system

Abstract

The system according to this embodiment aims to detect fraudulent links, messages, and call content in real time and to take appropriate action. [Solution] The system according to the embodiment comprises a detection unit, a warning unit, an analysis unit, a recording unit, and a notification unit. The detection unit detects fraudulent links and messages. The warning unit warns the user of any anomalies detected by the detection unit. The analysis unit processes the content of voice calls using natural language processing. The recording unit records the content of calls when fraudulent elements are detected by the analysis unit. The notification unit notifies a trusted third party when fraudulent activity is detected.

Description

Technical Field

[0006] , , ,

[0005] , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to detect fraudulent links, messages, and call contents in real time and appropriately handle them.

[0005] The system according to the embodiment aims to detect fraudulent links, messages, and call contents in real time and appropriately handle them.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a detection unit, a warning unit, an analysis unit, a recording unit, and a notification unit. The detection unit detects fraudulent links and messages. The warning unit warns the user of any anomalies detected by the detection unit. The analysis unit processes the content of voice calls using natural language processing. The recording unit records the content of calls when fraudulent elements are detected by the analysis unit. The notification unit notifies a trusted third party when fraudulent activity is detected. [Effects of the Invention]

[0007] The system according to this embodiment can detect fraudulent links, messages, and call content in real time and take appropriate action. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a receiving 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 receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The fraud detection system according to an embodiment of the present invention is a system that detects phishing scams and impersonation scams and warns the user. This fraud detection system uses AI to detect fraudulent links and messages sent from channels such as email, SMS, and SNS. It warns the user as soon as an anomaly is detected. It also processes voice calls using natural language processing with the user's permission to detect fraudulent patterns and phrases. If fraudulent elements are detected, the system records the conversation in real time from the beginning, even if it is still a call, and warns the user. Furthermore, if fraudulent activity is detected, it notifies not only the user but also a pre-designated trusted third party (e.g., family member or professional). This is especially important for elderly people, as it allows close relatives to respond quickly. The application also supports the user at any time; if the user receives a suspicious message or link, they can consult with the AI ​​on the spot and receive advice on the next course of action. As a result, the fraud detection system reduces the risk of the user becoming a victim of fraud and enables a quick and appropriate response. For example, when detecting fraudulent links or messages, the AI ​​analyzes a large amount of data to identify fraudulent patterns and phrases. This reduces the user's risk of becoming a victim of fraud. Next, the system warns the user as soon as an anomaly is detected. For example, if an email containing a fraudulent link is received, the AI ​​will detect the link and display a warning to the user. This allows the user to take preventative measures before falling victim to fraud. Furthermore, with the user's permission, the system also processes voice calls using natural language to detect fraudulent patterns and phrases. For example, it can detect fraudulent call content such as "ore-ore" (impersonation) scams. If fraudulent elements are detected, the system records the conversation in real time from the beginning, even if it is still a call, and warns the user. This helps users become more vigilant against fraud. In addition, if fraudulent activity is detected, the system notifies not only the user but also a pre-designated trusted third party (e.g., family member or professional). This is especially important for elderly people, as it allows close relatives to respond quickly. For example, if fraudulent call content is detected, the content can be notified to family members or professionals to encourage a swift response.Finally, the application supports users at all times; if a user receives a suspicious message or link, they can consult the AI ​​immediately and receive advice on what to do next. For example, if a user receives a suspicious email, the AI ​​can analyze the email to determine if it is potentially fraudulent and advise on appropriate countermeasures. This allows users to use the internet with peace of mind.

[0029] The fraud detection system according to the embodiment comprises a detection unit, a warning unit, an analysis unit, a recording unit, and a notification unit. The detection unit detects fraudulent links and messages. The detection unit uses AI to analyze fraudulent links and messages sent from channels such as email, SMS, and SNS, and identifies fraudulent patterns and phrases. For example, the detection unit can detect phishing links and "ore-ore" (impersonation) fraud messages. The detection unit can also use AI to detect fraudulent links and messages in real time. For example, the detection unit uses AI to analyze a large amount of data and identify fraudulent patterns and phrases. The warning unit warns the user of any anomalies detected by the detection unit. For example, if the user receives an email containing a fraudulent link, the AI ​​detects the link and displays a warning to the user. For example, the warning unit warns the user with a pop-up notification or an audio alert. The warning unit can also use AI to warn the user. For example, the warning unit displays a warning to the user based on anomalies detected by the AI. The analysis unit performs natural language processing on the content of voice calls. The analysis unit, for example, processes call content using natural language processing with the user's permission to detect fraudulent patterns and phrases. For example, the analysis unit can detect fraudulent call content such as "ore-ore" (impersonation) scams. The analysis unit can also analyze call content using AI. For example, the analysis unit can use AI to analyze call content and identify fraudulent patterns and phrases. The recording unit records call content when the analysis unit detects fraudulent elements. The recording unit can, for example, record conversations in real time from the beginning, even during a call, and issue warnings to the user. For example, the recording unit can use AI to record call content. For example, the recording unit can use AI to record call content in real time and issue warnings to the user. The notification unit notifies a trusted third party when fraudulent activity is detected. For example, if fraudulent call content is detected, the notification unit can notify family members or professionals to encourage prompt action. For example, the notification unit can use AI to notify a trusted third party when fraudulent activity is detected. For example, the notification unit can use AI to detect fraudulent activity and notify family members or professionals.As a result, the fraud detection system according to the embodiment can protect users from fraudulent activities by detecting fraudulent links and messages, warning users, analyzing and recording call content, and notifying trusted third parties.

[0030] The detection unit detects fraudulent links and messages. For example, the detection unit uses AI to analyze fraudulent links and messages sent through channels such as email, SMS, and social media, identifying fraudulent patterns and phrases. Specifically, the AI ​​uses natural language processing technology to analyze the message content and detect words and phrases with fraudulent characteristics. For example, messages containing keywords such as "urgent," "confirm," and "password," or links with specific URL patterns, are highly likely to be fraudulent. Furthermore, the AI ​​continuously learns by referencing a database of past fraudulent messages to adapt to new fraudulent methods. This allows the detection unit to detect phishing links and "ore-ore" (impersonation) scam messages with high accuracy. The detection unit can also detect fraudulent links and messages in real time using AI. For example, the AI ​​analyzes the content of an email the moment it is received and immediately determines whether it contains fraudulent elements. This allows for warnings to be issued before users fall for fraudulent messages. Additionally, the detection unit can use multilingual natural language processing models to handle different languages ​​and cultures. This enables effective detection of fraudulent messages even for a global user base.

[0031] The warning unit alerts the user to anomalies detected by the detection unit. For example, if the user receives an email containing a fraudulent link, the AI ​​will detect the link and display a warning to the user. Specifically, the warning unit warns the user through pop-up notifications and audio alerts. For example, a warning message may appear on the screen the moment the user opens an email, urging them not to click on fraudulent links. Audio alerts can also be used to attract the user's attention audibly, in addition to visually. Furthermore, the warning unit can also use AI to warn the user. For example, the warning unit may display a warning to the user based on anomalies detected by the AI. The AI ​​analyzes the user's behavior patterns and past data to provide warnings at the optimal timing and in the optimal way to maximize the effectiveness of warnings in specific situations. For example, if a user has a habit of checking emails at a specific time, displaying a warning at that time makes it easier to attract the user's attention. The warning unit can also collect user feedback and continuously improve the accuracy and effectiveness of warnings. For example, if a user ignores a warning, the reason can be analyzed and the method of the next warning can be adjusted. This allows the warning unit to provide effective warnings to users, preventing fraud from occurring.

[0032] The analysis unit processes the content of voice calls using natural language processing. For example, with the user's permission, the analysis unit processes the call content using natural language processing to detect fraudulent patterns and phrases. Specifically, the analysis unit converts the call content into text in real time, and the AI ​​analyzes that text. The AI ​​uses speech recognition technology to transcribe the call content and then analyzes that text using natural language processing technology. For example, to detect fraudulent call content such as "ore-ore" (impersonation) scams, it identifies specific keywords and phrases. Furthermore, the AI ​​can identify elements that further increase the likelihood of fraud by analyzing the tone of the call and the speaker's emotions. For example, if there is a tone emphasizing urgency or if phrases demanding money appear frequently, it will be judged as having a high probability of fraud. The analysis unit can also use AI to analyze the call content. For example, the analysis unit uses AI to analyze the call content and identify fraudulent patterns and phrases. The AI ​​learns from past fraudulent call data and continuously learns to respond to new fraudulent methods. As a result, the analysis unit can analyze the call content in real time and detect signs of fraud early. Furthermore, the analytics unit can analyze users' call history and past data to identify specific patterns and trends, thereby predicting future fraud risks. This allows the analytics unit to provide users with more effective fraud prevention measures.

[0033] The recording unit records call content when the analysis unit detects fraudulent elements. For example, the recording unit can record conversations in real time from the beginning, even during a call, and warn the user. Specifically, the recording unit can use AI to record call content. For instance, the AI ​​can record call content in real time and warn the user. The AI ​​transcribes the call content into text and saves it to a database. This allows the user to review the call content later and use it as evidence of fraud. The recording unit can also save call content as an audio file, allowing the user to replay and review the details of the call. Furthermore, the recording unit can record not only the call content but also call metadata (e.g., date and time of the call, information about the other party, etc.). This makes it easier to understand the overall picture of the call. The recording unit can also encrypt and securely store recorded data to protect user privacy. This allows the recording unit to secure important data for fraud prevention while protecting user privacy. Furthermore, the recording unit can support early detection and rapid response to fraud by linking the recorded data with the analysis unit and notification unit.

[0034] The notification unit notifies trusted third parties when fraudulent activity is detected. For example, if the notification unit detects fraudulent phone calls, it can notify family members or professionals of the content to encourage prompt action. Specifically, the notification unit can also use AI to notify trusted third parties when fraudulent activity is detected. For example, the notification unit's AI can detect fraudulent activity and notify family members or professionals of the content. If the AI ​​determines that there is a high probability of fraud, it will automatically send a notification to pre-registered contacts. Notifications are made using multiple means, such as email, SMS, and phone calls, ensuring that information is reliably transmitted. The notification unit can also provide detailed information in its notifications, including specific details of the fraud and countermeasures. For example, it can send notifications that include a summary of fraudulent phone calls, information on fraudulent methods, and appropriate response methods. Furthermore, the notification unit can also provide emergency contact information and support contact details so that the third party who receives the notification can respond quickly. In this way, the notification unit can protect users from fraud by detecting fraudulent activity early and encouraging prompt action. Furthermore, by recording notification history and making it available for later review, the notification unit can provide data to evaluate the effectiveness of fraud prevention measures and to make improvements. This allows the notification unit to play a crucial role in enabling users, their families, and professionals to work together to combat fraud.

[0035] The advisory department consults with AI when a user receives a suspicious message or link, and advises on the next course of action. For example, if a user receives a suspicious email, the advisory department can have the AI ​​analyze the email to determine if it is potentially fraudulent and advise on appropriate countermeasures. For example, the advisory department can have AI analyze suspicious messages or links and advise the user on the next course of action. The advisory department can also use AI to advise users on the next course of action when they receive a suspicious message or link. For example, the advisory department can have AI provide real-time advice to users regarding their questions. This allows users to consult with AI and receive appropriate advice when they receive a suspicious message or link.

[0036] The data collection unit collects data to detect fraudulent links and messages. For example, the unit collects data such as past fraud cases and user communication history, and the AI ​​analyzes this data to improve the accuracy of detecting fraudulent links and messages. For instance, the AI ​​in the data collection unit references a database of past fraud cases and extracts similar fraud patterns. The data collection unit can also use AI to collect data for detecting fraudulent links and messages. For example, the AI ​​in the data collection unit analyzes user communication history and identifies fraudulent patterns. This allows for the collection of data to detect fraudulent links and messages and improves detection accuracy.

