more realistic experience. This process allows users to participate in the simulation while maintaining a sense of tension and security.

[0135] All user responses and sentiment data are analyzed in detail on the server to assess fraud response capabilities. Based on the analysis, users are provided with feedback that includes specific areas for improvement. This feedback clearly identifies the user's strengths and weaknesses, similar to personalized coaching, and serves as material for appropriate guidance for future training.

[0136] For example, if a user makes an inappropriate response in a phone scam scenario, emotional data might be analyzed to show signs of tension. In this case, the feedback would provide advice on how to prepare for the next time and specific wording to use.

[0137] Thus, by closely combining emotions and interaction, this invention surpasses conventional fraud training systems, achieving a more advanced and personalized education. It provides a more effective and immersive learning experience for target users, such as the elderly and young people.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] The server extracts patterns from past fraud case data and uses a generation algorithm to create fraud scenarios for users. These scenarios are designed to replicate a variety of fraud methods.

[0141] Step 2:

[0142] The server sends the generated fraud scenario to the user's device. The device then presents this scenario to the user visually and audibly, providing an interactive experience.

[0143] Step 3:

[0144] Users respond to presented scenarios using voice and multiple-choice options. This input is based on the user's actions and decisions, and adapts to the situation at hand.

[0145] Step 4:

[0146] The device converts the user's voice responses into text in real time and sends it to the server. In parallel, the device analyzes the user's voice and facial expressions and generates emotion data using an emotion engine.

[0147] Step 5:

[0148] The server analyzes the received text data and sentiment data using an AI model. Based on this, it generates the next appropriate scammer response. Depending on the sentiment data, the scammer's response changes dynamically, determining the optimal tone and content to properly guide the user.

[0149] Step 6:

[0150] The device displays the scammer's response, sent from the server, to the user. During this process, the device continuously monitors the user's response and updates the sentiment data.

[0151] Step 7:

[0152] The server comprehensively analyzes the user's response history and sentiment data throughout the session to evaluate its fraud prevention capabilities.

[0153] Step 8:

[0154] The server generates feedback, including specific areas for improvement, based on the analysis results and sends it to the user's terminal. The terminal then presents this feedback to the user, providing information to help them in future training sessions and practical application in real life.

[0155] Step 9:

[0156] Users review feedback and choose to apply what they've learned to future training sessions and real-world situations. This allows them to enhance their defenses against fraud.

[0157] (Example 2)

[0158] 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".

[0159] In today's world, where fraud tactics continue to become more sophisticated, it is a difficult challenge for individual users to effectively improve their ability to respond to fraud. Traditional training methods often rely on general cases, making it difficult to learn flexible responses that are appropriate to the user's emotions and circumstances. Furthermore, there is a risk that users may repeat the same mistakes without realizing their own emotions.

[0160] 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.

[0161] In this invention, the server includes means for generating situation scenarios using a generation procedure, means for instantly recognizing voice input from the user and converting it into a string, and means for determining the user's emotional state using an emotion analysis engine and adaptively adjusting the response. This enables real-time responses that correspond to the user's emotions, thereby improving the ability to respond to fraud more effectively.

[0162] A "generative procedure" is a process for creating specific situations or scenarios based on a large amount of information.

[0163] A "situational scenario" is a virtual sequence that mimics a specific situation or event, designed to be experienced by users as a simulation.

[0164] A "user device" is a device used to receive and display information provided by the system, and includes smartphones, tablets, computers, and other similar devices.

[0165] "Voice input" is a method of having the system recognize what the user speaks as a digital signal.

[0166] A "string of characters" is data that has been converted to represent voice input in a digital format.

[0167] An "artificial intelligence model" is a computational model that uses algorithms to analyze unknown data and derive appropriate responses or conclusions based on that analysis.

[0168] "Response history" refers to a record of responses a user has made in the past, and is used to analyze patterns and trends in those responses.

[0169] "Improvement advice" refers to specific guidance and advice to help users provide better service.

[0170] An "emotion analysis engine" is a program or algorithm that analyzes a user's voice and facial expression data to determine their emotional state.

[0171] "Immediate" refers to processing or responding in real time without delay.

[0172] "Two-way communication" refers to methods or functions that enable users and systems to exchange information with each other.

[0173] This invention is a system that provides an interactive training environment to enhance the ability to respond to fraud. The system consists of a server, terminals, and users.

[0174] The server uses a generative AI model incorporating multiple deep learning algorithms to generate situational scenarios from a large amount of fraud data. These scenarios simulate various fraud situations that users may face, reproducing their methods and circumstances in detail. These generated scenarios are efficiently processed through a cloud computing environment.

[0175] The terminals are primarily mobile computing devices such as smartphones and tablets, which receive and display scenario data so that users can experience the scenarios in an interactive format. The terminals have speech recognition software installed, which converts the user's voice input into text data in real time. This converted text data is then sent back to the server and analyzed by an AI model.

[0176] Users can experience various scenarios using this system. For example, in a scenario where a scam call is received, the user responds through the device, and the response is immediately analyzed to generate the next reaction. At this time, the user's emotional state is determined from the user's voice and facial expressions by an emotion analysis engine, and the character playing the scammer can adjust their response based on that feedback.

[0177] As a concrete example, consider a scenario where a user practices responding to a phishing email. The prompt might read, "Your account has been used fraudulently. Click the link to learn more," and the user is required to attempt the appropriate course of action. In this way, the system enables real-time practice of responding to actual phishing scenarios.

[0178] This invention combines emotions and interaction to provide users with an environment where they can constantly learn the optimal coping mechanisms and avoid feeling anxious. As a result, this system realizes an educational environment that allows for individualized instruction.

[0179] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0180] Step 1:

[0181] The server collects a large amount of fraud data and generates situational scenarios using a generative AI model. Past fraud event data is used as input, and the AI ​​model analyzes this data to output a variety of fraud scenarios. Here, the fraud methods and situations are specifically visualized as scenarios.

[0182] Step 2:

[0183] The server distributes the generated fraud scenario to the user's device. Data transfer takes place, with the scenario data being sent from the server to the terminal. The terminal receives the data and displays it to the user in a visualized format. This allows the user to experience the fraud scenario presented interactively.

[0184] Step 3:

[0185] The device accepts the user's voice input and converts it into text data using speech recognition software. Actual voice input is analyzed by speech recognition technology, and the user's response is output as text. This allows the user's response to be obtained in digital format.

[0186] Step 4:

[0187] The server receives text data sent from the terminal and analyzes it using an AI model. This analysis evaluates the user's input text and generates the scammer's next response. Here, the AI ​​processes the data computationally, enabling the scenario to progress in a flexible manner.

[0188] Step 5:

[0189] The device uses an emotion analysis engine to analyze the user's voice and facial expression data to determine the user's emotional state. This process analyzes patterns in voice and facial expressions and outputs an emotional evaluation value. Based on this, the server adjusts the scammer's response in real time and presents the response to the user.

[0190] Step 6:

[0191] The server comprehensively analyzes all user responses and sentiment data to assess fraud response capabilities and generate improvement suggestions. This step uses data from across the entire system as input and outputs feedback to help users overcome their weaknesses. This allows users to reflect on their responses and prepare for future interactions.

[0192] (Application Example 2)

[0193] 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".

[0194] In recent years, fraudulent methods have become more sophisticated and diverse, making it difficult for ordinary people to respond accurately and quickly to these scams. Furthermore, conventional fraud prevention training systems lack real-time response adjustments based on the user's emotions, and therefore have the problem of not being able to adequately cultivate the ability to apply their skills in actual fraud situations. This invention aims to solve these problems and provide users with a training environment that is tailored to their individual psychological state.

[0195] 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.

[0196] In this invention, the server includes means for generating fraud scenarios using a generation algorithm, means for presenting the generated fraud scenarios to an information terminal, and means for analyzing the user's emotions with an emotion recognition engine and adjusting the fraudster's performance. This makes it possible for users to receive realistic and personalized training in response to fraud scenarios.

[0197] A "generative algorithm" is a computational method for automatically creating fraud scenarios, generating scenarios that reflect various situations and methods based on a vast amount of fraud data.

[0198] An "information terminal" refers to an electronic device used by a user to receive interactive fraud training, such as a smartphone or tablet.

[0199] An "emotion recognition engine" is a technology for analyzing a user's emotional state. It evaluates psychological responses from voice and facial expression data and adjusts interactions based on that information.

[0200] "Performing as a con artist" means dynamically changing the con artist's behavior in a scam scenario to make the user experience more realistic, such as altering their voice tone and word choice in response to the user's reactions.

[0201] To implement this invention, a system is required that utilizes a user terminal, a server, speech recognition technology, and an emotion recognition engine. The server constructs fraud scenarios using a generation algorithm. These fraud scenarios include various fraudulent methods and situations.

[0202] The device receives voice input from the user and converts it to text using speech recognition software. The widely used "speech_recognition" library can be utilized for this speech conversion. The converted text is sent to a server and analyzed by an AI model. If necessary, the generation AI model dynamically generates responses to the scammer and sends them to the user's device.

[0203] Furthermore, the emotion recognition engine analyzes the user's voice and facial expression data to evaluate their emotional state. Based on this evaluation, the server adjusts the con artist's performance to provide a more realistic scenario experience. For example, if the user feels uneasy, the con artist's tone and what they say can be changed.

[0204] Through an interactive interface on the device, users have the ability to choose from several possible responses. These options are optimized based on the user's response and emotional state.

[0205] Such systems are designed to help users acquire more practical skills in various fraud scenarios and are particularly useful in fraud prevention education for the elderly and young people. For example, a possible prompt for the generation AI model could be "Generate lines a fraudster would say when the user becomes anxious." This prompt allows for appropriate responses tailored to the user's psychological state.

[0206] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0207] Step 1:

[0208] The server generates fraud scenarios using a generation algorithm. It receives pre-stored fraud data as input, analyzes it, and outputs scenarios that include a variety of fraud situations. These generated fraud scenarios form the basis of the user's learning experience.

[0209] Step 2:

[0210] The server sends the generated fraud scenario to the user's terminal. The input here is the fraud scenario obtained in step 1, and the output is the scenario data displayed on the user's terminal. This data is presented through an interactive user interface and is displayed in a way that is easy for the user to understand.

[0211] Step 3:

[0212] The user uses a device to perform voice input. The user's voice is registered on the device as input and converted into text data by speech recognition software. The output is the user's response, converted into text. This text is necessary for subsequent analysis.

[0213] Step 4:

[0214] The terminal sends the user's voice, converted into text, to the server. Here, the input is the text obtained from the speech recognition process, and the output generates data that is sent to the server for analysis.

[0215] Step 5:

[0216] The server analyzes the user's text response using an AI model. The input is the user's text, and based on this, it generates a scammer's response. The output is the scammer's response data to the user's response. This response is adjusted in real time and presented to the user.

[0217] Step 6:

[0218] The server analyzes the user's emotions using an emotion recognition engine. The input is voice and facial expression data, and the output is an evaluation of the user's emotional state. This evaluation result is used to adjust the con artist's responses.

