system

Abstract

We provide the system. [Solution] A means of including a small artificial intelligence in a terminal to monitor user behavior, A means of evaluating data using statistical features to detect potentially fraudulent behavior, A means of sending data exceeding a threshold to the server, A means of running a large-scale artificial intelligence on a server to highly evaluate received data, A means of providing warning notifications to users based on the final evaluation, A system that includes this.

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】 Japanese Patent Application Laid-Open No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 There is a need to provide technical means for warning against fraud in real time and preventing it, especially against increasing fraud damages, particularly malicious fraud targeting the elderly. Many existing fraud prevention systems rely on manual confirmation and retrospective countermeasures, and there is a demand for quick and reliable automatic detection. However, there is a shortage of systems that can detect a wide range of diverse fraud patterns while considering the performance of restricted terminals. 【Means for Solving the Problems】 【0005】 This invention provides a system that uses a small artificial intelligence (AI) installed on a device to monitor user behavior and detect potentially fraudulent information in real time. The small AI evaluates data using statistical features and sends data exceeding a threshold to a server if it is suspected of being fraudulent. On the server, a larger AI uses advanced algorithms to scrutinize the data and generates a warning notification to the device based on the final evaluation results. This allows users to receive early warnings about the risk of fraud and prevent becoming a victim. Furthermore, by updating fraud feature patterns on the server using machine learning, the system is designed to always be able to respond to the latest fraud methods. 【0006】 "User behavior" refers to a series of operations and accesses that users perform on their devices, such as browsing the internet, clicking links, and viewing advertisements. 【0007】 "Small artificial intelligence" refers to artificial intelligence that operates within the limited resources of a device and monitors and analyzes user behavior data to perform initial evaluations. 【0008】 A "threshold" is a specific standard value set to determine the likelihood of fraud; exceeding this value indicates that further investigation is needed to determine if something is fraudulent. 【0009】 "Large-scale artificial intelligence" refers to artificial intelligence that operates on a server, uses advanced algorithms to analyze received data in detail, and makes a final fraud determination. 【0010】 A "warning notification" is a message displayed to a user when there is a possibility of fraud, and it provides information to help prevent users from becoming victims of fraud. 【0011】 "Machine learning" is a technological method that uses data-driven learning processes to improve artificial intelligence's capabilities, enabling it to respond to unknown fraud patterns. [Brief explanation of the drawing] 【0012】 [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of the data processing device and smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] 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, when an emotion engine is combined. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention] 【0013】 Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings. 【0014】 First, the terms used in the following description will be explained. 【0015】 In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like. 【0016】 In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0017】 In the following embodiments, the numbered storage 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, etc. 【0018】 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). 【0019】 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." 【0020】 [First Embodiment] 【0021】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0022】 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. 【0023】 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). 【0024】 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. 【0025】 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. 【0026】 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. 【0027】 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. 【0028】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0029】 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. 【0030】 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. 【0031】 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. 【0032】 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". 【0033】 The fraud prevention system based on this invention is realized by deploying a small artificial intelligence and a large artificial intelligence on the user's terminal and a central server, respectively. This configuration provides advanced fraud detection capabilities while efficiently utilizing the terminal's resources. 【0034】 Features on the device: 【0035】 The device has a small artificial intelligence installed that monitors user behavior in the background. This AI analyzes the web pages the user views, the links they click, and the advertisements they see, and evaluates the likelihood of fraud based on predefined statistical characteristics. For example, if a user visits a fake login page disguised as a bank's, it will determine it's fraudulent based on URL patterns and abnormalities in the SSL certificate. 【0036】 The evaluated information is used to determine whether or not it is potentially fraudulent. If the result exceeds a threshold, it triggers the sending of the relevant information to the server. The user does not need to take any action at this stage; the data is transferred automatically. 【0037】 Server functionality: 【0038】 A large-scale artificial intelligence (AI) is deployed on the server to receive data sent from terminals. The AI ​​compares accumulated fraud cases with current data and uses machine learning algorithms to perform highly accurate fraud detection. The server constantly learns new fraud patterns to improve the overall detection accuracy of the system. 【0039】 Once the information analysis is complete, the results are sent to the device in real time and the user is notified. Specifically, a warning message such as "This may be a scam, please be careful" will be displayed on the device screen. 【0040】 User response: 【0041】 Users can recognize the risk of fraud early through the displayed warnings and choose the appropriate course of action. If a user determines a particular notification is safe, they can provide this feedback to the system, further improving the accuracy of subsequent detections. 【0042】 Specific example: 【0043】 Suppose a user receives a suspicious email and clicks on a link. A small AI on the device analyzes the URL and initially assesses it as having an unusual pattern. This information is immediately sent to the server, where a larger AI compares it to past phishing cases. If it is determined that the email is highly likely to be fraudulent, a warning is displayed on the device, and the user can avoid entering personal information. 【0044】 Thus, the system according to the present invention provides an environment in which individual users can avoid fraud and engage in their daily digital activities with peace of mind, even without possessing advanced knowledge. 【0045】 The following describes the processing flow. 【0046】 Step 1: 【0047】 The device monitors the user's online behavior in the background. Specifically, it records in real time the URLs of websites accessed, the content viewed, the links clicked, and the advertisements displayed. 【0048】 Step 2: 【0049】 The small artificial intelligence installed in the device analyzes collected user behavior data and compares it to pre-configured fraud characteristic patterns and heuristic rules. It then calculates a score indicating the likelihood of fraud and determines whether this score exceeds a set threshold. 【0050】 Step 3: 【0051】 If a score exceeding a threshold is calculated, the device sends the corresponding data to the server. This data includes the URLs visited, the content of the pages, and any detected anomalies. 【0052】 Step 4: 【0053】 The server passes the received data to a large artificial intelligence for further advanced analysis. Here, the likelihood of fraud is scrutinized by comparing the received data with known fraud patterns registered in multiple databases. 【0054】 Step 5: 【0055】 The final fraud determination is made based on the analysis results of a large-scale artificial intelligence on the server. This result is immediately fed back to the terminal, including instructions to generate a warning notification if necessary. 【0056】 Step 6: 【0057】 The device displays a warning message to the user based on the analysis results received from the server. This message will be specific, such as, "This site may be a scam. Please check the details before proceeding." 【0058】 Step 7: 【0059】 Users should review the displayed warning message and take the necessary actions according to the warning. This may include leaving sites or links identified as fraudulent and refraining from entering personal information. 【0060】 Step 8: 【0061】 The system provides a feature that allows users to send feedback to their device indicating "safe" if they deem it safe, and the rules of the small artificial intelligence are updated based on this feedback. This improves the accuracy of the next warning across the entire system. 【0062】 (Example 1) 【0063】 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." 【0064】 In today's digital environment, fraudulent activities are becoming increasingly complex. Therefore, protecting oneself from fraud requires advanced knowledge and vigilance, which can be a burden for many ordinary users. Furthermore, the lack of systems that can immediately identify and warn of fraudulent activity means that many people are missing opportunities to prevent becoming victims. Consequently, there is a need for a system that efficiently detects fraudulent activity and provides real-time warnings without placing an excessive burden on users. 【0065】 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. 【0066】 In this invention, the server includes means for incorporating a small knowledge processing device into the information processing device for understanding user operations, means for evaluating information using statistical characteristics to identify operations that may be fraudulent, and means for transmitting information exceeding a threshold value to the computing device. This makes it possible to provide early detection and warning of fraudulent activities in real time, improving security while reducing the burden on users. 【0067】 A "compact knowledge processing device" is a lightweight and efficient intelligent system that operates on an information processing device and monitors user operations. 【0068】 "Information processing equipment" is a general term for computers or digital devices used for collecting, analyzing, and transmitting data. 【0069】 "Statistical characteristics" are numerical or patternic features used to determine the likelihood of fraudulent activity present in data. 【0070】 A "processing unit" is a high-performance computer or digital system used to analyze and evaluate received information. 【0071】 "User" refers to an individual or group that uses information processing equipment to perform various digital activities. 【0072】 An "interactive device" is a device that has interface functions to enable interaction with the user and to provide notifications and warnings. 【0073】 "Feedback" refers to the return of information based on user-provided data to improve the system's detection accuracy and effectiveness. 【0074】 This fraud prevention system is primarily implemented through a combination of terminals and servers. The terminals are equipped with a small knowledge processing unit that monitors user activity in real time, analyzing web page URLs and the links users click. Specifically, this small knowledge processing unit is designed as a lightweight AI model, collecting critical data while minimizing the resources used by the terminal. 【0075】 Data collected by the terminal is immediately evaluated using statistical properties. During the evaluation process, pattern recognition algorithms are used to search for anomalous features that suggest fraudulent activity. If the evaluated information exceeds a set threshold, the information is sent to a server acting as a computing device. 【0076】 The server is equipped with a large knowledge processing unit, which is responsible for more complex analyses. The server compares the received data with a vast amount of past fraud case data and uses a multi-layer neural network to make sophisticated judgments. The results of this analysis are quickly fed back to the terminal, and warnings are displayed to the user in real time. 【0077】 As a concrete example, when a user clicks on a link in a phishing email, a small knowledge processing device immediately analyzes the URL and detects new characteristics not found in previous patterns. The information is sent to the server, where a large knowledge processing device compares it with previous phishing patterns and determines that it is "highly likely to be a scam." Based on this result, a warning message such as "This may be a scam, please be careful" is displayed on the device, allowing the user to avoid entering personal information. 【0078】 An example of a prompt for the generating AI model is, "Explain how the system detects and warns users when they click on a suspicious link." In this way, the system helps users to safely navigate digital environments even without specialized knowledge. 【0079】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0080】 Step 1: 【0081】 The terminal monitors user activity using a small knowledge processing device. Specifically, the terminal inputs data such as the URLs of web pages viewed by the user, the links clicked, and the advertisements displayed, and then analyzes this data. In this analysis, a pattern recognition algorithm is used to identify features that indicate fraudulent activity. As output, initial evaluation data regarding suspicious activity is generated. 【0082】 Step 2: 【0083】 The terminal uses statistical properties to assess the likelihood of fraudulent activity based on the initial evaluation data generated in Step 1. This process applies a statistical model to the input data to detect anomalous patterns suggestive of fraudulent activity. As a result, it outputs a score indicating the likelihood of fraud. If this score exceeds a set threshold, the data proceeds to the next step. 【0084】 Step 3: 【0085】 The terminal sends data to the server indicating potential fraudulent activity exceeding a certain threshold. Specifically, the terminal forms a data packet and transfers it to the server using a secure communication method. The output is the data regarding the suspected fraudulent activity that reached the server. 【0086】 Step 4: 【0087】 The server analyzes the data received from the terminal in detail using a large-scale knowledge processing unit. The input includes all data transmitted from the terminal. This analysis compares the data with past phishing and fraud case data and uses deep learning algorithms to perform sophisticated fraud detection. The output is a precise assessment of the degree of fraud risk. 【0088】 Step 5: 【0089】 The server transmits the evaluation results obtained in step 4 to the terminal in real time. Specifically, the server generates a warning message and transfers it to the terminal via the communication protocol. The terminal receives this data and displays a warning to the user stating, "This may be a scam, please be careful." The output is a warning message that the user can see. 【0090】 Step 6: 【0091】 Users choose safe actions based on warnings displayed on their devices. For example, they can choose not to use the provided links or refrain from entering personal information. The user then provides feedback to the system regarding the safety-checked notification. This feedback contributes to improving the accuracy of future fraud detection. The input is the user's response to the warning message, and the output is the feedback information. 【0092】 (Application Example 1) 【0093】 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." 【0094】 In electronic payment services, rapid and advanced fraud detection and warning functions are necessary to protect users from online fraud. However, current systems have limitations in their ability to detect fraud in advance, making it difficult to completely eliminate the risk of users becoming victims of fraud. Furthermore, there is a lack of flexible responses that utilize user feedback. To solve this problem, technology is needed that effectively analyzes the characteristics of fraud while monitoring user behavior and provides appropriate warnings. 【0095】 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. 【0096】 In this invention, the server includes a device that includes a small artificial intelligence in a terminal for observing user behavior, a device that evaluates information using statistical characteristics to detect potentially fraudulent activity, a device that transmits information exceeding a predetermined value to a central control unit, a device that operates a large artificial intelligence on the central control unit for highly evaluating the received information, and a device having ergonomic interface means as a method for collecting user responses and improving fraud characteristic patterns. This makes it possible to quickly detect fraudulent activity online and immediately warn users. It also allows for processing user feedback and dynamically improving the system's detection accuracy. 【0097】 A "user" refers to an individual or group that uses the system, and is the entity whose actions are subject to monitoring. 【0098】 "Artificial intelligence" refers to algorithms and technologies that perform data analysis and pattern recognition, and is the foundation for systems to automatically learn and make decisions. 【0099】 A "terminal" refers to an electronic device used directly by the user, and functions as a platform on which a small artificial intelligence is installed. 【0100】 "Device" refers to a physical or software structure designed to perform a specific function or role. 【0101】 A "central control unit" refers to a server that connects to multiple user terminals via a network and functions as the central hub for information processing and analysis. 【0102】 "Behavioral observation" refers to the process of monitoring users' online actions and choices to detect specific patterns. 【0103】 "Statistical characteristics" refer to the mathematical and statistical methods and indicators used when analyzing data, and serve as criteria for evaluating the likelihood of fraud. 【0104】 A "warning display" refers to a means of providing a message or display to alert users in situations that are deemed highly likely to be fraudulent. 【0105】 "Feedback" refers to the process by which users return actions and opinions to a system, and this information is used to improve the system. 【0106】 An "ergonomic interface" refers to an interface designed to allow users to interact with the system intuitively, thereby improving ease of use and efficiency for the user. 【0107】 The system of this invention centers around a small artificial intelligence (AI) that runs on a terminal and a large artificial intelligence (AI) that runs on a server. The terminal consists of any electronic device such as a smartphone or personal computer, and the small AI monitors the user's web browsing behavior in real time and evaluates the possibility of fraud. Specifically, the terminal analyzes the URLs and links of the web pages that the user accesses and evaluates whether there is a possibility of fraud based on statistical characteristics. If an anomaly is detected, that information is sent to the server. 【0108】 The server functions as a central control unit, further analyzing received data using a large-scale artificial intelligence (AI). This AI operates based on machine learning frameworks such as TENSORFLOW® and PyTorch, performing highly accurate fraud detection by comparing it with past fraud data. Based on the detection results, a warning message is sent to the user's terminal in real time. The user can decide what to do based on the presented warning and provide feedback as needed. This feedback is used as training data for the system, dynamically updating the characteristic patterns of fraud. 