[0037] The warning system alerts users through pop-up notifications and audio alerts. For example, if a user receives an email containing a fraudulent link, the system will display a warning via a pop-up notification. For example, the system may use notifications displayed in the center of the screen or banner-style notifications to warn users. The system can also alert users with audio alerts. For example, the system may warn users with warning sounds or voice messages. This allows the system to raise awareness of fraudulent activities by providing users with both visual and auditory warnings.

[0038] The notification unit will notify family members or professionals if it detects fraudulent activity. For example, if the notification unit detects fraudulent phone call content, it can notify family members or professionals of the content to encourage a swift response. For example, the notification unit's AI can detect fraudulent activity and notify family members or professionals of the content. The notification unit can also use AI to notify trusted third parties if fraudulent activity is detected. For example, the notification unit's AI can detect fraudulent activity and notify family members or professionals of the content. This allows for a swift response by notifying not only the user but also trusted third parties when fraudulent activity is detected.

[0039] The analysis unit analyzes the content of voice calls and detects fraudulent patterns and phrases. For example, with the user's permission, the analysis unit can perform natural language processing on the call content to detect fraudulent patterns and phrases. For example, the analysis unit can detect fraudulent call content such as "ore-ore" (impersonation) scams. The analysis unit can also use AI to analyze the call content. For example, the analysis unit can use AI to analyze the call content and identify fraudulent patterns and phrases. This allows the system to detect fraudulent patterns and phrases by analyzing the content of voice calls and warn the user.

[0040] The detection unit optimizes its detection algorithm by referring to a database of past fraud cases during detection. For example, the detection unit extracts similar fraud patterns from the database of past fraud cases and reflects them in the detection algorithm. For example, the detection unit uses AI to analyze the database of past fraud cases and optimize the detection algorithm. The detection unit can also update the database and optimize the detection algorithm in real time when a new fraud case occurs. For example, the detection unit uses AI to analyze a new fraud case and update the database. Furthermore, the detection unit can periodically analyze the database of past fraud cases to improve the accuracy of the detection algorithm. For example, the detection unit uses AI to periodically analyze the database of past fraud cases and optimize the detection algorithm. This allows the accuracy of the detection algorithm to be improved by referring to the database of past fraud cases.

[0041] The detection unit analyzes the user's communication history at the time of detection and identifies fraudulent patterns. For example, the detection unit analyzes the user's past communication history to identify fraudulent patterns. For example, the detection unit uses AI to analyze the user's communication history and identify fraudulent patterns. The detection unit can also detect fraudulent messages from the user's communication history based on specific senders or content. For example, the detection unit uses AI to analyze the user's communication history and identify fraudulent messages based on specific senders or content. Furthermore, the detection unit can monitor the user's communication history in real time and identify new fraudulent patterns. For example, the detection unit uses AI to analyze the user's communication history in real time and identify new fraudulent patterns. This allows for the identification of fraudulent patterns by analyzing the user's communication history, thereby improving detection accuracy.

[0042] The detection unit prioritizes the detection of fraudulent links and messages by considering the user's geographical location information during detection. For example, if the user is in a specific region, the detection unit prioritizes the detection of fraud patterns that frequently occur in that region. For example, the detection unit uses AI to analyze the user's geographical location information and identify fraud patterns that frequently occur in that region. The detection unit can also detect region-specific fraudulent links and messages based on the user's current location. For example, the detection unit uses AI to analyze the user's current location and identify region-specific fraud patterns. Furthermore, if the user is traveling, the detection unit can optimize its detection algorithm by considering fraud patterns in the travel destination. For example, the detection unit uses AI to analyze the user's travel destination and identify fraud patterns. This allows for the priority detection of region-specific fraud patterns by considering the user's geographical location information.

[0043] The detection unit analyzes the user's social media activity during detection and detects relevant fraudulent links and messages. For example, the detection unit analyzes the user's social media activity and identifies fraudulent links and messages. For example, the detection unit uses AI to analyze the user's social media activity and identify fraudulent links and messages. The detection unit can also prioritize the detection of messages from accounts and groups that the user follows. For example, the detection unit uses AI to analyze accounts and groups that the user follows and identify fraudulent messages. Furthermore, the detection unit can monitor the user's social media activity in real time and identify new fraudulent patterns. For example, the detection unit uses AI to analyze the user's social media activity in real time and identify new fraudulent patterns. This allows the detection of relevant fraudulent links and messages by analyzing the user's social media activity.

[0044] The warning unit displays different warning messages depending on the type of fraud when a warning is issued. For example, in the case of a phishing scam, the warning unit displays a message warning the user not to click on the link. For example, the warning unit's AI detects phishing links and displays a warning message to the user. The warning unit can also display a message warning the user to end the call in the case of a "It's Me" scam. For example, the warning unit's AI detects the content of a "It's Me" scam call and displays a warning message to the user. Furthermore, if a new fraud method is discovered, the warning unit can also display a warning message corresponding to that method. For example, the warning unit's AI detects new fraud methods and displays a warning message to the user. This allows for effective alerting of users by displaying warning messages tailored to the type of fraud.

[0045] The warning system prioritizes warnings by referencing the user's past warning history. For example, it may redisplay warnings that the user has previously ignored, giving them higher priority. For instance, the AI ​​analyzes the user's past warning history and redisplays ignored warnings. The warning system can also prioritize similar warnings by referencing warnings the user has previously addressed. For example, the AI ​​analyzes the user's past warning history and prioritizes displaying addressed warnings. Furthermore, the warning system can analyze the user's past warning history and prioritize displaying the most important warnings. For example, the AI ​​analyzes the user's past warning history and prioritizes displaying important warnings. This allows the system to prioritize important warnings by referencing the user's past warning history.

[0046] The warning unit selects the optimal warning method when an alert is issued, taking into account the user's device information. For example, if the user is using a smartphone, the warning unit displays a pop-up notification. For example, the warning unit uses AI to analyze the user's device information and display a pop-up notification. The warning unit can also display a warning optimized for a larger screen if the user is using a tablet. For example, the warning unit uses AI to analyze the user's device information and display a warning optimized for a larger screen. Furthermore, if the user is using a smartwatch, the warning unit can display a warning via vibration or audio alert. For example, the warning unit uses AI to analyze the user's device information and display a warning via vibration or audio alert. In this way, the system can provide the optimal warning method by taking into account the user's device information.

[0047] The warning unit analyzes the user's communication history when a warning is issued and displays relevant warnings. For example, the warning unit analyzes the user's past communication history and displays relevant warnings. For example, the warning unit uses AI to analyze the user's communication history and displays relevant warnings. The warning unit can also display warnings related to a specific sender if the user receives a message from that sender. For example, the warning unit uses AI to analyze the user's communication history and displays warnings related to a specific sender. Furthermore, the warning unit can monitor the user's communication history in real time and display warnings based on new fraudulent patterns. For example, the warning unit uses AI to analyze the user's communication history in real time and display warnings based on new fraudulent patterns. This allows the system to analyze the user's communication history, display relevant warnings, and provide alerts.

[0048] The analysis unit optimizes the analysis algorithm by referring to past call data during analysis. For example, the analysis unit extracts similar fraud patterns from past call data and reflects them in the analysis algorithm. For example, the analysis unit uses AI to analyze past call data and optimize the analysis algorithm. The analysis unit can also update the database and optimize the analysis algorithm in real time when new fraud cases occur. For example, the analysis unit uses AI to analyze new fraud cases and update the database. Furthermore, the analysis unit can periodically analyze past call data to improve the accuracy of the analysis algorithm. For example, the analysis unit uses AI to periodically analyze past call data and optimize the analysis algorithm. This allows the accuracy of the analysis algorithm to be improved by referring to past call data.

[0049] The analysis unit identifies fraudulent patterns by considering the context of the call content during analysis. For example, the analysis unit analyzes the context of the call content and identifies fraudulent patterns. For example, the analysis unit uses AI to analyze the context of the call content and identify fraudulent patterns. The analysis unit can also detect fraudulent patterns based on specific phrases or keywords during the call. For example, the analysis unit uses AI to analyze the call content and identify fraudulent patterns based on specific phrases or keywords. Furthermore, the analysis unit can analyze the context of the call content in real time and identify new fraudulent patterns. For example, the analysis unit uses AI to analyze the call content in real time and identify new fraudulent patterns. This allows for more accurate identification of fraudulent patterns by considering the context of the call content.

[0050] The analysis unit prioritizes analyzing fraudulent call content by considering the user's geographical location during analysis. For example, if the user is in a specific region, the analysis unit prioritizes analyzing fraud patterns that frequently occur in that region. For instance, the analysis unit uses AI to analyze the user's geographical location and identify fraud patterns that frequently occur in that region. The analysis unit can also analyze region-specific fraudulent call content based on the user's current location. For example, the analysis unit uses AI to analyze the user's current location and identify region-specific fraud patterns. Furthermore, if the user is traveling, the analysis unit can optimize its analysis algorithm by considering fraud patterns in the travel destination. For example, the analysis unit uses AI to analyze the user's travel destination and identify fraud patterns. This allows for the prioritization of region-specific fraud patterns by considering the user's geographical location.

[0051] The analysis unit analyzes the user's social media activity and identifies related fraudulent call content during the analysis process. For example, the analysis unit analyzes the user's social media activity and identifies fraudulent call content. For example, the analysis unit uses AI to analyze the user's social media activity and identify fraudulent call content. The analysis unit can also prioritize the analysis of call content from accounts and groups that the user follows. For example, the analysis unit uses AI to analyze accounts and groups that the user follows and identify fraudulent call content. Furthermore, the analysis unit can monitor the user's social media activity in real time and identify new fraudulent patterns. For example, the analysis unit uses AI to analyze the user's social media activity in real time and identify new fraudulent patterns. This allows for the analysis of related fraudulent call content by analyzing the user's social media activity.

[0052] The recording unit adjusts the level of detail in the recording based on the importance of the call content. For example, if the call content is important, the recording unit will record it in detail. For example, the recording unit's AI will analyze the importance of the call content and record it in detail. The recording unit can also record a simplified version of the call content if it is a normal call. For example, the recording unit's AI will analyze the importance of the call content and record it in a simplified version. Furthermore, if the call contains fraudulent elements, the recording unit can record it in detail so that it can be analyzed later. For example, the recording unit's AI will analyze the importance of the call content and record it in detail. This allows the recording unit to appropriately record necessary information by adjusting the level of detail in the recording according to the importance of the call content.

[0053] The recording unit applies different recording algorithms depending on the call category during recording. For example, in the case of business calls, the recording unit creates detailed minutes. For example, the recording unit uses AI to analyze the call category and apply a recording algorithm suitable for business calls. The recording unit can also perform simplified recordings in the case of private calls. For example, the recording unit uses AI to analyze the call category and apply a recording algorithm suitable for private calls. Furthermore, in the case of fraudulent calls, the recording unit can perform detailed recordings for later analysis. For example, the recording unit uses AI to analyze the call category and apply a recording algorithm suitable for fraudulent calls. This improves the accuracy of recordings by applying the optimal recording algorithm according to the call category.

[0054] The recording unit selects the optimal recording method when recording, taking into account the user's geographical location information. For example, if the user is in a specific region, the recording unit optimizes the recording method for that region. For instance, the recording unit uses AI to analyze the user's geographical location information and optimize the recording method for that region. The recording unit can also select a region-specific recording method based on the user's current location. For example, the recording unit uses AI to analyze the user's current location and select a region-specific recording method. Furthermore, if the user is traveling, the recording unit can select the optimal recording method considering the recording methods of the travel destination. For example, the recording unit uses AI to analyze the user's travel destination and select the optimal recording method. In this way, by taking the user's geographical location information into consideration, the optimal recording method can be provided.

[0055] The recording unit analyzes the user's social media activity and records relevant call content at the time of recording. For example, the recording unit uses AI to analyze the user's social media activity and record relevant call content. The recording unit can also prioritize recording call content from accounts and groups that the user follows. For example, the recording unit uses AI to analyze accounts and groups that the user follows and record relevant call content. Furthermore, the recording unit can monitor the user's social media activity in real time and record call content based on new fraudulent patterns. For example, the recording unit uses AI to analyze the user's social media activity in real time and record call content based on new fraudulent patterns. This allows for the appropriate recording of relevant call content by analyzing the user's social media activity.

