System

Abstract

An object of the system according to the embodiment is to detect a sign of fraud from the content of a message or a phone call and warn the user.SOLUTION: A system includes a message analysis unit, a fraud detection unit, and a warning unit. The message analysis unit analyzes the content of the message or the telephone call using the generated AI. The fraud detection unit detects a sign of fraud from the content analyzed by the message analysis unit. The warning unit issues a warning message to the user based on the sign of fraud detected by the fraud detection unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has had the problem of making it difficult to quickly and accurately detect signs of fraud from the content of messages and phone calls.

[0005] The system according to the embodiment aims to detect signs of fraud from the contents of messages and phone calls and warn users. [Means for solving the problem]

[0006] The system according to the embodiment includes a message analysis unit, a fraud detection unit, and a warning unit. The message analysis unit analyzes the content of a message or phone call using a generation AI. The fraud detection unit detects signs of fraud from the content analyzed by the message analysis unit. The warning unit issues a warning message to the user based on the signs of fraud detected by the fraud detection unit. [Effects of the Invention]

[0007] The system according to the embodiment can detect signs of fraud from the content of messages and phone calls and warn the user. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A fraud detection system according to an embodiment of the present invention is a system for detecting refund fraud and protecting users. In this system, a generative AI analyzes the content of messages and phone calls, detects signs of fraud, and issues a warning to the user. This allows the fraud detection system to effectively detect refund fraud and protect users.

[0029] The fraud detection system according to the embodiment includes a message analysis unit, a fraud detection unit, and a warning unit. The message analysis unit analyzes the content of a message or phone call using a generation AI. For example, the generation AI analyzes the content of a message or phone call using a text generation AI (e.g., LLM). The generation AI can also convert the content of a phone call into text using speech recognition technology and analyze the text. The generation AI can also analyze the content of a message or phone call using natural language processing technology. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. Speech recognition technology can convert speech data into text with high accuracy. Natural language processing technology can analyze the meaning of text data and extract important information. The fraud detection unit detects signs of fraud from the content analyzed by the message analysis unit. For example, the fraud detection unit determines signs of fraud by detecting specific keywords or phrases. The fraud detection unit can also analyze the context of a message and sender information to comprehensively determine the likelihood of fraud. The fraud detection unit can also determine signs of fraud by detecting abnormal behavioral patterns. For example, the fraud detection unit determines the possibility of fraud by detecting keywords such as "refund," "bank account," and "personal information." Context analysis determines the possibility of fraud by taking into account the context of the message and sender information. Abnormal behavior pattern detection determines signs of fraud by detecting behavior that is different from normal. The warning unit issues a warning message to the user based on the signs of fraud detected by the fraud detection unit. For example, the warning unit displays a warning message such as "This message may be fraudulent. Do not provide personal information." The warning unit can also issue an audio alert. The warning unit can also display a visual alert. For example, the warning unit displays the warning as a text message. The audio alert issues a voice alert to the user. The visual alert displays a warning icon or message on the screen. As a result, the fraud detection system according to the embodiment can effectively detect refund fraud and protect users.For example, if a user receives a fraudulent message, the AI ​​can immediately issue a warning, reducing the risk of being scammed. It can also raise user awareness of fraud through fraud reporting and education features.

[0030] When analyzing the content of a message or phone call, the message analysis unit can compare it with a database of past fraud cases and detect similar patterns. For example, when the generation AI analyzes the content of a message or phone call, the message analysis unit compares it with a database of past fraud cases and detects similar patterns. For example, it analyzes based on fraud phrases and methods used in the past. The message analysis unit also uses the database of past fraud cases to allow the generation AI to analyze the content of a message or phone call and evaluate the possibility of fraud. For example, it detects keywords and phrases that match past fraud cases. The message analysis unit also compares it with the database of fraud cases, allowing the generation AI to analyze the content of a message or phone call and detect signs of fraud. For example, it finds patterns similar to past fraud cases. This allows the generation AI to compare it with the database of past fraud cases and determine the possibility of fraud with a high degree of accuracy.

[0031] In addition to analyzing messages or phone calls, the message analysis unit can also include other communication channels such as social media and emails in its analysis. For example, in addition to analyzing messages and phone calls, the message analysis unit can also include other communication channels such as social media and emails in its analysis. For example, it can also analyze messages on Facebook and Twitter. The message analysis unit also allows the generation AI to analyze the content of social media and emails to detect signs of fraud. For example, it can issue a warning if a potentially fraudulent message is being sent through multiple channels. By including other communication channels in its analysis, the message analysis unit allows the generation AI to detect signs of fraud more broadly. For example, it can analyze email and social media messages to assess the risk of fraud. By including other communication channels such as social media and emails in its analysis, it can detect the possibility of fraud more broadly.

[0032] The message analysis unit allows the generation AI to take into account fraud patterns in different languages ​​or cultural spheres when performing analysis, enabling fraud detection from a global perspective. For example, the message analysis unit may develop a fraud detection algorithm that supports multiple languages. The message analysis unit may also learn fraud patterns in different cultural spheres, and the generation AI may analyze the content of messages or phone calls. For example, it may consider fraud tactics commonly used in particular cultural spheres. The message analysis unit may also allow the generation AI to analyze fraud patterns in different languages ​​or cultural spheres when performing fraud detection from a global perspective. For example, it may utilize an international fraud case database. This may allow fraud detection from a global perspective by taking into account fraud patterns in different languages ​​and cultural spheres.

[0033] The fraud detection unit analyzes the entire context, not just specific keywords or phrases, and can make a comprehensive judgment on the possibility of fraud. For example, the generation AI analyzes the entire context, not just specific keywords or phrases, and makes a comprehensive judgment on the possibility of fraud. For example, it takes into account the context and order of the message. The fraud detection unit also uses context analysis to build a system in which the generation AI makes a comprehensive judgment on the content of a message or phone call. For example, even if a specific keyword is not included, it can detect signs of fraud from the context. The fraud detection unit also analyzes the entire context and assesses the possibility of fraud. For example, it analyzes the tone and intent of the message to determine the risk of fraud. This allows the generation AI to analyze the entire context and make a comprehensive judgment on the possibility of fraud.