【0109】 As a concrete example, consider a scenario where a user attempts to make a payment on a newly visited e-commerce site. A small artificial intelligence analyzes the URL and, if it detects an unusual pattern, sends that information to a server. A larger artificial intelligence on the server receives this information, compares and analyzes it with similar fraud cases reported in the past, and calculates the likelihood of fraud. If necessary, it displays a warning to the user that it may be a scam. Based on this information, the user can verify the security and provide feedback. 【0110】 An example of a prompt in a generative AI model is, "Design an algorithm that analyzes URL patterns and indicates fraud risk to prevent fraud on e-commerce sites." 【0111】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0112】 Step 1: 【0113】 The device retrieves the URLs and link information of the web pages accessed by the user. The input is the URLs of the various web pages the user visits, and the output is this URL information. The device collects this information and prepares it for analysis by a small artificial intelligence. 【0114】 Step 2: 【0115】 A small artificial intelligence on the device analyzes the collected URL information based on its statistical characteristics. The input is the URL information obtained in step 1, and the output is the analysis result indicating the possibility of fraud. Specifically, the small artificial intelligence checks for abnormalities in URL patterns and SSL certificates and evaluates whether there are any abnormalities. 【0116】 Step 3: 【0117】 The terminal sends URL information that is deemed highly likely to be fraudulent based on the analysis results to the server. The input is the analysis results from step 2, and the output is the data sent to the server. This step is executed only if the data exceeds a threshold, and the data is promptly sent to the server via the network. 【0118】 Step 4: 【0119】 The server further analyzes the URL information received from the terminal using a large-scale artificial intelligence. The input is the URL information sent from the terminal, and the output is a detailed fraud risk assessment result. The server uses a machine learning framework to compare it with past fraud cases and perform highly accurate fraud detection. 【0120】 Step 5: 【0121】 Based on the server's analysis results, a warning message is sent to the terminal. The input is the analysis results of a large artificial intelligence, and the output is a message as a warning to the user. If a fraud risk is detected, a warning such as "This may be a scam. Please be careful." will be displayed on the terminal. 【0122】 Step 6: 【0123】 Users provide feedback by reviewing displayed warnings and re-evaluating their actions. The input is warning information sent from the server, and the output is user feedback. If the user determines the situation is safe, this information is incorporated into the system's training data to improve accuracy in future instances. 【0124】 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. 【0125】 The system based on this invention is implemented with a configuration in which a small artificial intelligence and emotion engine are placed on the user's terminal, and a large artificial intelligence is placed on the server. This combination provides real-time fraud detection and interactive warning notifications that respond to the user's emotions. 【0126】 Features on the device: 【0127】 The device has a small artificial intelligence installed that monitors user behavior. This AI constantly analyzes viewed web pages, clicked links, and displayed advertisements to assess the likelihood of fraud. The assessment uses pre-set statistical characteristics, and behavior exceeding a certain threshold is deemed suspicious. 【0128】 At the same time, the device is equipped with an emotion engine that recognizes the user's current emotional state by analyzing their facial expressions and voice tone through the camera and microphone. This emotion data is used as feedback to adjust warning notifications. 【0129】 For example, if a user clicks on a potentially fraudulent link, a small AI immediately detects this action, and an emotion engine analyzes the user's reaction and facial expression at that time. This allows the AI ​​to determine whether the user is surprised or remaining calm. 【0130】 Server functionality: 【0131】 Data deemed potentially fraudulent by the device is sent to a server. A large-scale artificial intelligence on the server performs a deeper analysis, comparing the received data against multiple fraud databases and past analysis patterns. This process accurately assesses the likelihood of fraud. 【0132】 The server's analysis results are immediately sent back to the terminal and used as instructions for delivering detailed warning notifications to the user. 【0133】 Notifications and interactions with users: 【0134】 The warnings displayed to users are individually tailored based on the results of the emotion engine's analysis. For example, if a user shows strong surprise or anxiety in response to a warning, the tone of the notification is softened, and advice encouraging a calm response is added. 【0135】 Specific example: 【0136】 When a user accesses a suspicious website, a small AI on the device immediately detects it and sends data to the server. A larger AI on the server determines it is a scam and sends this result back to the device. If the user is feeling uneasy at this time, an emotion engine picks up on that emotion, and the device displays a message in a gentle tone saying, "This site may not be safe. Click here to check detailed safety measures." This allows the user to respond quickly and with peace of mind. 【0137】 Thus, the present invention aims to provide a more personalized and effective fraud prevention measure by taking into account the user's emotions. 【0138】 The following describes the processing flow. 【0139】 Step 1: 【0140】 The device monitors the user's internet activity in real time, recording the websites the user visits, the links they click, and the advertisements they see. This monitoring takes place in the background. 【0141】 Step 2: 【0142】 The device's miniature artificial intelligence analyzes the collected data and compares it to the statistical characteristics of registered scams to assess the likelihood of fraud. It generates a score as a result of the assessment and determines whether this value exceeds a threshold. 【0143】 Step 3: 【0144】 When the score exceeds a threshold, the device immediately sends that data to the server. The transmitted data includes the specific URLs and page content accessed by the user. 【0145】 Step 4: 【0146】 In parallel, the device's emotion engine analyzes the user's facial expressions and voice to detect their emotional state. Recognizing emotions such as surprise or anxiety is used to adjust the content of warning notifications. 【0147】 Step 5: 【0148】 The server analyzes the data received from the terminal using a large-scale artificial intelligence. Here, it compares the data against known fraud patterns in the database, performs anomaly detection using machine learning, and makes a final fraud determination. 【0149】 Step 6: 【0150】 The server's analysis results are sent to the terminal and reflected in the warning notification sent to the user. The terminal uses the emotion engine's analysis results to adapt the content and expression of the warning to the user's current emotions. 【0151】 Step 7: 【0152】 The user checks the warning message displayed on their device. If they express concern, the message may include something like, "This site may not be safe. Please remain calm." 【0153】 Step 8: 【0154】 Users should follow the warnings, quickly retreat from potentially fraudulent websites and links, and avoid entering personal information. They should also contribute to the system's learning through feedback if they deem it safe. 【0155】 (Example 2) 【0156】 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". 【0157】 In today's information society, users are at increasing risk of encountering online fraud. In this situation, there is a need for systems that can quickly detect potential fraud and respond appropriately. However, conventional systems have struggled to provide highly accurate warning notifications based on user behavior and emotional states. Furthermore, as fraud patterns diversify and evolve daily, an updatable detection framework is also required to adapt to these changes. 【0158】 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. 【0159】 In this invention, the server includes means for incorporating a mechanism in the terminal to monitor user behavior, means for evaluating information using statistical features to detect potentially fraudulent behavior, and means for utilizing a device to analyze user emotions and construct emotion-responsive warning notifications. This enables users to anticipate fraudulent activity in advance and respond quickly and calmly based on personalized warnings. 【0160】 A "user behavior monitoring mechanism" is a device or program that tracks a user's online actions in real time and collects and analyzes that behavior as data. 【0161】 "Means of evaluating information using statistical features" refers to algorithms or techniques for evaluating the anomalies and regularities of obtained information based on pre-defined mathematical characteristics or patterns, and for determining the possibility of fraud. 【0162】 A "central processing unit" is a server or computer system that centrally processes information transmitted from terminals via a network and performs large-scale data analysis. 【0163】 A "large-scale learning algorithm" is an artificial intelligence technology that uses massive datasets to perform pattern recognition and prediction with high accuracy, and is generally based on machine learning or deep learning. 【0164】 A "device that analyzes user emotions" is a device or software that analyzes a user's facial expressions and voice to identify their emotional state at a given moment and convert it into digital information. 【0165】 "Means for configuring emotion-responsive warning notifications" refers to a process or system for customizing warnings with appropriate content and tone based on the user's emotional state and effectively communicating them to the user. 【0166】 The system for implementing this invention consists of equipping the user's terminal with a small artificial intelligence (AI) and an emotion analysis device, and deploying a large-scale artificial intelligence on a server. The user's terminal constantly monitors the user's behavior and assesses the risk of fraud based on the collected data. Specifically, the terminal analyzes the web pages the user visits, the links they click, and the advertisements they see in real time. The analysis uses statistical algorithms to calculate the likelihood of fraud. 【0167】 The device is also equipped with emotion analysis software that analyzes the user's facial expressions and voice data acquired through the camera and microphone to identify the user's current emotional state. This information is a crucial element in personalizing warning notifications for the user. 【0168】 The server aggregates information sent from terminals and performs detailed data analysis using a large-scale AI. This AI is designed to make precise judgments about the likelihood of fraud by comparing it with a known fraud database and past detection patterns. It also utilizes machine learning techniques to continuously learn and update new fraud characteristic patterns. 【0169】 If a user engages in potentially fraudulent behavior, a small AI on the device immediately detects it, and an emotion engine analyzes the user's facial expressions and voice as their response. For example, the prompt message when a user clicks a suspicious link is as follows: "This site may not be safe. Click here to see more safety information." In this way, the system generates personalized warning notifications that take into account the user's emotional state, helping them to respond calmly and quickly. 【0170】 This system allows users to recognize the risk of fraud in real time and use the internet with peace of mind. Furthermore, the content of warnings is dynamically optimized in response to changes in user behavior, ensuring that users always receive the most relevant information. 【0171】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0172】 Step 1: 【0173】 The device begins monitoring the user's online behavior in real time. It receives data as input, including the web pages the user accesses, the links they click, and the advertisements they see. Based on this data, a small AI uses statistical algorithms to assess the risk of fraud. Specifically, it detects URL structure and content patterns and calculates a risk score. The output generates an initial assessment of the likelihood of fraud and a risk score. 【0174】 Step 2: 【0175】 The device evaluates the user's emotional state via an emotion analysis device. It uses user facial expression data and voice data acquired through the camera and microphone as input. The emotion engine analyzes changes in facial expression and voice tone to determine whether the user is feeling surprise, anxiety, or other emotions. Specific actions include analyzing facial muscle movements and voice pitch and tempo. The output is the evaluation result of the user's emotional state. 【0176】 Step 3: 【0177】 The device sends data that it deems to be at high risk of fraud to the server. As input, it uses evaluation data including risk score, initial judgment, and user sentiment state. This data is encrypted and transmitted using a secure communication protocol. Specifically, a data transfer function is activated, and the server prepares to receive the data. As output, the data is transmitted to the server. 【0178】 Step 4: 【0179】 The server uses a large-scale artificial intelligence to perform detailed analysis based on the received data. It uses data sent from the terminal as input, comparing it against a fraud database and past analysis patterns. Using machine learning models, it re-evaluates the likelihood of fraud and makes a more precise judgment. The output generates a final fraud risk score and judgment result. 【0180】 Step 5: 【0181】 Based on the final assessment, the server generates and sends a warning notification to the user's device. The inputs used are the detailed evaluation results and the user's emotional state. This data is used to personalize the notification content and construct a message in a tone appropriate to the user. Specifically, the warning generation engine operates and generates an appropriate notification message. The output is the warning message sent to the device. 【0182】 Step 6: 【0183】 The terminal receives instructions from the server and displays a warning to the user. It uses the warning message sent from the server as input. A notification containing links and advice is presented to the user. Specifically, the screen display function operates, and information is provided using the user interface. The output is the actual warning notification delivered to the user. 【0184】 (Application Example 2) 【0185】 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". 【0186】 In today's information society, economic damage caused by fraudulent activities is increasing, and this is a particularly serious problem in electronic payments. To prevent fraud, users need early warnings and concrete countermeasures, but existing systems lack the interactive capabilities to consider users' emotional responses. Therefore, there is a need for a system that monitors user behavior and emotions in real time and provides appropriate warnings. 【0187】 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. 【0188】 In this invention, the server includes a processing system for monitoring user behavior, a processing system for evaluating data using statistical features to detect potentially fraudulent behavior, a processing system that operates an analysis system for highly evaluating received data on a central processing unit, an information processing unit including an emotion analysis system for analyzing the user's emotional state and adaptively adjusting warning notifications, and a processing system for providing warning notifications to the user based on the final evaluation. This makes it possible not only to detect anomalies in real time based on user behavior, but also to provide flexible and personalized warning notifications that are appropriate to the user's emotions. 【0189】 A "processing system for monitoring user behavior" is a system that records user operations and access history on information terminals and detects fraudulent behavior by analyzing that data. 【0190】 A "processing system that uses statistical features to evaluate data in order to detect potentially fraudulent behavior" is a system that quantitatively evaluates user behavior patterns and automatically identifies behavior that exceeds predefined thresholds as potentially fraudulent. 【0191】 The "analysis system for highly evaluating received data on the central processing unit" is a system in which high-performance artificial intelligence located on a server analyzes the collected data from multiple angles to determine the likelihood of fraud. 【0192】 An "information processing device including an emotion analysis system" is a device equipped with the processing capability to recognize the user's emotional state from their voice and facial expressions, and to generate adaptive warning notifications based on that information. 【0193】 A "system that provides warning notifications to users" is a system that, based on analysis results, displays specific and action-oriented warning messages to users at the appropriate time. 【0194】 This invention is a system that detects fraudulent activity in real time and provides interactive warnings tailored to the user's emotions by linking the user's terminal with a server. Specific embodiments of this system are described below. 【0195】 The device has a small artificial intelligence (AI) installed that constantly monitors the user's behavior history and access data. This AI evaluates the data based on specific statistical characteristics and immediately issues a warning if it detects potential fraud. The device also has a camera and microphone, and an emotion analysis engine analyzes the user's facial expressions and tone of voice to recognize the user's emotional state in real time. This emotion data is used to generate individually tailored warning notifications. 【0196】 The server houses a large-scale artificial intelligence (AI) that receives data transmitted from terminals and performs in-depth analysis. This analysis process compares the collected data with existing fraud databases and past analysis patterns, enabling highly accurate assessment of the probability of fraud. The evaluation results are then sent back to the terminal, helping to provide users with accurate warning notifications. 【0197】 As a concrete example, if a user accesses a suspicious website, a small AI on the device detects the anomaly of the site and sends that data to the server. A larger AI on the server analyzes this data, and if fraud is suspected, it sends a notification to the user. If the system recognizes that the user is feeling anxious, the notification will be displayed in a gentle tone, such as, "This site may not be safe. Please check the details." In this way, the system provides an appropriate response tailored to the user's emotions. 【0198】 An example of a prompt message is: "Generate a warning message to guide the user safely when they click on a fraudulent payment link. Please use a tone that alleviates any anxiety or surprise the user may feel." 【0199】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0200】 Step 1: 【0201】 The device monitors user behavior data. Specifically, it continuously collects website access history, clicked links, and viewed content. The input is a log of user actions, and the output is initial data indicating potential fraud. A small artificial intelligence statistically evaluates this data and detects anomalies. 【0202】 Step 2: 【0203】 The emotion analysis engine built into the device uses the camera and microphone to analyze the user's facial expressions and voice tone. The input is the user's facial image and voice data, and the output is data indicating the user's emotional state. This analysis process makes it possible to infer the emotions the user is feeling in real time. 【0204】 Step 3: 【0205】 If an anomaly is detected, the terminal transmits the relevant data to the central processing unit. The input is the data that has been statistically determined to be an anomaly, and the output is the transmission of the data to the server. This step includes the terminal uploading the data to the cloud in real time. 【0206】 Step 4: 【0207】 The server analyzes the received data using a large-scale artificial intelligence. The input is data on the user's abnormal behavior, and the output is highly accurate analysis results indicating the possibility of fraud. The server uses a fraud database and past analysis patterns to cross-reference the data and increase the likelihood of fraud. 