[0056] The notification unit displays different notification messages depending on the type of fraud. For example, in the case of a phishing scam, the notification unit displays a message advising the user not to click on the link. For example, the notification unit's AI detects a phishing scam link and displays a notification message to the user. The notification unit can also display a message advising the user to end the call in the case of a "It's Me" scam. For example, the notification unit's AI detects the content of a "It's Me" scam call and displays a notification message to the user. Furthermore, if a new fraud method is discovered, the notification unit can display a notification message corresponding to that method. For example, the notification unit's AI detects a new fraud method and displays a notification message to the user. This allows for effective alerting of users by displaying notification messages tailored to the type of fraud.

[0057] The notification system prioritizes notifications by referencing the user's past notification history. For example, it may redisplay notifications that the user has previously ignored, giving them higher priority. For instance, the AI ​​analyzes the user's past notification history and redisplays ignored notifications. The notification system can also prioritize similar notifications by referencing notifications the user has previously responded to. For example, the AI ​​analyzes the user's past notification history and prioritizes displayed notifications that were responded to. Furthermore, the notification system can analyze the user's past notification history and prioritize displaying the most important notifications. For example, the AI ​​analyzes the user's past notification history and prioritizes displayed important notifications. This allows the system to prioritize important notifications by referencing the user's past notification history.

[0058] The notification unit selects the optimal notification method by considering the user's device information when a notification is sent. For example, if the user is using a smartphone, the notification unit will display a pop-up notification. For example, the notification unit's AI will analyze the user's device information and display a pop-up notification. The notification unit can also display notifications optimized for the larger screen if the user is using a tablet. For example, the notification unit's AI will analyze the user's device information and display a notification optimized for the larger screen. Furthermore, if the user is using a smartwatch, the notification unit can display notifications via vibration or audio alerts. For example, the notification unit's AI will analyze the user's device information and display notifications via vibration or audio alerts. In this way, the system can provide the optimal notification method by considering the user's device information.

[0059] The notification unit analyzes the user's communication history and displays relevant notifications when a notification is sent. For example, the notification unit analyzes the user's past communication history and displays relevant notifications. For example, the notification unit uses AI to analyze the user's communication history and displays relevant notifications. The notification unit can also display notifications related to a specific sender if the user receives a message from that sender. For example, the notification unit uses AI to analyze the user's communication history and displays notifications related to that specific sender. Furthermore, the notification unit can monitor the user's communication history in real time and display notifications based on new fraudulent patterns. For example, the notification unit uses AI to analyze the user's communication history in real time and display notifications based on new fraudulent patterns. This allows the system to display relevant notifications and provide warnings by analyzing the user's communication history.

[0060] The advisory unit displays different advice messages depending on the type of fraud. For example, in the case of a phishing scam, the advisory unit displays a message advising the user not to click on the link. For example, the advisory unit's AI detects phishing links and displays an advice message to the user. The advisory unit can also display a message advising the user to end the call in the case of a "It's Me" scam. For example, the advisory unit's AI detects the content of a "It's Me" scam call and displays an advice message to the user. Furthermore, if a new fraud method is discovered, the advisory unit can also display an advice message corresponding to that method. For example, the advisory unit's AI detects a new fraud method and displays an advice message to the user. This allows for effective warning of users by displaying advice messages tailored to the type of fraud.

[0061] The advisory unit, when providing advice, determines the priority of advice by referring to the user's past advice history. For example, the advisory unit may redisplay advice that the user has previously ignored and give it a higher priority. For example, the advisory unit's AI analyzes the user's past advice history and redisplays ignored advice. The advisory unit can also refer to advice the user has responded to in the past and prioritize displaying similar advice. For example, the advisory unit's AI analyzes the user's past advice history and prioritizes displaying the advice that was responded to. Furthermore, the advisory unit can analyze the user's past advice history and prioritize displaying the most important advice. For example, the advisory unit's AI analyzes the user's past advice history and prioritizes displaying important advice. In this way, by referring to the user's past advice history, important advice can be prioritized.

[0062] The advisory unit selects the optimal advice method by considering the user's device information when providing advice. For example, if the user is using a smartphone, the advisory unit displays advice via a pop-up notification. For example, the advisory unit uses AI to analyze the user's device information and display a pop-up notification. The advisory unit can also display advice optimized for a larger screen if the user is using a tablet. For example, the advisory unit uses AI to analyze the user's device information and display advice optimized for a larger screen. Furthermore, if the user is using a smartwatch, the advisory unit can display advice via vibration or audio alerts. For example, the advisory unit uses AI to analyze the user's device information and display advice via vibration or audio alerts. In this way, the system can provide the optimal advice method by considering the user's device information.

[0063] The advisory unit analyzes the user's communication history and displays relevant advice when providing advice. For example, the advisory unit analyzes the user's past communication history and displays relevant advice. For example, the advisory unit uses AI to analyze the user's communication history and displays relevant advice. The advisory unit can also display advice related to a specific sender if the user receives a message from that sender. For example, the advisory unit uses AI to analyze the user's communication history and displays advice related to that specific sender. Furthermore, the advisory unit can monitor the user's communication history in real time and display advice based on new fraudulent patterns. For example, the advisory unit uses AI to analyze the user's communication history in real time and display advice based on new fraudulent patterns. This allows the advisory unit to analyze the user's communication history, display relevant advice, and prompt appropriate action.

[0064] The data collection unit optimizes its collection algorithm by referring to a database of past fraud cases during the collection process. For example, the data collection unit extracts similar fraud patterns from the database of past fraud cases and incorporates them into the collection algorithm. For example, the data collection unit uses AI to analyze the database of past fraud cases and optimize the collection algorithm. The data collection unit can also update the database and optimize the collection algorithm in real time when new fraud cases occur. For example, the data collection unit uses AI to analyze new fraud cases and update the database. Furthermore, the data collection unit can periodically analyze the database of past fraud cases to improve the accuracy of the collection algorithm. For example, the data collection unit uses AI to periodically analyze the database of past fraud cases and optimize the collection algorithm. This allows the accuracy of the collection algorithm to be improved by referring to the database of past fraud cases.

[0065] The data collection unit analyzes the user's communication history and collects relevant data during collection. For example, the data collection unit analyzes the user's past communication history and collects relevant data. For example, the data collection unit uses AI to analyze the user's communication history and collect relevant data. The data collection unit can also collect data related to a specific sender if the user receives a message from that sender. For example, the data collection unit uses AI to analyze the user's communication history and collect data related to a specific sender. Furthermore, the data collection unit can monitor the user's communication history in real time and collect data based on new fraudulent patterns. For example, the data collection unit uses AI to analyze the user's communication history in real time and collect data based on new fraudulent patterns. This allows for the collection of relevant data and improved detection accuracy by analyzing the user's communication history.

[0066] The data collection unit analyzes the user's social media activity and collects relevant data during the collection process. For example, the data collection unit uses AI to analyze the user's social media activity and collect relevant data. The data collection unit can also prioritize collecting data from accounts and groups that the user follows. For example, the data collection unit uses AI to analyze accounts and groups that the user follows and collect relevant data. Furthermore, the data collection unit can monitor the user's social media activity in real time and collect data based on emerging fraudulent patterns. For example, the data collection unit uses AI to analyze the user's social media activity in real time and collect data based on emerging fraudulent patterns. This allows for the collection of relevant data and improved detection accuracy by analyzing the user's social media activity.

[0067] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0068] The fraud detection system may also include a behavioral analysis unit that analyzes the user's behavioral history. For example, the behavioral analysis unit analyzes what links the user has clicked on in the past and what messages they have responded to, improving the accuracy of detecting fraudulent links and messages. For instance, the behavioral analysis unit analyzes patterns in the websites and applications the user frequently accesses to detect abnormal behavior. It can also analyze how a user behaves during specific time periods to identify fraudulent behavior. Furthermore, if the user is using a specific device, the behavioral analysis unit can analyze the usage patterns of that device to detect fraudulent behavior. This allows for more accurate detection of fraudulent links and messages by analyzing the user's behavioral history.

[0069] The fraud detection system may also include a geographic analysis unit that prioritizes the detection of fraudulent links and messages by considering the user's geographic location. For example, if the user is in a specific region, the geographic analysis unit will prioritize the detection of fraud patterns that frequently occur in that region. For instance, the geographic analysis unit's AI will analyze the user's geographic location and identify fraud patterns that frequently occur in that region. The geographic analysis unit can also detect region-specific fraudulent links and messages based on the user's current location. For example, the geographic analysis unit's AI will analyze the user's current location and identify region-specific fraud patterns. Furthermore, if the user is traveling, the geographic analysis unit can optimize its detection algorithm by considering fraud patterns in the travel destination. For example, the geographic analysis unit's AI will analyze the user's travel destination and identify fraud patterns. This allows for the priority detection of region-specific fraud patterns by considering the user's geographic location.

[0070] The fraud detection system may also include a social media analysis unit that analyzes the user's social media activity and detects relevant fraudulent links and messages. For example, the social media analysis unit might use AI to analyze the user's social media activity and identify fraudulent links and messages. The social media analysis unit can also prioritize the detection of messages from accounts and groups the user follows. For example, the social media analysis unit might use AI to analyze the accounts and groups the user follows and identify fraudulent messages. Furthermore, the social media analysis unit can monitor the user's social media activity in real time and identify new fraudulent patterns. For example, the social media analysis unit might use AI to analyze the user's social media activity in real time and identify new fraudulent patterns. This allows for the detection of relevant fraudulent links and messages by analyzing the user's social media activity.

[0071] The fraud detection system may further include a communication history analysis unit that analyzes the user's communication history and detects relevant fraudulent links and messages. The communication history analysis unit, for example, analyzes the user's past communication history and identifies fraudulent patterns. For example, the communication history analysis unit uses AI to analyze the user's communication history and identify fraudulent patterns. The communication history analysis unit can also detect fraudulent messages from the user's communication history based on specific senders or content. For example, the communication history analysis unit uses AI to analyze the user's communication history and identify fraudulent messages based on specific senders or content. Furthermore, the communication history analysis unit can monitor the user's communication history in real time and identify new fraudulent patterns. For example, the communication history analysis unit uses AI to analyze the user's communication history in real time and identify new fraudulent patterns. This allows for the identification of fraudulent patterns and improved detection accuracy by analyzing the user's communication history.

[0072] The fraud detection system may further include a warning history analysis unit that determines the priority of warnings by referring to the user's past warning history. For example, the warning history analysis unit may redisplay warnings that the user has previously ignored, giving them higher priority. For instance, the AI ​​in the warning history analysis unit analyzes the user's past warning history and redisplays ignored warnings. The warning history analysis unit can also prioritize the display of similar warnings by referring to warnings the user has previously responded to. For example, the AI ​​in the warning history analysis unit analyzes the user's past warning history and prioritizes the display of corresponding warnings. Furthermore, the warning history analysis unit can analyze the user's past warning history and prioritize the display of the most important warnings. For example, the AI ​​in the warning history analysis unit analyzes the user's past warning history and prioritizes the display of important warnings. This allows for the prioritization of important warnings by referring to the user's past warning history.

[0073] The fraud detection system may also include a geographic recording unit that selects the optimal recording method by considering the user's geographic location information. For example, if the user is in a specific region, the geographic recording unit optimizes the recording method for that region. For instance, the AI ​​in the geographic recording unit analyzes the user's geographic location information and optimizes the recording method for that region. The geographic recording unit can also select a region-specific recording method based on the user's current location. For example, the AI ​​in the geographic recording unit analyzes the user's current location and selects a region-specific recording method. Furthermore, if the user is traveling, the geographic recording unit can select the optimal recording method by considering the recording methods of the travel destination. For example, the AI ​​in the geographic recording unit analyzes the user's travel destination and selects the optimal recording method. This allows the system to provide the optimal recording method by considering the user's geographic location information.

[0074] The following briefly describes the processing flow for example form 1.