[0034] The fraud detection unit can analyze the sender's past behavioral history or credit information to assess the possibility of fraud. For example, the generation AI analyzes the sender's past behavioral history and credit information to assess the possibility of fraud. For example, if there has been any fraudulent activity in the past, it will issue a warning. The fraud detection unit also analyzes the sender's credit information, and builds a system in which the generation AI assesses the possibility of fraud. For example, it will issue a warning for messages from senders with low credit scores. The fraud detection unit also analyzes the sender's past behavioral history and detects signs of fraud. For example, it will issue a warning for messages from senders who have committed fraud in the past. In this way, by analyzing the sender's past behavioral history and credit information, the possibility of fraud can be assessed with high accuracy.

[0035] The fraud detection unit can also include multimedia content such as images or videos in its analysis when detecting signs of fraud. For example, the fraud detection unit may also include multimedia content such as images or videos in its analysis when detecting signs of fraud. For example, it may analyze images or videos that may be fraudulent. The fraud detection unit also builds a system in which a generative AI analyzes the content of images and videos to detect signs of fraud. For example, it may analyze videos that show fraudulent methods. By including multimedia content in its analysis, the generative AI can detect signs of fraud more widely. For example, it may analyze the content of images or videos to assess the risk of fraud. In this way, by including multimedia content such as images and videos in its analysis, a wider range of signs of fraud can be detected.

[0036] The fraud detection unit allows the generation AI to consider fraud patterns from different industries or fields when detecting signs of fraud, enabling it to respond to a wide range of fraud methods. For example, the fraud detection unit learns fraud patterns from the financial and medical industries. The fraud detection unit also learns fraud patterns from different industries, and the generation AI analyzes the content of messages and phone calls. For example, it considers fraud methods commonly used in specific industries. In order to respond to a wide range of fraud methods, the fraud detection unit allows the generation AI to analyze fraud patterns from different industries and fields. For example, it utilizes a database of fraud cases for each industry. This allows it to consider fraud patterns from different industries and fields, enabling it to respond to a wide range of fraud methods.

[0037] When the generation AI issues a warning, the warning unit can generate an optimal warning message by taking into account the user's past behavioral history or reaction patterns. For example, the generation AI analyzes the user's past behavioral history to generate an optimal warning message. For example, a stronger warning is issued to a user who has previously reacted to fraudulent messages. The warning unit also takes into account the user's reaction patterns and customizes the warning message. For example, a warning including a detailed explanation is issued to a user who has ignored warnings in the past. The warning unit also builds a system in which the generation AI generates an optimal warning message based on the user's behavioral history. For example, it analyzes past behavioral data and issues a warning appropriate for the user. This makes it possible to generate an optimal warning message by taking into account the user's past behavioral history and reaction patterns.

[0038] The warning unit allows the generation AI to issue a warning at an appropriate time, taking into account the user's current situation. For example, the generation AI analyzes the user's current situation and issues a warning at an appropriate time. For example, if a fraudulent message is received late at night, the warning will be issued immediately. The warning unit also considers the user's location and time of day, and the generation AI customizes the warning message. For example, if the user is in a public place, the warning will be issued quietly. The warning unit also builds a system in which the generation AI issues a warning at the optimal time based on the user's current situation. For example, if the user is busy during certain hours, the warning will be issued briefly. This allows the generation AI to issue a warning at an appropriate time by taking into account the user's current situation.

[0039] The warning unit provides the warning message not only as text but also as audio or visual content, thereby strengthening the user's attention. The warning unit, for example, provides the warning message not only as text but also as audio or visual content. For example, it displays an audio message or a warning icon. The warning unit also constructs a system in which a generation AI generates the warning message as audio or visual content, thereby strengthening the user's attention. For example, it issues a warning using animation or video. The warning unit also strengthens the user's attention by providing the warning message in various formats. For example, it displays an audio alert or visual warning in addition to a text message. In this way, the warning message can be provided in various formats, thereby strengthening the user's attention.

[0040] When the generation AI issues a warning, the warning unit can also send a notification to the user's family or friends, encouraging support from those around them. For example, the warning unit builds a system that sends a notification to the user's family and friends when the generation AI issues a warning. For example, if the user receives a fraudulent message, the warning unit also sends a warning to family members. The warning unit also sends a notification to the user's family and friends to encourage support from those around them. For example, if the user is at risk of fraud, the warning unit sends a message to the family warning them to be careful. The warning unit also sends a notification to the user's family and friends when the generation AI issues a warning, thereby strengthening support from those around them. For example, if the user receives a fraudulent message, the warning unit also sends a warning to friends. This makes it possible to encourage support from those around them by sending notifications to the user's family and friends.

[0041] Generative AI can analyze the content of reported frauds and automatically classify the fraud methods or patterns. For example, generative AI can analyze the content of reported frauds and build a system that automatically classifies fraud methods and patterns. For example, it can classify them by type of fraud and method. Generative AI can also analyze the content of reported frauds and automatically classify the fraud methods and patterns. For example, it can classify them into refund frauds, phishing frauds, etc. Generative AI can also analyze the content of reported frauds and automatically classify the fraud methods and patterns to understand fraud trends. For example, it can update a database for each fraud method. This makes it possible to analyze the content of reported frauds and automatically classify the fraud methods and patterns to understand fraud trends.

[0042] The generating AI can analyze the contents of reported frauds and share them with other users, thereby widely publicizing the methods used by fraudsters. For example, the generating AI can build a system that analyzes the contents of reported frauds and shares them with other users. For example, it can notify other users of fraud methods and points to watch out for. The generating AI can also analyze the contents of reported frauds and share them with other users. For example, it can send warning messages to widely publicize the methods used by fraudsters. The generating AI can also analyze the contents of reported frauds and share them with other users, thereby widely publicizing the methods used by fraudsters. For example, it can share examples of fraud and warn users to be careful. In this way, the contents of reported frauds can be shared with other users, thereby widely publicizing the methods used by fraudsters.