【0208】 Step 5: 【0209】 The server sends the analysis results back to the terminal. The input is the result of evaluating the probability of fraud, and the output is the transmission of the analysis information to the terminal. This communication function prepares the system for issuing warnings to the user. 【0210】 Step 6: 【0211】 The device generates interactive warning notifications that take into account the user's emotional data. Inputs are analysis results from the server and the user's emotional data, and output is a personalized warning message. The device can display the notification and encourage the user to respond calmly. 【0212】 Step 7: 【0213】 The user reviews the displayed warning notification and takes safety precautions. The input is the warning message from the device, and the output is the change in the user's behavior. In this final step, the user can prevent becoming a victim of fraud by taking safer actions. 【0214】 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. 【0215】 Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0216】 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. 【0217】 [Second Embodiment] 【0218】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0219】 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. 【0220】 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). 【0221】 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. 【0222】 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. 【0223】 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). 【0224】 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. 【0225】 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. 【0226】 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. 【0227】 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. 【0228】 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. 【0229】 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". 【0230】 The fraud prevention system based on this invention is realized by deploying a small artificial intelligence and a large artificial intelligence on the user's terminal and a central server, respectively. This configuration provides advanced fraud detection capabilities while efficiently utilizing the terminal's resources. 【0231】 Features on the device: 【0232】 The device has a small artificial intelligence installed that monitors user behavior in the background. This AI analyzes the web pages the user views, the links they click, and the advertisements they see, and evaluates the likelihood of fraud based on predefined statistical characteristics. For example, if a user visits a fake login page disguised as a bank's, it will determine it's fraudulent based on URL patterns and abnormalities in the SSL certificate. 【0233】 The evaluated information is used to determine whether or not it is potentially fraudulent. If the result exceeds a threshold, it triggers the sending of the relevant information to the server. The user does not need to take any action at this stage; the data is transferred automatically. 【0234】 Server functionality: 【0235】 A large-scale artificial intelligence (AI) is deployed on the server to receive data sent from terminals. The AI ​​compares accumulated fraud cases with current data and uses machine learning algorithms to perform highly accurate fraud detection. The server constantly learns new fraud patterns to improve the overall detection accuracy of the system. 【0236】 Once the information analysis is complete, the results are sent to the device in real time and the user is notified. Specifically, a warning message such as "This may be a scam, please be careful" will be displayed on the device screen. 【0237】 User response: 【0238】 Users can recognize the risk of fraud early through the displayed warnings and choose the appropriate course of action. If a user determines a particular notification is safe, they can provide this feedback to the system, further improving the accuracy of subsequent detections. 【0239】 Specific example: 【0240】 Suppose a user receives a suspicious email and clicks on a link. A small AI on the device analyzes the URL and initially assesses it as having an unusual pattern. This information is immediately sent to the server, where a larger AI compares it to past phishing cases. If it is determined that the email is highly likely to be fraudulent, a warning is displayed on the device, and the user can avoid entering personal information. 【0241】 Thus, the system according to the present invention provides an environment in which individual users can avoid fraud and engage in their daily digital activities with peace of mind, even without possessing advanced knowledge. 【0242】 The following describes the processing flow. 【0243】 Step 1: 【0244】 The device monitors the user's online behavior in the background. Specifically, it records in real time the URLs of websites accessed, the content viewed, the links clicked, and the advertisements displayed. 【0245】 Step 2: 【0246】 The small artificial intelligence installed in the device analyzes collected user behavior data and compares it to pre-configured fraud characteristic patterns and heuristic rules. It then calculates a score indicating the likelihood of fraud and determines whether this score exceeds a set threshold. 【0247】 Step 3: 【0248】 If a score exceeding a threshold is calculated, the device sends the corresponding data to the server. This data includes the URLs visited, the content of the pages, and any detected anomalies. 【0249】 Step 4: 【0250】 The server passes the received data to a large artificial intelligence for further advanced analysis. Here, the likelihood of fraud is scrutinized by comparing the received data with known fraud patterns registered in multiple databases. 【0251】 Step 5: 【0252】 The final fraud determination is made based on the analysis results of a large-scale artificial intelligence on the server. This result is immediately fed back to the terminal, including instructions to generate a warning notification if necessary. 【0253】 Step 6: 【0254】 The device displays a warning message to the user based on the analysis results received from the server. This message will be specific, such as, "This site may be a scam. Please check the details before proceeding." 【0255】 Step 7: 【0256】 Users should review the displayed warning message and take the necessary actions according to the warning. This may include leaving sites or links identified as fraudulent and refraining from entering personal information. 【0257】 Step 8: 【0258】 The system provides a feature that allows users to send feedback to their device indicating "safe" if they deem it safe, and the rules of the small artificial intelligence are updated based on this feedback. This improves the accuracy of the next warning across the entire system. 【0259】 (Example 1) 【0260】 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." 【0261】 In today's digital environment, fraudulent activities are becoming increasingly complex. Therefore, protecting oneself from fraud requires advanced knowledge and vigilance, which can be a burden for many ordinary users. Furthermore, the lack of systems that can immediately identify and warn of fraudulent activity means that many people are missing opportunities to prevent becoming victims. Consequently, there is a need for a system that efficiently detects fraudulent activity and provides real-time warnings without placing an excessive burden on users. 【0262】 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. 【0263】 In this invention, the server includes means for incorporating a small knowledge processing device into the information processing device for understanding user operations, means for evaluating information using statistical characteristics to identify operations that may be fraudulent, and means for transmitting information exceeding a threshold value to the computing device. This makes it possible to provide early detection and warning of fraudulent activities in real time, improving security while reducing the burden on users. 【0264】 A "compact knowledge processing device" is a lightweight and efficient intelligent system that operates on an information processing device and monitors user operations. 【0265】 "Information processing equipment" is a general term for computers or digital devices used for collecting, analyzing, and transmitting data. 【0266】 "Statistical characteristics" are numerical or patternic features used to determine the likelihood of fraudulent activity present in data. 【0267】 A "processing unit" is a high-performance computer or digital system used to analyze and evaluate received information. 【0268】 "User" refers to an individual or group that uses information processing equipment to perform various digital activities. 【0269】 An "interactive device" is a device that has interface functions to enable interaction with the user and to provide notifications and warnings. 【0270】 "Feedback" refers to the return of information based on user-provided data to improve the system's detection accuracy and effectiveness. 【0271】 This fraud prevention system is primarily implemented through a combination of terminals and servers. The terminals are equipped with a small knowledge processing unit that monitors user activity in real time, analyzing web page URLs and the links users click. Specifically, this small knowledge processing unit is designed as a lightweight AI model, collecting critical data while minimizing the resources used by the terminal. 【0272】 Data collected by the terminal is immediately evaluated using statistical properties. During the evaluation process, pattern recognition algorithms are used to search for anomalous features that suggest fraudulent activity. If the evaluated information exceeds a set threshold, the information is sent to a server acting as a computing device. 【0273】 The server is equipped with a large knowledge processing unit, which is responsible for more complex analyses. The server compares the received data with a vast amount of past fraud case data and uses a multi-layer neural network to make sophisticated judgments. The results of this analysis are quickly fed back to the terminal, and warnings are displayed to the user in real time. 【0274】 As a concrete example, when a user clicks on a link in a phishing email, a small knowledge processing device immediately analyzes the URL and detects new characteristics not found in previous patterns. The information is sent to the server, where a large knowledge processing device compares it with previous phishing patterns and determines that it is "highly likely to be a scam." Based on this result, a warning message such as "This may be a scam, please be careful" is displayed on the device, allowing the user to avoid entering personal information. 【0275】 An example of a prompt for the generating AI model is, "Explain how the system detects and warns users when they click on a suspicious link." In this way, the system helps users to safely navigate digital environments even without specialized knowledge. 【0276】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0277】 Step 1: 【0278】 The terminal monitors user activity using a small knowledge processing device. Specifically, the terminal inputs data such as the URLs of web pages viewed by the user, the links clicked, and the advertisements displayed, and then analyzes this data. In this analysis, a pattern recognition algorithm is used to identify features that indicate fraudulent activity. As output, initial evaluation data regarding suspicious activity is generated. 【0279】 Step 2: 【0280】 The terminal uses statistical properties to assess the likelihood of fraudulent activity based on the initial evaluation data generated in Step 1. This process applies a statistical model to the input data to detect anomalous patterns suggestive of fraudulent activity. As a result, it outputs a score indicating the likelihood of fraud. If this score exceeds a set threshold, the data proceeds to the next step. 【0281】 Step 3: 【0282】 The terminal sends data to the server indicating potential fraudulent activity exceeding a certain threshold. Specifically, the terminal forms a data packet and transfers it to the server using a secure communication method. The output is the data regarding the suspected fraudulent activity that reached the server. 【0283】 Step 4: 【0284】 The server analyzes in detail the data received from the terminal using a large-scale knowledge processing device. The input includes all the data transmitted from the terminal. In this analysis, it is compared with past phishing and fraud case data, and an advanced fraud determination is performed using deep learning algorithms. The output is a precise evaluation result regarding the degree of increase in fraud risk. 【0285】 Step 5: 【0286】 The server transmits the evaluation result obtained in Step 4 to the terminal in real time. As a specific operation, the server generates a warning message and transfers it to the terminal via a communication protocol. The terminal receives this data and displays a warning to the user saying "Please be careful as there may be fraud." The output is a warning message that the user can see. 【0287】 Step 6: 【0288】 The user selects a safe action based on the warning displayed on the terminal. For example, the user can choose not to use the provided link or refrain from entering personal information. Then, the user provides feedback to the system regarding the notification of the safety confirmation. This feedback contributes to improving the fraud detection accuracy in the future. The input is the user's reaction to the warning message, and the output is the feedback information. 【0289】 (Application Example 1) 【0290】 Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal". 【0291】 In electronic payment services, rapid and advanced fraud detection and warning functions are necessary to protect users from online fraud. However, current systems have limitations in their ability to detect fraud in advance, making it difficult to completely eliminate the risk of users becoming victims of fraud. Furthermore, there is a lack of flexible responses that utilize user feedback. To solve this problem, technology is needed that effectively analyzes the characteristics of fraud while monitoring user behavior and provides appropriate warnings. 【0292】 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. 【0293】 In this invention, the server includes a device that includes a small artificial intelligence in a terminal for observing user behavior, a device that evaluates information using statistical characteristics to detect potentially fraudulent activity, a device that transmits information exceeding a predetermined value to a central control unit, a device that operates a large artificial intelligence on the central control unit for highly evaluating the received information, and a device having ergonomic interface means as a method for collecting user responses and improving fraud characteristic patterns. This makes it possible to quickly detect fraudulent activity online and immediately warn users. It also allows for processing user feedback and dynamically improving the system's detection accuracy. 【0294】 A "user" refers to an individual or group that uses the system, and is the entity whose actions are subject to monitoring. 【0295】 "Artificial intelligence" refers to algorithms and technologies that perform data analysis and pattern recognition, and is the foundation for systems to automatically learn and make decisions. 【0296】 A "terminal" refers to an electronic device used directly by the user, and functions as a platform on which a small artificial intelligence is installed. 【0297】 "Device" refers to a physical or software structure designed to perform a specific function or role. 【0298】 A "central control unit" refers to a server that connects to multiple user terminals via a network and functions as the central hub for information processing and analysis. 【0299】 "Behavioral observation" refers to the process of monitoring users' online actions and choices to detect specific patterns. 【0300】 "Statistical characteristics" refer to the mathematical and statistical methods and indicators used when analyzing data, and serve as criteria for evaluating the likelihood of fraud. 【0301】 A "warning display" refers to a means of providing a message or display to alert users in situations that are deemed highly likely to be fraudulent. 【0302】 "Feedback" refers to the process by which users return actions and opinions to a system, and this information is used to improve the system. 【0303】 An "ergonomic interface" refers to an interface designed to allow users to interact with the system intuitively, thereby improving ease of use and efficiency for the user. 【0304】 The system of this invention centers around a small artificial intelligence (AI) that runs on a terminal and a large artificial intelligence (AI) that runs on a server. The terminal consists of any electronic device such as a smartphone or personal computer, and the small AI monitors the user's web browsing behavior in real time and evaluates the possibility of fraud. Specifically, the terminal analyzes the URLs and links of the web pages that the user accesses and evaluates whether there is a possibility of fraud based on statistical characteristics. If an anomaly is detected, that information is sent to the server. 【0305】 The server functions as a central control device and further analyzes the received data using a large artificial intelligence. This large artificial intelligence operates based on machine learning frameworks such as TensorFlow or PyTorch, and performs high-precision fraud determination by comparing with past fraud data. Based on the determination result, a warning message is sent to the user's terminal in real time. The user can judge their actions based on the presented warning and provide feedback if necessary. This feedback is utilized as the learning data of the system to dynamically update the characteristic patterns of fraud. 【0306】 As a specific example, consider the case where a user attempts to make a payment on an e-commerce site they newly visit. When a small artificial intelligence analyzes the URL and detects a pattern different from normal, it sends that information to the server. The large artificial intelligence on the server receives this, compares and analyzes it with similar fraud cases reported in the past, and calculates the possibility of fraud. If necessary, it displays a warning to the user indicating the possibility of fraud. The user can confirm the security and provide feedback based on that information. 【0307】 An example of a prompt sentence in the generative AI model is "In order to prevent fraud on e-commerce sites, design an algorithm that analyzes URL patterns and indicates fraud risks." 【0308】 The flow of the specific process in Application Example 1 will be described using Figure 12. 【0309】 Step 1: 【0310】 The terminal obtains the URL and link information of the web page accessed by the user. The input is the URL of various web pages visited by the user, and the output is this URL information. The terminal collects this information and prepares for analysis by a small artificial intelligence. 【0311】 Step 2: 【0312】 <0……0983>A small artificial intelligence on the device analyzes the collected URL information based on its statistical characteristics. The input is the URL information obtained in step 1, and the output is the analysis result indicating the possibility of fraud. Specifically, the small artificial intelligence checks for abnormalities in URL patterns and SSL certificates and evaluates whether there are any abnormalities. 【0313】 Step 3: 【0314】 The terminal sends URL information that is deemed highly likely to be fraudulent based on the analysis results to the server. The input is the analysis results from step 2, and the output is the data sent to the server. This step is executed only if the data exceeds a threshold, and the data is promptly sent to the server via the network. 【0315】 Step 4: 【0316】 The server further analyzes the URL information received from the terminal using a large-scale artificial intelligence. The input is the URL information sent from the terminal, and the output is a detailed fraud risk assessment result. The server uses a machine learning framework to compare it with past fraud cases and perform highly accurate fraud detection. 【0317】 Step 5: 【0318】 Based on the server's analysis results, a warning message is sent to the terminal. The input is the analysis results of a large artificial intelligence, and the output is a message as a warning to the user. If a fraud risk is detected, a warning such as "This may be a scam. Please be careful." will be displayed on the terminal. 【0319】 Step 6: 【0320】 Users provide feedback by reviewing displayed warnings and re-evaluating their actions. The input is warning information sent from the server, and the output is user feedback. If the user determines the situation is safe, this information is incorporated into the system's training data to improve accuracy in future instances. 