[0219] Step 7:

[0220] The server dynamically adjusts the con artist's performance based on the results of emotion recognition. The emotion recognition evaluation results are used as input, and the con artist's tone and speech are changed in real time. The output is a refined scenario designed to provide the user with a more immersive dialogue.

[0221] Step 8:

[0222] The user selects their next action from interactive options displayed on their device. The input is pre-configured scenario information from the server, which presents options to help determine the next action. The output is the next scenario development based on the user's selection.

[0223] 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.

[0224] Data generation model 58 is a type of 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.

[0225] 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.

[0226] [Second Embodiment]

[0227] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0228] 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.

[0229] 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).

[0230] 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.

[0231] 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.

[0232] 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).

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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".

[0239] This invention provides an educational system to improve users' ability to respond to fraud. The system consists of a server and user terminals and conducts fraud training in an interactive manner that encourages active user participation.

[0240] The server first generates fraud scenarios using a generation algorithm. These scenarios mimic specific fraud methods and situations, and are designed to be intuitively understandable to the user. The generated scenarios are immediately delivered to the user's terminal.

[0241] On the user's terminal, the received fraud scenario is presented to the user in an interactive format. Through voice output and text display, the user chooses how to respond based on the presented scenario. At this time, the server converts the user's voice response into text in real time and uses an AI model to generate the fraudster's reaction to that response.

[0242] Users can test their judgment within a scenario by selecting from options or freely entering answers. The server analyzes the user's response history in detail, generating personalized feedback based on that analysis. This feedback includes specific advice on how the user can improve.

[0243] For example, if a user attempts a wire fraud scenario and makes a wrong choice, the server provides feedback on how that choice could be exploited by the fraudster. This allows the user to make better decisions in subsequent training sessions.

[0244] In this way, the present invention provides effective training for users to develop practical and continuous resistance to fraud. In particular, by creating an environment where the elderly and young people can learn while having fun, it realizes social value in preventing fraud.

[0245] The following describes the processing flow.

[0246] Step 1:

[0247] The server generates fraud scenarios using a generation algorithm based on past fraud case data stored in the database. Multiple patterns are available to reflect a variety of fraud methods.

[0248] Step 2:

[0249] The server sends the generated fraud scenario to the user's device. The user's device then transforms this scenario into an interactive UI and presents it to the user. This UI includes audio output and text display, allowing the user to understand the situation within the scenario.

[0250] Step 3:

[0251] The user reads the presented scenario and responds using voice or by selecting options. The user's response is recorded on the device using the voice input function and immediately sent to the server.

[0252] Step 4:

[0253] The server converts the received user's voice data into text and analyzes it using an AI model. Based on this analysis, it generates the scammer's next response and sends it back to the user's device.

[0254] Step 5:

[0255] The user's device receives a new scammer response from the server and presents it to the user. The user repeats this process, advancing the scenario.

[0256] Step 6:

[0257] The server analyzes the user's response history to assess their ability to handle fraud. Based on this assessment, it generates feedback for improvement and sends it to the user's device.

[0258] Step 7:

[0259] The user's device presents feedback from the server to the user. Based on this, the user reflects on their own response capabilities and learns how to deal with fraud.

[0260] Step 8:

[0261] Users can then choose to use the feedback to move on to the next training session or to challenge themselves with more practical applications.

[0262] (Example 1)

[0263] 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."

[0264] In modern society, fraudulent methods are becoming increasingly sophisticated, raising the risk of many people becoming victims. In particular, there is a need for effective training methods to prevent fraud, especially for users who lack sufficient knowledge and skills to deal with such scams. Current educational methods do not encourage interactive participation from users, making it difficult to adequately improve practical response capabilities.

[0265] 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.

[0266] In this invention, the server includes means for generating fraud scenarios using a generation program, means for recognizing voice input from a user in real time and converting it into text information, and means for generating a fraudster's response using a generation AI model based on the text information. This makes it possible for users to effectively and interactively improve their ability to respond to fraud through scenarios that are based on actual fraud situations.

[0267] A "generator program" is software that includes algorithms for automatically creating fraud scenarios.

[0268] A "fraud scenario" is a hypothetical scenario that simulates the methods and circumstances of fraudulent activities and is provided to users for training purposes.

[0269] A "user terminal" is a computer device that receives fraud scenarios sent from the server and presents them to the user.

[0270] "Voice input" refers to the words or sounds that a user speaks into a device, and the medium through which this is captured by the system.

[0271] "Textual information" refers to information obtained by converting voice input into text format, and serves as the basis for analysis by generative AI models.

[0272] A "generative AI model" is an artificial intelligence model used to analyze input data and generate a specific output, such as the response of a con artist.

[0273] "Fraudster responses" refer to the actions and words of a virtual fraudster, generated by a generative AI model and presented in real time in response to the user's responses.

[0274] "Interactive methods" refer to interaction functions that allow users to directly select or input responses to the system, thereby testing their decision-making abilities within a scenario.

[0275] This invention is an educational system aimed at improving users' ability to respond to fraud. The system mainly consists of a server and user terminals.

[0276] The server first generates fraud scenarios using a generation program. These fraud scenarios are created using a generative AI model and natural language processing technology, simulating fraudulent methods and situations. The generated scenarios are sent to the user's terminal in JSON format. A concrete example is a scenario simulating a phishing email.

[0277] The user terminal interactively presents the received fraud scenario. The terminal features text display and audio output capabilities and is designed for intuitive user understanding. For example, it uses speech synthesis technology to play the scenario aloud while displaying the corresponding text on the screen.

[0278] Based on the presented scenario, users either click on an option or enter their answer via free text. If voice input is used, the device sends it back to the server. The server uses speech recognition technology to convert this into text, and then uses a generative AI model based on this text to generate a scammer's reaction. Through this interaction, users can experience a situation similar to a real scam and learn how to respond appropriately.

[0279] The responses provided by users are analyzed by the server. Based on the collected data, the server creates personalized improvement guidance for users and provides specific advice for the next training session. This allows users to deepen their understanding of fraud and develop effective response skills.

[0280] An example of a prompt might be, "Guide the best response for a user who has received a phishing email and is required to respond." Based on this prompt, the generative AI model generates new scenarios and responses to further improve user feedback.

[0281] The present invention, configured in this manner, is a system that helps users enhance their practical skills against fraud and contribute to a safer social life.

[0282] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0283] Step 1:

[0284] The server generates fraud scenarios using a generation program. As input, it receives prompt texts and past scenario data, and uses natural language processing and generative AI models to generate new fraud scenarios. The generated scenarios simulate fraud methods and situations, and as a specific example, a phishing email scenario is obtained as output.

[0285] Step 2:

[0286] The server sends the generated fraud scenario to the user terminal. The output scenario is converted into JSON format and transferred to the terminal. The user terminal receives this data and prepares for the next step.

[0287] Step 3:

[0288] The user terminal presents the received fraud scenario in an interactive format. It obtains the scenario data in JSON format as input and presents the scenario to the user using text display and voice playback technologies. As specific operations, text display on the screen and information presentation by voice synthesis are performed.

[0289] Step 4:

[0290] The user makes selections or freely enters responses based on the presented scenario. In the case of voice input, the terminal receives the voice data as input and sends it to the server. In this process, what options the user selects or what voice commands the user issues are recorded and prepared for the next step.

[0291] Step 5:

[0292] The server converts the voice data received from the user into character information in real time. It uses voice recognition software to convert the voice into text and supplies this text as input to the generative AI model. As output, a response from the fraudster based on the generative AI model is obtained.

[0293] Step 6:

[0294] The server uses a generative AI model to generate responses from fraudsters and sends them to the user's terminal. The AI ​​model analyzes the input text and generates an appropriate response. This response is provided to the terminal as output, enabling the next interaction.

[0295] Step 7:

[0296] The user's device displays the scammer's response received from the server. The system then presents the user with further options and facilitates interaction for the next step. Specifically, new text or audio responses are presented.

[0297] Step 8:

[0298] The server analyzes the user's entire response history to generate improvement guidance. It uses the user's response history data as input and analyzes the data using machine learning algorithms. The output provides specific feedback on how the user should improve their behavior.

[0299] (Application Example 1)

[0300] 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."

[0301] This invention aims to solve the problem of providing an interactive educational system that helps users acquire the skills to effectively respond to actual fraud situations in order to prevent fraud from occurring.

[0302] 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.

[0303] In this invention, the server includes means for generating a fraud situation using a generation algorithm, means for presenting the generated fraud situation to a communication device, and means for implementing an interactive fraud training application on the user's communication device. As a result, the user can learn while experiencing a fraud situation similar to the real one, and it becomes possible to enhance the defensive ability against actual fraud.

[0304] The "generation algorithm" is a computational procedure for automatically creating a fraud situation according to a specific purpose.

[0305] The "fraud situation" refers to a simulation that imitates the methods and situations of fraud and is used for educating and training users.

[0306] The "communication device" is a hardware device having a function of transmitting and receiving data and is used for a user to access interactive content.

[0307] The "document" is what converts voice input into text format and is used to visually provide information.

[0308] The "machine learning model" is a form of artificial intelligence for making predictions and judgments based on data and is used to generate the reactions of fraudsters in this invention.

[0309] The "interactive fraud training application" is a two-way educational software for users to enhance their ability to respond to fraud through the application.

[0310] The "data processing device" is a computer system having functions of receiving, processing, and outputting information and constitutes the entire system of the present invention.

[0311] This invention is a system for developing users' ability to effectively respond to fraud. This system consists of a server and a communication device for the user.

[0312] The server uses a generation algorithm to create a virtual fraud scenario for the user to experience. For example, in a "telephone fraud" scenario, it generates a scenario in the voice of a fraudster, making suspicious requests to the user. This generated fraud scenario is presented to the user's communication device through an interactive fraud training application.

[0313] The user's communication device has the capability to recognize the user's voice input in real time and convert it into text. Speech recognition technologies such as the Google Speech-to-Text API are used for this process. The converted text is sent to a server, where a machine learning model (a generative AI model in this system) generates a fraudster's response and presents the user with the following scenario.

[0314] Furthermore, the server analyzes the user's response history in detail and generates personalized feedback based on that history. This feedback includes specific guidance on how the user can improve, helping them prepare for the next training session.

[0315] For example, in a scenario where a user is told over the phone that they "need money," if they decide it's "suspicious" and choose to hang up, the machine learning model will evaluate that action positively and provide feedback such as "contact the police after hanging up."

[0316] This system allows you to use prompts like this: "Choose the appropriate course of action to take when someone calls you and says, 'I need money.' Then, explain, with specific examples, why that choice is the best."

[0317] Through this invention, users can confidently develop their resistance to fraud and create a safer living environment.

[0318] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0319] Step 1:

[0320] The server creates fraud scenarios using a generation algorithm. Parameters such as the type and difficulty of the fraud are provided as input. Based on this data, the algorithm constructs fraud scenarios, and a virtual fraud scenario is obtained as output.

[0321] Step 2:

[0322] The server sends the generated fraud situation to the user's communication device. It receives fraud situation data as input and converts it into a format that can be distributed to the communication device. This converted data is then sent to the communication device as output.