[0043] Generative AI can make the fraud reporting function available on different platforms. For example, generative AI builds a system that makes the fraud reporting function available on different platforms. For example, it accepts fraud reports via social media and email. The generative AI also analyzes fraud reports from different platforms to learn about fraud methods. For example, it analyzes reports from Facebook and Twitter. By making the fraud reporting function available on different platforms, the generative AI learns from more fraud cases. For example, it accepts reports from email and social media. By making the fraud reporting function available on different platforms, more fraud cases can be collected.

[0044] The generation AI can analyze the content of reported frauds, generate statistical data on the fraud methods, and provide it to users. For example, the generation AI builds a system that analyzes the content of reported frauds and generates statistical data on the fraud methods. For example, it provides statistical data on the frequency of frauds and the types of methods used. The generation AI also analyzes the content of reported frauds and generates statistical data on the fraud methods. For example, it provides statistical data on the areas and time periods in which frauds occur. The generation AI also analyzes the content of reported frauds and generates statistical data on the fraud methods and provides it to users. For example, it provides statistical data on fraud trends and patterns. In this way, useful information can be provided to users by analyzing the content of reported frauds and generating statistical data on the fraud methods.

[0045] When providing fraud prevention education to users, the generation AI can provide optimal educational content by taking into account the user's past behavioral history or reaction patterns. For example, the generation AI analyzes the user's past behavioral history to provide optimal fraud prevention educational content. For example, for a user who has previously reacted to fraudulent messages, the generation AI provides education using specific examples. The generation AI also customizes the educational content by taking into account the user's reaction patterns. For example, for a user who has previously ignored warnings, the generation AI provides educational content with more detailed explanations. The generation AI also builds a system that provides optimal fraud prevention educational content based on the user's behavioral history. For example, it analyzes past behavioral data and provides education that is appropriate for the user. This makes it possible to provide optimal educational content by taking into account the user's past behavioral history and reaction patterns.

[0046] When educating users on fraud prevention, the generation AI can provide them with the latest fraud methods or trend information in real time. For example, the generation AI builds a system that collects the latest fraud methods and trend information and provides it to users in real time. For example, it immediately notifies users of newly emerged fraud methods. The generation AI also updates information in real time to provide users with the latest fraud methods and trend information. For example, it immediately updates educational content when fraud trends change. The generation AI also analyzes the latest fraud methods and trend information and provides it to users in real time. For example, if fraud methods evolve, that information is immediately communicated to users. In this way, by providing the latest fraud methods and trend information in real time, users' awareness of fraud prevention can be increased.

[0047] Generative AI can provide educational content for fraud prevention not only as text but also as video or interactive content. For example, generative AI can provide educational content for fraud prevention not only as text but also as video or interactive content. For example, it can provide educational content in the form of videos or quizzes that explain fraud methods. Generative AI can also build a system that generates educational content in video or interactive format and provides it to users. For example, it can provide education using animations and simulations. Generative AI can also deepen users' understanding by providing educational content in a variety of formats. For example, it can provide videos and interactive content in addition to text messages. This can deepen users' understanding by providing educational content in a variety of formats.

[0048] When providing fraud prevention education to users, the generation AI can provide content that corresponds to different languages ​​or cultural spheres. For example, the generation AI builds a system that provides fraud prevention education content that corresponds to different languages ​​or cultural spheres. For example, it generates educational content that corresponds to multiple languages. The generation AI also customizes fraud prevention education content for users from different cultural spheres. For example, it provides education that takes into account fraud methods commonly used in specific cultural spheres. The generation AI also provides fraud prevention education from a global perspective by providing educational content that corresponds to different languages ​​or cultural spheres. For example, it provides education using international fraud cases. In this way, by providing educational content that corresponds to different languages ​​and cultural spheres, it is possible to provide fraud prevention education from a global perspective.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The fraud detection unit analyzes the entire context, not just specific keywords or phrases, and can make a comprehensive judgment on the possibility of fraud. For example, the generation AI analyzes the entire context, not just specific keywords or phrases, and makes a comprehensive judgment on the possibility of fraud. For example, it takes into account the context and order of the message. The fraud detection unit also uses context analysis to build a system in which the generation AI makes a comprehensive judgment on the content of a message or phone call. For example, even if a specific keyword is not included, it can detect signs of fraud from the context. The fraud detection unit also uses the generation AI to analyze the entire context and evaluate the possibility of fraud. For example, it analyzes the tone and intent of the message to determine the risk of fraud. This allows the generation AI to make a comprehensive judgment on the possibility of fraud by analyzing the entire context.

[0051] The fraud detection unit can analyze the sender's past behavioral history or credit information to assess the possibility of fraud. For example, the generation AI analyzes the sender's past behavioral history and credit information to assess the possibility of fraud. For example, if there has been any fraudulent activity in the past, it will issue a warning. The fraud detection unit also analyzes the sender's credit information, and builds a system in which the generation AI assesses the possibility of fraud. For example, it will issue a warning for messages from senders with low credit scores. The fraud detection unit also analyzes the sender's past behavioral history to detect signs of fraud. For example, it will issue a warning for messages from senders who have committed fraud in the past. In this way, by analyzing the sender's past behavioral history and credit information, it is possible to assess the possibility of fraud with high accuracy.

[0052] When detecting signs of fraud, the fraud detection unit can also include multimedia content such as images or videos in its analysis. For example, it analyzes images and videos that may contain fraud. The fraud detection unit also builds a system in which the generative AI analyzes the content of images and videos to detect signs of fraud. For example, it analyzes videos that show fraudulent methods. By including multimedia content in its analysis, the generative AI can detect signs of fraud more widely. For example, it can analyze the content of images and videos to assess the risk of fraud. By including multimedia content such as images and videos in its analysis, it can detect signs of fraud more widely.