【0321】 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. 【0322】 The system based on this invention is implemented with a configuration in which a small artificial intelligence and emotion engine are placed on the user's terminal, and a large artificial intelligence is placed on the server. This combination provides real-time fraud detection and interactive warning notifications that respond to the user's emotions. 【0323】 Features on the device: 【0324】 The device has a small artificial intelligence installed that monitors user behavior. This AI constantly analyzes viewed web pages, clicked links, and displayed advertisements to assess the likelihood of fraud. The assessment uses pre-set statistical characteristics, and behavior exceeding a certain threshold is deemed suspicious. 【0325】 At the same time, the device is equipped with an emotion engine that recognizes the user's current emotional state by analyzing their facial expressions and voice tone through the camera and microphone. This emotion data is used as feedback to adjust warning notifications. 【0326】 For example, if a user clicks on a potentially fraudulent link, a small AI immediately detects this action, and an emotion engine analyzes the user's reaction and facial expression at that time. This allows the AI ​​to determine whether the user is surprised or remaining calm. 【0327】 Server functionality: 【0328】 Data deemed potentially fraudulent by the device is sent to a server. A large-scale artificial intelligence on the server performs a deeper analysis, comparing the received data against multiple fraud databases and past analysis patterns. This process accurately assesses the likelihood of fraud. 【0329】 The server's analysis results are immediately sent back to the terminal and used as instructions for delivering detailed warning notifications to the user. 【0330】 Notifications and interactions with users: 【0331】 The warnings displayed to users are individually tailored based on the results of the emotion engine's analysis. For example, if a user shows strong surprise or anxiety in response to a warning, the tone of the notification is softened, and advice encouraging a calm response is added. 【0332】 Specific example: 【0333】 When a user accesses a suspicious website, a small AI on the device immediately detects it and sends data to the server. A larger AI on the server determines it is a scam and sends this result back to the device. If the user is feeling uneasy at this time, an emotion engine picks up on that emotion, and the device displays a message in a gentle tone saying, "This site may not be safe. Click here to check detailed safety measures." This allows the user to respond quickly and with peace of mind. 【0334】 Thus, the present invention aims to provide a more personalized and effective fraud prevention measure by taking into account the user's emotions. 【0335】 The following describes the processing flow. 【0336】 Step 1: 【0337】 The device monitors the user's internet activity in real time, recording the websites the user visits, the links they click, and the advertisements they see. This monitoring takes place in the background. 【0338】 Step 2: 【0339】 The device's miniature artificial intelligence analyzes the collected data and compares it to the statistical characteristics of registered scams to assess the likelihood of fraud. It generates a score as a result of the assessment and determines whether this value exceeds a threshold. 【0340】 Step 3: 【0341】 When the score exceeds a threshold, the device immediately sends that data to the server. The transmitted data includes the specific URLs and page content accessed by the user. 【0342】 Step 4: 【0343】 In parallel, the device's emotion engine analyzes the user's facial expressions and voice to detect their emotional state. Recognizing emotions such as surprise or anxiety is used to adjust the content of warning notifications. 【0344】 Step 5: 【0345】 The server analyzes the data received from the terminal using a large-scale artificial intelligence. Here, it compares the data against known fraud patterns in the database, performs anomaly detection using machine learning, and makes a final fraud determination. 【0346】 Step 6: 【0347】 The server's analysis results are sent to the terminal and reflected in the warning notification sent to the user. The terminal uses the emotion engine's analysis results to adapt the content and expression of the warning to the user's current emotions. 【0348】 Step 7: 【0349】 The user checks the warning message displayed on their device. If they express concern, the message may include something like, "This site may not be safe. Please remain calm." 【0350】 Step 8: 【0351】 Users should follow the warnings, quickly retreat from potentially fraudulent websites and links, and avoid entering personal information. They should also contribute to the system's learning through feedback if they deem it safe. 【0352】 (Example 2) 【0353】 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". 【0354】 In today's information society, users are at increasing risk of encountering online fraud. In this situation, there is a need for systems that can quickly detect potential fraud and respond appropriately. However, conventional systems have struggled to provide highly accurate warning notifications based on user behavior and emotional states. Furthermore, as fraud patterns diversify and evolve daily, an updatable detection framework is also required to adapt to these changes. 【0355】 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. 【0356】 In this invention, the server includes means for incorporating a mechanism in the terminal to monitor user behavior, means for evaluating information using statistical features to detect potentially fraudulent behavior, and means for utilizing a device to analyze user emotions and construct emotion-responsive warning notifications. This enables users to anticipate fraudulent activity in advance and respond quickly and calmly based on personalized warnings. 【0357】 A "user behavior monitoring mechanism" is a device or program that tracks a user's online actions in real time and collects and analyzes that behavior as data. 【0358】 "Means of evaluating information using statistical features" refers to algorithms or techniques for evaluating the anomalies and regularities of obtained information based on pre-defined mathematical characteristics or patterns, and for determining the possibility of fraud. 【0359】 A "central processing unit" is a server or computer system that centrally processes information transmitted from terminals via a network and performs large-scale data analysis. 【0360】 A "large-scale learning algorithm" is an artificial intelligence technology that uses massive datasets to perform pattern recognition and prediction with high accuracy, and is generally based on machine learning or deep learning. 【0361】 A "device that analyzes user emotions" is a device or software that analyzes a user's facial expressions and voice to identify their emotional state at a given moment and convert it into digital information. 【0362】 "Means for configuring emotion-responsive warning notifications" refers to a process or system for customizing warnings with appropriate content and tone based on the user's emotional state and effectively communicating them to the user. 【0363】 The system for implementing this invention consists of equipping the user's terminal with a small artificial intelligence (AI) and an emotion analysis device, and deploying a large-scale artificial intelligence on a server. The user's terminal constantly monitors the user's behavior and assesses the risk of fraud based on the collected data. Specifically, the terminal analyzes the web pages the user visits, the links they click, and the advertisements they see in real time. The analysis uses statistical algorithms to calculate the likelihood of fraud. 【0364】 The device is also equipped with emotion analysis software that analyzes the user's facial expressions and voice data acquired through the camera and microphone to identify the user's current emotional state. This information is a crucial element in personalizing warning notifications for the user. 【0365】 The server aggregates information sent from terminals and performs detailed data analysis using a large-scale AI. This AI is designed to make precise judgments about the likelihood of fraud by comparing it with a known fraud database and past detection patterns. It also utilizes machine learning techniques to continuously learn and update new fraud characteristic patterns. 【0366】 If a user engages in potentially fraudulent behavior, a small AI on the device immediately detects it, and an emotion engine analyzes the user's facial expressions and voice as their response. For example, the prompt message when a user clicks a suspicious link is as follows: "This site may not be safe. Click here to see more safety information." In this way, the system generates personalized warning notifications that take into account the user's emotional state, helping them to respond calmly and quickly. 【0367】 This system allows users to recognize the risk of fraud in real time and use the internet with peace of mind. Furthermore, the content of warnings is dynamically optimized in response to changes in user behavior, ensuring that users always receive the most relevant information. 【0368】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0369】 Step 1: 【0370】 The device begins monitoring the user's online behavior in real time. It receives data as input, including the web pages the user accesses, the links they click, and the advertisements they see. Based on this data, a small AI uses statistical algorithms to assess the risk of fraud. Specifically, it detects URL structure and content patterns and calculates a risk score. The output generates an initial assessment of the likelihood of fraud and a risk score. 【0371】 Step 2: 【0372】 The device evaluates the user's emotional state via an emotion analysis device. It uses user facial expression data and voice data acquired through the camera and microphone as input. The emotion engine analyzes changes in facial expression and voice tone to determine whether the user is feeling surprise, anxiety, or other emotions. Specific actions include analyzing facial muscle movements and voice pitch and tempo. The output is the evaluation result of the user's emotional state. 【0373】 Step 3: 【0374】 The device sends data that it deems to be at high risk of fraud to the server. As input, it uses evaluation data including risk score, initial judgment, and user sentiment state. This data is encrypted and transmitted using a secure communication protocol. Specifically, a data transfer function is activated, and the server prepares to receive the data. As output, the data is transmitted to the server. 【0375】 Step 4: 【0376】 The server uses a large-scale artificial intelligence to perform detailed analysis based on the received data. It uses data sent from the terminal as input, comparing it against a fraud database and past analysis patterns. Using machine learning models, it re-evaluates the likelihood of fraud and makes a more precise judgment. The output generates a final fraud risk score and judgment result. 【0377】 Step 5: 【0378】 Based on the final assessment, the server generates and sends a warning notification to the user's device. The inputs used are the detailed evaluation results and the user's emotional state. This data is used to personalize the notification content and construct a message in a tone appropriate to the user. Specifically, the warning generation engine operates and generates an appropriate notification message. The output is the warning message sent to the device. 【0379】 Step 6: 【0380】 The terminal receives instructions from the server and displays a warning to the user. It uses the warning message sent from the server as input. A notification containing links and advice is presented to the user. Specifically, the screen display function operates, and information is provided using the user interface. The output is the actual warning notification delivered to the user. 【0381】 (Application Example 2) 【0382】 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." 【0383】 In today's information society, economic damage caused by fraudulent activities is increasing, and this is a particularly serious problem in electronic payments. To prevent fraud, users need early warnings and concrete countermeasures, but existing systems lack the interactive capabilities to consider users' emotional responses. Therefore, there is a need for a system that monitors user behavior and emotions in real time and provides appropriate warnings. 【0384】 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. 【0385】 In this invention, the server includes a processing system for monitoring user behavior, a processing system for evaluating data using statistical features to detect potentially fraudulent behavior, a processing system that operates an analysis system for highly evaluating received data on a central processing unit, an information processing unit including an emotion analysis system for analyzing the user's emotional state and adaptively adjusting warning notifications, and a processing system for providing warning notifications to the user based on the final evaluation. This makes it possible not only to detect anomalies in real time based on user behavior, but also to provide flexible and personalized warning notifications that are appropriate to the user's emotions. 【0386】 A "processing system for monitoring user behavior" is a system that records user operations and access history on information terminals and detects fraudulent behavior by analyzing that data. 【0387】 A "processing system that uses statistical features to evaluate data in order to detect potentially fraudulent behavior" is a system that quantitatively evaluates user behavior patterns and automatically identifies behavior that exceeds predefined thresholds as potentially fraudulent. 【0388】 The "analysis system for highly evaluating received data on the central processing unit" is a system in which high-performance artificial intelligence located on a server analyzes the collected data from multiple angles to determine the likelihood of fraud. 【0389】 An "information processing device including an emotion analysis system" is a device equipped with the processing capability to recognize the user's emotional state from their voice and facial expressions, and to generate adaptive warning notifications based on that information. 【0390】 A "system that provides warning notifications to users" is a system that, based on analysis results, displays specific and action-oriented warning messages to users at the appropriate time. 【0391】 This invention is a system that detects fraudulent activity in real time and provides interactive warnings tailored to the user's emotions by linking the user's terminal with a server. Specific embodiments of this system are described below. 【0392】 The device has a small artificial intelligence (AI) installed that constantly monitors the user's behavior history and access data. This AI evaluates the data based on specific statistical characteristics and immediately issues a warning if it detects potential fraud. The device also has a camera and microphone, and an emotion analysis engine analyzes the user's facial expressions and tone of voice to recognize the user's emotional state in real time. This emotion data is used to generate individually tailored warning notifications. 【0393】 The server houses a large-scale artificial intelligence (AI) that receives data transmitted from terminals and performs in-depth analysis. This analysis process compares the collected data with existing fraud databases and past analysis patterns, enabling highly accurate assessment of the probability of fraud. The evaluation results are then sent back to the terminal, helping to provide users with accurate warning notifications. 【0394】 As a concrete example, if a user accesses a suspicious website, a small AI on the device detects the anomaly of the site and sends that data to the server. A larger AI on the server analyzes this data, and if fraud is suspected, it sends a notification to the user. If the system recognizes that the user is feeling anxious, the notification will be displayed in a gentle tone, such as, "This site may not be safe. Please check the details." In this way, the system provides an appropriate response tailored to the user's emotions. 【0395】 An example of a prompt message is: "Generate a warning message to guide the user safely when they click on a fraudulent payment link. Please use a tone that alleviates any anxiety or surprise the user may feel." 【0396】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0397】 Step 1: 【0398】 The device monitors user behavior data. Specifically, it continuously collects website access history, clicked links, and viewed content. The input is a log of user actions, and the output is initial data indicating potential fraud. A small artificial intelligence statistically evaluates this data and detects anomalies. 【0399】 Step 2: 【0400】 The emotion analysis engine built into the device uses the camera and microphone to analyze the user's facial expressions and voice tone. The input is the user's facial image and voice data, and the output is data indicating the user's emotional state. This analysis process makes it possible to infer the emotions the user is feeling in real time. 【0401】 Step 3: 【0402】 If an anomaly is detected, the terminal transmits the relevant data to the central processing unit. The input is the data that has been statistically determined to be an anomaly, and the output is the transmission of the data to the server. This step includes the terminal uploading the data to the cloud in real time. 【0403】 Step 4: 【0404】 The server analyzes the received data using a large-scale artificial intelligence. The input is data on the user's abnormal behavior, and the output is highly accurate analysis results indicating the possibility of fraud. The server uses a fraud database and past analysis patterns to cross-reference the data and increase the likelihood of fraud. 【0405】 Step 5: 【0406】 The server sends the analysis results back to the terminal. The input is the result of evaluating the probability of fraud, and the output is the transmission of the analysis information to the terminal. This communication function prepares the system for issuing warnings to the user. 【0407】 Step 6: 【0408】 The device generates interactive warning notifications that take into account the user's emotional data. Inputs are analysis results from the server and the user's emotional data, and output is a personalized warning message. The device can display the notification and encourage the user to respond calmly. 【0409】 Step 7: 【0410】 The user reviews the displayed warning notification and takes safety precautions. The input is the warning message from the device, and the output is the change in the user's behavior. In this final step, the user can prevent becoming a victim of fraud by taking safer actions. 【0411】 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. 【0412】 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. 【0413】 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. 【0414】 [Third Embodiment] 【0415】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0416】 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. 【0417】 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). 【0418】 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. 【0419】 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. 【0420】 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). 【0421】 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. 【0422】 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. 【0423】 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. 【0424】 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. 【0425】 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. 【0426】 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". 【0427】 The fraud prevention system based on this invention is realized by deploying a small artificial intelligence and a large artificial intelligence on the user's terminal and a central server, respectively. This configuration provides advanced fraud detection capabilities while efficiently utilizing the terminal's resources. 【0428】 Features on the device: 【0429】 The device has a small artificial intelligence installed that monitors user behavior in the background. This AI analyzes the web pages the user views, the links they click, and the advertisements they see, and evaluates the likelihood of fraud based on predefined statistical characteristics. For example, if a user visits a fake login page disguised as a bank's, it will determine it's fraudulent based on URL patterns and abnormalities in the SSL certificate. 