[0075] Step 1: The detection unit detects fraudulent links and messages. For example, the AI ​​analyzes fraudulent links and messages sent from channels such as email, SMS, and social media, and identifies fraudulent patterns and phrases. The detection unit can detect phishing scam links and impersonation scam messages. It can also use AI to detect fraudulent links and messages in real time. Step 2: The warning unit alerts the user to any anomalies detected by the detection unit. For example, if the user receives an email containing a fraudulent link, the AI ​​will detect the link and display a warning to the user. The warning unit can alert the user via pop-up notifications or audio alerts. Step 3: The analysis unit processes the voice call content using natural language processing. For example, with the user's permission, it processes the call content using natural language processing to detect fraudulent patterns and phrases. The analysis unit can detect fraudulent call content, such as those used in "ore-ore" (impersonation) scams. It can also analyze the call content using AI. Step 4: The recording unit records the call content if the analysis unit detects fraudulent elements. For example, it can record the conversation in real time from the beginning, even during a call, and warn the user. The recording unit can also use AI to record the call content. Step 5: The notification unit notifies a trusted third party if fraudulent activity is detected. For example, if fraudulent phone call content is detected, it can notify family members or professionals to encourage prompt action. The notification unit can also notify a trusted third party if fraudulent activity is detected using AI.

[0076] (Example of form 2) The fraud detection system according to an embodiment of the present invention is a system that detects phishing scams and impersonation scams and warns the user. This fraud detection system uses AI to detect fraudulent links and messages sent from channels such as email, SMS, and SNS. It warns the user as soon as an anomaly is detected. It also processes voice calls using natural language processing with the user's permission to detect fraudulent patterns and phrases. If fraudulent elements are detected, the system records the conversation in real time from the beginning, even if it is still a call, and warns the user. Furthermore, if fraudulent activity is detected, it notifies not only the user but also a pre-designated trusted third party (e.g., family member or professional). This is especially important for elderly people, as it allows close relatives to respond quickly. The application also supports the user at any time; if the user receives a suspicious message or link, they can consult with the AI ​​on the spot and receive advice on the next course of action. As a result, the fraud detection system reduces the risk of the user becoming a victim of fraud and enables a quick and appropriate response. For example, when detecting fraudulent links or messages, the AI ​​analyzes a large amount of data to identify fraudulent patterns and phrases. This reduces the user's risk of becoming a victim of fraud. Next, the system warns the user as soon as an anomaly is detected. For example, if an email containing a fraudulent link is received, the AI ​​will detect the link and display a warning to the user. This allows the user to take preventative measures before falling victim to fraud. Furthermore, with the user's permission, the system also processes voice calls using natural language to detect fraudulent patterns and phrases. For example, it can detect fraudulent call content such as "ore-ore" (impersonation) scams. If fraudulent elements are detected, the system records the conversation in real time from the beginning, even if it is still a call, and warns the user. This helps users become more vigilant against fraud. In addition, if fraudulent activity is detected, the system notifies not only the user but also a pre-designated trusted third party (e.g., family member or professional). This is especially important for elderly people, as it allows close relatives to respond quickly. For example, if fraudulent call content is detected, the content can be notified to family members or professionals to encourage a swift response.Finally, the application supports users at all times; if a user receives a suspicious message or link, they can consult the AI ​​immediately and receive advice on what to do next. For example, if a user receives a suspicious email, the AI ​​can analyze the email to determine if it is potentially fraudulent and advise on appropriate countermeasures. This allows users to use the internet with peace of mind.

[0077] The fraud detection system according to the embodiment comprises a detection unit, a warning unit, an analysis unit, a recording unit, and a notification unit. The detection unit detects fraudulent links and messages. The detection unit uses AI to analyze fraudulent links and messages sent from channels such as email, SMS, and SNS, and identifies fraudulent patterns and phrases. For example, the detection unit can detect phishing links and "ore-ore" (impersonation) fraud messages. The detection unit can also use AI to detect fraudulent links and messages in real time. For example, the detection unit uses AI to analyze a large amount of data and identify fraudulent patterns and phrases. The warning unit warns the user of any anomalies detected by the detection unit. For example, if the user receives an email containing a fraudulent link, the AI ​​detects the link and displays a warning to the user. For example, the warning unit warns the user with a pop-up notification or an audio alert. The warning unit can also use AI to warn the user. For example, the warning unit displays a warning to the user based on anomalies detected by the AI. The analysis unit performs natural language processing on the content of voice calls. The analysis unit, for example, processes call content using natural language processing with the user's permission to detect fraudulent patterns and phrases. For example, the analysis unit can detect fraudulent call content such as "ore-ore" (impersonation) scams. The analysis unit can also analyze call content using AI. For example, the analysis unit can use AI to analyze call content and identify fraudulent patterns and phrases. The recording unit records call content when the analysis unit detects fraudulent elements. The recording unit can, for example, record conversations in real time from the beginning, even during a call, and issue warnings to the user. For example, the recording unit can use AI to record call content. For example, the recording unit can use AI to record call content in real time and issue warnings to the user. The notification unit notifies a trusted third party when fraudulent activity is detected. For example, if fraudulent call content is detected, the notification unit can notify family members or professionals to encourage prompt action. For example, the notification unit can use AI to notify a trusted third party when fraudulent activity is detected. For example, the notification unit can use AI to detect fraudulent activity and notify family members or professionals.As a result, the fraud detection system according to the embodiment can protect users from fraudulent activities by detecting fraudulent links and messages, warning users, analyzing and recording call content, and notifying trusted third parties.

[0078] The detection unit detects fraudulent links and messages. For example, the detection unit uses AI to analyze fraudulent links and messages sent through channels such as email, SMS, and social media, identifying fraudulent patterns and phrases. Specifically, the AI ​​uses natural language processing technology to analyze the message content and detect words and phrases with fraudulent characteristics. For example, messages containing keywords such as "urgent," "confirm," and "password," or links with specific URL patterns, are highly likely to be fraudulent. Furthermore, the AI ​​continuously learns by referencing a database of past fraudulent messages to adapt to new fraudulent methods. This allows the detection unit to detect phishing links and "ore-ore" (impersonation) scam messages with high accuracy. The detection unit can also detect fraudulent links and messages in real time using AI. For example, the AI ​​analyzes the content of an email the moment it is received and immediately determines whether it contains fraudulent elements. This allows for warnings to be issued before users fall for fraudulent messages. Additionally, the detection unit can use multilingual natural language processing models to handle different languages ​​and cultures. This enables effective detection of fraudulent messages even for a global user base.

[0079] The warning unit alerts the user to anomalies detected by the detection unit. For example, if the user receives an email containing a fraudulent link, the AI ​​will detect the link and display a warning to the user. Specifically, the warning unit warns the user through pop-up notifications and audio alerts. For example, a warning message may appear on the screen the moment the user opens an email, urging them not to click on fraudulent links. Audio alerts can also be used to attract the user's attention audibly, in addition to visually. Furthermore, the warning unit can also use AI to warn the user. For example, the warning unit may display a warning to the user based on anomalies detected by the AI. The AI ​​analyzes the user's behavior patterns and past data to provide warnings at the optimal timing and in the optimal way to maximize the effectiveness of warnings in specific situations. For example, if a user has a habit of checking emails at a specific time, displaying a warning at that time makes it easier to attract the user's attention. The warning unit can also collect user feedback and continuously improve the accuracy and effectiveness of warnings. For example, if a user ignores a warning, the reason can be analyzed and the method of the next warning can be adjusted. This allows the warning unit to provide effective warnings to users, preventing fraud from occurring.

[0080] The analysis unit processes the content of voice calls using natural language processing. For example, with the user's permission, the analysis unit processes the call content using natural language processing to detect fraudulent patterns and phrases. Specifically, the analysis unit converts the call content into text in real time, and the AI ​​analyzes that text. The AI ​​uses speech recognition technology to transcribe the call content and then analyzes that text using natural language processing technology. For example, to detect fraudulent call content such as "ore-ore" (impersonation) scams, it identifies specific keywords and phrases. Furthermore, the AI ​​can identify elements that further increase the likelihood of fraud by analyzing the tone of the call and the speaker's emotions. For example, if there is a tone emphasizing urgency or if phrases demanding money appear frequently, it will be judged as having a high probability of fraud. The analysis unit can also use AI to analyze the call content. For example, the analysis unit uses AI to analyze the call content and identify fraudulent patterns and phrases. The AI ​​learns from past fraudulent call data and continuously learns to respond to new fraudulent methods. As a result, the analysis unit can analyze the call content in real time and detect signs of fraud early. Furthermore, the analytics unit can analyze users' call history and past data to identify specific patterns and trends, thereby predicting future fraud risks. This allows the analytics unit to provide users with more effective fraud prevention measures.

[0081] The recording unit records call content when the analysis unit detects fraudulent elements. For example, the recording unit can record conversations in real time from the beginning, even during a call, and warn the user. Specifically, the recording unit can use AI to record call content. For instance, the AI ​​can record call content in real time and warn the user. The AI ​​transcribes the call content into text and saves it to a database. This allows the user to review the call content later and use it as evidence of fraud. The recording unit can also save call content as an audio file, allowing the user to replay and review the details of the call. Furthermore, the recording unit can record not only the call content but also call metadata (e.g., date and time of the call, information about the other party, etc.). This makes it easier to understand the overall picture of the call. The recording unit can also encrypt and securely store recorded data to protect user privacy. This allows the recording unit to secure important data for fraud prevention while protecting user privacy. Furthermore, the recording unit can support early detection and rapid response to fraud by linking the recorded data with the analysis unit and notification unit.

[0082] The notification unit notifies trusted third parties when fraudulent activity is detected. For example, if the notification unit detects fraudulent phone calls, it can notify family members or professionals of the content to encourage prompt action. Specifically, the notification unit can also use AI to notify trusted third parties when fraudulent activity is detected. For example, the notification unit's AI can detect fraudulent activity and notify family members or professionals of the content. If the AI ​​determines that there is a high probability of fraud, it will automatically send a notification to pre-registered contacts. Notifications are made using multiple means, such as email, SMS, and phone calls, ensuring that information is reliably transmitted. The notification unit can also provide detailed information in its notifications, including specific details of the fraud and countermeasures. For example, it can send notifications that include a summary of fraudulent phone calls, information on fraudulent methods, and appropriate response methods. Furthermore, the notification unit can also provide emergency contact information and support contact details so that the third party who receives the notification can respond quickly. In this way, the notification unit can protect users from fraud by detecting fraudulent activity early and encouraging prompt action. Furthermore, by recording notification history and making it available for later review, the notification unit can provide data to evaluate the effectiveness of fraud prevention measures and to make improvements. This allows the notification unit to play a crucial role in enabling users, their families, and professionals to work together to combat fraud.

[0083] The advisory department consults with AI when a user receives a suspicious message or link, and advises on the next course of action. For example, if a user receives a suspicious email, the advisory department can have the AI ​​analyze the email to determine if it is potentially fraudulent and advise on appropriate countermeasures. For example, the advisory department can have AI analyze suspicious messages or links and advise the user on the next course of action. The advisory department can also use AI to advise users on the next course of action when they receive a suspicious message or link. For example, the advisory department can have AI provide real-time advice to users regarding their questions. This allows users to consult with AI and receive appropriate advice when they receive a suspicious message or link.

[0084] The data collection unit collects data to detect fraudulent links and messages. For example, the unit collects data such as past fraud cases and user communication history, and the AI ​​analyzes this data to improve the accuracy of detecting fraudulent links and messages. For instance, the AI ​​in the data collection unit references a database of past fraud cases and extracts similar fraud patterns. The data collection unit can also use AI to collect data for detecting fraudulent links and messages. For example, the AI ​​in the data collection unit analyzes user communication history and identifies fraudulent patterns. This allows for the collection of data to detect fraudulent links and messages and improves detection accuracy.

[0085] The warning system alerts users through pop-up notifications and audio alerts. For example, if a user receives an email containing a fraudulent link, the system will display a warning via a pop-up notification. For example, the system may use notifications displayed in the center of the screen or banner-style notifications to warn users. The system can also alert users with audio alerts. For example, the system may warn users with warning sounds or voice messages. This allows the system to raise awareness of fraudulent activities by providing users with both visual and auditory warnings.