[0323] Step 3:

[0324] The communication device presents the received fraud scenario to the user through an interactive fraud training application. This includes audio and text displays. The user experiences the presented fraud scenario and chooses an action based on the content.

[0325] Step 4:

[0326] The voice input spoken by the user is recognized in real time by the communication device and converted into text. The input is voice data, which is processed into text using the Google Speech-to-Text API. The output is the user's response in text format.

[0327] Step 5:

[0328] The server receives user responses in text format and uses a generative AI model to generate scammer responses based on them. The input for this step is the user's response text, which is parsed and processed by the AI ​​model, and the output is the scammer's next scenario.

[0329] Step 6:

[0330] The server collects and analyzes the user's response history and generates personalized improvement feedback. The input consists of data on the user's past choices and responses. Using data analysis techniques, the server evaluates the user's decisions and generates specific advice for improvement as output.

[0331] Step 7:

[0332] The feedback is sent to the user's communication device and presented to the user through the application. This allows the user to understand the correctness of their judgment and areas for improvement, and use this information to improve their next training session.

[0333] 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.

[0334] The system according to the present invention provides an interactive training environment that combines an emotion engine to enhance users' ability to respond to fraud. This system consists of a server, terminals, and diverse input data from users.

[0335] First, the server uses a generation algorithm to create fraud scenarios from a large amount of fraud data. These scenarios include various fraud methods and situations. The created fraud scenarios are immediately delivered to the user's device and presented to the user in an interactive format.

[0336] The device uses speech recognition technology to convert the user's voice responses into text. This text data is sent to a server and analyzed by an AI model. The scammer's response is generated based on this analysis and sent back to the device, where it is presented to the user. Throughout this interaction, an emotion engine recognizes the user's emotions from their voice and facial expressions, and makes dynamic adjustments according to the user's psychological state.

[0337] In particular, the scammer's reactions are adjusted in real time based on the user's emotions. For example, if the user is feeling anxious, the scammer's tone and content can be changed to provide a more realistic experience. This process allows users to participate in the simulation while maintaining a sense of tension and security.

[0338] All user responses and sentiment data are analyzed in detail on the server to assess fraud response capabilities. Based on the analysis, users are provided with feedback that includes specific areas for improvement. This feedback clearly identifies the user's strengths and weaknesses, similar to personalized coaching, and serves as material for appropriate guidance for future training.

[0339] For example, if a user makes an inappropriate response in a phone scam scenario, emotional data might be analyzed to show signs of tension. In this case, the feedback would provide advice on how to prepare for the next time and specific wording to use.

[0340] Thus, by closely combining emotions and interaction, this invention surpasses conventional fraud training systems, achieving a more advanced and personalized education. It provides a more effective and immersive learning experience for target users, such as the elderly and young people.

[0341] The following describes the processing flow.

[0342] Step 1:

[0343] The server extracts patterns from past fraud case data and uses a generation algorithm to create fraud scenarios for users. These scenarios are designed to replicate a variety of fraud methods.

[0344] Step 2:

[0345] The server sends the generated fraud scenario to the user's device. The device then presents this scenario to the user visually and audibly, providing an interactive experience.

[0346] Step 3:

[0347] Users respond to presented scenarios using voice and multiple-choice options. This input is based on the user's actions and decisions, and adapts to the situation at hand.

[0348] Step 4:

[0349] The device converts the user's voice responses into text in real time and sends it to the server. In parallel, the device analyzes the user's voice and facial expressions and generates emotion data using an emotion engine.

[0350] Step 5:

[0351] The server analyzes the received text data and sentiment data using an AI model. Based on this, it generates the next appropriate scammer response. Depending on the sentiment data, the scammer's response changes dynamically, determining the optimal tone and content to properly guide the user.

[0352] Step 6:

[0353] The device displays the scammer's response, sent from the server, to the user. During this process, the device continuously monitors the user's response and updates the sentiment data.

[0354] Step 7:

[0355] The server comprehensively analyzes the user's response history and sentiment data throughout the session to evaluate its fraud prevention capabilities.

[0356] Step 8:

[0357] The server generates feedback, including specific areas for improvement, based on the analysis results and sends it to the user's terminal. The terminal then presents this feedback to the user, providing information to help them in future training sessions and practical application in real life.

[0358] Step 9:

[0359] Users review feedback and choose to apply what they've learned to future training sessions and real-world situations. This allows them to enhance their defenses against fraud.

[0360] (Example 2)

[0361] 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".

[0362] In today's world, where fraud tactics continue to become more sophisticated, it is a difficult challenge for individual users to effectively improve their ability to respond to fraud. Traditional training methods often rely on general cases, making it difficult to learn flexible responses that are appropriate to the user's emotions and circumstances. Furthermore, there is a risk that users may repeat the same mistakes without realizing their own emotions.

[0363] 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.

[0364] In this invention, the server includes means for generating situation scenarios using a generation procedure, means for instantly recognizing voice input from the user and converting it into a string, and means for determining the user's emotional state using an emotion analysis engine and adaptively adjusting the response. This enables real-time responses that correspond to the user's emotions, thereby improving the ability to respond to fraud more effectively.

[0365] A "generative procedure" is a process for creating specific situations or scenarios based on a large amount of information.

[0366] A "situational scenario" is a virtual sequence that mimics a specific situation or event, designed to be experienced by users as a simulation.

[0367] A "user device" is a device used to receive and display information provided by the system, and includes smartphones, tablets, computers, and other similar devices.

[0368] "Voice input" is a method of having the system recognize what the user speaks as a digital signal.

[0369] A "string of characters" is data that has been converted to represent voice input in a digital format.

[0370] An "artificial intelligence model" is a computational model that uses algorithms to analyze unknown data and derive appropriate responses or conclusions based on that analysis.

[0371] "Response history" refers to a record of responses a user has made in the past, and is used to analyze patterns and trends in those responses.

[0372] "Improvement advice" refers to specific guidance and advice to help users provide better service.

[0373] An "emotion analysis engine" is a program or algorithm that analyzes a user's voice and facial expression data to determine their emotional state.

[0374] "Immediate" refers to processing or responding in real time without delay.

[0375] "Two-way communication" refers to methods or functions that enable users and systems to exchange information with each other.

[0376] This invention is a system that provides an interactive training environment to enhance the ability to respond to fraud. The system consists of a server, terminals, and users.

[0377] The server uses a generative AI model incorporating multiple deep learning algorithms to generate situational scenarios from a large amount of fraud data. These scenarios simulate various fraud situations that users may face, reproducing their methods and circumstances in detail. These generated scenarios are efficiently processed through a cloud computing environment.

[0378] The terminals are primarily mobile computing devices such as smartphones and tablets, which receive and display scenario data so that users can experience the scenarios in an interactive format. The terminals have speech recognition software installed, which converts the user's voice input into text data in real time. This converted text data is then sent back to the server and analyzed by an AI model.

[0379] Users can experience various scenarios using this system. For example, in a scenario where a scam call is received, the user responds through the device, and the response is immediately analyzed to generate the next reaction. At this time, the user's emotional state is determined from the user's voice and facial expressions by an emotion analysis engine, and the character playing the scammer can adjust their response based on that feedback.

[0380] As a concrete example, consider a scenario where a user practices responding to a phishing email. The prompt might read, "Your account has been used fraudulently. Click the link to learn more," and the user is required to attempt the appropriate course of action. In this way, the system enables real-time practice of responding to actual phishing scenarios.

[0381] This invention combines emotions and interaction to provide users with an environment where they can constantly learn the optimal coping mechanisms and avoid feeling anxious. As a result, this system realizes an educational environment that allows for individualized instruction.

[0382] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0383] Step 1:

[0384] The server collects a large amount of fraud data and generates situational scenarios using a generative AI model. Past fraud event data is used as input, and the AI ​​model analyzes this data to output a variety of fraud scenarios. Here, the fraud methods and situations are specifically visualized as scenarios.

[0385] Step 2:

[0386] The server distributes the generated fraud scenario to the user's device. Data transfer takes place, with the scenario data being sent from the server to the terminal. The terminal receives the data and displays it to the user in a visualized format. This allows the user to experience the fraud scenario presented interactively.

[0387] Step 3:

[0388] The device accepts the user's voice input and converts it into text data using speech recognition software. Actual voice input is analyzed by speech recognition technology, and the user's response is output as text. This allows the user's response to be obtained in digital format.

[0389] Step 4:

[0390] The server receives text data sent from the terminal and analyzes it using an AI model. This analysis evaluates the user's input text and generates the scammer's next response. Here, the AI ​​processes the data computationally, enabling the scenario to progress in a flexible manner.

[0391] Step 5:

[0392] The device uses an emotion analysis engine to analyze the user's voice and facial expression data to determine the user's emotional state. This process analyzes patterns in voice and facial expressions and outputs an emotional evaluation value. Based on this, the server adjusts the scammer's response in real time and presents the response to the user.

[0393] Step 6:

[0394] The server comprehensively analyzes all user responses and sentiment data to assess fraud response capabilities and generate improvement suggestions. This step uses data from across the entire system as input and outputs feedback to help users overcome their weaknesses. This allows users to reflect on their responses and prepare for future interactions.

[0395] (Application Example 2)

[0396] 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."

[0397] In recent years, fraudulent methods have become more sophisticated and diverse, making it difficult for ordinary people to respond accurately and quickly to these scams. Furthermore, conventional fraud prevention training systems lack real-time response adjustments based on the user's emotions, and therefore have the problem of not being able to adequately cultivate the ability to apply their skills in actual fraud situations. This invention aims to solve these problems and provide users with a training environment that is tailored to their individual psychological state.

[0398] 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.

[0399] In this invention, the server includes means for generating fraud scenarios using a generation algorithm, means for presenting the generated fraud scenarios to an information terminal, and means for analyzing the user's emotions with an emotion recognition engine and adjusting the fraudster's performance. This makes it possible for users to receive realistic and personalized training in response to fraud scenarios.

[0400] A "generative algorithm" is a computational method for automatically creating fraud scenarios, generating scenarios that reflect various situations and methods based on a vast amount of fraud data.

[0401] An "information terminal" refers to an electronic device used by a user to receive interactive fraud training, such as a smartphone or tablet.

[0402] An "emotion recognition engine" is a technology for analyzing a user's emotional state. It evaluates psychological responses from voice and facial expression data and adjusts interactions based on that information.

[0403] "Performing as a con artist" means dynamically changing the con artist's behavior in a scam scenario to make the user experience more realistic, such as altering their voice tone and word choice in response to the user's reactions.

[0404] To implement this invention, a system is required that utilizes a user terminal, a server, speech recognition technology, and an emotion recognition engine. The server constructs fraud scenarios using a generation algorithm. These fraud scenarios include various fraudulent methods and situations.

[0405] The device receives voice input from the user and converts it to text using speech recognition software. The widely used "speech_recognition" library can be utilized for this speech conversion. The converted text is sent to a server and analyzed by an AI model. If necessary, the generation AI model dynamically generates responses to the scammer and sends them to the user's device.