【0430】 The evaluated information is used to determine whether or not it is potentially fraudulent. If the result exceeds a threshold, it triggers the sending of the relevant information to the server. The user does not need to take any action at this stage; the data is transferred automatically. 【0431】 Server functionality: 【0432】 A large-scale artificial intelligence (AI) is deployed on the server to receive data sent from terminals. The AI ​​compares accumulated fraud cases with current data and uses machine learning algorithms to perform highly accurate fraud detection. The server constantly learns new fraud patterns to improve the overall detection accuracy of the system. 【0433】 Once the information analysis is complete, the results are sent to the device in real time and the user is notified. Specifically, a warning message such as "This may be a scam, please be careful" will be displayed on the device screen. 【0434】 User response: 【0435】 Users can recognize the risk of fraud early through the displayed warnings and choose the appropriate course of action. If a user determines a particular notification is safe, they can provide this feedback to the system, further improving the accuracy of subsequent detections. 【0436】 Specific example: 【0437】 Suppose a user receives a suspicious email and clicks on a link. A small AI on the device analyzes the URL and initially assesses it as having an unusual pattern. This information is immediately sent to the server, where a larger AI compares it to past phishing cases. If it is determined that the email is highly likely to be fraudulent, a warning is displayed on the device, and the user can avoid entering personal information. 【0438】 Thus, the system according to the present invention provides an environment in which individual users can avoid fraud and engage in their daily digital activities with peace of mind, even without possessing advanced knowledge. 【0439】 The following describes the processing flow. 【0440】 Step 1: 【0441】 The device monitors the user's online behavior in the background. Specifically, it records in real time the URLs of websites accessed, the content viewed, the links clicked, and the advertisements displayed. 【0442】 Step 2: 【0443】 The small artificial intelligence installed in the device analyzes collected user behavior data and compares it to pre-configured fraud characteristic patterns and heuristic rules. It then calculates a score indicating the likelihood of fraud and determines whether this score exceeds a set threshold. 【0444】 Step 3: 【0445】 If a score exceeding a threshold is calculated, the device sends the corresponding data to the server. This data includes the URLs visited, the content of the pages, and any detected anomalies. 【0446】 Step 4: 【0447】 The server passes the received data to a large artificial intelligence for further advanced analysis. Here, the likelihood of fraud is scrutinized by comparing the received data with known fraud patterns registered in multiple databases. 【0448】 Step 5: 【0449】 The final fraud determination is made based on the analysis results of a large-scale artificial intelligence on the server. This result is immediately fed back to the terminal, including instructions to generate a warning notification if necessary. 【0450】 Step 6: 【0451】 The device displays a warning message to the user based on the analysis results received from the server. This message will be specific, such as, "This site may be a scam. Please check the details before proceeding." 【0452】 Step 7: 【0453】 Users should review the displayed warning message and take the necessary actions according to the warning. This may include leaving sites or links identified as fraudulent and refraining from entering personal information. 【0454】 Step 8: 【0455】 The system provides a feature that allows users to send feedback to their device indicating "safe" if they deem it safe, and the rules of the small artificial intelligence are updated based on this feedback. This improves the accuracy of the next warning across the entire system. 【0456】 (Example 1) 【0457】 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." 【0458】 In today's digital environment, fraudulent activities are becoming increasingly complex. Therefore, protecting oneself from fraud requires advanced knowledge and vigilance, which can be a burden for many ordinary users. Furthermore, the lack of systems that can immediately identify and warn of fraudulent activity means that many people are missing opportunities to prevent becoming victims. Consequently, there is a need for a system that efficiently detects fraudulent activity and provides real-time warnings without placing an excessive burden on users. 【0459】 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. 【0460】 In this invention, the server includes means for incorporating a small knowledge processing device into the information processing device for understanding user operations, means for evaluating information using statistical characteristics to identify operations that may be fraudulent, and means for transmitting information exceeding a threshold value to the computing device. This makes it possible to provide early detection and warning of fraudulent activities in real time, improving security while reducing the burden on users. 【0461】 A "compact knowledge processing device" is a lightweight and efficient intelligent system that operates on an information processing device and monitors user operations. 【0462】 "Information processing equipment" is a general term for computers or digital devices used for collecting, analyzing, and transmitting data. 【0463】 "Statistical characteristics" are numerical or patternic features used to determine the likelihood of fraudulent activity present in data. 【0464】 A "processing unit" is a high-performance computer or digital system used to analyze and evaluate received information. 【0465】 "User" refers to an individual or group that uses information processing equipment to perform various digital activities. 【0466】 An "interactive device" is a device that has interface functions to enable interaction with the user and to provide notifications and warnings. 【0467】 "Feedback" refers to the return of information based on user-provided data to improve the system's detection accuracy and effectiveness. 【0468】 This fraud prevention system is primarily implemented through a combination of terminals and servers. The terminals are equipped with a small knowledge processing unit that monitors user activity in real time, analyzing web page URLs and the links users click. Specifically, this small knowledge processing unit is designed as a lightweight AI model, collecting critical data while minimizing the resources used by the terminal. 【0469】 Data collected by the terminal is immediately evaluated using statistical properties. During the evaluation process, pattern recognition algorithms are used to search for anomalous features that suggest fraudulent activity. If the evaluated information exceeds a set threshold, the information is sent to a server acting as a computing device. 【0470】 The server is equipped with a large knowledge processing unit, which is responsible for more complex analyses. The server compares the received data with a vast amount of past fraud case data and uses a multi-layer neural network to make sophisticated judgments. The results of this analysis are quickly fed back to the terminal, and warnings are displayed to the user in real time. 【0471】 As a concrete example, when a user clicks on a link in a phishing email, a small knowledge processing device immediately analyzes the URL and detects new characteristics not found in previous patterns. The information is sent to the server, where a large knowledge processing device compares it with previous phishing patterns and determines that it is "highly likely to be a scam." Based on this result, a warning message such as "This may be a scam, please be careful" is displayed on the device, allowing the user to avoid entering personal information. 【0472】 An example of a prompt for the generating AI model is, "Explain how the system detects and warns users when they click on a suspicious link." In this way, the system helps users to safely navigate digital environments even without specialized knowledge. 【0473】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0474】 Step 1: 【0475】 The terminal monitors user activity using a small knowledge processing device. Specifically, the terminal inputs data such as the URLs of web pages viewed by the user, the links clicked, and the advertisements displayed, and then analyzes this data. In this analysis, a pattern recognition algorithm is used to identify features that indicate fraudulent activity. As output, initial evaluation data regarding suspicious activity is generated. 【0476】 Step 2: 【0477】 The terminal uses statistical properties to assess the likelihood of fraudulent activity based on the initial evaluation data generated in Step 1. This process applies a statistical model to the input data to detect anomalous patterns suggestive of fraudulent activity. As a result, it outputs a score indicating the likelihood of fraud. If this score exceeds a set threshold, the data proceeds to the next step. 【0478】 Step 3: 【0479】 The terminal sends data to the server indicating potential fraudulent activity exceeding a certain threshold. Specifically, the terminal forms a data packet and transfers it to the server using a secure communication method. The output is the data regarding the suspected fraudulent activity that reached the server. 【0480】 Step 4: 【0481】 The server analyzes the data received from the terminal in detail using a large-scale knowledge processing unit. The input includes all data transmitted from the terminal. This analysis compares the data with past phishing and fraud case data and uses deep learning algorithms to perform sophisticated fraud detection. The output is a precise assessment of the degree of fraud risk. 【0482】 Step 5: 【0483】 The server transmits the evaluation results obtained in step 4 to the terminal in real time. Specifically, the server generates a warning message and transfers it to the terminal via the communication protocol. The terminal receives this data and displays a warning to the user stating, "This may be a scam, please be careful." The output is a warning message that the user can see. 【0484】 Step 6: 【0485】 Users choose safe actions based on warnings displayed on their devices. For example, they can choose not to use the provided links or refrain from entering personal information. The user then provides feedback to the system regarding the safety-checked notification. This feedback contributes to improving the accuracy of future fraud detection. The input is the user's response to the warning message, and the output is the feedback information. 【0486】 (Application Example 1) 【0487】 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." 【0488】 In electronic payment services, rapid and advanced fraud detection and warning functions are necessary to protect users from online fraud. However, current systems have limitations in their ability to detect fraud in advance, making it difficult to completely eliminate the risk of users becoming victims of fraud. Furthermore, there is a lack of flexible responses that utilize user feedback. To solve this problem, technology is needed that effectively analyzes the characteristics of fraud while monitoring user behavior and provides appropriate warnings. 【0489】 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. 【0490】 In this invention, the server includes a device that includes a small artificial intelligence in a terminal for observing user behavior, a device that evaluates information using statistical characteristics to detect potentially fraudulent activity, a device that transmits information exceeding a predetermined value to a central control unit, a device that operates a large artificial intelligence on the central control unit for highly evaluating the received information, and a device having ergonomic interface means as a method for collecting user responses and improving fraud characteristic patterns. This makes it possible to quickly detect fraudulent activity online and immediately warn users. It also allows for processing user feedback and dynamically improving the system's detection accuracy. 【0491】 A "user" refers to an individual or group that uses the system, and is the entity whose actions are subject to monitoring. 【0492】 "Artificial intelligence" refers to algorithms and technologies that perform data analysis and pattern recognition, and is the foundation for systems to automatically learn and make decisions. 【0493】 A "terminal" refers to an electronic device used directly by the user, and functions as a platform on which a small artificial intelligence is installed. 【0494】 "Device" refers to a physical or software structure designed to perform a specific function or role. 【0495】 A "central control unit" refers to a server that connects to multiple user terminals via a network and functions as the central hub for information processing and analysis. 【0496】 "Behavioral observation" refers to the process of monitoring users' online actions and choices to detect specific patterns. 【0497】 "Statistical characteristics" refer to the mathematical and statistical methods and indicators used when analyzing data, and serve as criteria for evaluating the likelihood of fraud. 【0498】 A "warning display" refers to a means of providing a message or display to alert users in situations that are deemed highly likely to be fraudulent. 【0499】 "Feedback" refers to the process by which users return actions and opinions to a system, and this information is used to improve the system. 【0500】 An "ergonomic interface" refers to an interface designed to allow users to interact with the system intuitively, thereby improving ease of use and efficiency for the user. 【0501】 The system of this invention centers around a small artificial intelligence (AI) that runs on a terminal and a large artificial intelligence (AI) that runs on a server. The terminal consists of any electronic device such as a smartphone or personal computer, and the small AI monitors the user's web browsing behavior in real time and evaluates the possibility of fraud. Specifically, the terminal analyzes the URLs and links of the web pages that the user accesses and evaluates whether there is a possibility of fraud based on statistical characteristics. If an anomaly is detected, that information is sent to the server. 【0502】 The server functions as a central control unit, further analyzing the received data using a large-scale artificial intelligence (AI). This AI operates based on machine learning frameworks such as TensorFlow and PyTorch, and performs highly accurate fraud detection by comparing it with historical fraud data. Based on the detection results, a warning message is sent to the user's terminal in real time. The user can decide what to do based on the presented warning and provide feedback as needed. This feedback is used as training data for the system, dynamically updating the characteristic patterns of fraud. 【0503】 As a concrete example, consider a scenario where a user attempts to make a payment on a newly visited e-commerce site. A small artificial intelligence analyzes the URL and, if it detects an unusual pattern, sends that information to a server. A larger artificial intelligence on the server receives this information, compares and analyzes it with similar fraud cases reported in the past, and calculates the likelihood of fraud. If necessary, it displays a warning to the user that it may be a scam. Based on this information, the user can verify the security and provide feedback. 【0504】 An example of a prompt in a generative AI model is, "Design an algorithm that analyzes URL patterns and indicates fraud risk to prevent fraud on e-commerce sites." 【0505】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0506】 Step 1: 【0507】 The device retrieves the URLs and link information of the web pages accessed by the user. The input is the URLs of the various web pages the user visits, and the output is this URL information. The device collects this information and prepares it for analysis by a small artificial intelligence. 【0508】 Step 2: 【0509】 A small artificial intelligence on the device analyzes the collected URL information based on its statistical characteristics. The input is the URL information obtained in step 1, and the output is the analysis result indicating the possibility of fraud. Specifically, the small artificial intelligence checks for abnormalities in URL patterns and SSL certificates and evaluates whether there are any abnormalities. 【0510】 Step 3: 【0511】 The terminal sends URL information that is deemed highly likely to be fraudulent based on the analysis results to the server. The input is the analysis results from step 2, and the output is the data sent to the server. This step is executed only if the data exceeds a threshold, and the data is promptly sent to the server via the network. 【0512】 Step 4: 【0513】 The server further analyzes the URL information received from the terminal using a large-scale artificial intelligence. The input is the URL information sent from the terminal, and the output is a detailed fraud risk assessment result. The server uses a machine learning framework to compare it with past fraud cases and perform highly accurate fraud detection. 【0514】 Step 5: 【0515】 Based on the server's analysis results, a warning message is sent to the terminal. The input is the analysis results of a large artificial intelligence, and the output is a message as a warning to the user. If a fraud risk is detected, a warning such as "This may be a scam. Please be careful." will be displayed on the terminal. 【0516】 Step 6: 【0517】 Users provide feedback by reviewing displayed warnings and re-evaluating their actions. The input is warning information sent from the server, and the output is user feedback. If the user determines the situation is safe, this information is incorporated into the system's training data to improve accuracy in future instances. 【0518】 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. 【0519】 The system based on this invention is implemented with a configuration in which a small artificial intelligence and emotion engine are placed on the user's terminal, and a large artificial intelligence is placed on the server. This combination provides real-time fraud detection and interactive warning notifications that respond to the user's emotions. 【0520】 Features on the device: 【0521】 The device has a small artificial intelligence installed that monitors user behavior. This AI constantly analyzes viewed web pages, clicked links, and displayed advertisements to assess the likelihood of fraud. The assessment uses pre-set statistical characteristics, and behavior exceeding a certain threshold is deemed suspicious. 【0522】 At the same time, the device is equipped with an emotion engine that recognizes the user's current emotional state by analyzing their facial expressions and voice tone through the camera and microphone. This emotion data is used as feedback to adjust warning notifications. 【0523】 For example, if a user clicks on a potentially fraudulent link, a small AI immediately detects this action, and an emotion engine analyzes the user's reaction and facial expression at that time. This allows the AI ​​to determine whether the user is surprised or remaining calm. 【0524】 Server functionality: 【0525】 Data deemed potentially fraudulent by the device is sent to a server. A large-scale artificial intelligence on the server performs a deeper analysis, comparing the received data against multiple fraud databases and past analysis patterns. This process accurately assesses the likelihood of fraud. 【0526】 The server's analysis results are immediately sent back to the terminal and used as instructions for delivering detailed warning notifications to the user. 【0527】 Notifications and interactions with users: 【0528】 The warnings displayed to users are individually tailored based on the results of the emotion engine's analysis. For example, if a user shows strong surprise or anxiety in response to a warning, the tone of the notification is softened, and advice encouraging a calm response is added. 【0529】 Specific example: 【0530】 When a user accesses a suspicious website, a small AI on the device immediately detects it and sends data to the server. A larger AI on the server determines it is a scam and sends this result back to the device. If the user is feeling uneasy at this time, an emotion engine picks up on that emotion, and the device displays a message in a gentle tone saying, "This site may not be safe. Click here to check detailed safety measures." This allows the user to respond quickly and with peace of mind. 【0531】 Thus, the present invention aims to provide a more personalized and effective fraud prevention measure by taking into account the user's emotions. 