[0086] The notification unit will notify family members or professionals if it detects fraudulent activity. For example, if the notification unit detects fraudulent phone call content, it can notify family members or professionals of the content to encourage a swift response. For example, the notification unit's AI can detect fraudulent activity and notify family members or professionals of the content. The notification unit can also use AI to notify trusted third parties if fraudulent activity is detected. For example, the notification unit's AI can detect fraudulent activity and notify family members or professionals of the content. This allows for a swift response by notifying not only the user but also trusted third parties when fraudulent activity is detected.

[0087] The analysis unit analyzes the content of voice calls and detects fraudulent patterns and phrases. For example, with the user's permission, the analysis unit can perform natural language processing on the call content to detect fraudulent patterns and phrases. For example, the analysis unit can detect fraudulent call content such as "ore-ore" (impersonation) scams. The analysis unit can also use AI to analyze the call content. For example, the analysis unit can use AI to analyze the call content and identify fraudulent patterns and phrases. This allows the system to detect fraudulent patterns and phrases by analyzing the content of voice calls and warn the user.

[0088] The detection unit estimates the user's emotions and adjusts the detection accuracy of fraudulent links and messages based on the estimated emotions. For example, if the user is feeling anxious, the detection unit increases its detection accuracy to more strictly detect fraudulent links and messages. For example, the detection unit uses AI to analyze the user's emotions and adjust the detection accuracy. The detection unit can also return the detection accuracy to normal when the user is relaxed, avoiding excessive warnings. For example, the detection unit uses AI to analyze the user's emotions and adjust the detection accuracy. Furthermore, if the user is in a hurry, the detection unit can optimize the detection algorithm to provide results quickly. For example, the detection unit uses AI to analyze the user's emotions and optimize the detection algorithm. This allows for more appropriate detection results by adjusting the detection accuracy according to the user's emotions.

[0089] The detection unit optimizes its detection algorithm by referring to a database of past fraud cases during detection. For example, the detection unit extracts similar fraud patterns from the database of past fraud cases and reflects them in the detection algorithm. For example, the detection unit uses AI to analyze the database of past fraud cases and optimize the detection algorithm. The detection unit can also update the database and optimize the detection algorithm in real time when a new fraud case occurs. For example, the detection unit uses AI to analyze a new fraud case and update the database. Furthermore, the detection unit can periodically analyze the database of past fraud cases to improve the accuracy of the detection algorithm. For example, the detection unit uses AI to periodically analyze the database of past fraud cases and optimize the detection algorithm. This allows the accuracy of the detection algorithm to be improved by referring to the database of past fraud cases.

[0090] The detection unit analyzes the user's communication history at the time of detection and identifies fraudulent patterns. For example, the detection unit analyzes the user's past communication history to identify fraudulent patterns. For example, the detection unit uses AI to analyze the user's communication history and identify fraudulent patterns. The detection unit can also detect fraudulent messages from the user's communication history based on specific senders or content. For example, the detection unit uses AI to analyze the user's communication history and identify fraudulent messages based on specific senders or content. Furthermore, the detection unit can monitor the user's communication history in real time and identify new fraudulent patterns. For example, the detection unit uses AI to analyze the user's communication history in real time and identify new fraudulent patterns. This allows for the identification of fraudulent patterns by analyzing the user's communication history, thereby improving detection accuracy.

[0091] The detection unit estimates the user's emotions and adjusts the display method of the detection results based on the estimated emotions. For example, if the user is tense, the detection unit provides a simple and highly visible display method. For example, the detection unit uses AI to analyze the user's emotions and provides a simple display method. The detection unit can also provide a display method that includes detailed information if the user is relaxed. For example, the detection unit uses AI to analyze the user's emotions and provides a detailed display method. Furthermore, if the user is in a hurry, the detection unit can provide a display method that gets straight to the point. For example, the detection unit uses AI to analyze the user's emotions and provides a display method that gets straight to the point. By adjusting the display method of the detection results according to the user's emotions, it becomes possible to provide more appropriate information.

[0092] The detection unit prioritizes the detection of fraudulent links and messages by considering the user's geographical location information during detection. For example, if the user is in a specific region, the detection unit prioritizes the detection of fraud patterns that frequently occur in that region. For example, the detection unit uses AI to analyze the user's geographical location information and identify fraud patterns that frequently occur in that region. The detection unit can also detect region-specific fraudulent links and messages based on the user's current location. For example, the detection unit uses AI to analyze the user's current location and identify region-specific fraud patterns. Furthermore, if the user is traveling, the detection unit can optimize its detection algorithm by considering fraud patterns in the travel destination. For example, the detection unit uses AI to analyze the user's travel destination and identify fraud patterns. This allows for the priority detection of region-specific fraud patterns by considering the user's geographical location information.

[0093] The detection unit analyzes the user's social media activity during detection and detects relevant fraudulent links and messages. For example, the detection unit analyzes the user's social media activity and identifies fraudulent links and messages. For example, the detection unit uses AI to analyze the user's social media activity and identify fraudulent links and messages. The detection unit can also prioritize the detection of messages from accounts and groups that the user follows. For example, the detection unit uses AI to analyze accounts and groups that the user follows and identify fraudulent messages. Furthermore, the detection unit can monitor the user's social media activity in real time and identify new fraudulent patterns. For example, the detection unit uses AI to analyze the user's social media activity in real time and identify new fraudulent patterns. This allows the detection of relevant fraudulent links and messages by analyzing the user's social media activity.

[0094] The warning unit estimates the user's emotions and adjusts the way the warning is expressed based on those emotions. For example, if the user is tense, the warning unit will display a warning in a calm tone. For example, the warning unit's AI will analyze the user's emotions and display a warning in a calm tone. The warning unit can also provide detailed warning information if the user is relaxed. For example, the warning unit's AI will analyze the user's emotions and provide detailed warning information. Furthermore, if the user is in a hurry, the warning unit can display a concise and quick warning. For example, the AI ​​will analyze the user's emotions and display a concise and quick warning. This allows for the provision of more appropriate warnings by adjusting the way the warning is expressed according to the user's emotions.

[0095] The warning unit displays different warning messages depending on the type of fraud when a warning is issued. For example, in the case of a phishing scam, the warning unit displays a message warning the user not to click on the link. For example, the warning unit's AI detects phishing links and displays a warning message to the user. The warning unit can also display a message warning the user to end the call in the case of a "It's Me" scam. For example, the warning unit's AI detects the content of a "It's Me" scam call and displays a warning message to the user. Furthermore, if a new fraud method is discovered, the warning unit can also display a warning message corresponding to that method. For example, the warning unit's AI detects new fraud methods and displays a warning message to the user. This allows for effective alerting of users by displaying warning messages tailored to the type of fraud.

[0096] The warning system prioritizes warnings by referencing the user's past warning history. For example, it may redisplay warnings that the user has previously ignored, giving them higher priority. For instance, the AI ​​analyzes the user's past warning history and redisplays ignored warnings. The warning system can also prioritize similar warnings by referencing warnings the user has previously addressed. For example, the AI ​​analyzes the user's past warning history and prioritizes displaying addressed warnings. Furthermore, the warning system can analyze the user's past warning history and prioritize displaying the most important warnings. For example, the AI ​​analyzes the user's past warning history and prioritizes displaying important warnings. This allows the system to prioritize important warnings by referencing the user's past warning history.

[0097] The warning unit estimates the user's emotions and adjusts the timing of warnings based on those emotions. For example, if the user is stressed, the warning unit will display a warning immediately. For example, the warning unit's AI will analyze the user's emotions and display a warning immediately. The warning unit can also display a warning at an appropriate time if the user is relaxed. For example, the warning unit's AI will analyze the user's emotions and display a warning at an appropriate time. Furthermore, the warning unit can display a warning quickly if the user is in a hurry. For example, the warning unit's AI will analyze the user's emotions and display a warning quickly. This allows for more timely warnings by adjusting the timing according to the user's emotions.

[0098] The warning unit selects the optimal warning method when an alert is issued, taking into account the user's device information. For example, if the user is using a smartphone, the warning unit displays a pop-up notification. For example, the warning unit uses AI to analyze the user's device information and display a pop-up notification. The warning unit can also display a warning optimized for a larger screen if the user is using a tablet. For example, the warning unit uses AI to analyze the user's device information and display a warning optimized for a larger screen. Furthermore, if the user is using a smartwatch, the warning unit can display a warning via vibration or audio alert. For example, the warning unit uses AI to analyze the user's device information and display a warning via vibration or audio alert. In this way, the system can provide the optimal warning method by taking into account the user's device information.

[0099] The warning unit analyzes the user's communication history when a warning is issued and displays relevant warnings. For example, the warning unit analyzes the user's past communication history and displays relevant warnings. For example, the warning unit uses AI to analyze the user's communication history and displays relevant warnings. The warning unit can also display warnings related to a specific sender if the user receives a message from that sender. For example, the warning unit uses AI to analyze the user's communication history and displays warnings related to a specific sender. Furthermore, the warning unit can monitor the user's communication history in real time and display warnings based on new fraudulent patterns. For example, the warning unit uses AI to analyze the user's communication history in real time and display warnings based on new fraudulent patterns. This allows the system to analyze the user's communication history, display relevant warnings, and provide alerts.

[0100] The analysis unit estimates the user's emotions and adjusts the accuracy of the analysis based on the estimated emotions. For example, if the user is feeling anxious, the analysis unit increases the accuracy of the analysis to more rigorously detect fraudulent patterns. For example, the analysis unit uses AI to analyze the user's emotions and adjusts the accuracy of the analysis. The analysis unit can also return the accuracy of the analysis to normal when the user is relaxed, avoiding excessive warnings. For example, the analysis unit uses AI to analyze the user's emotions and adjusts the accuracy of the analysis. Furthermore, if the user is in a hurry, the analysis unit can optimize the analysis algorithm to provide results quickly. For example, the analysis unit uses AI to analyze the user's emotions and optimize the analysis algorithm. This allows for more appropriate analysis results by adjusting the accuracy of the analysis according to the user's emotions.

[0101] The analysis unit optimizes the analysis algorithm by referring to past call data during analysis. For example, the analysis unit extracts similar fraud patterns from past call data and reflects them in the analysis algorithm. For example, the analysis unit uses AI to analyze past call data and optimize the analysis algorithm. The analysis unit can also update the database and optimize the analysis algorithm in real time when new fraud cases occur. For example, the analysis unit uses AI to analyze new fraud cases and update the database. Furthermore, the analysis unit can periodically analyze past call data to improve the accuracy of the analysis algorithm. For example, the analysis unit uses AI to periodically analyze past call data and optimize the analysis algorithm. This allows the accuracy of the analysis algorithm to be improved by referring to past call data.

[0102] The analysis unit identifies fraudulent patterns by considering the context of the call content during analysis. For example, the analysis unit analyzes the context of the call content and identifies fraudulent patterns. For example, the analysis unit uses AI to analyze the context of the call content and identify fraudulent patterns. The analysis unit can also detect fraudulent patterns based on specific phrases or keywords during the call. For example, the analysis unit uses AI to analyze the call content and identify fraudulent patterns based on specific phrases or keywords. Furthermore, the analysis unit can analyze the context of the call content in real time and identify new fraudulent patterns. For example, the analysis unit uses AI to analyze the call content in real time and identify new fraudulent patterns. This allows for more accurate identification of fraudulent patterns by considering the context of the call content.

[0103] The analysis unit estimates the user's emotions and adjusts the display method of the analysis results based on the estimated emotions. For example, if the user is tense, the analysis unit provides a simple and highly visible display method. For example, the analysis unit uses AI to analyze the user's emotions and provides a simple display method. The analysis unit can also provide a display method that includes detailed information if the user is relaxed. For example, the analysis unit uses AI to analyze the user's emotions and provides a detailed display method. Furthermore, if the user is in a hurry, the analysis unit can provide a display method that gets straight to the point. For example, the analysis unit uses AI to analyze the user's emotions and provides a display method that gets straight to the point. By adjusting the display method of the analysis results according to the user's emotions, it becomes possible to provide more appropriate information.