[0406] Furthermore, the emotion recognition engine analyzes the user's voice and facial expression data to evaluate their emotional state. Based on this evaluation, the server adjusts the con artist's performance to provide a more realistic scenario experience. For example, if the user feels uneasy, the con artist's tone and what they say can be changed.

[0407] Through an interactive interface on the device, users have the ability to choose from several possible responses. These options are optimized based on the user's response and emotional state.

[0408] Such systems are designed to help users acquire more practical skills in various fraud scenarios and are particularly useful in fraud prevention education for the elderly and young people. For example, a possible prompt for the generation AI model could be "Generate lines a fraudster would say when the user becomes anxious." This prompt allows for appropriate responses tailored to the user's psychological state.

[0409] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0410] Step 1:

[0411] The server generates fraud scenarios using a generation algorithm. It receives pre-stored fraud data as input, analyzes it, and outputs scenarios that include a variety of fraud situations. These generated fraud scenarios form the basis of the user's learning experience.

[0412] Step 2:

[0413] The server sends the generated fraud scenario to the user's terminal. The input here is the fraud scenario obtained in step 1, and the output is the scenario data displayed on the user's terminal. This data is presented through an interactive user interface and is displayed in a way that is easy for the user to understand.

[0414] Step 3:

[0415] The user uses a device to perform voice input. The user's voice is registered on the device as input and converted into text data by speech recognition software. The output is the user's response, converted into text. This text is necessary for subsequent analysis.

[0416] Step 4:

[0417] The terminal sends the user's voice, converted into text, to the server. Here, the input is the text obtained from the speech recognition process, and the output generates data that is sent to the server for analysis.

[0418] Step 5:

[0419] The server analyzes the user's text response using an AI model. The input is the user's text, and based on this, it generates a scammer's response. The output is the scammer's response data to the user's response. This response is adjusted in real time and presented to the user.

[0420] Step 6:

[0421] The server analyzes the user's emotions using an emotion recognition engine. The input is voice and facial expression data, and the output is an evaluation of the user's emotional state. This evaluation result is used to adjust the con artist's responses.

[0422] Step 7:

[0423] The server dynamically adjusts the con artist's performance based on the results of emotion recognition. The emotion recognition evaluation results are used as input, and the con artist's tone and speech are changed in real time. The output is a refined scenario designed to provide the user with a more immersive dialogue.

[0424] Step 8:

[0425] The user selects their next action from interactive options displayed on their device. The input is pre-configured scenario information from the server, which presents options to help determine the next action. The output is the next scenario development based on the user's selection.

[0426] 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.

[0427] 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.

[0428] 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.

[0429] [Third Embodiment]

[0430] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0431] 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.

[0432] 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).

[0433] 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.

[0434] 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.

[0435] 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).

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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.

[0440] 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.

[0441] 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".

[0442] This invention provides an educational system to improve users' ability to respond to fraud. The system consists of a server and user terminals and conducts fraud training in an interactive manner that encourages active user participation.

[0443] The server first generates fraud scenarios using a generation algorithm. These scenarios mimic specific fraud methods and situations, and are designed to be intuitively understandable to the user. The generated scenarios are immediately delivered to the user's terminal.

[0444] On the user's terminal, the received fraud scenario is presented to the user in an interactive format. Through voice output and text display, the user chooses how to respond based on the presented scenario. At this time, the server converts the user's voice response into text in real time and uses an AI model to generate the fraudster's reaction to that response.

[0445] Users can test their judgment within a scenario by selecting from options or freely entering answers. The server analyzes the user's response history in detail, generating personalized feedback based on that analysis. This feedback includes specific advice on how the user can improve.

[0446] For example, if a user attempts a wire fraud scenario and makes a wrong choice, the server provides feedback on how that choice could be exploited by the fraudster. This allows the user to make better decisions in subsequent training sessions.

[0447] In this way, the present invention provides effective training for users to develop practical and continuous resistance to fraud. In particular, by creating an environment where the elderly and young people can learn while having fun, it realizes social value in preventing fraud.

[0448] The following describes the processing flow.

[0449] Step 1:

[0450] The server generates fraud scenarios using a generation algorithm based on past fraud case data stored in the database. Multiple patterns are available to reflect a variety of fraud methods.

[0451] Step 2:

[0452] The server sends the generated fraud scenario to the user's device. The user's device then transforms this scenario into an interactive UI and presents it to the user. This UI includes audio output and text display, allowing the user to understand the situation within the scenario.

[0453] Step 3:

[0454] The user reads the presented scenario and responds using voice or by selecting options. The user's response is recorded on the device using the voice input function and immediately sent to the server.

[0455] Step 4:

[0456] The server converts the received user's voice data into text and analyzes it using an AI model. Based on this analysis, it generates the scammer's next response and sends it back to the user's device.

[0457] Step 5:

[0458] The user's device receives a new scammer response from the server and presents it to the user. The user repeats this process, advancing the scenario.

[0459] Step 6:

[0460] The server analyzes the user's response history to assess their ability to handle fraud. Based on this assessment, it generates feedback for improvement and sends it to the user's device.

[0461] Step 7:

[0462] The user's device presents feedback from the server to the user. Based on this, the user reflects on their own response capabilities and learns how to deal with fraud.

[0463] Step 8:

[0464] Users can then choose to use the feedback to move on to the next training session or to challenge themselves with more practical applications.

[0465] (Example 1)

[0466] 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."

[0467] In modern society, fraudulent methods are becoming increasingly sophisticated, raising the risk of many people becoming victims. In particular, there is a need for effective training methods to prevent fraud, especially for users who lack sufficient knowledge and skills to deal with such scams. Current educational methods do not encourage interactive participation from users, making it difficult to adequately improve practical response capabilities.

[0468] 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.

[0469] In this invention, the server includes means for generating fraud scenarios using a generation program, means for recognizing voice input from a user in real time and converting it into text information, and means for generating a fraudster's response using a generation AI model based on the text information. This makes it possible for users to effectively and interactively improve their ability to respond to fraud through scenarios that are based on actual fraud situations.

[0470] A "generator program" is software that includes algorithms for automatically creating fraud scenarios.

[0471] A "fraud scenario" is a hypothetical scenario that simulates the methods and circumstances of fraudulent activities and is provided to users for training purposes.

[0472] A "user terminal" is a computer device that receives fraud scenarios sent from the server and presents them to the user.

[0473] "Voice input" refers to the words or sounds that a user speaks into a device, and the medium through which this is captured by the system.

[0474] "Textual information" refers to information obtained by converting voice input into text format, and serves as the basis for analysis by generative AI models.

[0475] A "generative AI model" is an artificial intelligence model used to analyze input data and generate a specific output, such as the response of a con artist.

[0476] "Fraudster responses" refer to the actions and words of a virtual fraudster, generated by a generative AI model and presented in real time in response to the user's responses.

[0477] "Interactive methods" refer to interaction functions that allow users to directly select or input responses to the system, thereby testing their decision-making abilities within a scenario.

[0478] This invention is an educational system aimed at improving users' ability to respond to fraud. The system mainly consists of a server and user terminals.

[0479] The server first generates fraud scenarios using a generation program. These fraud scenarios are created using a generative AI model and natural language processing technology, simulating fraudulent methods and situations. The generated scenarios are sent to the user's terminal in JSON format. A concrete example is a scenario simulating a phishing email.

[0480] The user terminal interactively presents the received fraud scenario. The terminal features text display and audio output capabilities and is designed for intuitive user understanding. For example, it uses speech synthesis technology to play the scenario aloud while displaying the corresponding text on the screen.

[0481] Based on the presented scenario, users either click on an option or enter their answer via free text. If voice input is used, the device sends it back to the server. The server uses speech recognition technology to convert this into text, and then uses a generative AI model based on this text to generate a scammer's reaction. Through this interaction, users can experience a situation similar to a real scam and learn how to respond appropriately.

[0482] The responses provided by users are analyzed by the server. Based on the collected data, the server creates personalized improvement guidance for users and provides specific advice for the next training session. This allows users to deepen their understanding of fraud and develop effective response skills.

[0483] An example of a prompt might be, "Guide the best response for a user who has received a phishing email and is required to respond." Based on this prompt, the generative AI model generates new scenarios and responses to further improve user feedback.

[0484] The present invention, configured in this manner, is a system that helps users enhance their practical skills against fraud and contribute to a safer social life.

[0485] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0486] Step 1:

[0487] The server generates fraud scenarios using a generation program. It receives prompts and past scenario data as input and uses natural language processing and generative AI models to generate new fraud scenarios. The generated scenarios mimic fraudulent methods and situations, with a phishing email scenario being a concrete example of output.

[0488] Step 2:

[0489] The server sends the generated fraud scenario to the user's device. The output scenario is converted to JSON format and transferred to the device. The user's device receives this data and prepares for the next step.

[0490] Step 3:

[0491] The user terminal presents the received fraud scenario in an interactive format. It takes scenario data in JSON format as input and presents the scenario to the user using text display and audio playback technologies. Specifically, it displays text on the screen and presents information through speech synthesis.

[0492] Step 4:

[0493] Users make selections based on the presented scenario or freely enter answers. In the case of voice input, the device receives voice data as input and sends it to the server. During this process, the user's choices and voice commands are recorded and prepared for the next step.

[0494] Step 5:

[0495] The server converts the audio data received from the user into text in real time. Using speech recognition software, it transcribes the speech into text and supplies this text as input to a generative AI model. The output is the fraudster's response based on the generative AI model.

[0496] Step 6:

[0497] The server uses a generative AI model to generate responses from fraudsters and sends them to the user's terminal. The AI ​​model analyzes the input text and generates an appropriate response. This response is provided to the terminal as output, enabling the next interaction.

[0498] Step 7:

[0499] The user's device displays the scammer's response received from the server. The system then presents the user with further options and facilitates interaction for the next step. Specifically, new text or audio responses are presented.

[0500] Step 8:

[0501] The server analyzes the user's entire response history to generate improvement guidance. It uses the user's response history data as input and analyzes the data using machine learning algorithms. The output provides specific feedback on how the user should improve their behavior.

[0502] (Application Example 1)

[0503] 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."

[0504] This invention aims to solve the problem of providing an interactive educational system that helps users acquire the skills to effectively respond to actual fraud situations in order to prevent fraud from occurring.

[0505] 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.

[0506] In this invention, the server includes means for generating fraud scenarios using a generation algorithm, means for presenting the generated fraud scenarios to a communication device, and means for implementing an interactive fraud training application on the user's communication device. This allows users to learn while experiencing fraud scenarios similar to reality and strengthen their ability to defend against actual fraud.

[0507] A "generative algorithm" is a set of calculations used to automatically create fraudulent situations for a specific purpose.

[0508] A "fraud scenario" is a simulation that imitates fraudulent methods and situations, and is used for user education and training.

[0509] A "communication device" is a hardware device that has the function of sending and receiving data, and is used by users to access interactive content.

[0510] A "document" is a text format converted from voice input, used to provide information visually.

[0511] A "machine learning model" is a form of artificial intelligence that makes predictions and judgments based on data, and in this invention, it is used to generate the responses of a con artist.