【0532】 The following describes the processing flow. 【0533】 Step 1: 【0534】 The device monitors the user's internet activity in real time, recording the websites the user visits, the links they click, and the advertisements they see. This monitoring takes place in the background. 【0535】 Step 2: 【0536】 The device's miniature artificial intelligence analyzes the collected data and compares it to the statistical characteristics of registered scams to assess the likelihood of fraud. It generates a score as a result of the assessment and determines whether this value exceeds a threshold. 【0537】 Step 3: 【0538】 When the score exceeds a threshold, the device immediately sends that data to the server. The transmitted data includes the specific URLs and page content accessed by the user. 【0539】 Step 4: 【0540】 In parallel, the device's emotion engine analyzes the user's facial expressions and voice to detect their emotional state. Recognizing emotions such as surprise or anxiety is used to adjust the content of warning notifications. 【0541】 Step 5: 【0542】 The server analyzes the data received from the terminal using a large-scale artificial intelligence. Here, it compares the data against known fraud patterns in the database, performs anomaly detection using machine learning, and makes a final fraud determination. 【0543】 Step 6: 【0544】 The server's analysis results are sent to the terminal and reflected in the warning notification sent to the user. The terminal uses the emotion engine's analysis results to adapt the content and expression of the warning to the user's current emotions. 【0545】 Step 7: 【0546】 The user checks the warning message displayed on their device. If they express concern, the message may include something like, "This site may not be safe. Please remain calm." 【0547】 Step 8: 【0548】 Users should follow the warnings, quickly retreat from potentially fraudulent websites and links, and avoid entering personal information. They should also contribute to the system's learning through feedback if they deem it safe. 【0549】 (Example 2) 【0550】 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." 【0551】 In today's information society, users are at increasing risk of encountering online fraud. In this situation, there is a need for systems that can quickly detect potential fraud and respond appropriately. However, conventional systems have struggled to provide highly accurate warning notifications based on user behavior and emotional states. Furthermore, as fraud patterns diversify and evolve daily, an updatable detection framework is also required to adapt to these changes. 【0552】 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. 【0553】 In this invention, the server includes means for incorporating a mechanism in the terminal to monitor user behavior, means for evaluating information using statistical features to detect potentially fraudulent behavior, and means for utilizing a device to analyze user emotions and construct emotion-responsive warning notifications. This enables users to anticipate fraudulent activity in advance and respond quickly and calmly based on personalized warnings. 【0554】 A "user behavior monitoring mechanism" is a device or program that tracks a user's online actions in real time and collects and analyzes that behavior as data. 【0555】 "Means of evaluating information using statistical features" refers to algorithms or techniques for evaluating the anomalies and regularities of obtained information based on pre-defined mathematical characteristics or patterns, and for determining the possibility of fraud. 【0556】 A "central processing unit" is a server or computer system that centrally processes information transmitted from terminals via a network and performs large-scale data analysis. 【0557】 A "large-scale learning algorithm" is an artificial intelligence technology that uses massive datasets to perform pattern recognition and prediction with high accuracy, and is generally based on machine learning or deep learning. 【0558】 A "device that analyzes user emotions" is a device or software that analyzes a user's facial expressions and voice to identify their emotional state at a given moment and convert it into digital information. 【0559】 "Means for configuring emotion-responsive warning notifications" refers to a process or system for customizing warnings with appropriate content and tone based on the user's emotional state and effectively communicating them to the user. 【0560】 The system for implementing this invention consists of equipping the user's terminal with a small artificial intelligence (AI) and an emotion analysis device, and deploying a large-scale artificial intelligence on a server. The user's terminal constantly monitors the user's behavior and assesses the risk of fraud based on the collected data. Specifically, the terminal analyzes the web pages the user visits, the links they click, and the advertisements they see in real time. The analysis uses statistical algorithms to calculate the likelihood of fraud. 【0561】 The device is also equipped with emotion analysis software that analyzes the user's facial expressions and voice data acquired through the camera and microphone to identify the user's current emotional state. This information is a crucial element in personalizing warning notifications for the user. 【0562】 The server aggregates information sent from terminals and performs detailed data analysis using a large-scale AI. This AI is designed to make precise judgments about the likelihood of fraud by comparing it with a known fraud database and past detection patterns. It also utilizes machine learning techniques to continuously learn and update new fraud characteristic patterns. 【0563】 If a user engages in potentially fraudulent behavior, a small AI on the device immediately detects it, and an emotion engine analyzes the user's facial expressions and voice as their response. For example, the prompt message when a user clicks a suspicious link is as follows: "This site may not be safe. Click here to see more safety information." In this way, the system generates personalized warning notifications that take into account the user's emotional state, helping them to respond calmly and quickly. 【0564】 This system allows users to recognize the risk of fraud in real time and use the internet with peace of mind. Furthermore, the content of warnings is dynamically optimized in response to changes in user behavior, ensuring that users always receive the most relevant information. 【0565】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0566】 Step 1: 【0567】 The device begins monitoring the user's online behavior in real time. It receives data as input, including the web pages the user accesses, the links they click, and the advertisements they see. Based on this data, a small AI uses statistical algorithms to assess the risk of fraud. Specifically, it detects URL structure and content patterns and calculates a risk score. The output generates an initial assessment of the likelihood of fraud and a risk score. 【0568】 Step 2: 【0569】 The device evaluates the user's emotional state via an emotion analysis device. It uses user facial expression data and voice data acquired through the camera and microphone as input. The emotion engine analyzes changes in facial expression and voice tone to determine whether the user is feeling surprise, anxiety, or other emotions. Specific actions include analyzing facial muscle movements and voice pitch and tempo. The output is the evaluation result of the user's emotional state. 【0570】 Step 3: 【0571】 The device sends data that it deems to be at high risk of fraud to the server. As input, it uses evaluation data including risk score, initial judgment, and user sentiment state. This data is encrypted and transmitted using a secure communication protocol. Specifically, a data transfer function is activated, and the server prepares to receive the data. As output, the data is transmitted to the server. 【0572】 Step 4: 【0573】 The server uses a large-scale artificial intelligence to perform detailed analysis based on the received data. It uses data sent from the terminal as input, comparing it against a fraud database and past analysis patterns. Using machine learning models, it re-evaluates the likelihood of fraud and makes a more precise judgment. The output generates a final fraud risk score and judgment result. 【0574】 Step 5: 【0575】 Based on the final assessment, the server generates and sends a warning notification to the user's device. The inputs used are the detailed evaluation results and the user's emotional state. This data is used to personalize the notification content and construct a message in a tone appropriate to the user. Specifically, the warning generation engine operates and generates an appropriate notification message. The output is the warning message sent to the device. 【0576】 Step 6: 【0577】 The terminal receives instructions from the server and displays a warning to the user. It uses the warning message sent from the server as input. A notification containing links and advice is presented to the user. Specifically, the screen display function operates, and information is provided using the user interface. The output is the actual warning notification delivered to the user. 【0578】 (Application Example 2) 【0579】 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." 【0580】 In today's information society, economic damage caused by fraudulent activities is increasing, and this is a particularly serious problem in electronic payments. To prevent fraud, users need early warnings and concrete countermeasures, but existing systems lack the interactive capabilities to consider users' emotional responses. Therefore, there is a need for a system that monitors user behavior and emotions in real time and provides appropriate warnings. 【0581】 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. 【0582】 In this invention, the server includes a processing system for monitoring user behavior, a processing system for evaluating data using statistical features to detect potentially fraudulent behavior, a processing system that operates an analysis system for highly evaluating received data on a central processing unit, an information processing unit including an emotion analysis system for analyzing the user's emotional state and adaptively adjusting warning notifications, and a processing system for providing warning notifications to the user based on the final evaluation. This makes it possible not only to detect anomalies in real time based on user behavior, but also to provide flexible and personalized warning notifications that are appropriate to the user's emotions. 【0583】 A "processing system for monitoring user behavior" is a system that records user operations and access history on information terminals and detects fraudulent behavior by analyzing that data. 【0584】 A "processing system that uses statistical features to evaluate data in order to detect potentially fraudulent behavior" is a system that quantitatively evaluates user behavior patterns and automatically identifies behavior that exceeds predefined thresholds as potentially fraudulent. 【0585】 The "analysis system for highly evaluating received data on the central processing unit" is a system in which high-performance artificial intelligence located on a server analyzes the collected data from multiple angles to determine the likelihood of fraud. 【0586】 An "information processing device including an emotion analysis system" is a device equipped with the processing capability to recognize the user's emotional state from their voice and facial expressions, and to generate adaptive warning notifications based on that information. 【0587】 A "system that provides warning notifications to users" is a system that, based on analysis results, displays specific and action-oriented warning messages to users at the appropriate time. 【0588】 This invention is a system that detects fraudulent activity in real time and provides interactive warnings tailored to the user's emotions by linking the user's terminal with a server. Specific embodiments of this system are described below. 【0589】 The device has a small artificial intelligence (AI) installed that constantly monitors the user's behavior history and access data. This AI evaluates the data based on specific statistical characteristics and immediately issues a warning if it detects potential fraud. The device also has a camera and microphone, and an emotion analysis engine analyzes the user's facial expressions and tone of voice to recognize the user's emotional state in real time. This emotion data is used to generate individually tailored warning notifications. 【0590】 The server houses a large-scale artificial intelligence (AI) that receives data transmitted from terminals and performs in-depth analysis. This analysis process compares the collected data with existing fraud databases and past analysis patterns, enabling highly accurate assessment of the probability of fraud. The evaluation results are then sent back to the terminal, helping to provide users with accurate warning notifications. 【0591】 As a concrete example, if a user accesses a suspicious website, a small AI on the device detects the anomaly of the site and sends that data to the server. A larger AI on the server analyzes this data, and if fraud is suspected, it sends a notification to the user. If the system recognizes that the user is feeling anxious, the notification will be displayed in a gentle tone, such as, "This site may not be safe. Please check the details." In this way, the system provides an appropriate response tailored to the user's emotions. 【0592】 An example of a prompt message is: "Generate a warning message to guide the user safely when they click on a fraudulent payment link. Please use a tone that alleviates any anxiety or surprise the user may feel." 【0593】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0594】 Step 1: 【0595】 The device monitors user behavior data. Specifically, it continuously collects website access history, clicked links, and viewed content. The input is a log of user actions, and the output is initial data indicating potential fraud. A small artificial intelligence statistically evaluates this data and detects anomalies. 【0596】 Step 2: 【0597】 The emotion analysis engine built into the device uses the camera and microphone to analyze the user's facial expressions and voice tone. The input is the user's facial image and voice data, and the output is data indicating the user's emotional state. This analysis process makes it possible to infer the emotions the user is feeling in real time. 【0598】 Step 3: 【0599】 If an anomaly is detected, the terminal transmits the relevant data to the central processing unit. The input is the data that has been statistically determined to be an anomaly, and the output is the transmission of the data to the server. This step includes the terminal uploading the data to the cloud in real time. 【0600】 Step 4: 【0601】 The server analyzes the received data using a large-scale artificial intelligence. The input is data on the user's abnormal behavior, and the output is highly accurate analysis results indicating the possibility of fraud. The server uses a fraud database and past analysis patterns to cross-reference the data and increase the likelihood of fraud. 【0602】 Step 5: 【0603】 The server sends the analysis results back to the terminal. The input is the result of evaluating the probability of fraud, and the output is the transmission of the analysis information to the terminal. This communication function prepares the system for issuing warnings to the user. 【0604】 Step 6: 【0605】 The device generates interactive warning notifications that take into account the user's emotional data. Inputs are analysis results from the server and the user's emotional data, and output is a personalized warning message. The device can display the notification and encourage the user to respond calmly. 【0606】 Step 7: 【0607】 The user reviews the displayed warning notification and takes safety precautions. The input is the warning message from the device, and the output is the change in the user's behavior. In this final step, the user can prevent becoming a victim of fraud by taking safer actions. 【0608】 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. 【0609】 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. 【0610】 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. 【0611】 [Fourth Embodiment] 【0612】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0613】 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. 【0614】 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). 【0615】 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. 【0616】 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. 【0617】 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). 【0618】 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. 【0619】 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. 【0620】 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. 【0621】 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. 【0622】 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. 【0623】 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. 【0624】 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". 【0625】 The fraud prevention system based on this invention is realized by deploying a small artificial intelligence and a large artificial intelligence on the user's terminal and a central server, respectively. This configuration provides advanced fraud detection capabilities while efficiently utilizing the terminal's resources. 【0626】 Features on the device: 【0627】 The device has a small artificial intelligence installed that monitors user behavior in the background. This AI analyzes the web pages the user views, the links they click, and the advertisements they see, and evaluates the likelihood of fraud based on predefined statistical characteristics. For example, if a user visits a fake login page disguised as a bank's, it will determine it's fraudulent based on URL patterns and abnormalities in the SSL certificate. 【0628】 The evaluated information is used to determine whether or not it is potentially fraudulent. If the result exceeds a threshold, it triggers the sending of the relevant information to the server. The user does not need to take any action at this stage; the data is transferred automatically. 【0629】 Server functionality: 【0630】 A large-scale artificial intelligence (AI) is deployed on the server to receive data sent from terminals. The AI ​​compares accumulated fraud cases with current data and uses machine learning algorithms to perform highly accurate fraud detection. The server constantly learns new fraud patterns to improve the overall detection accuracy of the system. 【0631】 Once the information analysis is complete, the results are sent to the device in real time and the user is notified. Specifically, a warning message such as "This may be a scam, please be careful" will be displayed on the device screen. 【0632】 User response: 【0633】 Users can recognize the risk of fraud early through the displayed warnings and choose the appropriate course of action. If a user determines a particular notification is safe, they can provide this feedback to the system, further improving the accuracy of subsequent detections. 【0634】 Specific example: 【0635】 Suppose a user receives a suspicious email and clicks on a link. A small AI on the device analyzes the URL and initially assesses it as having an unusual pattern. This information is immediately sent to the server, where a larger AI compares it to past phishing cases. If it is determined that the email is highly likely to be fraudulent, a warning is displayed on the device, and the user can avoid entering personal information. 【0636】 Thus, the system according to the present invention provides an environment in which individual users can avoid fraud and engage in their daily digital activities with peace of mind, even without possessing advanced knowledge. 【0637】 The following describes the processing flow. 【0638】 Step 1: 【0639】 The device monitors the user's online behavior in the background. Specifically, it records in real time the URLs of websites accessed, the content viewed, the links clicked, and the advertisements displayed. 【0640】 Step 2: 【0641】 The small artificial intelligence installed in the device analyzes collected user behavior data and compares it to pre-configured fraud characteristic patterns and heuristic rules. It then calculates a score indicating the likelihood of fraud and determines whether this score exceeds a set threshold. 【0642】 Step 3: 【0643】 If a score exceeding a threshold is calculated, the device sends the corresponding data to the server. This data includes the URLs visited, the content of the pages, and any detected anomalies. 