[0053] The fraud detection unit allows the generation AI to consider fraud patterns from different industries or fields when detecting signs of fraud, enabling it to respond to a wide range of fraud methods. For example, when the generation AI detects signs of fraud, it also considers fraud patterns from different industries or fields, enabling it to respond to a wide range of fraud methods. For example, it learns fraud patterns from the financial and medical industries. The fraud detection unit also learns fraud patterns from different industries, and the generation AI analyzes the content of messages and phone calls. For example, it considers fraud methods commonly used in specific industries. In addition, in order to respond to a wide range of fraud methods, the fraud detection unit allows the generation AI to analyze fraud patterns from different industries and fields. For example, it utilizes a database of fraud cases for each industry. This allows it to consider fraud patterns from different industries and fields, enabling it to respond to a wide range of fraud methods.

[0054] The fraud detection unit allows the generation AI to take into account fraud patterns in different languages ​​or cultural spheres when conducting analysis, enabling fraud detection from a global perspective. For example, the generation AI can take into account fraud patterns in different languages ​​or cultural spheres when conducting analysis, enabling fraud detection from a global perspective. For example, developing a fraud detection algorithm that supports multiple languages. The fraud detection unit also learns fraud patterns in different cultural spheres, and the generation AI analyzes the content of messages and phone calls. For example, it takes into account fraud methods commonly used in particular cultural spheres. The fraud detection unit also allows the generation AI to analyze fraud patterns in different languages ​​and cultural spheres in order to detect fraud from a global perspective. For example, it can utilize an international fraud case database. This allows for fraud detection from a global perspective, taking into account fraud patterns in different languages ​​and cultural spheres.

[0055] When the generation AI issues a warning, the warning unit can also send a notification to the user's family or friends, encouraging support from those around them. For example, a system can be constructed in which, when the generation AI issues a warning, a notification is also sent to the user's family and friends. For example, if the user receives a fraudulent message, a warning is also sent to family members. The warning unit also sends notifications to the user's family and friends, encouraging support from those around them. For example, if the user is at risk of fraud, a message is sent to the family warning them to be careful. The warning unit also sends notifications to the user's family and friends when the generation AI issues a warning, thereby strengthening support from those around them. For example, if the user receives a fraudulent message, a warning is also sent to friends. This makes it possible to encourage support from those around them by sending notifications to the user's family and friends.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The message analysis unit uses the generation AI to analyze the contents of the message or phone call. For example, the generation AI may use a text generation AI (e.g., LLM) to analyze the contents of the message or phone call. The generation AI may also use voice recognition technology to convert the contents of the phone call into text and analyze that text. Furthermore, the generation AI may also analyze the contents of the message or phone call using natural language processing technology. This makes it possible to analyze the meaning of the text data and extract important information. Step 2: The fraud detection unit detects signs of fraud from the content analyzed by the message analysis unit. For example, the fraud detection unit can determine signs of fraud by detecting specific keywords or phrases. It can also analyze the message context and sender information to comprehensively determine the possibility of fraud. It can also determine signs of fraud by detecting abnormal behavioral patterns. Step 3: The warning unit issues a warning message to the user based on the fraud signs detected by the fraud detection unit. For example, the warning message may say, "This message may be fraudulent. Do not provide personal information." It can also issue audio and visual alerts. This allows the user to immediately recognize the risk of fraud and take appropriate action.

[0058] (Example 2) A fraud detection system according to an embodiment of the present invention is a system for detecting refund fraud and protecting users. In this system, a generative AI analyzes the content of messages and phone calls, detects signs of fraud, and issues a warning to the user. This allows the fraud detection system to effectively detect refund fraud and protect users.

[0059] The fraud detection system according to the embodiment includes a message analysis unit, a fraud detection unit, and a warning unit. The message analysis unit analyzes the content of a message or phone call using a generation AI. For example, the generation AI analyzes the content of a message or phone call using a text generation AI (e.g., LLM). The generation AI can also convert the content of a phone call into text using speech recognition technology and analyze the text. The generation AI can also analyze the content of a message or phone call using natural language processing technology. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. Speech recognition technology can convert speech data into text with high accuracy. Natural language processing technology can analyze the meaning of text data and extract important information. The fraud detection unit detects signs of fraud from the content analyzed by the message analysis unit. For example, the fraud detection unit determines signs of fraud by detecting specific keywords or phrases. The fraud detection unit can also analyze the context of a message and sender information to comprehensively determine the likelihood of fraud. The fraud detection unit can also determine signs of fraud by detecting abnormal behavioral patterns. For example, the fraud detection unit determines the possibility of fraud by detecting keywords such as "refund," "bank account," and "personal information." Context analysis determines the possibility of fraud by taking into account the context of the message and sender information. Abnormal behavior pattern detection determines signs of fraud by detecting behavior that is different from normal. The warning unit issues a warning message to the user based on the signs of fraud detected by the fraud detection unit. For example, the warning unit displays a warning message such as "This message may be fraudulent. Do not provide personal information." The warning unit can also issue an audio alert. The warning unit can also display a visual alert. For example, the warning unit displays the warning as a text message. The audio alert issues a voice alert to the user. The visual alert displays a warning icon or message on the screen. As a result, the fraud detection system according to the embodiment can effectively detect refund fraud and protect users.For example, if a user receives a fraudulent message, the AI ​​can immediately issue a warning, reducing the risk of being scammed. It can also raise user awareness of fraud through fraud reporting and education features.