[0512] An "interactive fraud training application" is interactive educational software designed to help users improve their ability to respond to fraud through the application.

[0513] A "data processing device" is a computer system that has the functions of receiving, processing, and outputting information, and constitutes the entire system of the present invention.

[0514] This invention is a system for developing users' ability to effectively respond to fraud. This system consists of a server and a communication device for the user.

[0515] The server uses a generation algorithm to create a virtual fraud scenario for the user to experience. For example, in a "telephone fraud" scenario, it generates a scenario in the voice of a fraudster, making suspicious requests to the user. This generated fraud scenario is presented to the user's communication device through an interactive fraud training application.

[0516] The user's communication device has the capability to recognize the user's voice input in real time and convert it into text. Speech recognition technologies such as the Google Speech-to-Text API are used for this process. The converted text is sent to a server, where a machine learning model (a generative AI model in this system) generates a fraudster's response and presents the user with the following scenario.

[0517] Furthermore, the server analyzes the user's response history in detail and generates personalized feedback based on that history. This feedback includes specific guidance on how the user can improve, helping them prepare for the next training session.

[0518] For example, in a scenario where a user is told over the phone that they "need money," if they decide it's "suspicious" and choose to hang up, the machine learning model will evaluate that action positively and provide feedback such as "contact the police after hanging up."

[0519] This system allows you to use prompts like this: "Choose the appropriate course of action to take when someone calls you and says, 'I need money.' Then, explain, with specific examples, why that choice is the best."

[0520] Through this invention, users can confidently develop their resistance to fraud and create a safer living environment.

[0521] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0522] Step 1:

[0523] The server creates fraud scenarios using a generation algorithm. Parameters such as the type and difficulty of the fraud are provided as input. Based on this data, the algorithm constructs fraud scenarios, and a virtual fraud scenario is obtained as output.

[0524] Step 2:

[0525] The server sends the generated fraud situation to the user's communication device. It receives fraud situation data as input and converts it into a format that can be distributed to the communication device. This converted data is then sent to the communication device as output.

[0526] Step 3:

[0527] The communication device presents the received fraud scenario to the user through an interactive fraud training application. This includes audio and text displays. The user experiences the presented fraud scenario and chooses an action based on the content.

[0528] Step 4:

[0529] The voice input spoken by the user is recognized in real time by the communication device and converted into text. The input is voice data, which is processed into text using the Google Speech-to-Text API. The output is the user's response in text format.

[0530] Step 5:

[0531] The server receives user responses in text format and uses a generative AI model to generate scammer responses based on them. The input for this step is the user's response text, which is parsed and processed by the AI ​​model, and the output is the scammer's next scenario.

[0532] Step 6:

[0533] The server collects and analyzes the user's response history and generates personalized improvement feedback. The input consists of data on the user's past choices and responses. Using data analysis techniques, the server evaluates the user's decisions and generates specific advice for improvement as output.

[0534] Step 7:

[0535] The feedback is sent to the user's communication device and presented to the user through the application. This allows the user to understand the correctness of their judgment and areas for improvement, and use this information to improve their next training session.

[0536] 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.

[0537] The system according to the present invention provides an interactive training environment that combines an emotion engine to enhance users' ability to respond to fraud. This system consists of a server, terminals, and diverse input data from users.

[0538] First, the server uses a generation algorithm to create fraud scenarios from a large amount of fraud data. These scenarios include various fraud methods and situations. The created fraud scenarios are immediately delivered to the user's device and presented to the user in an interactive format.

[0539] The device uses speech recognition technology to convert the user's voice responses into text. This text data is sent to a server and analyzed by an AI model. The scammer's response is generated based on this analysis and sent back to the device, where it is presented to the user. Throughout this interaction, an emotion engine recognizes the user's emotions from their voice and facial expressions, and makes dynamic adjustments according to the user's psychological state.

[0540] In particular, the scammer's reactions are adjusted in real time based on the user's emotions. For example, if the user is feeling anxious, the scammer's tone and content can be changed to provide a more realistic experience. This process allows users to participate in the simulation while maintaining a sense of tension and security.

[0541] All user responses and sentiment data are analyzed in detail on the server to assess fraud response capabilities. Based on the analysis, users are provided with feedback that includes specific areas for improvement. This feedback clearly identifies the user's strengths and weaknesses, similar to personalized coaching, and serves as material for appropriate guidance for future training.

[0542] For example, if a user makes an inappropriate response in a phone scam scenario, emotional data might be analyzed to show signs of tension. In this case, the feedback would provide advice on how to prepare for the next time and specific wording to use.

[0543] Thus, by closely combining emotions and interaction, this invention surpasses conventional fraud training systems, achieving a more advanced and personalized education. It provides a more effective and immersive learning experience for target users, such as the elderly and young people.

[0544] The following describes the processing flow.

[0545] Step 1:

[0546] The server extracts patterns from past fraud case data and uses a generation algorithm to create fraud scenarios for users. These scenarios are designed to replicate a variety of fraud methods.

[0547] Step 2:

[0548] The server sends the generated fraud scenario to the user's device. The device then presents this scenario to the user visually and audibly, providing an interactive experience.

[0549] Step 3:

[0550] Users respond to presented scenarios using voice and multiple-choice options. This input is based on the user's actions and decisions, and adapts to the situation at hand.

[0551] Step 4:

[0552] The device converts the user's voice responses into text in real time and sends it to the server. In parallel, the device analyzes the user's voice and facial expressions and generates emotion data using an emotion engine.

[0553] Step 5:

[0554] The server analyzes the received text data and sentiment data using an AI model. Based on this, it generates the next appropriate scammer response. Depending on the sentiment data, the scammer's response changes dynamically, determining the optimal tone and content to properly guide the user.

[0555] Step 6:

[0556] The device displays the scammer's response, sent from the server, to the user. During this process, the device continuously monitors the user's response and updates the sentiment data.

[0557] Step 7:

[0558] The server comprehensively analyzes the user's response history and sentiment data throughout the session to evaluate its fraud prevention capabilities.

[0559] Step 8:

[0560] The server generates feedback, including specific areas for improvement, based on the analysis results and sends it to the user's terminal. The terminal then presents this feedback to the user, providing information to help them in future training sessions and practical application in real life.

[0561] Step 9:

[0562] Users review feedback and choose to apply what they've learned to future training sessions and real-world situations. This allows them to enhance their defenses against fraud.

[0563] (Example 2)

[0564] 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."

[0565] In today's world, where fraud tactics continue to become more sophisticated, it is a difficult challenge for individual users to effectively improve their ability to respond to fraud. Traditional training methods often rely on general cases, making it difficult to learn flexible responses that are appropriate to the user's emotions and circumstances. Furthermore, there is a risk that users may repeat the same mistakes without realizing their own emotions.

[0566] 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.

[0567] In this invention, the server includes means for generating situation scenarios using a generation procedure, means for instantly recognizing voice input from the user and converting it into a string, and means for determining the user's emotional state using an emotion analysis engine and adaptively adjusting the response. This enables real-time responses that correspond to the user's emotions, thereby improving the ability to respond to fraud more effectively.

[0568] A "generative procedure" is a process for creating specific situations or scenarios based on a large amount of information.

[0569] A "situational scenario" is a virtual sequence that mimics a specific situation or event, designed to be experienced by users as a simulation.

[0570] A "user device" is a device used to receive and display information provided by the system, and includes smartphones, tablets, computers, and other similar devices.

[0571] "Voice input" is a method of having the system recognize what the user speaks as a digital signal.

[0572] A "string of characters" is data that has been converted to represent voice input in a digital format.

[0573] An "artificial intelligence model" is a computational model that uses algorithms to analyze unknown data and derive appropriate responses or conclusions based on that analysis.

[0574] "Response history" refers to a record of responses a user has made in the past, and is used to analyze patterns and trends in those responses.

[0575] "Improvement advice" refers to specific guidance and advice to help users provide better service.

[0576] An "emotion analysis engine" is a program or algorithm that analyzes a user's voice and facial expression data to determine their emotional state.

[0577] "Immediate" refers to processing or responding in real time without delay.

[0578] "Two-way communication" refers to methods or functions that enable users and systems to exchange information with each other.

[0579] This invention is a system that provides an interactive training environment to enhance the ability to respond to fraud. The system consists of a server, terminals, and users.

[0580] The server uses a generative AI model incorporating multiple deep learning algorithms to generate situational scenarios from a large amount of fraud data. These scenarios simulate various fraud situations that users may face, reproducing their methods and circumstances in detail. These generated scenarios are efficiently processed through a cloud computing environment.

[0581] The terminals are primarily mobile computing devices such as smartphones and tablets, which receive and display scenario data so that users can experience the scenarios in an interactive format. The terminals have speech recognition software installed, which converts the user's voice input into text data in real time. This converted text data is then sent back to the server and analyzed by an AI model.

[0582] Users can experience various scenarios using this system. For example, in a scenario where a scam call is received, the user responds through the device, and the response is immediately analyzed to generate the next reaction. At this time, the user's emotional state is determined from the user's voice and facial expressions by an emotion analysis engine, and the character playing the scammer can adjust their response based on that feedback.

[0583] As a concrete example, consider a scenario where a user practices responding to a phishing email. The prompt might read, "Your account has been used fraudulently. Click the link to learn more," and the user is required to attempt the appropriate course of action. In this way, the system enables real-time practice of responding to actual phishing scenarios.

[0584] This invention combines emotions and interaction to provide users with an environment where they can constantly learn the optimal coping mechanisms and avoid feeling anxious. As a result, this system realizes an educational environment that allows for individualized instruction.

[0585] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0586] Step 1:

[0587] The server collects a large amount of fraud data and generates situational scenarios using a generative AI model. Past fraud event data is used as input, and the AI ​​model analyzes this data to output a variety of fraud scenarios. Here, the fraud methods and situations are specifically visualized as scenarios.

[0588] Step 2:

[0589] The server distributes the generated fraud scenario to the user's device. Data transfer takes place, with the scenario data being sent from the server to the terminal. The terminal receives the data and displays it to the user in a visualized format. This allows the user to experience the fraud scenario presented interactively.

[0590] Step 3:

[0591] The device accepts the user's voice input and converts it into text data using speech recognition software. Actual voice input is analyzed by speech recognition technology, and the user's response is output as text. This allows the user's response to be obtained in digital format.

[0592] Step 4:

[0593] The server receives text data sent from the terminal and analyzes it using an AI model. This analysis evaluates the user's input text and generates the scammer's next response. Here, the AI ​​processes the data computationally, enabling the scenario to progress in a flexible manner.

[0594] Step 5:

[0595] The device uses an emotion analysis engine to analyze the user's voice and facial expression data to determine the user's emotional state. This process analyzes patterns in voice and facial expressions and outputs an emotional evaluation value. Based on this, the server adjusts the scammer's response in real time and presents the response to the user.

[0596] Step 6:

[0597] The server comprehensively analyzes all user responses and sentiment data to assess fraud response capabilities and generate improvement suggestions. This step uses data from across the entire system as input and outputs feedback to help users overcome their weaknesses. This allows users to reflect on their responses and prepare for future interactions.