[0104] The analysis unit prioritizes analyzing fraudulent call content by considering the user's geographical location during analysis. For example, if the user is in a specific region, the analysis unit prioritizes analyzing fraud patterns that frequently occur in that region. For instance, the analysis unit uses AI to analyze the user's geographical location and identify fraud patterns that frequently occur in that region. The analysis unit can also analyze region-specific fraudulent call content based on the user's current location. For example, the analysis unit uses AI to analyze the user's current location and identify region-specific fraud patterns. Furthermore, if the user is traveling, the analysis unit can optimize its analysis algorithm by considering fraud patterns in the travel destination. For example, the analysis unit uses AI to analyze the user's travel destination and identify fraud patterns. This allows for the prioritization of region-specific fraud patterns by considering the user's geographical location.

[0105] The analysis unit analyzes the user's social media activity and identifies related fraudulent call content during the analysis process. For example, the analysis unit analyzes the user's social media activity and identifies fraudulent call content. For example, the analysis unit uses AI to analyze the user's social media activity and identify fraudulent call content. The analysis unit can also prioritize the analysis of call content from accounts and groups that the user follows. For example, the analysis unit uses AI to analyze accounts and groups that the user follows and identify fraudulent call content. Furthermore, the analysis unit can monitor the user's social media activity in real time and identify new fraudulent patterns. For example, the analysis unit uses AI to analyze the user's social media activity in real time and identify new fraudulent patterns. This allows for the analysis of related fraudulent call content by analyzing the user's social media activity.

[0106] The recording unit estimates the user's emotions and adjusts the recording start time based on the estimated emotions. For example, if the user is feeling anxious, the recording unit will start recording immediately. For example, the recording unit's AI will analyze the user's emotions and start recording immediately. The recording unit can also start recording at an appropriate time if the user is relaxed. For example, the recording unit's AI will analyze the user's emotions and start recording at an appropriate time. Furthermore, if the user is in a hurry, the recording unit can start recording quickly. For example, the recording unit's AI will analyze the user's emotions and start recording quickly. By adjusting the recording start time according to the user's emotions, more appropriate recording becomes possible.

[0107] The recording unit adjusts the level of detail in the recording based on the importance of the call content. For example, if the call content is important, the recording unit will record it in detail. For example, the recording unit's AI will analyze the importance of the call content and record it in detail. The recording unit can also record a simplified version of the call content if it is a normal call. For example, the recording unit's AI will analyze the importance of the call content and record it in a simplified version. Furthermore, if the call contains fraudulent elements, the recording unit can record it in detail so that it can be analyzed later. For example, the recording unit's AI will analyze the importance of the call content and record it in detail. This allows the recording unit to appropriately record necessary information by adjusting the level of detail in the recording according to the importance of the call content.

[0108] The recording unit applies different recording algorithms depending on the call category during recording. For example, in the case of business calls, the recording unit creates detailed minutes. For example, the recording unit uses AI to analyze the call category and apply a recording algorithm suitable for business calls. The recording unit can also perform simplified recordings in the case of private calls. For example, the recording unit uses AI to analyze the call category and apply a recording algorithm suitable for private calls. Furthermore, in the case of fraudulent calls, the recording unit can perform detailed recordings for later analysis. For example, the recording unit uses AI to analyze the call category and apply a recording algorithm suitable for fraudulent calls. This improves the accuracy of recordings by applying the optimal recording algorithm according to the call category.

[0109] The recording unit estimates the user's emotions and determines recording priorities based on those estimates. For example, if the user is feeling anxious, the recording unit will prioritize recording. For instance, the AI ​​analyzes the user's emotions and prioritizes recording. The recording unit can also record with normal priority if the user is relaxed. For instance, the AI ​​analyzes the user's emotions and prioritizes recording. Furthermore, if the user is in a hurry, the recording unit can record quickly. For instance, the AI ​​analyzes the user's emotions and records quickly. This allows for prioritizing important call content by determining recording priorities according to the user's emotions.

[0110] The recording unit selects the optimal recording method when recording, taking into account the user's geographical location information. For example, if the user is in a specific region, the recording unit optimizes the recording method for that region. For instance, the recording unit uses AI to analyze the user's geographical location information and optimize the recording method for that region. The recording unit can also select a region-specific recording method based on the user's current location. For example, the recording unit uses AI to analyze the user's current location and select a region-specific recording method. Furthermore, if the user is traveling, the recording unit can select the optimal recording method considering the recording methods of the travel destination. For example, the recording unit uses AI to analyze the user's travel destination and select the optimal recording method. In this way, by taking the user's geographical location information into consideration, the optimal recording method can be provided.

[0111] The recording unit analyzes the user's social media activity and records relevant call content at the time of recording. For example, the recording unit uses AI to analyze the user's social media activity and record relevant call content. The recording unit can also prioritize recording call content from accounts and groups that the user follows. For example, the recording unit uses AI to analyze accounts and groups that the user follows and record relevant call content. Furthermore, the recording unit can monitor the user's social media activity in real time and record call content based on new fraudulent patterns. For example, the recording unit uses AI to analyze the user's social media activity in real time and record call content based on new fraudulent patterns. This allows for the appropriate recording of relevant call content by analyzing the user's social media activity.

[0112] The notification unit estimates the user's emotions and adjusts the way notifications are presented based on those emotions. For example, if the user is stressed, the notification unit will display notifications in a calm tone. For example, the notification unit's AI will analyze the user's emotions and display notifications in a calm tone. The notification unit can also provide detailed notification information if the user is relaxed. For example, the notification unit's AI will analyze the user's emotions and provide detailed notification information. Furthermore, if the user is in a hurry, the notification unit can display concise and quick notifications. For example, the notification unit's AI will analyze the user's emotions and display concise and quick notifications. This allows for the provision of more appropriate notifications by adjusting the way notifications are presented according to the user's emotions.

[0113] The notification unit displays different notification messages depending on the type of fraud. For example, in the case of a phishing scam, the notification unit displays a message advising the user not to click on the link. For example, the notification unit's AI detects a phishing scam link and displays a notification message to the user. The notification unit can also display a message advising the user to end the call in the case of a "It's Me" scam. For example, the notification unit's AI detects the content of a "It's Me" scam call and displays a notification message to the user. Furthermore, if a new fraud method is discovered, the notification unit can display a notification message corresponding to that method. For example, the notification unit's AI detects a new fraud method and displays a notification message to the user. This allows for effective alerting of users by displaying notification messages tailored to the type of fraud.

[0114] The notification system prioritizes notifications by referencing the user's past notification history. For example, it may redisplay notifications that the user has previously ignored, giving them higher priority. For instance, the AI ​​analyzes the user's past notification history and redisplays ignored notifications. The notification system can also prioritize similar notifications by referencing notifications the user has previously responded to. For example, the AI ​​analyzes the user's past notification history and prioritizes displayed notifications that were responded to. Furthermore, the notification system can analyze the user's past notification history and prioritize displaying the most important notifications. For example, the AI ​​analyzes the user's past notification history and prioritizes displayed important notifications. This allows the system to prioritize important notifications by referencing the user's past notification history.

[0115] The notification unit estimates the user's emotions and adjusts the timing of notifications based on those emotions. For example, if the user is stressed, the notification unit will display a notification immediately. For example, the notification unit's AI will analyze the user's emotions and display a notification immediately. The notification unit can also display a notification at an appropriate time if the user is relaxed. For example, the notification unit's AI will analyze the user's emotions and display a notification at an appropriate time. Furthermore, the notification unit can display a notification quickly if the user is in a hurry. For example, the notification unit's AI will analyze the user's emotions and display a notification quickly. By adjusting the timing of notifications according to the user's emotions, notifications can be provided at a more appropriate time.

[0116] The notification unit selects the optimal notification method by considering the user's device information when a notification is sent. For example, if the user is using a smartphone, the notification unit will display a pop-up notification. For example, the notification unit's AI will analyze the user's device information and display a pop-up notification. The notification unit can also display notifications optimized for the larger screen if the user is using a tablet. For example, the notification unit's AI will analyze the user's device information and display a notification optimized for the larger screen. Furthermore, if the user is using a smartwatch, the notification unit can display notifications via vibration or audio alerts. For example, the notification unit's AI will analyze the user's device information and display notifications via vibration or audio alerts. In this way, the system can provide the optimal notification method by considering the user's device information.

[0117] The notification unit analyzes the user's communication history and displays relevant notifications when a notification is sent. For example, the notification unit analyzes the user's past communication history and displays relevant notifications. For example, the notification unit uses AI to analyze the user's communication history and displays relevant notifications. The notification unit can also display notifications related to a specific sender if the user receives a message from that sender. For example, the notification unit uses AI to analyze the user's communication history and displays notifications related to that specific sender. Furthermore, the notification unit can monitor the user's communication history in real time and display notifications based on new fraudulent patterns. For example, the notification unit uses AI to analyze the user's communication history in real time and display notifications based on new fraudulent patterns. This allows the system to display relevant notifications and provide warnings by analyzing the user's communication history.

[0118] The advisory unit estimates the user's emotions and adjusts the way it expresses advice based on those emotions. For example, if the user is tense, the advisory unit will provide advice in a calm tone. For example, the AI ​​will analyze the user's emotions and provide advice in a calm tone. The advisory unit can also provide detailed advice if the user is relaxed. For example, the AI ​​will analyze the user's emotions and provide detailed advice. Furthermore, if the user is in a hurry, the advisory unit can provide concise and quick advice. For example, the AI ​​will analyze the user's emotions and provide concise and quick advice. This allows the system to provide more appropriate advice by adjusting the way it expresses advice according to the user's emotions.

[0119] The advisory unit displays different advice messages depending on the type of fraud. For example, in the case of a phishing scam, the advisory unit displays a message advising the user not to click on the link. For example, the advisory unit's AI detects phishing links and displays an advice message to the user. The advisory unit can also display a message advising the user to end the call in the case of a "It's Me" scam. For example, the advisory unit's AI detects the content of a "It's Me" scam call and displays an advice message to the user. Furthermore, if a new fraud method is discovered, the advisory unit can also display an advice message corresponding to that method. For example, the advisory unit's AI detects a new fraud method and displays an advice message to the user. This allows for effective warning of users by displaying advice messages tailored to the type of fraud.

[0120] The advisory unit, when providing advice, determines the priority of advice by referring to the user's past advice history. For example, the advisory unit may redisplay advice that the user has previously ignored and give it a higher priority. For example, the advisory unit's AI analyzes the user's past advice history and redisplays ignored advice. The advisory unit can also refer to advice the user has responded to in the past and prioritize displaying similar advice. For example, the advisory unit's AI analyzes the user's past advice history and prioritizes displaying the advice that was responded to. Furthermore, the advisory unit can analyze the user's past advice history and prioritize displaying the most important advice. For example, the advisory unit's AI analyzes the user's past advice history and prioritizes displaying important advice. In this way, by referring to the user's past advice history, important advice can be prioritized.

[0121] The advisory unit estimates the user's emotions and adjusts the timing of advice based on the estimated emotions. For example, if the user is feeling anxious, the advisory unit can provide advice immediately. For example, the advisory unit's AI analyzes the user's emotions and provides advice immediately. The advisory unit can also provide advice at an appropriate time if the user is relaxed. For example, the advisory unit's AI analyzes the user's emotions and provides advice at an appropriate time. Furthermore, if the user is in a hurry, the advisory unit can provide advice quickly. For example, the advisory unit's AI analyzes the user's emotions and provides advice quickly. By adjusting the timing of advice according to the user's emotions, it is possible to provide advice at a more appropriate time.

[0122] The advisory unit selects the optimal advice method by considering the user's device information when providing advice. For example, if the user is using a smartphone, the advisory unit displays advice via a pop-up notification. For example, the advisory unit uses AI to analyze the user's device information and display a pop-up notification. The advisory unit can also display advice optimized for a larger screen if the user is using a tablet. For example, the advisory unit uses AI to analyze the user's device information and display advice optimized for a larger screen. Furthermore, if the user is using a smartwatch, the advisory unit can display advice via vibration or audio alerts. For example, the advisory unit uses AI to analyze the user's device information and display advice via vibration or audio alerts. In this way, the system can provide the optimal advice method by considering the user's device information.