[0060] When analyzing the content of a message or phone call, the message analysis unit also analyzes the voice tone and the speaker's emotional state, allowing for more accurate assessment of the possibility of fraud. For example, when the generation AI analyzes the content of a message or phone call, the message analysis unit analyzes changes in voice tone and the speaker's emotional state. For example, if the speaker is nervous or in a hurry, it determines that there is a high possibility of fraud. The message analysis unit also uses voice tone analysis to estimate the speaker's emotional state in real time and evaluate the possibility of fraud. For example, if the speaker is not calm, it determines that there is a high risk of fraud. The message analysis unit also inputs voice data into an emotion recognition algorithm to analyze the speaker's emotional state and detect signs of fraud. For example, if the speaker shows anger or anxiety, it determines that there is a high possibility of fraud. This allows for more accurate assessment of the possibility of fraud.

[0061] When analyzing the content of a message or phone call, the message analysis unit can compare it with a database of past fraud cases and detect similar patterns. For example, when the generation AI analyzes the content of a message or phone call, the message analysis unit compares it with a database of past fraud cases and detects similar patterns. For example, it analyzes based on fraud phrases and methods used in the past. The message analysis unit also uses the database of past fraud cases to allow the generation AI to analyze the content of a message or phone call and evaluate the possibility of fraud. For example, it detects keywords and phrases that match past fraud cases. The message analysis unit also compares it with the database of fraud cases, allowing the generation AI to analyze the content of a message or phone call and detect signs of fraud. For example, it finds patterns similar to past fraud cases. This allows the generation AI to compare it with the database of past fraud cases and determine the possibility of fraud with a high degree of accuracy.

[0062] The message analysis unit uses the emotion estimation function to estimate the user's emotion from the content of messages and phone calls, and can urge the user to be particularly careful when the user is in an emotionally unstable state. The message analysis unit, for example, uses the emotion estimation function to estimate the user's emotion from the content of messages and phone calls, and can urge the user to be particularly careful when the user is in an emotionally unstable state. For example, if the user is feeling anxious or scared, the warning is intensified. The message analysis unit also analyzes the user's emotional state in real time, and issues a special warning when the user is in an emotionally unstable state. For example, if the user is feeling stressed, a detailed warning is issued. The message analysis unit also uses the emotion estimation function to analyze the user's emotional state, and can urge the user to be particularly careful when the user is in an emotionally unstable state. For example, if the user is showing signs of impatience or confusion, the warning message is emphasized. This can urge the user to be particularly careful when the user is in an emotionally unstable state.

[0063] In addition to analyzing messages or phone calls, the message analysis unit can also include other communication channels such as social media and emails in its analysis. For example, in addition to analyzing messages and phone calls, the message analysis unit can also include other communication channels such as social media and emails in its analysis. For example, it can also analyze messages on Facebook and Twitter. The message analysis unit also allows the generation AI to analyze the content of social media and emails to detect signs of fraud. For example, it can issue a warning if a potentially fraudulent message is being sent through multiple channels. By including other communication channels in its analysis, the message analysis unit allows the generation AI to detect signs of fraud more broadly. For example, it can analyze email and social media messages to assess the risk of fraud. By including other communication channels such as social media and emails in its analysis, it can detect the possibility of fraud more broadly.

[0064] The message analysis unit allows the generation AI to take into account fraud patterns in different languages ​​or cultural spheres when performing analysis, enabling fraud detection from a global perspective. For example, the message analysis unit may develop a fraud detection algorithm that supports multiple languages. The message analysis unit may also learn fraud patterns in different cultural spheres, and the generation AI may analyze the content of messages or phone calls. For example, it may consider fraud tactics commonly used in particular cultural spheres. The message analysis unit may also allow the generation AI to analyze fraud patterns in different languages ​​or cultural spheres when performing fraud detection from a global perspective. For example, it may utilize an international fraud case database. This may allow fraud detection from a global perspective by taking into account fraud patterns in different languages ​​and cultural spheres.

[0065] The message analysis unit can use the emotion estimation function to analyze the user's real-time emotional response when receiving a message or a phone call and determine the possibility of fraud. The message analysis unit, for example, uses the emotion estimation function to analyze the user's real-time emotional response when receiving a message or a phone call and determine the possibility of fraud. For example, if the user shows signs of surprise or anxiety, it determines that there is a high risk of fraud. The message analysis unit also analyzes the user's real-time emotional response and builds a system that evaluates the possibility of fraud. For example, if the user shows signs of fear, it intensifies the warning. The message analysis unit also uses the emotion estimation function to analyze the user's emotional response in real time and determine the possibility of fraud. For example, if the user shows signs of confusion or impatience, it determines that there is a high risk of fraud. In this way, by analyzing the user's real-time emotional response when receiving a message or a phone call, it is possible to determine the possibility of fraud with high accuracy.

[0066] The fraud detection unit analyzes the entire context, not just specific keywords or phrases, and can make a comprehensive judgment on the possibility of fraud. For example, the generation AI analyzes the entire context, not just specific keywords or phrases, and makes a comprehensive judgment on the possibility of fraud. For example, it takes into account the context and order of the message. The fraud detection unit also uses context analysis to build a system in which the generation AI makes a comprehensive judgment on the content of a message or phone call. For example, even if a specific keyword is not included, it can detect signs of fraud from the context. The fraud detection unit also analyzes the entire context and assesses the possibility of fraud. For example, it analyzes the tone and intent of the message to determine the risk of fraud. This allows the generation AI to analyze the entire context and make a comprehensive judgment on the possibility of fraud.

[0067] The fraud detection unit can analyze the sender's past behavioral history or credit information to assess the possibility of fraud. For example, the generation AI analyzes the sender's past behavioral history and credit information to assess the possibility of fraud. For example, if there has been any fraudulent activity in the past, it will issue a warning. The fraud detection unit also analyzes the sender's credit information, and builds a system in which the generation AI assesses the possibility of fraud. For example, it will issue a warning for messages from senders with low credit scores. The fraud detection unit also analyzes the sender's past behavioral history and detects signs of fraud. For example, it will issue a warning for messages from senders who have committed fraud in the past. In this way, by analyzing the sender's past behavioral history and credit information, the possibility of fraud can be assessed with high accuracy.