[0598] (Application Example 2)

[0599] 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."

[0600] In recent years, fraudulent methods have become more sophisticated and diverse, making it difficult for ordinary people to respond accurately and quickly to these scams. Furthermore, conventional fraud prevention training systems lack real-time response adjustments based on the user's emotions, and therefore have the problem of not being able to adequately cultivate the ability to apply their skills in actual fraud situations. This invention aims to solve these problems and provide users with a training environment that is tailored to their individual psychological state.

[0601] 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.

[0602] In this invention, the server includes means for generating fraud scenarios using a generation algorithm, means for presenting the generated fraud scenarios to an information terminal, and means for analyzing the user's emotions with an emotion recognition engine and adjusting the fraudster's performance. This makes it possible for users to receive realistic and personalized training in response to fraud scenarios.

[0603] A "generative algorithm" is a computational method for automatically creating fraud scenarios, generating scenarios that reflect various situations and methods based on a vast amount of fraud data.

[0604] An "information terminal" refers to an electronic device used by a user to receive interactive fraud training, such as a smartphone or tablet.

[0605] An "emotion recognition engine" is a technology for analyzing a user's emotional state. It evaluates psychological responses from voice and facial expression data and adjusts interactions based on that information.

[0606] "Performing as a con artist" means dynamically changing the con artist's behavior in a scam scenario to make the user experience more realistic, such as altering their voice tone and word choice in response to the user's reactions.

[0607] To implement this invention, a system is required that utilizes a user terminal, a server, speech recognition technology, and an emotion recognition engine. The server constructs fraud scenarios using a generation algorithm. These fraud scenarios include various fraudulent methods and situations.

[0608] The device receives voice input from the user and converts it to text using speech recognition software. The widely used "speech_recognition" library can be utilized for this speech conversion. The converted text is sent to a server and analyzed by an AI model. If necessary, the generation AI model dynamically generates responses to the scammer and sends them to the user's device.

[0609] Furthermore, the emotion recognition engine analyzes the user's voice and facial expression data to evaluate their emotional state. Based on this evaluation, the server adjusts the con artist's performance to provide a more realistic scenario experience. For example, if the user feels uneasy, the con artist's tone and what they say can be changed.

[0610] Through an interactive interface on the device, users have the ability to choose from several possible responses. These options are optimized based on the user's response and emotional state.

[0611] Such systems are designed to help users acquire more practical skills in various fraud scenarios and are particularly useful in fraud prevention education for the elderly and young people. For example, a possible prompt for the generation AI model could be "Generate lines a fraudster would say when the user becomes anxious." This prompt allows for appropriate responses tailored to the user's psychological state.

[0612] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0613] Step 1:

[0614] The server generates fraud scenarios using a generation algorithm. It receives pre-stored fraud data as input, analyzes it, and outputs scenarios that include a variety of fraud situations. These generated fraud scenarios form the basis of the user's learning experience.

[0615] Step 2:

[0616] The server sends the generated fraud scenario to the user's terminal. The input here is the fraud scenario obtained in step 1, and the output is the scenario data displayed on the user's terminal. This data is presented through an interactive user interface and is displayed in a way that is easy for the user to understand.

[0617] Step 3:

[0618] The user uses a device to perform voice input. The user's voice is registered on the device as input and converted into text data by speech recognition software. The output is the user's response, converted into text. This text is necessary for subsequent analysis.

[0619] Step 4:

[0620] The terminal sends the user's voice, converted into text, to the server. Here, the input is the text obtained from the speech recognition process, and the output generates data that is sent to the server for analysis.

[0621] Step 5:

[0622] The server analyzes the user's text response using an AI model. The input is the user's text, and based on this, it generates a scammer's response. The output is the scammer's response data to the user's response. This response is adjusted in real time and presented to the user.

[0623] Step 6:

[0624] The server analyzes the user's emotions using an emotion recognition engine. The input is voice and facial expression data, and the output is an evaluation of the user's emotional state. This evaluation result is used to adjust the con artist's responses.

[0625] Step 7:

[0626] The server dynamically adjusts the con artist's performance based on the results of emotion recognition. The emotion recognition evaluation results are used as input, and the con artist's tone and speech are changed in real time. The output is a refined scenario designed to provide the user with a more immersive dialogue.

[0627] Step 8:

[0628] The user selects their next action from interactive options displayed on their device. The input is pre-configured scenario information from the server, which presents options to help determine the next action. The output is the next scenario development based on the user's selection.

[0629] 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.

[0630] 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.

[0631] 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.

[0632] [Fourth Embodiment]

[0633] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0634] 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.

[0635] 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).

[0636] 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.

[0637] 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.

[0638] 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).

[0639] 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.

[0640] 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.

[0641] 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.

[0642] 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.

[0643] 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.

[0644] 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.

[0645] 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".

[0646] This invention provides an educational system to improve users' ability to respond to fraud. The system consists of a server and user terminals and conducts fraud training in an interactive manner that encourages active user participation.

[0647] The server first generates fraud scenarios using a generation algorithm. These scenarios mimic specific fraud methods and situations, and are designed to be intuitively understandable to the user. The generated scenarios are immediately delivered to the user's terminal.

[0648] On the user's terminal, the received fraud scenario is presented to the user in an interactive format. Through voice output and text display, the user chooses how to respond based on the presented scenario. At this time, the server converts the user's voice response into text in real time and uses an AI model to generate the fraudster's reaction to that response.

[0649] Users can test their judgment within a scenario by selecting from options or freely entering answers. The server analyzes the user's response history in detail, generating personalized feedback based on that analysis. This feedback includes specific advice on how the user can improve.

[0650] For example, if a user attempts a wire fraud scenario and makes a wrong choice, the server provides feedback on how that choice could be exploited by the fraudster. This allows the user to make better decisions in subsequent training sessions.

[0651] In this way, the present invention provides effective training for users to develop practical and continuous resistance to fraud. In particular, by creating an environment where the elderly and young people can learn while having fun, it realizes social value in preventing fraud.

[0652] The following describes the processing flow.

[0653] Step 1:

[0654] The server generates fraud scenarios using a generation algorithm based on past fraud case data stored in the database. Multiple patterns are available to reflect a variety of fraud methods.

[0655] Step 2:

[0656] The server sends the generated fraud scenario to the user's device. The user's device then transforms this scenario into an interactive UI and presents it to the user. This UI includes audio output and text display, allowing the user to understand the situation within the scenario.

[0657] Step 3:

[0658] The user reads the presented scenario and responds using voice or by selecting options. The user's response is recorded on the device using the voice input function and immediately sent to the server.

[0659] Step 4:

[0660] The server converts the received user's voice data into text and analyzes it using an AI model. Based on this analysis, it generates the scammer's next response and sends it back to the user's device.

[0661] Step 5:

[0662] The user's device receives a new scammer response from the server and presents it to the user. The user repeats this process, advancing the scenario.

[0663] Step 6:

[0664] The server analyzes the user's response history to assess their ability to handle fraud. Based on this assessment, it generates feedback for improvement and sends it to the user's device.

[0665] Step 7:

[0666] The user's device presents feedback from the server to the user. Based on this, the user reflects on their own response capabilities and learns how to deal with fraud.

[0667] Step 8:

[0668] Users can then choose to use the feedback to move on to the next training session or to challenge themselves with more practical applications.

[0669] (Example 1)

[0670] 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".

[0671] In modern society, fraudulent methods are becoming increasingly sophisticated, raising the risk of many people becoming victims. In particular, there is a need for effective training methods to prevent fraud, especially for users who lack sufficient knowledge and skills to deal with such scams. Current educational methods do not encourage interactive participation from users, making it difficult to adequately improve practical response capabilities.

[0672] 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.

[0673] In this invention, the server includes means for generating fraud scenarios using a generation program, means for recognizing voice input from a user in real time and converting it into text information, and means for generating a fraudster's response using a generation AI model based on the text information. This makes it possible for users to effectively and interactively improve their ability to respond to fraud through scenarios that are based on actual fraud situations.

[0674] A "generator program" is software that includes algorithms for automatically creating fraud scenarios.

[0675] A "fraud scenario" is a hypothetical scenario that simulates the methods and circumstances of fraudulent activities and is provided to users for training purposes.

[0676] A "user terminal" is a computer device that receives fraud scenarios sent from the server and presents them to the user.

[0677] "Voice input" refers to the words or sounds that a user speaks into a device, and the medium through which this is captured by the system.

[0678] "Textual information" refers to information obtained by converting voice input into text format, and serves as the basis for analysis by generative AI models.

[0679] A "generative AI model" is an artificial intelligence model used to analyze input data and generate a specific output, such as the response of a con artist.

[0680] "Fraudster responses" refer to the actions and words of a virtual fraudster, generated by a generative AI model and presented in real time in response to the user's responses.

[0681] "Interactive methods" refer to interaction functions that allow users to directly select or input responses to the system, thereby testing their decision-making abilities within a scenario.

[0682] This invention is an educational system aimed at improving users' ability to respond to fraud. The system mainly consists of a server and user terminals.

[0683] The server first generates fraud scenarios using a generation program. These fraud scenarios are created using a generative AI model and natural language processing technology, simulating fraudulent methods and situations. The generated scenarios are sent to the user's terminal in JSON format. A concrete example is a scenario simulating a phishing email.

[0684] The user terminal interactively presents the received fraud scenario. The terminal features text display and audio output capabilities and is designed for intuitive user understanding. For example, it uses speech synthesis technology to play the scenario aloud while displaying the corresponding text on the screen.

[0685] Based on the presented scenario, users either click on an option or enter their answer via free text. If voice input is used, the device sends it back to the server. The server uses speech recognition technology to convert this into text, and then uses a generative AI model based on this text to generate a scammer's reaction. Through this interaction, users can experience a situation similar to a real scam and learn how to respond appropriately.

[0686] The responses provided by users are analyzed by the server. Based on the collected data, the server creates personalized improvement guidance for users and provides specific advice for the next training session. This allows users to deepen their understanding of fraud and develop effective response skills.

[0687] An example of a prompt might be, "Guide the best response for a user who has received a phishing email and is required to respond." Based on this prompt, the generative AI model generates new scenarios and responses to further improve user feedback.

[0688] The present invention, configured in this manner, is a system that helps users enhance their practical skills against fraud and contribute to a safer social life.

[0689] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0690] Step 1:

[0691] The server generates fraud scenarios using a generation program. It receives prompts and past scenario data as input and uses natural language processing and generative AI models to generate new fraud scenarios. The generated scenarios mimic fraudulent methods and situations, with a phishing email scenario being a concrete example of output.

[0692] Step 2:

[0693] The server sends the generated fraud scenario to the user's device. The output scenario is converted to JSON format and transferred to the device. The user's device receives this data and prepares for the next step.

[0694] Step 3:

[0695] The user terminal presents the received fraud scenario in an interactive format. It takes scenario data in JSON format as input and presents the scenario to the user using text display and audio playback technologies. Specifically, it displays text on the screen and presents information through speech synthesis.