[0123] The advisory unit analyzes the user's communication history and displays relevant advice when providing advice. For example, the advisory unit analyzes the user's past communication history and displays relevant advice. For example, the advisory unit uses AI to analyze the user's communication history and displays relevant advice. The advisory unit can also display advice related to a specific sender if the user receives a message from that sender. For example, the advisory unit uses AI to analyze the user's communication history and displays advice related to that specific sender. Furthermore, the advisory unit can monitor the user's communication history in real time and display advice based on new fraudulent patterns. For example, the advisory unit uses AI to analyze the user's communication history in real time and display advice based on new fraudulent patterns. This allows the advisory unit to analyze the user's communication history, display relevant advice, and prompt appropriate action.

[0124] The data collection unit estimates the user's emotions and selects data to collect based on those estimated emotions. For example, if the user is feeling anxious, the data collection unit will prioritize collecting fraudulent data. For example, the data collection unit's AI will analyze the user's emotions and prioritize collecting fraudulent data. The data collection unit can also perform normal data collection if the user is relaxed. For example, the data collection unit's AI will analyze the user's emotions and perform normal data collection. Furthermore, if the user is in a hurry, the data collection unit can collect data quickly. For example, the data collection unit's AI will analyze the user's emotions and collect data quickly. This allows for more appropriate data collection by selecting data according to the user's emotions.

[0125] The data collection unit optimizes its collection algorithm by referring to a database of past fraud cases during the collection process. For example, the data collection unit extracts similar fraud patterns from the database of past fraud cases and incorporates them into the collection algorithm. For example, the data collection unit uses AI to analyze the database of past fraud cases and optimize the collection algorithm. The data collection unit can also update the database and optimize the collection algorithm in real time when new fraud cases occur. For example, the data collection unit uses AI to analyze new fraud cases and update the database. Furthermore, the data collection unit can periodically analyze the database of past fraud cases to improve the accuracy of the collection algorithm. For example, the data collection unit uses AI to periodically analyze the database of past fraud cases and optimize the collection algorithm. This allows the accuracy of the collection algorithm to be improved by referring to the database of past fraud cases.

[0126] The data collection unit estimates the user's emotions and adjusts the collection frequency based on the estimated emotions. For example, if the user is feeling anxious, the collection unit increases the collection frequency to quickly collect fraudulent data. For example, the collection unit uses AI to analyze the user's emotions and increase the collection frequency. The collection unit can also collect data at a normal frequency if the user is relaxed. For example, the collection unit uses AI to analyze the user's emotions and collect data at a normal frequency. Furthermore, if the user is in a hurry, the collection unit can optimize the collection frequency to quickly collect data. For example, the collection unit uses AI to analyze the user's emotions and optimize the collection frequency. This allows for more appropriate data collection by adjusting the collection frequency according to the user's emotions.

[0127] The data collection unit analyzes the user's communication history and collects relevant data during collection. For example, the data collection unit analyzes the user's past communication history and collects relevant data. For example, the data collection unit uses AI to analyze the user's communication history and collect relevant data. The data collection unit can also collect data related to a specific sender if the user receives a message from that sender. For example, the data collection unit uses AI to analyze the user's communication history and collect data related to a specific sender. Furthermore, the data collection unit can monitor the user's communication history in real time and collect data based on new fraudulent patterns. For example, the data collection unit uses AI to analyze the user's communication history in real time and collect data based on new fraudulent patterns. This allows for the collection of relevant data and improved detection accuracy by analyzing the user's communication history.

[0128] The data collection unit analyzes the user's social media activity and collects relevant data during the collection process. For example, the data collection unit uses AI to analyze the user's social media activity and collect relevant data. The data collection unit can also prioritize collecting data from accounts and groups that the user follows. For example, the data collection unit uses AI to analyze accounts and groups that the user follows and collect relevant data. Furthermore, the data collection unit can monitor the user's social media activity in real time and collect data based on emerging fraudulent patterns. For example, the data collection unit uses AI to analyze the user's social media activity in real time and collect data based on emerging fraudulent patterns. This allows for the collection of relevant data and improved detection accuracy by analyzing the user's social media activity.

[0129] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0130] The fraud detection system may also include a behavioral analysis unit that analyzes the user's behavioral history. For example, the behavioral analysis unit analyzes what links the user has clicked on in the past and what messages they have responded to, improving the accuracy of detecting fraudulent links and messages. For instance, the behavioral analysis unit analyzes patterns in the websites and applications the user frequently accesses to detect abnormal behavior. It can also analyze how a user behaves during specific time periods to identify fraudulent behavior. Furthermore, if the user is using a specific device, the behavioral analysis unit can analyze the usage patterns of that device to detect fraudulent behavior. This allows for more accurate detection of fraudulent links and messages by analyzing the user's behavioral history.

[0131] The fraud detection system may also include a warning adjustment unit that estimates the user's emotions and adjusts the content of the warning based on those emotions. For example, if the user is feeling anxious, the warning adjustment unit may provide more detailed warning information. For instance, the AI ​​in the warning adjustment unit might analyze the user's emotions and display a detailed warning message. The warning adjustment unit can also provide a concise warning message if the user is relaxed. For example, the AI ​​in the warning adjustment unit might analyze the user's emotions and display a concise warning message. Furthermore, the warning adjustment unit can display a warning quickly if the user is in a hurry. For example, the AI ​​in the warning adjustment unit might analyze the user's emotions and display a warning quickly. This allows for the provision of more appropriate warnings by adjusting the content of the warning according to the user's emotions.

[0132] The fraud detection system may also include a geographic analysis unit that prioritizes the detection of fraudulent links and messages by considering the user's geographic location. For example, if the user is in a specific region, the geographic analysis unit will prioritize the detection of fraud patterns that frequently occur in that region. For instance, the geographic analysis unit's AI will analyze the user's geographic location and identify fraud patterns that frequently occur in that region. The geographic analysis unit can also detect region-specific fraudulent links and messages based on the user's current location. For example, the geographic analysis unit's AI will analyze the user's current location and identify region-specific fraud patterns. Furthermore, if the user is traveling, the geographic analysis unit can optimize its detection algorithm by considering fraud patterns in the travel destination. For example, the geographic analysis unit's AI will analyze the user's travel destination and identify fraud patterns. This allows for the priority detection of region-specific fraud patterns by considering the user's geographic location.

[0133] The fraud detection system may also include a social media analysis unit that analyzes the user's social media activity and detects relevant fraudulent links and messages. For example, the social media analysis unit might use AI to analyze the user's social media activity and identify fraudulent links and messages. The social media analysis unit can also prioritize the detection of messages from accounts and groups the user follows. For example, the social media analysis unit might use AI to analyze the accounts and groups the user follows and identify fraudulent messages. Furthermore, the social media analysis unit can monitor the user's social media activity in real time and identify new fraudulent patterns. For example, the social media analysis unit might use AI to analyze the user's social media activity in real time and identify new fraudulent patterns. This allows for the detection of relevant fraudulent links and messages by analyzing the user's social media activity.

[0134] The fraud detection system may further include a notification adjustment unit that estimates the user's emotions and adjusts the way notifications are presented based on those emotions. For example, if the user is feeling stressed, the notification adjustment unit might display notifications in a calm tone. For example, the AI ​​might analyze the user's emotions and display notifications in a calm tone. The notification adjustment unit can also provide detailed notification information if the user is relaxed. For example, the AI ​​might analyze the user's emotions and provide detailed notification information. Furthermore, the notification adjustment unit can display concise and quick notifications if the user is in a hurry. For example, the AI ​​might analyze the user's emotions and display concise and quick notifications. This allows for the provision of more appropriate notifications by adjusting the way notifications are presented according to the user's emotions.

[0135] The fraud detection system may further include a communication history analysis unit that analyzes the user's communication history and detects relevant fraudulent links and messages. The communication history analysis unit, for example, analyzes the user's past communication history and identifies fraudulent patterns. For example, the communication history analysis unit uses AI to analyze the user's communication history and identify fraudulent patterns. The communication history analysis unit can also detect fraudulent messages from the user's communication history based on specific senders or content. For example, the communication history analysis unit uses AI to analyze the user's communication history and identify fraudulent messages based on specific senders or content. Furthermore, the communication history analysis unit can monitor the user's communication history in real time and identify new fraudulent patterns. For example, the communication history analysis unit uses AI to analyze the user's communication history in real time and identify new fraudulent patterns. This allows for the identification of fraudulent patterns and improved detection accuracy by analyzing the user's communication history.

[0136] The fraud detection system may also include an analysis adjustment unit that estimates the user's emotions and adjusts the accuracy of the analysis based on those emotions. For example, if the user is feeling anxious, the analysis adjustment unit can increase the accuracy of the analysis to more precisely detect fraudulent patterns. For instance, the AI ​​in the analysis adjustment unit analyzes the user's emotions and adjusts the accuracy. The analysis adjustment unit can also return the accuracy to normal when the user is relaxed, avoiding excessive warnings. For example, the AI ​​in the analysis adjustment unit analyzes the user's emotions and adjusts the accuracy. Furthermore, if the user is in a hurry, the analysis adjustment unit can optimize the analysis algorithm to provide results quickly. For example, the AI ​​in the analysis adjustment unit analyzes the user's emotions and optimizes the analysis algorithm. This allows for more appropriate analysis results by adjusting the accuracy of the analysis according to the user's emotions.

[0137] The fraud detection system may further include a warning history analysis unit that determines the priority of warnings by referring to the user's past warning history. For example, the warning history analysis unit may redisplay warnings that the user has previously ignored, giving them higher priority. For instance, the AI ​​in the warning history analysis unit analyzes the user's past warning history and redisplays ignored warnings. The warning history analysis unit can also prioritize the display of similar warnings by referring to warnings the user has previously responded to. For example, the AI ​​in the warning history analysis unit analyzes the user's past warning history and prioritizes the display of corresponding warnings. Furthermore, the warning history analysis unit can analyze the user's past warning history and prioritize the display of the most important warnings. For example, the AI ​​in the warning history analysis unit analyzes the user's past warning history and prioritizes the display of important warnings. This allows for the prioritization of important warnings by referring to the user's past warning history.

[0138] The fraud detection system may also include a recording adjustment unit that estimates the user's emotions and adjusts the recording start time based on the estimated emotions. For example, if the user is feeling anxious, the recording adjustment unit may start recording immediately. For example, the recording adjustment unit may use AI to analyze the user's emotions and start recording immediately. The recording adjustment unit may also start recording at an appropriate time if the user is relaxed. For example, the recording adjustment unit may use AI to analyze the user's emotions and start recording at an appropriate time. Furthermore, if the user is in a hurry, the recording adjustment unit may start recording quickly. For example, the recording adjustment unit may use AI to analyze the user's emotions and start recording quickly. This allows for more appropriate recording by adjusting the recording start time according to the user's emotions.

[0139] The fraud detection system may also include a geographic recording unit that selects the optimal recording method by considering the user's geographic location information. For example, if the user is in a specific region, the geographic recording unit optimizes the recording method for that region. For instance, the AI ​​in the geographic recording unit analyzes the user's geographic location information and optimizes the recording method for that region. The geographic recording unit can also select a region-specific recording method based on the user's current location. For example, the AI ​​in the geographic recording unit analyzes the user's current location and selects a region-specific recording method. Furthermore, if the user is traveling, the geographic recording unit can select the optimal recording method by considering the recording methods of the travel destination. For example, the AI ​​in the geographic recording unit analyzes the user's travel destination and selects the optimal recording method. This allows the system to provide the optimal recording method by considering the user's geographic location information.

[0140] The following briefly describes the processing flow for example form 2.