[0068] The fraud detection unit can use the emotion estimation function to estimate the emotional state of a fraudster from the content of a message or phone call and determine the possibility of fraud. For example, the fraud detection unit uses the emotion estimation function to estimate the emotional state of a fraudster from the content of a message or phone call and determine the possibility of fraud. For example, if the fraudster shows signs of impatience or tension, it determines that there is a high risk of fraud. The fraud detection unit also analyzes the emotional state of a fraudster and builds a system in which the generative AI evaluates the possibility of fraud. For example, if the fraudster shows signs of anxiety or anger, it issues a warning. The fraud detection unit also uses the emotion estimation function to analyze the emotional state of a fraudster in real time and determine the possibility of fraud. For example, if the fraudster is not calm, it determines that there is a high risk of fraud. In this way, by estimating the emotional state of a fraudster, it is possible to determine the possibility of fraud with high accuracy.

[0069] The fraud detection unit can also include multimedia content such as images or videos in its analysis when detecting signs of fraud. For example, the fraud detection unit may also include multimedia content such as images or videos in its analysis when detecting signs of fraud. For example, it may analyze images or videos that may be fraudulent. The fraud detection unit also builds a system in which a generative AI analyzes the content of images and videos to detect signs of fraud. For example, it may analyze videos that show fraudulent methods. By including multimedia content in its analysis, the generative AI can detect signs of fraud more widely. For example, it may analyze the content of images or videos to assess the risk of fraud. In this way, by including multimedia content such as images and videos in its analysis, a wider range of signs of fraud can be detected.

[0070] The fraud detection unit allows the generation AI to consider fraud patterns from different industries or fields when detecting signs of fraud, enabling it to respond to a wide range of fraud methods. For example, the fraud detection unit learns fraud patterns from the financial and medical industries. The fraud detection unit also learns fraud patterns from different industries, and the generation AI analyzes the content of messages and phone calls. For example, it considers fraud methods commonly used in specific industries. In order to respond to a wide range of fraud methods, the fraud detection unit allows the generation AI to analyze fraud patterns from different industries and fields. For example, it utilizes a database of fraud cases for each industry. This allows it to consider fraud patterns from different industries and fields, enabling it to respond to a wide range of fraud methods.

[0071] The fraud detection unit can use the emotion estimation function to analyze the user's emotional response to a message or phone call received and determine the possibility of fraud. For example, the fraud detection unit uses the emotion estimation function to analyze the user's emotional response to a message or phone call received and determine the possibility of fraud. For example, if the user shows signs of surprise or anxiety, it determines that there is a high risk of fraud. The fraud detection unit also analyzes the user's emotional response in real time and builds a system that evaluates the possibility of fraud. For example, if the user shows signs of fear, it intensifies the warning. The fraud detection unit also uses the emotion estimation function to analyze the user's emotional response in real time and determine the possibility of fraud. For example, if the user shows signs of confusion or impatience, it determines that there is a high risk of fraud. In this way, by analyzing the user's emotional response to a message or phone call received, it is possible to determine the possibility of fraud with high accuracy.

[0072] When the generation AI issues a warning, the warning unit can generate an optimal warning message by taking into account the user's past behavioral history or reaction patterns. For example, the generation AI analyzes the user's past behavioral history to generate an optimal warning message. For example, a stronger warning is issued to a user who has previously reacted to fraudulent messages. The warning unit also takes into account the user's reaction patterns and customizes the warning message. For example, a warning including a detailed explanation is issued to a user who has ignored warnings in the past. The warning unit also builds a system in which the generation AI generates an optimal warning message based on the user's behavioral history. For example, it analyzes past behavioral data and issues a warning appropriate for the user. This makes it possible to generate an optimal warning message by taking into account the user's past behavioral history and reaction patterns.

[0073] The warning unit allows the generation AI to issue a warning at an appropriate time, taking into account the user's current situation. For example, the generation AI analyzes the user's current situation and issues a warning at an appropriate time. For example, if a fraudulent message is received late at night, the warning will be issued immediately. The warning unit also considers the user's location and time of day, and the generation AI customizes the warning message. For example, if the user is in a public place, the warning will be issued quietly. The warning unit also builds a system in which the generation AI issues a warning at the optimal time based on the user's current situation. For example, if the user is busy during certain hours, the warning will be issued briefly. This allows the generation AI to issue a warning at an appropriate time by taking into account the user's current situation.

[0074] The warning unit uses the emotion estimation function to generate a warning message according to the user's emotional state, thereby enabling more effective warnings. The warning unit, for example, uses the emotion estimation function to generate a warning message according to the user's emotional state. For example, if the user is feeling anxious, a warning message that reassures the user is issued. The warning unit also analyzes the user's emotional state in real time, and a generation AI builds a system that generates an optimal warning message. For example, if the user is feeling impatient, a warning urging the user to stay calm is issued. The warning unit also uses the emotion estimation function to generate a warning message according to the user's emotional state, thereby enabling more effective warnings. For example, if the user is feeling angry, a warning message urging the user to stay calm is issued. In this way, by generating a warning message according to the user's emotional state, more effective warnings can be provided.

[0075] The warning unit provides the warning message not only as text but also as audio or visual content, thereby strengthening the user's attention. The warning unit, for example, provides the warning message not only as text but also as audio or visual content. For example, it displays an audio message or a warning icon. The warning unit also constructs a system in which a generation AI generates the warning message as audio or visual content, thereby strengthening the user's attention. For example, it issues a warning using animation or video. The warning unit also strengthens the user's attention by providing the warning message in various formats. For example, it displays an audio alert or visual warning in addition to a text message. In this way, the warning message can be provided in various formats, thereby strengthening the user's attention.