[0696] Step 4:

[0697] Users make selections based on the presented scenario or freely enter answers. In the case of voice input, the device receives voice data as input and sends it to the server. During this process, the user's choices and voice commands are recorded and prepared for the next step.

[0698] Step 5:

[0699] The server converts the audio data received from the user into text in real time. Using speech recognition software, it transcribes the speech into text and supplies this text as input to a generative AI model. The output is the fraudster's response based on the generative AI model.

[0700] Step 6:

[0701] The server uses a generative AI model to generate responses from fraudsters and sends them to the user's terminal. The AI ​​model analyzes the input text and generates an appropriate response. This response is provided to the terminal as output, enabling the next interaction.

[0702] Step 7:

[0703] The user's device displays the scammer's response received from the server. The system then presents the user with further options and facilitates interaction for the next step. Specifically, new text or audio responses are presented.

[0704] Step 8:

[0705] The server analyzes the user's entire response history to generate improvement guidance. It uses the user's response history data as input and analyzes the data using machine learning algorithms. The output provides specific feedback on how the user should improve their behavior.

[0706] (Application Example 1)

[0707] 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".

[0708] This invention aims to solve the problem of providing an interactive educational system that helps users acquire the skills to effectively respond to actual fraud situations in order to prevent fraud from occurring.

[0709] 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.

[0710] In this invention, the server includes means for generating fraud scenarios using a generation algorithm, means for presenting the generated fraud scenarios to a communication device, and means for implementing an interactive fraud training application on the user's communication device. This allows users to learn while experiencing fraud scenarios similar to reality and strengthen their ability to defend against actual fraud.

[0711] A "generative algorithm" is a set of calculations used to automatically create fraudulent situations for a specific purpose.

[0712] A "fraud scenario" is a simulation that imitates fraudulent methods and situations, and is used for user education and training.

[0713] A "communication device" is a hardware device that has the function of sending and receiving data, and is used by users to access interactive content.

[0714] A "document" is a text format converted from voice input, used to provide information visually.

[0715] A "machine learning model" is a form of artificial intelligence that makes predictions and judgments based on data, and in this invention, it is used to generate the responses of a con artist.

[0716] An "interactive fraud training application" is interactive educational software designed to help users improve their ability to respond to fraud through the application.

[0717] A "data processing device" is a computer system that has the functions of receiving, processing, and outputting information, and constitutes the entire system of the present invention.

[0718] This invention is a system for developing users' ability to effectively respond to fraud. This system consists of a server and a communication device for the user.

[0719] The server uses a generation algorithm to create a virtual fraud scenario for the user to experience. For example, in a "telephone fraud" scenario, it generates a scenario in the voice of a fraudster, making suspicious requests to the user. This generated fraud scenario is presented to the user's communication device through an interactive fraud training application.

[0720] The user's communication device has the capability to recognize the user's voice input in real time and convert it into text. Speech recognition technologies such as the Google Speech-to-Text API are used for this process. The converted text is sent to a server, where a machine learning model (a generative AI model in this system) generates a fraudster's response and presents the user with the following scenario.

[0721] Furthermore, the server analyzes the user's response history in detail and generates personalized feedback based on that history. This feedback includes specific guidance on how the user can improve, helping them prepare for the next training session.

[0722] For example, in a scenario where a user is told over the phone that they "need money," if they decide it's "suspicious" and choose to hang up, the machine learning model will evaluate that action positively and provide feedback such as "contact the police after hanging up."

[0723] This system allows you to use prompts like this: "Choose the appropriate course of action to take when someone calls you and says, 'I need money.' Then, explain, with specific examples, why that choice is the best."

[0724] Through this invention, users can confidently develop their resistance to fraud and create a safer living environment.

[0725] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0726] Step 1:

[0727] The server creates fraud scenarios using a generation algorithm. Parameters such as the type and difficulty of the fraud are provided as input. Based on this data, the algorithm constructs fraud scenarios, and a virtual fraud scenario is obtained as output.

[0728] Step 2:

[0729] The server sends the generated fraud situation to the user's communication device. It receives fraud situation data as input and converts it into a format that can be distributed to the communication device. This converted data is then sent to the communication device as output.

[0730] Step 3:

[0731] The communication device presents the received fraud scenario to the user through an interactive fraud training application. This includes audio and text displays. The user experiences the presented fraud scenario and chooses an action based on the content.

[0732] Step 4:

[0733] The voice input spoken by the user is recognized in real time by the communication device and converted into text. The input is voice data, which is processed into text using the Google Speech-to-Text API. The output is the user's response in text format.

[0734] Step 5:

[0735] The server receives user responses in text format and uses a generative AI model to generate scammer responses based on them. The input for this step is the user's response text, which is parsed and processed by the AI ​​model, and the output is the scammer's next scenario.

[0736] Step 6:

[0737] The server collects and analyzes the user's response history and generates personalized improvement feedback. The input consists of data on the user's past choices and responses. Using data analysis techniques, the server evaluates the user's decisions and generates specific advice for improvement as output.

[0738] Step 7:

[0739] The feedback is sent to the user's communication device and presented to the user through the application. This allows the user to understand the correctness of their judgment and areas for improvement, and use this information to improve their next training session.

[0740] 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.

[0741] The system according to the present invention provides an interactive training environment that combines an emotion engine to enhance users' ability to respond to fraud. This system consists of a server, terminals, and diverse input data from users.

[0742] First, the server uses a generation algorithm to create fraud scenarios from a large amount of fraud data. These scenarios include various fraud methods and situations. The created fraud scenarios are immediately delivered to the user's device and presented to the user in an interactive format.

[0743] The device uses speech recognition technology to convert the user's voice responses into text. This text data is sent to a server and analyzed by an AI model. The scammer's response is generated based on this analysis and sent back to the device, where it is presented to the user. Throughout this interaction, an emotion engine recognizes the user's emotions from their voice and facial expressions, and makes dynamic adjustments according to the user's psychological state.

[0744] In particular, the scammer's reactions are adjusted in real time based on the user's emotions. For example, if the user is feeling anxious, the scammer's tone and content can be changed to provide a more realistic experience. This process allows users to participate in the simulation while maintaining a sense of tension and security.

[0745] All user responses and sentiment data are analyzed in detail on the server to assess fraud response capabilities. Based on the analysis, users are provided with feedback that includes specific areas for improvement. This feedback clearly identifies the user's strengths and weaknesses, similar to personalized coaching, and serves as material for appropriate guidance for future training.

[0746] For example, if a user makes an inappropriate response in a phone scam scenario, emotional data might be analyzed to show signs of tension. In this case, the feedback would provide advice on how to prepare for the next time and specific wording to use.

[0747] Thus, by closely combining emotions and interaction, this invention surpasses conventional fraud training systems, achieving a more advanced and personalized education. It provides a more effective and immersive learning experience for target users, such as the elderly and young people.

[0748] The following describes the processing flow.

[0749] Step 1:

[0750] The server extracts patterns from past fraud case data and uses a generation algorithm to create fraud scenarios for users. These scenarios are designed to replicate a variety of fraud methods.

[0751] Step 2:

[0752] The server sends the generated fraud scenario to the user's device. The device then presents this scenario to the user visually and audibly, providing an interactive experience.

[0753] Step 3:

[0754] Users respond to presented scenarios using voice and multiple-choice options. This input is based on the user's actions and decisions, and adapts to the situation at hand.

[0755] Step 4:

[0756] The device converts the user's voice responses into text in real time and sends it to the server. In parallel, the device analyzes the user's voice and facial expressions and generates emotion data using an emotion engine.

[0757] Step 5:

[0758] The server analyzes the received text data and sentiment data using an AI model. Based on this, it generates the next appropriate scammer response. Depending on the sentiment data, the scammer's response changes dynamically, determining the optimal tone and content to properly guide the user.

[0759] Step 6:

[0760] The device displays the scammer's response, sent from the server, to the user. During this process, the device continuously monitors the user's response and updates the sentiment data.

[0761] Step 7:

[0762] The server comprehensively analyzes the user's response history and sentiment data throughout the session to evaluate its fraud prevention capabilities.

[0763] Step 8:

[0764] The server generates feedback, including specific areas for improvement, based on the analysis results and sends it to the user's terminal. The terminal then presents this feedback to the user, providing information to help them in future training sessions and practical application in real life.

[0765] Step 9:

[0766] Users review feedback and choose to apply what they've learned to future training sessions and real-world situations. This allows them to enhance their defenses against fraud.

[0767] (Example 2)

[0768] 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".

[0769] In today's world, where fraud tactics continue to become more sophisticated, it is a difficult challenge for individual users to effectively improve their ability to respond to fraud. Traditional training methods often rely on general cases, making it difficult to learn flexible responses that are appropriate to the user's emotions and circumstances. Furthermore, there is a risk that users may repeat the same mistakes without realizing their own emotions.

[0770] 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.

[0771] In this invention, the server includes means for generating situation scenarios using a generation procedure, means for instantly recognizing voice input from the user and converting it into a string, and means for determining the user's emotional state using an emotion analysis engine and adaptively adjusting the response. This enables real-time responses that correspond to the user's emotions, thereby improving the ability to respond to fraud more effectively.

[0772] A "generative procedure" is a process for creating specific situations or scenarios based on a large amount of information.

[0773] A "situational scenario" is a virtual sequence that mimics a specific situation or event, designed to be experienced by users as a simulation.

[0774] A "user device" is a device used to receive and display information provided by the system, and includes smartphones, tablets, computers, and other similar devices.

[0775] "Voice input" is a method of having the system recognize what the user speaks as a digital signal.

[0776] A "string of characters" is data that has been converted to represent voice input in a digital format.

[0777] An "artificial intelligence model" is a computational model that uses algorithms to analyze unknown data and derive appropriate responses or conclusions based on that analysis.

[0778] "Response history" refers to a record of responses a user has made in the past, and is used to analyze patterns and trends in those responses.

[0779] "Improvement advice" refers to specific guidance and advice to help users provide better service.

[0780] An "emotion analysis engine" is a program or algorithm that analyzes a user's voice and facial expression data to determine their emotional state.

[0781] "Immediate" refers to processing or responding in real time without delay.

[0782] "Two-way communication" refers to methods or functions that enable users and systems to exchange information with each other.

[0783] This invention is a system that provides an interactive training environment to enhance the ability to respond to fraud. The system consists of a server, terminals, and users.

[0784] The server uses a generative AI model incorporating multiple deep learning algorithms to generate situational scenarios from a large amount of fraud data. These scenarios simulate various fraud situations that users may face, reproducing their methods and circumstances in detail. These generated scenarios are efficiently processed through a cloud computing environment.

[0785] The terminals are primarily mobile computing devices such as smartphones and tablets, which receive and display scenario data so that users can experience the scenarios in an interactive format. The terminals have speech recognition software installed, which converts the user's voice input into text data in real time. This converted text data is then sent back to the server and analyzed by an AI model.

[0786] Users can experience various scenarios using this system. For example, in a scenario where a scam call is received, the user responds through the device, and the response is immediately analyzed to generate the next reaction. At this time, the user's emotional state is determined from the user's voice and facial expressions by an emotion analysis engine, and the character playing the scammer can adjust their response based on that feedback.