[0141] Step 1: The detection unit detects fraudulent links and messages. For example, the AI ​​analyzes fraudulent links and messages sent from channels such as email, SMS, and social media, and identifies fraudulent patterns and phrases. The detection unit can detect phishing scam links and impersonation scam messages. It can also use AI to detect fraudulent links and messages in real time. Step 2: The warning unit alerts the user to any anomalies detected by the detection unit. For example, if the user receives an email containing a fraudulent link, the AI ​​will detect the link and display a warning to the user. The warning unit can alert the user via pop-up notifications or audio alerts. Step 3: The analysis unit processes the voice call content using natural language processing. For example, with the user's permission, it processes the call content using natural language processing to detect fraudulent patterns and phrases. The analysis unit can detect fraudulent call content, such as those used in "ore-ore" (impersonation) scams. It can also analyze the call content using AI. Step 4: The recording unit records the call content if the analysis unit detects fraudulent elements. For example, it can record the conversation in real time from the beginning, even during a call, and warn the user. The recording unit can also use AI to record the call content. Step 5: The notification unit notifies a trusted third party if fraudulent activity is detected. For example, if fraudulent phone call content is detected, it can notify family members or professionals to encourage prompt action. The notification unit can also notify a trusted third party if fraudulent activity is detected using AI.

[0142] 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.

[0143] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0144] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0145] Each of the multiple elements described above, including the detection unit, warning unit, analysis unit, recording unit, notification unit, advice unit, and collection unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the detection unit is implemented by the computer 36 of the smart device 14, where AI analyzes fraudulent links and messages sent from channels such as email, SMS, and SNS. The warning unit is implemented by the output device 40 of the smart device 14, which displays a warning to the user when an email containing a fraudulent link is received. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12, which performs natural language processing on voice call content to detect fraudulent patterns and phrases. The recording unit is implemented by the storage 32 of the data processing unit 12, which records call content when fraudulent elements are detected. The notification unit is implemented by the communication I / F 26 of the data processing unit 12, which notifies a trusted third party when fraudulent activity is detected. The advice unit is implemented by the control unit 46A of the smart device 14, which consults with the AI ​​when the user receives a suspicious message or link and advises on the next course of action. The data collection unit is implemented by the database 24 of the data processing device 12, which collects data for detecting fraudulent links and messages. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0146] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0147] 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.

[0148] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0149] 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.

[0150] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0151] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0152] 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.

[0153] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0154] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0155] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0156] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0157] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0158] 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.

[0159] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0160] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0161] Each of the multiple elements described above, including the detection unit, warning unit, analysis unit, recording unit, notification unit, advice unit, and collection unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the detection unit is implemented by the computer 36 of the smart glasses 214, where AI analyzes fraudulent links and messages sent from channels such as email, SMS, and SNS. The warning unit is implemented by the speaker 240 of the smart glasses 214, which displays a warning to the user when an email containing a fraudulent link is received. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12, which processes voice call content using natural language processing to detect fraudulent patterns and phrases. The recording unit is implemented by the storage 32 of the data processing unit 12, which records call content when fraudulent elements are detected. The notification unit is implemented by the communication I / F 26 of the data processing unit 12, which notifies a trusted third party when fraudulent activity is detected. The advice unit is implemented by the control unit 46A of the smart glasses 214, which consults with the AI ​​when the user receives a suspicious message or link and advises on the next course of action. The data collection unit is implemented by the database 24 of the data processing device 12, which collects data for detecting fraudulent links and messages. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0162] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0163] 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.

[0164] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0165] 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.

[0166] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0167] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0168] 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.

[0169] 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.

[0170] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0171] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0172] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0173] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0174] 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.

[0175] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0176] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0177] Each of the multiple elements described above, including the detection unit, warning unit, analysis unit, recording unit, notification unit, advice unit, and collection unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the detection unit is implemented by the computer 36 of the headset terminal 314, where AI analyzes fraudulent links and messages sent from channels such as email, SMS, and SNS. The warning unit is implemented by the display 343 of the headset terminal 314, which displays a warning to the user when an email containing a fraudulent link is received. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12, which processes voice call content using natural language processing to detect fraudulent patterns and phrases. The recording unit is implemented by the storage 32 of the data processing unit 12, which records call content when fraudulent elements are detected. The notification unit is implemented by the communication I / F 26 of the data processing unit 12, which notifies a trusted third party when fraudulent activity is detected. The advice unit is implemented by the control unit 46A of the headset terminal 314, which consults with the AI ​​when the user receives a suspicious message or link and advises on the next course of action. The data collection unit is implemented by the database 24 of the data processing device 12, which collects data for detecting fraudulent links and messages. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0178] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0179] 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.

[0180] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0181] 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.

[0182] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0183] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0184] 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.

[0185] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0186] 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.

[0187] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0188] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0189] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0190] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0191] 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.

[0192] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0193] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0194] Each of the multiple elements described above, including the detection unit, warning unit, analysis unit, recording unit, notification unit, advice unit, and collection unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the detection unit is implemented by the computer 36 of the robot 414, where AI analyzes fraudulent links and messages sent from channels such as email, SMS, and SNS. The warning unit is implemented by the speaker 240 of the robot 414, which displays a warning to the user when an email containing a fraudulent link is received. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12, which processes voice call content using natural language processing to detect fraudulent patterns and phrases. The recording unit is implemented by the storage 32 of the data processing unit 12, which records call content when fraudulent elements are detected. The notification unit is implemented by the communication I / F 26 of the data processing unit 12, which notifies a trusted third party when fraudulent activity is detected. The advisory unit is implemented by the control unit 46A of the robot 414, which consults with the AI ​​when the user receives a suspicious message or link and advises on the next course of action. The data collection unit is implemented by the database 24 of the data processing device 12, which collects data for detecting fraudulent links and messages. The correspondence between each unit and the devices and control units is not limited to the example described above and can be modified in various ways.

[0195] 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.

[0196] Figure 9 shows the 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.

[0197] 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.

[0198] 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.

[0199] 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, and motorcycles, 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 based, for example, 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.

[0200] 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."

[0201] 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.

[0202] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0211] 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 other things 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.

[0212] 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.

[0213] (Note 1) A detection unit that detects fraudulent links and messages, A warning unit that warns the user of an abnormality detected by the detection unit, An analysis unit that processes the content of voice calls using natural language processing, A recording unit records the content of a call when the analysis unit detects fraudulent elements, It includes a notification unit that notifies a trusted third party when fraudulent activity is detected. A system characterized by the following features. (Note 2) It includes an advisory section that consults with AI when a user receives a suspicious message or link, and advises on the next course of action. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes a data collection unit that collects data to detect fraudulent links and messages. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned warning unit is The system warns users with pop-up notifications and audio alerts. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned notification unit, If fraudulent activity is detected, family members or professionals will be notified. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, It analyzes voice call content to detect fraudulent patterns and phrases. The system described in Appendix 1, characterized by the features described herein. (Note 7) The detection unit is It estimates the user's sentiment and adjusts the accuracy of detecting fraudulent links and messages based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 8) The detection unit is During detection, the detection algorithm is optimized by referring to a database of past fraud cases. The system described in Appendix 1, characterized by the features described herein. (Note 9) The detection unit is Upon detection, the system analyzes the user's communication history to identify fraudulent patterns. The system described in Appendix 1, characterized by the features described herein. (Note 10) The detection unit is It estimates the user's emotions and adjusts how the detection results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The detection unit is During detection, the system prioritizes the detection of fraudulent links and messages by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The detection unit is During detection, the system analyzes the user's social media activity to identify any related fraudulent links or messages. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned warning unit is The system estimates the user's emotions and adjusts the way warnings are presented based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned warning unit is When a warning is issued, different warning messages will be displayed depending on the type of fraud. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned warning unit is When an alert is issued, the system prioritizes the alert by referring to the user's past alert history. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned warning unit is It estimates the user's emotions and adjusts the timing of warnings based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned warning unit is When issuing a warning, the system selects the most appropriate warning method, taking into account the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned warning unit is When a warning is issued, the system analyzes the user's communication history and displays relevant warnings. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, It estimates the user's emotions and adjusts the accuracy of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned analysis unit, During analysis, the analysis algorithm is optimized by referring to past call data. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned analysis unit, During analysis, fraudulent patterns are identified by considering the context of the call content. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned analysis unit, During analysis, the system prioritizes analyzing fraudulent call content by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned analysis unit, During the analysis, the user's social media activity is analyzed, and related fraudulent call content is examined. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned recording unit is The system estimates the user's emotions and adjusts the recording start time based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned recording unit is During recording, the level of detail in the recording is adjusted based on the importance of the call content. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned recording unit is During recording, different recording algorithms are applied depending on the call category. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned recording unit is The system estimates the user's emotions and prioritizes recordings based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned recording unit is During recording, the optimal recording method is selected considering the user's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned recording unit is During recording, the system analyzes the user's social media activity and records relevant call content. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned notification unit, It estimates the user's emotions and adjusts the way notifications are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned notification unit, When a notification is sent, different notification messages will be displayed depending on the type of fraud. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned notification unit, When sending notifications, the system prioritizes them by referencing the user's past notification history. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned notification unit, It estimates the user's emotions and adjusts the timing of notifications based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned notification unit, When sending notifications, the system selects the most suitable notification method, taking into account the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned notification unit, When a notification is sent, the system analyzes the user's communication history and displays relevant notifications. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned advisory unit, It estimates the user's emotions and adjusts the way advice is presented based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 38) The aforementioned advisory unit, When providing advice, different advice messages will be displayed depending on the type of fraud. The system described in Appendix 2, characterized by the features described herein. (Note 39) The aforementioned advisory unit, When providing advice, the system prioritizes the advice by referring to the user's past advice history. The system described in Appendix 2, characterized by the features described herein. (Note 40) The aforementioned advisory unit, It estimates the user's emotions and adjusts the timing of advice based on those emotions. The system described in Appendix 2, characterized by the features described herein. (Note 41) The aforementioned advisory unit, When providing advice, the optimal advice method is selected considering the user's device information. The system described in Appendix 2, characterized by the features described herein. (Note 42) The aforementioned advisory unit, When providing advice, the system analyzes the user's communication history and displays relevant advice. The system described in Appendix 2, characterized by the features described herein. (Note 43) The aforementioned collection unit is The system estimates the user's emotions and selects the data to collect based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 44) The aforementioned collection unit is During data collection, the collection algorithm is optimized by referring to a database of past fraud cases. The system described in Appendix 3, characterized by the features described herein. (Note 45) The aforementioned collection unit is It estimates the user's sentiment and adjusts the frequency of data collection based on the estimated user sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 46) The aforementioned collection unit is During data collection, the system analyzes the user's communication history and collects relevant data. The system described in Appendix 3, characterized by the features described herein. (Note 47) The aforementioned collection unit is During data collection, the system analyzes the user's social media activity and collects relevant data. The system described in Appendix 3, characterized by the features described herein. [Explanation of Symbols]

[0214] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A detection unit that detects fraudulent links and messages, A warning unit that warns the user of an abnormality detected by the detection unit, An analysis unit that processes the content of voice calls using natural language processing, A recording unit records the content of a call when the analysis unit detects fraudulent elements, It includes a notification unit that notifies a trusted third party when fraudulent activity is detected. A system characterized by the following features.

2. It includes an advisory section that consults with AI when a user receives a suspicious message or link, and advises on the next course of action. The system according to feature 1.

3. It includes a data collection unit that collects data to detect fraudulent links and messages. The system according to feature 1.

4. The aforementioned warning unit is The system warns users with pop-up notifications and audio alerts. The system according to feature 1.

5. The aforementioned notification unit, If fraudulent activity is detected, family members or professionals will be notified. The system according to feature 1.

6. The aforementioned analysis unit, It analyzes voice call content to detect fraudulent patterns and phrases. The system according to feature 1.

7. The detection unit is It estimates the user's sentiment and adjusts the accuracy of detecting fraudulent links and messages based on the estimated user sentiment. The system according to feature 1.

8. The detection unit is During detection, the detection algorithm is optimized by referring to a database of past fraud cases. The system according to feature 1.

Images