[0076] When the generation AI issues a warning, the warning unit can also send a notification to the user's family or friends, encouraging support from those around them. For example, the warning unit builds a system that sends a notification to the user's family and friends when the generation AI issues a warning. For example, if the user receives a fraudulent message, the warning unit also sends a warning to family members. The warning unit also sends a notification to the user's family and friends to encourage support from those around them. For example, if the user is at risk of fraud, the warning unit sends a message to the family warning them to be careful. The warning unit also sends a notification to the user's family and friends when the generation AI issues a warning, thereby strengthening support from those around them. For example, if the user receives a fraudulent message, the warning unit also sends a warning to friends. This makes it possible to encourage support from those around them by sending notifications to the user's family and friends.

[0077] The warning unit can use the emotion estimation function to analyze the emotional reaction of the user when they receive the warning message and evaluate the effectiveness of the warning. For example, the warning unit uses the emotion estimation function to analyze the emotional reaction of the user when they receive the warning message and evaluate the effectiveness of the warning. For example, the warning unit monitors emotional changes after the user receives the warning. The warning unit also analyzes the user's emotional reaction in real time and builds a system to evaluate the effectiveness of the warning message. For example, the warning unit analyzes the emotion score after the user receives the warning. The warning unit also uses the emotion estimation function to analyze the user's emotional reaction and evaluate the effectiveness of the warning. For example, the warning unit checks whether the user has calmed down after receiving the warning. In this way, the effectiveness of the warning can be evaluated by analyzing the emotional reaction of the user when they receive the warning message.

[0078] Generative AI can analyze the content of reported frauds and automatically classify the fraud methods or patterns. For example, generative AI can analyze the content of reported frauds and build a system that automatically classifies fraud methods and patterns. For example, it can classify them by type of fraud and method. Generative AI can also analyze the content of reported frauds and automatically classify the fraud methods and patterns. For example, it can classify them into refund frauds, phishing frauds, etc. Generative AI can also analyze the content of reported frauds and automatically classify the fraud methods and patterns to understand fraud trends. For example, it can update a database for each fraud method. This makes it possible to analyze the content of reported frauds and automatically classify the fraud methods and patterns to understand fraud trends.

[0079] The generating AI can analyze the contents of reported frauds and share them with other users, thereby widely publicizing the methods used by fraudsters. For example, the generating AI can build a system that analyzes the contents of reported frauds and shares them with other users. For example, it can notify other users of fraud methods and points to watch out for. The generating AI can also analyze the contents of reported frauds and share them with other users. For example, it can send warning messages to widely publicize the methods used by fraudsters. The generating AI can also analyze the contents of reported frauds and share them with other users, thereby widely publicizing the methods used by fraudsters. For example, it can share examples of fraud and warn users to be careful. In this way, the contents of reported frauds can be shared with other users, thereby widely publicizing the methods used by fraudsters.

[0080] The generation AI can use the emotion estimation function to analyze the emotional state of a user when reporting a fraud and evaluate the reliability of the report. For example, the generation AI can use the emotion estimation function to analyze the emotional state of a user when reporting a fraud and evaluate the reliability of the report. For example, if the user is not calm, the reliability of the report can be evaluated low. The generation AI can also build a system that analyzes the user's emotional state in real time and evaluates the reliability of the report. For example, if the user shows signs of impatience or anxiety, the reliability of the report can be evaluated low. The generation AI can also use the emotion estimation function to analyze the user's emotional state and evaluate the reliability of the report. For example, if the user shows anger or fear, the reliability of the report can be evaluated low. In this way, the reliability of the report can be evaluated by analyzing the emotional state of a user when reporting a fraud.

[0081] Generative AI can make the fraud reporting function available on different platforms. For example, generative AI builds a system that makes the fraud reporting function available on different platforms. For example, it accepts fraud reports via social media and email. The generative AI also analyzes fraud reports from different platforms to learn about fraud methods. For example, it analyzes reports from Facebook and Twitter. By making the fraud reporting function available on different platforms, the generative AI learns from more fraud cases. For example, it accepts reports from email and social media. By making the fraud reporting function available on different platforms, more fraud cases can be collected.

[0082] The generation AI can analyze the content of reported frauds, generate statistical data on the fraud methods, and provide it to users. For example, the generation AI builds a system that analyzes the content of reported frauds and generates statistical data on the fraud methods. For example, it provides statistical data on the frequency of frauds and the types of methods used. The generation AI also analyzes the content of reported frauds and generates statistical data on the fraud methods. For example, it provides statistical data on the areas and time periods in which frauds occur. The generation AI also analyzes the content of reported frauds and generates statistical data on the fraud methods and provides it to users. For example, it provides statistical data on fraud trends and patterns. In this way, useful information can be provided to users by analyzing the content of reported frauds and generating statistical data on the fraud methods.

[0083] The generative AI can use its emotion estimation function to analyze the emotional reactions of users when reporting fraud and improve the reporting process. For example, the generative AI can use its emotion estimation function to analyze the emotional reactions of users when reporting fraud and improve the reporting process. For example, if the user is feeling anxious, the reporting procedure can be simplified. The generative AI can also analyze the user's emotional reactions in real time and build a system to improve the reporting process. For example, if the user is feeling impatient, the reporting procedure can be simplified. The generative AI can also use its emotion estimation function to analyze the user's emotional reactions and improve the reporting process. For example, if the user is confused, the reporting procedure can be made easier to understand. In this way, the reporting process can be improved by analyzing the emotional reactions of users when reporting fraud.

[0084] When providing fraud prevention education to users, the generation AI can provide optimal educational content by taking into account the user's past behavioral history or reaction patterns. For example, the generation AI analyzes the user's past behavioral history to provide optimal fraud prevention educational content. For example, for a user who has previously reacted to fraudulent messages, the generation AI provides education using specific examples. The generation AI also customizes the educational content by taking into account the user's reaction patterns. For example, for a user who has previously ignored warnings, the generation AI provides educational content with more detailed explanations. The generation AI also builds a system that provides optimal fraud prevention educational content based on the user's behavioral history. For example, it analyzes past behavioral data and provides education that is appropriate for the user. This makes it possible to provide optimal educational content by taking into account the user's past behavioral history and reaction patterns.