【0644】 Step 4: 【0645】 The server passes the received data to a large artificial intelligence for further advanced analysis. Here, the likelihood of fraud is scrutinized by comparing the received data with known fraud patterns registered in multiple databases. 【0646】 Step 5: 【0647】 The final fraud determination is made based on the analysis results of a large-scale artificial intelligence on the server. This result is immediately fed back to the terminal, including instructions to generate a warning notification if necessary. 【0648】 Step 6: 【0649】 The device displays a warning message to the user based on the analysis results received from the server. This message will be specific, such as, "This site may be a scam. Please check the details before proceeding." 【0650】 Step 7: 【0651】 Users should review the displayed warning message and take the necessary actions according to the warning. This may include leaving sites or links identified as fraudulent and refraining from entering personal information. 【0652】 Step 8: 【0653】 The system provides a feature that allows users to send feedback to their device indicating "safe" if they deem it safe, and the rules of the small artificial intelligence are updated based on this feedback. This improves the accuracy of the next warning across the entire system. 【0654】 (Example 1) 【0655】 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". 【0656】 In today's digital environment, fraudulent activities are becoming increasingly complex. Therefore, protecting oneself from fraud requires advanced knowledge and vigilance, which can be a burden for many ordinary users. Furthermore, the lack of systems that can immediately identify and warn of fraudulent activity means that many people are missing opportunities to prevent becoming victims. Consequently, there is a need for a system that efficiently detects fraudulent activity and provides real-time warnings without placing an excessive burden on users. 【0657】 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. 【0658】 In this invention, the server includes means for incorporating a small knowledge processing device into the information processing device for understanding user operations, means for evaluating information using statistical characteristics to identify operations that may be fraudulent, and means for transmitting information exceeding a threshold value to the computing device. This makes it possible to provide early detection and warning of fraudulent activities in real time, improving security while reducing the burden on users. 【0659】 A "compact knowledge processing device" is a lightweight and efficient intelligent system that operates on an information processing device and monitors user operations. 【0660】 "Information processing equipment" is a general term for computers or digital devices used for collecting, analyzing, and transmitting data. 【0661】 "Statistical characteristics" are numerical or patternic features used to determine the likelihood of fraudulent activity present in data. 【0662】 A "processing unit" is a high-performance computer or digital system used to analyze and evaluate received information. 【0663】 "User" refers to an individual or group that uses information processing equipment to perform various digital activities. 【0664】 An "interactive device" is a device that has interface functions to enable interaction with the user and to provide notifications and warnings. 【0665】 "Feedback" refers to the return of information based on user-provided data to improve the system's detection accuracy and effectiveness. 【0666】 This fraud prevention system is primarily implemented through a combination of terminals and servers. The terminals are equipped with a small knowledge processing unit that monitors user activity in real time, analyzing web page URLs and the links users click. Specifically, this small knowledge processing unit is designed as a lightweight AI model, collecting critical data while minimizing the resources used by the terminal. 【0667】 Data collected by the terminal is immediately evaluated using statistical properties. During the evaluation process, pattern recognition algorithms are used to search for anomalous features that suggest fraudulent activity. If the evaluated information exceeds a set threshold, the information is sent to a server acting as a computing device. 【0668】 The server is equipped with a large knowledge processing unit, which is responsible for more complex analyses. The server compares the received data with a vast amount of past fraud case data and uses a multi-layer neural network to make sophisticated judgments. The results of this analysis are quickly fed back to the terminal, and warnings are displayed to the user in real time. 【0669】 As a concrete example, when a user clicks on a link in a phishing email, a small knowledge processing device immediately analyzes the URL and detects new characteristics not found in previous patterns. The information is sent to the server, where a large knowledge processing device compares it with previous phishing patterns and determines that it is "highly likely to be a scam." Based on this result, a warning message such as "This may be a scam, please be careful" is displayed on the device, allowing the user to avoid entering personal information. 【0670】 An example of a prompt for the generating AI model is, "Explain how the system detects and warns users when they click on a suspicious link." In this way, the system helps users to safely navigate digital environments even without specialized knowledge. 【0671】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0672】 Step 1: 【0673】 The terminal monitors user activity using a small knowledge processing device. Specifically, the terminal inputs data such as the URLs of web pages viewed by the user, the links clicked, and the advertisements displayed, and then analyzes this data. In this analysis, a pattern recognition algorithm is used to identify features that indicate fraudulent activity. As output, initial evaluation data regarding suspicious activity is generated. 【0674】 Step 2: 【0675】 The terminal uses statistical properties to assess the likelihood of fraudulent activity based on the initial evaluation data generated in Step 1. This process applies a statistical model to the input data to detect anomalous patterns suggestive of fraudulent activity. As a result, it outputs a score indicating the likelihood of fraud. If this score exceeds a set threshold, the data proceeds to the next step. 【0676】 Step 3: 【0677】 The terminal sends data to the server indicating potential fraudulent activity exceeding a certain threshold. Specifically, the terminal forms a data packet and transfers it to the server using a secure communication method. The output is the data regarding the suspected fraudulent activity that reached the server. 【0678】 Step 4: 【0679】 The server analyzes the data received from the terminal in detail using a large-scale knowledge processing unit. The input includes all data transmitted from the terminal. This analysis compares the data with past phishing and fraud case data and uses deep learning algorithms to perform sophisticated fraud detection. The output is a precise assessment of the degree of fraud risk. 【0680】 Step 5: 【0681】 The server transmits the evaluation results obtained in step 4 to the terminal in real time. Specifically, the server generates a warning message and transfers it to the terminal via the communication protocol. The terminal receives this data and displays a warning to the user stating, "This may be a scam, please be careful." The output is a warning message that the user can see. 【0682】 Step 6: 【0683】 Users choose safe actions based on warnings displayed on their devices. For example, they can choose not to use the provided links or refrain from entering personal information. The user then provides feedback to the system regarding the safety-checked notification. This feedback contributes to improving the accuracy of future fraud detection. The input is the user's response to the warning message, and the output is the feedback information. 【0684】 (Application Example 1) 【0685】 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". 【0686】 In electronic payment services, rapid and advanced fraud detection and warning functions are necessary to protect users from online fraud. However, current systems have limitations in their ability to detect fraud in advance, making it difficult to completely eliminate the risk of users becoming victims of fraud. Furthermore, there is a lack of flexible responses that utilize user feedback. To solve this problem, technology is needed that effectively analyzes the characteristics of fraud while monitoring user behavior and provides appropriate warnings. 【0687】 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. 【0688】 In this invention, the server includes a device that includes a small artificial intelligence in a terminal for observing user behavior, a device that evaluates information using statistical characteristics to detect potentially fraudulent activity, a device that transmits information exceeding a predetermined value to a central control unit, a device that operates a large artificial intelligence on the central control unit for highly evaluating the received information, and a device having ergonomic interface means as a method for collecting user responses and improving fraud characteristic patterns. This makes it possible to quickly detect fraudulent activity online and immediately warn users. It also allows for processing user feedback and dynamically improving the system's detection accuracy. 【0689】 A "user" refers to an individual or group that uses the system, and is the entity whose actions are subject to monitoring. 【0690】 "Artificial intelligence" refers to algorithms and technologies that perform data analysis and pattern recognition, and is the foundation for systems to automatically learn and make decisions. 【0691】 A "terminal" refers to an electronic device used directly by the user, and functions as a platform on which a small artificial intelligence is installed. 【0692】 "Device" refers to a physical or software structure designed to perform a specific function or role. 【0693】 A "central control unit" refers to a server that connects to multiple user terminals via a network and functions as the central hub for information processing and analysis. 【0694】 "Behavioral observation" refers to the process of monitoring users' online actions and choices to detect specific patterns. 【0695】 "Statistical characteristics" refer to the mathematical and statistical methods and indicators used when analyzing data, and serve as criteria for evaluating the likelihood of fraud. 【0696】 A "warning display" refers to a means of providing a message or display to alert users in situations that are deemed highly likely to be fraudulent. 【0697】 "Feedback" refers to the process by which users return actions and opinions to a system, and this information is used to improve the system. 【0698】 An "ergonomic interface" refers to an interface designed to allow users to interact with the system intuitively, thereby improving ease of use and efficiency for the user. 【0699】 The system of this invention centers around a small artificial intelligence (AI) that runs on a terminal and a large artificial intelligence (AI) that runs on a server. The terminal consists of any electronic device such as a smartphone or personal computer, and the small AI monitors the user's web browsing behavior in real time and evaluates the possibility of fraud. Specifically, the terminal analyzes the URLs and links of the web pages that the user accesses and evaluates whether there is a possibility of fraud based on statistical characteristics. If an anomaly is detected, that information is sent to the server. 【0700】 The server functions as a central control unit, further analyzing the received data using a large-scale artificial intelligence (AI). This AI operates based on machine learning frameworks such as TensorFlow and PyTorch, and performs highly accurate fraud detection by comparing it with historical fraud data. Based on the detection results, a warning message is sent to the user's terminal in real time. The user can decide what to do based on the presented warning and provide feedback as needed. This feedback is used as training data for the system, dynamically updating the characteristic patterns of fraud. 【0701】 As a concrete example, consider a scenario where a user attempts to make a payment on a newly visited e-commerce site. A small artificial intelligence analyzes the URL and, if it detects an unusual pattern, sends that information to a server. A larger artificial intelligence on the server receives this information, compares and analyzes it with similar fraud cases reported in the past, and calculates the likelihood of fraud. If necessary, it displays a warning to the user that it may be a scam. Based on this information, the user can verify the security and provide feedback. 【0702】 An example of a prompt in a generative AI model is, "Design an algorithm that analyzes URL patterns and indicates fraud risk to prevent fraud on e-commerce sites." 【0703】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0704】 Step 1: 【0705】 The device retrieves the URLs and link information of the web pages accessed by the user. The input is the URLs of the various web pages the user visits, and the output is this URL information. The device collects this information and prepares it for analysis by a small artificial intelligence. 【0706】 Step 2: 【0707】 A small artificial intelligence on the device analyzes the collected URL information based on its statistical characteristics. The input is the URL information obtained in step 1, and the output is the analysis result indicating the possibility of fraud. Specifically, the small artificial intelligence checks for abnormalities in URL patterns and SSL certificates and evaluates whether there are any abnormalities. 【0708】 Step 3: 【0709】 The terminal sends URL information that is deemed highly likely to be fraudulent based on the analysis results to the server. The input is the analysis results from step 2, and the output is the data sent to the server. This step is executed only if the data exceeds a threshold, and the data is promptly sent to the server via the network. 【0710】 Step 4: 【0711】 The server further analyzes the URL information received from the terminal using a large-scale artificial intelligence. The input is the URL information sent from the terminal, and the output is a detailed fraud risk assessment result. The server uses a machine learning framework to compare it with past fraud cases and perform highly accurate fraud detection. 【0712】 Step 5: 【0713】 Based on the server's analysis results, a warning message is sent to the terminal. The input is the analysis results of a large artificial intelligence, and the output is a message as a warning to the user. If a fraud risk is detected, a warning such as "This may be a scam. Please be careful." will be displayed on the terminal. 【0714】 Step 6: 【0715】 Users provide feedback by reviewing displayed warnings and re-evaluating their actions. The input is warning information sent from the server, and the output is user feedback. If the user determines the situation is safe, this information is incorporated into the system's training data to improve accuracy in future instances. 【0716】 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. 【0717】 The system based on this invention is implemented with a configuration in which a small artificial intelligence and emotion engine are placed on the user's terminal, and a large artificial intelligence is placed on the server. This combination provides real-time fraud detection and interactive warning notifications that respond to the user's emotions. 【0718】 Features on the device: 【0719】 The device has a small artificial intelligence installed that monitors user behavior. This AI constantly analyzes viewed web pages, clicked links, and displayed advertisements to assess the likelihood of fraud. The assessment uses pre-set statistical characteristics, and behavior exceeding a certain threshold is deemed suspicious. 【0720】 At the same time, the device is equipped with an emotion engine that recognizes the user's current emotional state by analyzing their facial expressions and voice tone through the camera and microphone. This emotion data is used as feedback to adjust warning notifications. 【0721】 For example, if a user clicks on a potentially fraudulent link, a small AI immediately detects this action, and an emotion engine analyzes the user's reaction and facial expression at that time. This allows the AI ​​to determine whether the user is surprised or remaining calm. 【0722】 Server functionality: 【0723】 Data deemed potentially fraudulent by the device is sent to a server. A large-scale artificial intelligence on the server performs a deeper analysis, comparing the received data against multiple fraud databases and past analysis patterns. This process accurately assesses the likelihood of fraud. 【0724】 The server's analysis results are immediately sent back to the terminal and used as instructions for delivering detailed warning notifications to the user. 【0725】 Notifications and interactions with users: 【0726】 The warnings displayed to users are individually tailored based on the results of the emotion engine's analysis. For example, if a user shows strong surprise or anxiety in response to a warning, the tone of the notification is softened, and advice encouraging a calm response is added. 【0727】 Specific example: 【0728】 When a user accesses a suspicious website, a small AI on the device immediately detects it and sends data to the server. A larger AI on the server determines it is a scam and sends this result back to the device. If the user is feeling uneasy at this time, an emotion engine picks up on that emotion, and the device displays a message in a gentle tone saying, "This site may not be safe. Click here to check detailed safety measures." This allows the user to respond quickly and with peace of mind. 【0729】 Thus, the present invention aims to provide a more personalized and effective fraud prevention measure by taking into account the user's emotions. 【0730】 The following describes the processing flow. 【0731】 Step 1: 【0732】 The device monitors the user's internet activity in real time, recording the websites the user visits, the links they click, and the advertisements they see. This monitoring takes place in the background. 【0733】 Step 2: 【0734】 The device's miniature artificial intelligence analyzes the collected data and compares it to the statistical characteristics of registered scams to assess the likelihood of fraud. It generates a score as a result of the assessment and determines whether this value exceeds a threshold. 【0735】 Step 3: 【0736】 When the score exceeds a threshold, the device immediately sends that data to the server. The transmitted data includes the specific URLs and page content accessed by the user. 【0737】 Step 4: 【0738】 In parallel, the device's emotion engine analyzes the user's facial expressions and voice to detect their emotional state. Recognizing emotions such as surprise or anxiety is used to adjust the content of warning notifications. 【0739】 Step 5: 【0740】 The server analyzes the data received from the terminal using a large-scale artificial intelligence. Here, it compares the data against known fraud patterns in the database, performs anomaly detection using machine learning, and makes a final fraud determination. 【0741】 Step 6: 【0742】 The server's analysis results are sent to the terminal and reflected in the warning notification sent to the user. The terminal uses the emotion engine's analysis results to adapt the content and expression of the warning to the user's current emotions. 【0743】 Step 7: 【0744】 The user checks the warning message displayed on their device. If they express concern, the message may include something like, "This site may not be safe. Please remain calm." 【0745】 Step 8: 【0746】 Users should follow the warnings, quickly retreat from potentially fraudulent websites and links, and avoid entering personal information. They should also contribute to the system's learning through feedback if they deem it safe. 【0747】 (Example 2) 【0748】 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". 【0749】 In today's information society, users are at increasing risk of encountering online fraud. In this situation, there is a need for systems that can quickly detect potential fraud and respond appropriately. However, conventional systems have struggled to provide highly accurate warning notifications based on user behavior and emotional states. Furthermore, as fraud patterns diversify and evolve daily, an updatable detection framework is also required to adapt to these changes. 【0750】 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. 