[0787] As a concrete example, consider a scenario where a user practices responding to a phishing email. The prompt might read, "Your account has been used fraudulently. Click the link to learn more," and the user is required to attempt the appropriate course of action. In this way, the system enables real-time practice of responding to actual phishing scenarios.

[0788] This invention combines emotions and interaction to provide users with an environment where they can constantly learn the optimal coping mechanisms and avoid feeling anxious. As a result, this system realizes an educational environment that allows for individualized instruction.

[0789] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0790] Step 1:

[0791] The server collects a large amount of fraud data and generates situational scenarios using a generative AI model. Past fraud event data is used as input, and the AI ​​model analyzes this data to output a variety of fraud scenarios. Here, the fraud methods and situations are specifically visualized as scenarios.

[0792] Step 2:

[0793] The server distributes the generated fraud scenario to the user's device. Data transfer takes place, with the scenario data being sent from the server to the terminal. The terminal receives the data and displays it to the user in a visualized format. This allows the user to experience the fraud scenario presented interactively.

[0794] Step 3:

[0795] The device accepts the user's voice input and converts it into text data using speech recognition software. Actual voice input is analyzed by speech recognition technology, and the user's response is output as text. This allows the user's response to be obtained in digital format.

[0796] Step 4:

[0797] The server receives text data sent from the terminal and analyzes it using an AI model. This analysis evaluates the user's input text and generates the scammer's next response. Here, the AI ​​processes the data computationally, enabling the scenario to progress in a flexible manner.

[0798] Step 5:

[0799] The device uses an emotion analysis engine to analyze the user's voice and facial expression data to determine the user's emotional state. This process analyzes patterns in voice and facial expressions and outputs an emotional evaluation value. Based on this, the server adjusts the scammer's response in real time and presents the response to the user.

[0800] Step 6:

[0801] The server comprehensively analyzes all user responses and sentiment data to assess fraud response capabilities and generate improvement suggestions. This step uses data from across the entire system as input and outputs feedback to help users overcome their weaknesses. This allows users to reflect on their responses and prepare for future interactions.

[0802] (Application Example 2)

[0803] 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".

[0804] In recent years, fraudulent methods have become more sophisticated and diverse, making it difficult for ordinary people to respond accurately and quickly to these scams. Furthermore, conventional fraud prevention training systems lack real-time response adjustments based on the user's emotions, and therefore have the problem of not being able to adequately cultivate the ability to apply their skills in actual fraud situations. This invention aims to solve these problems and provide users with a training environment that is tailored to their individual psychological state.

[0805] 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.

[0806] In this invention, the server includes means for generating fraud scenarios using a generation algorithm, means for presenting the generated fraud scenarios to an information terminal, and means for analyzing the user's emotions with an emotion recognition engine and adjusting the fraudster's performance. This makes it possible for users to receive realistic and personalized training in response to fraud scenarios.

[0807] A "generative algorithm" is a computational method for automatically creating fraud scenarios, generating scenarios that reflect various situations and methods based on a vast amount of fraud data.

[0808] An "information terminal" refers to an electronic device used by a user to receive interactive fraud training, such as a smartphone or tablet.

[0809] An "emotion recognition engine" is a technology for analyzing a user's emotional state. It evaluates psychological responses from voice and facial expression data and adjusts interactions based on that information.

[0810] "Performing as a con artist" means dynamically changing the con artist's behavior in a scam scenario to make the user experience more realistic, such as altering their voice tone and word choice in response to the user's reactions.

[0811] To implement this invention, a system is required that utilizes a user terminal, a server, speech recognition technology, and an emotion recognition engine. The server constructs fraud scenarios using a generation algorithm. These fraud scenarios include various fraudulent methods and situations.

[0812] The device receives voice input from the user and converts it to text using speech recognition software. The widely used "speech_recognition" library can be utilized for this speech conversion. The converted text is sent to a server and analyzed by an AI model. If necessary, the generation AI model dynamically generates responses to the scammer and sends them to the user's device.

[0813] Furthermore, the emotion recognition engine analyzes the user's voice and facial expression data to evaluate their emotional state. Based on this evaluation, the server adjusts the con artist's performance to provide a more realistic scenario experience. For example, if the user feels uneasy, the con artist's tone and what they say can be changed.

[0814] Through an interactive interface on the device, users have the ability to choose from several possible responses. These options are optimized based on the user's response and emotional state.

[0815] Such systems are designed to help users acquire more practical skills in various fraud scenarios and are particularly useful in fraud prevention education for the elderly and young people. For example, a possible prompt for the generation AI model could be "Generate lines a fraudster would say when the user becomes anxious." This prompt allows for appropriate responses tailored to the user's psychological state.

[0816] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0817] Step 1:

[0818] The server generates fraud scenarios using a generation algorithm. It receives pre-stored fraud data as input, analyzes it, and outputs scenarios that include a variety of fraud situations. These generated fraud scenarios form the basis of the user's learning experience.

[0819] Step 2:

[0820] The server sends the generated fraud scenario to the user's terminal. The input here is the fraud scenario obtained in step 1, and the output is the scenario data displayed on the user's terminal. This data is presented through an interactive user interface and is displayed in a way that is easy for the user to understand.

[0821] Step 3:

[0822] The user uses a device to perform voice input. The user's voice is registered on the device as input and converted into text data by speech recognition software. The output is the user's response, converted into text. This text is necessary for subsequent analysis.

[0823] Step 4:

[0824] The terminal sends the user's voice, converted into text, to the server. Here, the input is the text obtained from the speech recognition process, and the output generates data that is sent to the server for analysis.

[0825] Step 5:

[0826] The server analyzes the user's text response using an AI model. The input is the user's text, and based on this, it generates a scammer's response. The output is the scammer's response data to the user's response. This response is adjusted in real time and presented to the user.

[0827] Step 6:

[0828] The server analyzes the user's emotions using an emotion recognition engine. The input is voice and facial expression data, and the output is an evaluation of the user's emotional state. This evaluation result is used to adjust the con artist's responses.

[0829] Step 7:

[0830] The server dynamically adjusts the con artist's performance based on the results of emotion recognition. The emotion recognition evaluation results are used as input, and the con artist's tone and speech are changed in real time. The output is a refined scenario designed to provide the user with a more immersive dialogue.

[0831] Step 8:

[0832] The user selects their next action from interactive options displayed on their device. The input is pre-configured scenario information from the server, which presents options to help determine the next action. The output is the next scenario development based on the user's selection.

[0833] 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.

[0834] 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.

[0835] 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 robot 414.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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."

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] The following is further disclosed regarding the embodiments described above.

[0855] (Claim 1)

[0856] A means of generating fraud scenarios using a generation algorithm,

[0857] A means for presenting the generated fraud scenario to the user's terminal,

[0858] A means of recognizing voice input from users in real time and converting it to text,

[0859] A means for generating a scammer's response using an AI model based on the text,

[0860] A means of analyzing user response history and providing users with improvement feedback,

[0861] A system that includes this.

[0862] (Claim 2)

[0863] The system according to claim 1, which presents fraud scenarios to a user in the form of a quiz or a simulation.

[0864] (Claim 3)

[0865] The system according to claim 1, comprising an interactive means for allowing the user to select the following course of action.

[0866] "Example 1"

[0867] (Claim 1)

[0868] A means of generating fraud scenarios using a generation program,

[0869] A means for presenting the generated fraud scenario to the user's terminal,

[0870] A means of recognizing voice input from users in real time and converting it into text information,

[0871] A means for generating a fraudster's response using a generative AI model based on the textual information,

[0872] A means of analyzing the user's response history and providing improvement guidance to the user,

[0873] A method of presenting fraud scenarios received on the device in both audio and text, and offering the user choices,

[0874] A system that includes this.

[0875] (Claim 2)

[0876] The system according to claim 1, which presents fraud scenarios to a user in the form of a problem or a simulation.

[0877] (Claim 3)

[0878] The system according to claim 1, comprising an interactive means for allowing the user to select the following response method.

[0879] "Application Example 1"

[0880] (Claim 1)

[0881] A means of generating fraud situations using a generation algorithm,

[0882] A means for presenting the generated fraud situation to a communication device,

[0883] A means of recognizing voice input from users in real time and converting it into text,

[0884] A means for generating a fraudster's response using a machine learning model based on the said document,

[0885] A means of analyzing user response history and providing improvement feedback to users,

[0886] A means of implementing an interactive fraud training application on a user's communication device,

[0887] A data processing device that includes a data processing device.

[0888] (Claim 2)

[0889] The data processing device according to claim 1, which presents a fraud situation to a user in the form of a problem or a simulation.

[0890] (Claim 3)

[0891] The data processing device according to claim 1, further comprising an interactive means for allowing the user to select one of the following response methods.

[0892] "Example 2 of combining an emotion engine"

[0893] (Claim 1)

[0894] A means for generating situation scenarios using a generation procedure,

[0895] A means for presenting the generated situation scenario to the user device,

[0896] A means of instantly recognizing voice input from users and converting it into text,

[0897] A means for generating a response using an artificial intelligence model based on the string,

[0898] A means of analyzing the user's response history and providing improvement advice to the user,

[0899] A means of determining the user's emotional state using an emotion analysis engine and adaptively adjusting the response,

[0900] A system that includes this.

[0901] (Claim 2)

[0902] The system according to claim 1, which presents situational scenarios to the user in the form of a quiz or a simulated experience.

[0903] (Claim 3)

[0904] The system according to claim 1, comprising a two-way means for allowing the user to select the next course of action.

[0905] "Application example 2 when combining with an emotional engine"

[0906] (Claim 1)

[0907] A means of generating fraud scenarios using a generation algorithm,

[0908] A means for presenting the generated fraud scenario to an information terminal,

[0909] A means of recognizing voice input from users in real time and converting it to text,

[0910] A means for generating a fraudster's response using an artificial intelligence model based on the text,

[0911] A means of analyzing the user's emotions with an emotion recognition engine and adjusting the con artist's performance accordingly,

[0912] A means of analyzing user response history and providing improvement feedback to users,

[0913] A system that includes this.

[0914] (Claim 2)

[0915] The system according to claim 1, which presents a fraud scenario to the user in the form of a quiz or simulation, and modifies the content of the dialogue according to the user's emotional state.

[0916] (Claim 3)

[0917] The system according to claim 1, which includes an interactive means to allow the user to select the next course of action, and further dynamically adjusts the flow of the dialogue based on emotion recognition. [Explanation of Symbols]

[0918] 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 means of generating fraud situations using a generation algorithm, A means for presenting the generated fraud situation to a communication device, A means of recognizing voice input from users in real time and converting it into text, A means for generating a fraudster's response using a machine learning model based on the said document, A means of analyzing user response history and providing improvement feedback to users, A means of implementing an interactive fraud training application on a user's communication device, A data processing device that includes a data processing device.

2. The data processing device according to claim 1, which presents a fraud situation to a user in the form of a problem or a simulation.

3. The data processing device according to claim 1, further comprising an interactive means for allowing the user to select the following response method.

Images