【0751】 In this invention, the server includes means for incorporating a mechanism in the terminal to monitor user behavior, means for evaluating information using statistical features to detect potentially fraudulent behavior, and means for utilizing a device to analyze user emotions and construct emotion-responsive warning notifications. This enables users to anticipate fraudulent activity in advance and respond quickly and calmly based on personalized warnings. 【0752】 A "user behavior monitoring mechanism" is a device or program that tracks a user's online actions in real time and collects and analyzes that behavior as data. 【0753】 "Means of evaluating information using statistical features" refers to algorithms or techniques for evaluating the anomalies and regularities of obtained information based on pre-defined mathematical characteristics or patterns, and for determining the possibility of fraud. 【0754】 A "central processing unit" is a server or computer system that centrally processes information transmitted from terminals via a network and performs large-scale data analysis. 【0755】 A "large-scale learning algorithm" is an artificial intelligence technology that uses massive datasets to perform pattern recognition and prediction with high accuracy, and is generally based on machine learning or deep learning. 【0756】 A "device that analyzes user emotions" is a device or software that analyzes a user's facial expressions and voice to identify their emotional state at a given moment and convert it into digital information. 【0757】 "Means for configuring emotion-responsive warning notifications" refers to a process or system for customizing warnings with appropriate content and tone based on the user's emotional state and effectively communicating them to the user. 【0758】 The system for implementing this invention consists of equipping the user's terminal with a small artificial intelligence (AI) and an emotion analysis device, and deploying a large-scale artificial intelligence on a server. The user's terminal constantly monitors the user's behavior and assesses the risk of fraud based on the collected data. Specifically, the terminal analyzes the web pages the user visits, the links they click, and the advertisements they see in real time. The analysis uses statistical algorithms to calculate the likelihood of fraud. 【0759】 The device is also equipped with emotion analysis software that analyzes the user's facial expressions and voice data acquired through the camera and microphone to identify the user's current emotional state. This information is a crucial element in personalizing warning notifications for the user. 【0760】 The server aggregates information sent from terminals and performs detailed data analysis using a large-scale AI. This AI is designed to make precise judgments about the likelihood of fraud by comparing it with a known fraud database and past detection patterns. It also utilizes machine learning techniques to continuously learn and update new fraud characteristic patterns. 【0761】 If a user engages in potentially fraudulent behavior, a small AI on the device immediately detects it, and an emotion engine analyzes the user's facial expressions and voice as their response. For example, the prompt message when a user clicks a suspicious link is as follows: "This site may not be safe. Click here to see more safety information." In this way, the system generates personalized warning notifications that take into account the user's emotional state, helping them to respond calmly and quickly. 【0762】 This system allows users to recognize the risk of fraud in real time and use the internet with peace of mind. Furthermore, the content of warnings is dynamically optimized in response to changes in user behavior, ensuring that users always receive the most relevant information. 【0763】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0764】 Step 1: 【0765】 The device begins monitoring the user's online behavior in real time. It receives data as input, including the web pages the user accesses, the links they click, and the advertisements they see. Based on this data, a small AI uses statistical algorithms to assess the risk of fraud. Specifically, it detects URL structure and content patterns and calculates a risk score. The output generates an initial assessment of the likelihood of fraud and a risk score. 【0766】 Step 2: 【0767】 The device evaluates the user's emotional state via an emotion analysis device. It uses user facial expression data and voice data acquired through the camera and microphone as input. The emotion engine analyzes changes in facial expression and voice tone to determine whether the user is feeling surprise, anxiety, or other emotions. Specific actions include analyzing facial muscle movements and voice pitch and tempo. The output is the evaluation result of the user's emotional state. 【0768】 Step 3: 【0769】 The device sends data that it deems to be at high risk of fraud to the server. As input, it uses evaluation data including risk score, initial judgment, and user sentiment state. This data is encrypted and transmitted using a secure communication protocol. Specifically, a data transfer function is activated, and the server prepares to receive the data. As output, the data is transmitted to the server. 【0770】 Step 4: 【0771】 The server uses a large-scale artificial intelligence to perform detailed analysis based on the received data. It uses data sent from the terminal as input, comparing it against a fraud database and past analysis patterns. Using machine learning models, it re-evaluates the likelihood of fraud and makes a more precise judgment. The output generates a final fraud risk score and judgment result. 【0772】 Step 5: 【0773】 Based on the final assessment, the server generates and sends a warning notification to the user's device. The inputs used are the detailed evaluation results and the user's emotional state. This data is used to personalize the notification content and construct a message in a tone appropriate to the user. Specifically, the warning generation engine operates and generates an appropriate notification message. The output is the warning message sent to the device. 【0774】 Step 6: 【0775】 The terminal receives instructions from the server and displays a warning to the user. It uses the warning message sent from the server as input. A notification containing links and advice is presented to the user. Specifically, the screen display function operates, and information is provided using the user interface. The output is the actual warning notification delivered to the user. 【0776】 (Application Example 2) 【0777】 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". 【0778】 In today's information society, economic damage caused by fraudulent activities is increasing, and this is a particularly serious problem in electronic payments. To prevent fraud, users need early warnings and concrete countermeasures, but existing systems lack the interactive capabilities to consider users' emotional responses. Therefore, there is a need for a system that monitors user behavior and emotions in real time and provides appropriate warnings. 【0779】 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. 【0780】 In this invention, the server includes a processing system for monitoring user behavior, a processing system for evaluating data using statistical features to detect potentially fraudulent behavior, a processing system that operates an analysis system for highly evaluating received data on a central processing unit, an information processing unit including an emotion analysis system for analyzing the user's emotional state and adaptively adjusting warning notifications, and a processing system for providing warning notifications to the user based on the final evaluation. This makes it possible not only to detect anomalies in real time based on user behavior, but also to provide flexible and personalized warning notifications that are appropriate to the user's emotions. 【0781】 A "processing system for monitoring user behavior" is a system that records user operations and access history on information terminals and detects fraudulent behavior by analyzing that data. 【0782】 A "processing system that uses statistical features to evaluate data in order to detect potentially fraudulent behavior" is a system that quantitatively evaluates user behavior patterns and automatically identifies behavior that exceeds predefined thresholds as potentially fraudulent. 【0783】 The "analysis system for highly evaluating received data on the central processing unit" is a system in which high-performance artificial intelligence located on a server analyzes the collected data from multiple angles to determine the likelihood of fraud. 【0784】 An "information processing device including an emotion analysis system" is a device equipped with the processing capability to recognize the user's emotional state from their voice and facial expressions, and to generate adaptive warning notifications based on that information. 【0785】 A "system that provides warning notifications to users" is a system that, based on analysis results, displays specific and action-oriented warning messages to users at the appropriate time. 【0786】 This invention is a system that detects fraudulent activity in real time and provides interactive warnings tailored to the user's emotions by linking the user's terminal with a server. Specific embodiments of this system are described below. 【0787】 The device has a small artificial intelligence (AI) installed that constantly monitors the user's behavior history and access data. This AI evaluates the data based on specific statistical characteristics and immediately issues a warning if it detects potential fraud. The device also has a camera and microphone, and an emotion analysis engine analyzes the user's facial expressions and tone of voice to recognize the user's emotional state in real time. This emotion data is used to generate individually tailored warning notifications. 【0788】 The server houses a large-scale artificial intelligence (AI) that receives data transmitted from terminals and performs in-depth analysis. This analysis process compares the collected data with existing fraud databases and past analysis patterns, enabling highly accurate assessment of the probability of fraud. The evaluation results are then sent back to the terminal, helping to provide users with accurate warning notifications. 【0789】 As a concrete example, if a user accesses a suspicious website, a small AI on the device detects the anomaly of the site and sends that data to the server. A larger AI on the server analyzes this data, and if fraud is suspected, it sends a notification to the user. If the system recognizes that the user is feeling anxious, the notification will be displayed in a gentle tone, such as, "This site may not be safe. Please check the details." In this way, the system provides an appropriate response tailored to the user's emotions. 【0790】 An example of a prompt message is: "Generate a warning message to guide the user safely when they click on a fraudulent payment link. Please use a tone that alleviates any anxiety or surprise the user may feel." 【0791】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0792】 Step 1: 【0793】 The device monitors user behavior data. Specifically, it continuously collects website access history, clicked links, and viewed content. The input is a log of user actions, and the output is initial data indicating potential fraud. A small artificial intelligence statistically evaluates this data and detects anomalies. 【0794】 Step 2: 【0795】 The emotion analysis engine built into the device uses the camera and microphone to analyze the user's facial expressions and voice tone. The input is the user's facial image and voice data, and the output is data indicating the user's emotional state. This analysis process makes it possible to infer the emotions the user is feeling in real time. 【0796】 Step 3: 【0797】 If an anomaly is detected, the terminal transmits the relevant data to the central processing unit. The input is the data that has been statistically determined to be an anomaly, and the output is the transmission of the data to the server. This step includes the terminal uploading the data to the cloud in real time. 【0798】 Step 4: 【0799】 The server analyzes the received data using a large-scale artificial intelligence. The input is data on the user's abnormal behavior, and the output is highly accurate analysis results indicating the possibility of fraud. The server uses a fraud database and past analysis patterns to cross-reference the data and increase the likelihood of fraud. 【0800】 Step 5: 【0801】 The server sends the analysis results back to the terminal. The input is the result of evaluating the probability of fraud, and the output is the transmission of the analysis information to the terminal. This communication function prepares the system for issuing warnings to the user. 【0802】 Step 6: 【0803】 The device generates interactive warning notifications that take into account the user's emotional data. Inputs are analysis results from the server and the user's emotional data, and output is a personalized warning message. The device can display the notification and encourage the user to respond calmly. 【0804】 Step 7: 【0805】 The user reviews the displayed warning notification and takes safety precautions. The input is the warning message from the device, and the output is the change in the user's behavior. In this final step, the user can prevent becoming a victim of fraud by taking safer actions. 【0806】 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. 【0807】 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. 【0808】 In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414. 【0809】 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. 【0810】 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. 【0811】 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. 【0812】 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. 【0813】 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. 【0814】 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." 【0815】 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. 【0816】 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. 【0817】 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. 【0818】 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. 【0819】 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. 【0820】 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. 【0821】 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. 【0822】 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. 【0823】 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. 【0824】 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. 【0825】 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. 【0826】 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. 【0827】 The following is further disclosed regarding the embodiments described above. 【0828】 (Claim 1) 【0829】 A means of including a small artificial intelligence in a terminal to monitor user behavior, 【0830】 A means of evaluating data using statistical features to detect potentially fraudulent behavior, 【0831】 A means of sending data exceeding a threshold to the server, 【0832】 A means of running a large-scale artificial intelligence on a server to highly evaluate received data, 【0833】 A means of providing warning notifications to users based on the final evaluation, 【0834】 A system that includes this. 【0835】 (Claim 2) 【0836】 A means for using machine learning to update the feature patterns that constitute fraud in the system according to claim 1. 【0837】 (Claim 3) 【0838】 The system according to claim 1, comprising means for an interface to assist the user in reviewing their actions in response to a provided notification. 【0839】 "Example 1" 【0840】 (Claim 1) 【0841】 A means of including a small knowledge processing device for understanding user operations in an information processing device, 【0842】 A means of evaluating information using statistical characteristics to identify operations that may be fraudulent, 【0843】 Means for transmitting information exceeding a reference value to a computing device, 【0844】 A means for operating a large-scale knowledge processing device on a computing device to highly evaluate received information, 【0845】 A means of providing warnings to users based on the final evaluation, 【0846】 A means for users to feed back notifications they deem safe into the system, 【0847】 A system that includes this. 【0848】 (Claim 2) 【0849】 The system according to claim 1, comprising means for updating characteristic patterns that constitute fraudulent activity using machine learning. 【0850】 (Claim 3) 【0851】 The system according to claim 1, comprising an interactive device for assisting a user in reviewing their actions based on a notification provided. 【0852】 "Application Example 1" 【0853】 (Claim 1) 【0854】 A device that includes a small artificial intelligence in the terminal for observing user behavior, 【0855】 A device that uses statistical characteristics to evaluate information in order to detect potentially fraudulent activities, 【0856】 A device that transmits information exceeding a default value to the central control unit, 【0857】 A device that operates a large-scale artificial intelligence for highly evaluating received information on a central control unit, 【0858】 A device that provides a warning to the user based on the final evaluation, 【0859】 A device having an ergonomic interface means as a method for collecting user responses and improving fraud characteristic patterns, 【0860】 A system that includes this. 【0861】 (Claim 2) 【0862】 The system according to claim 1, which uses machine learning to dynamically update characteristic patterns that constitute fraud. 【0863】 (Claim 3) 【0864】 The system according to claim 1, comprising an ergonomic interface for helping the user confirm their actions in response to a provided display. 【0865】 "Example 2 of combining an emotion engine" 【0866】 (Claim 1) 【0867】 A means of incorporating a mechanism to monitor user behavior into the terminal, 【0868】 A means of evaluating information using statistical features to detect potentially fraudulent behavior, 【0869】 Means for transmitting information exceeding a threshold to a central processing unit, 【0870】 A means for running a large-scale learning algorithm on a central processing unit to analyze received information in detail, 【0871】 A means for constructing a warning notification that responds to a user's emotions, using a device that analyzes the user's emotions. 【0872】 A means of providing users with personalized warning notifications based on the final evaluation, 【0873】 A system that includes this. 【0874】 (Claim 2) 【0875】 The system according to claim 1, which uses machine learning to update the characteristic patterns that constitute fraud. 【0876】 (Claim 3) 【0877】 The system according to claim 1, comprising a user interaction device for assisting the user in reviewing their actions in response to a notification provided. 【0878】 "Application example 2 when combining with an emotional engine" 【0879】 (Claim 1) 【0880】 A processing system for monitoring user behavior, 【0881】 A processing system that uses statistical features to evaluate data in order to detect potentially fraudulent behavior, 【0882】 A processing system that transmits data exceeding a threshold to a central processing unit, 【0883】 A processing system that operates an analysis system for highly evaluating received data on a central processing unit, 【0884】 An information processing device including an emotion analysis system for analyzing the user's emotional state and adaptively adjusting warning notifications, 【0885】 A processing system that provides warning notifications to users based on the final evaluation, 【0886】 A system that includes this. 【0887】 (Claim 2) 【0888】 The system according to claim 1, comprising a processing function for which machine learning is used to update characteristic patterns that constitute fraud. 【0889】 (Claim 3) 【0890】 The system according to claim 1, comprising information processing means including an interface for assisting a user in reviewing their actions in response to a notification provided. [Explanation of symbols] 【0891】 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

[Claim 1] A means of including a small artificial intelligence in a terminal to monitor user behavior, A means of evaluating data using statistical features to detect potentially fraudulent behavior, A means of sending data exceeding a threshold to the server, A means of running a large-scale artificial intelligence on a server to highly evaluate received data, A means of providing warning notifications to users based on the final evaluation, A system that includes this. [Claim 2] A means for using machine learning to update the feature patterns that constitute fraud in the system described in claim 1. [Claim 3] The system according to claim 1, comprising means for an interface to assist the user in reviewing their actions in response to a provided notification.

Images