[0085] When educating users on fraud prevention, the generation AI can provide them with the latest fraud methods or trend information in real time. For example, the generation AI builds a system that collects the latest fraud methods and trend information and provides it to users in real time. For example, it immediately notifies users of newly emerged fraud methods. The generation AI also updates information in real time to provide users with the latest fraud methods and trend information. For example, it immediately updates educational content when fraud trends change. The generation AI also analyzes the latest fraud methods and trend information and provides it to users in real time. For example, if fraud methods evolve, that information is immediately communicated to users. In this way, by providing the latest fraud methods and trend information in real time, users' awareness of fraud prevention can be increased.

[0086] The generation AI uses the emotion estimation function to provide educational content that corresponds to the user's emotional state, enabling more effective education. The generation AI, for example, uses the emotion estimation function to provide educational content that corresponds to the user's emotional state. For example, if the user is feeling anxious, it provides educational content that reassures the user. The generation AI also analyzes the user's emotional state in real time and builds a system that provides optimal educational content. For example, if the user is feeling impatient, it provides education that encourages the user to stay calm. The generation AI also uses the emotion estimation function to provide educational content that corresponds to the user's emotional state, enabling more effective education. For example, if the user is feeling angry, it provides educational content that encourages the user to stay calm. This allows more effective education by providing educational content that corresponds to the user's emotional state.

[0087] Generative AI can provide educational content for fraud prevention not only as text but also as video or interactive content. For example, generative AI can provide educational content for fraud prevention not only as text but also as video or interactive content. For example, it can provide educational content in the form of videos or quizzes that explain fraud methods. Generative AI can also build a system that generates educational content in video or interactive format and provides it to users. For example, it can provide education using animations and simulations. Generative AI can also deepen users' understanding by providing educational content in a variety of formats. For example, it can provide videos and interactive content in addition to text messages. This can deepen users' understanding by providing educational content in a variety of formats.

[0088] When providing fraud prevention education to users, the generation AI can provide content that corresponds to different languages ​​or cultural spheres. For example, the generation AI builds a system that provides fraud prevention education content that corresponds to different languages ​​or cultural spheres. For example, it generates educational content that corresponds to multiple languages. The generation AI also customizes fraud prevention education content for users from different cultural spheres. For example, it provides education that takes into account fraud methods commonly used in specific cultural spheres. The generation AI also provides fraud prevention education from a global perspective by providing educational content that corresponds to different languages ​​or cultural spheres. For example, it provides education using international fraud cases. In this way, by providing educational content that corresponds to different languages ​​and cultural spheres, it is possible to provide fraud prevention education from a global perspective.

[0089] The generation AI can use the emotion estimation function to analyze the emotional reactions of users when they receive educational content and evaluate the effectiveness of the education. For example, the generation AI can use the emotion estimation function to analyze the emotional reactions of users when they receive educational content and evaluate the effectiveness of the education. For example, it can monitor emotional changes after the user has received the education. The generation AI can also analyze the user's emotional reactions in real time and build a system to evaluate the effectiveness of the educational content. For example, it can analyze the emotional score after the user has received the education. The generation AI can also use the emotion estimation function to analyze the user's emotional reactions and evaluate the effectiveness of the education. For example, it can check whether the user has become calmer after receiving the education. In this way, the effectiveness of the education can be evaluated by analyzing the emotional reactions of users when they receive the educational content.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The fraud detection unit analyzes the entire context, not just specific keywords or phrases, and can make a comprehensive judgment on the possibility of fraud. For example, the generation AI analyzes the entire context, not just specific keywords or phrases, and makes a comprehensive judgment on the possibility of fraud. For example, it takes into account the context and order of the message. The fraud detection unit also uses context analysis to build a system in which the generation AI makes a comprehensive judgment on the content of a message or phone call. For example, even if a specific keyword is not included, it can detect signs of fraud from the context. The fraud detection unit also uses the generation AI to analyze the entire context and evaluate the possibility of fraud. For example, it analyzes the tone and intent of the message to determine the risk of fraud. This allows the generation AI to make a comprehensive judgment on the possibility of fraud by analyzing the entire context.

[0092] The fraud detection unit can analyze the sender's past behavioral history or credit information to assess the possibility of fraud. For example, the generation AI analyzes the sender's past behavioral history and credit information to assess the possibility of fraud. For example, if there has been any fraudulent activity in the past, it will issue a warning. The fraud detection unit also analyzes the sender's credit information, and builds a system in which the generation AI assesses the possibility of fraud. For example, it will issue a warning for messages from senders with low credit scores. The fraud detection unit also analyzes the sender's past behavioral history to detect signs of fraud. For example, it will issue a warning for messages from senders who have committed fraud in the past. In this way, by analyzing the sender's past behavioral history and credit information, it is possible to assess the possibility of fraud with high accuracy.

[0093] When detecting signs of fraud, the fraud detection unit can also include multimedia content such as images or videos in its analysis. For example, it analyzes images and videos that may contain fraud. The fraud detection unit also builds a system in which the generative AI analyzes the content of images and videos to detect signs of fraud. For example, it analyzes videos that show fraudulent methods. By including multimedia content in its analysis, the generative AI can detect signs of fraud more widely. For example, it can analyze the content of images and videos to assess the risk of fraud. By including multimedia content such as images and videos in its analysis, it can detect signs of fraud more widely.

[0094] The fraud detection unit allows the generation AI to consider fraud patterns from different industries or fields when detecting signs of fraud, enabling it to respond to a wide range of fraud methods. For example, when the generation AI detects signs of fraud, it also considers fraud patterns from different industries or fields, enabling it to respond to a wide range of fraud methods. For example, it learns fraud patterns from the financial and medical industries. The fraud detection unit also learns fraud patterns from different industries, and the generation AI analyzes the content of messages and phone calls. For example, it considers fraud methods commonly used in specific industries. In addition, in order to respond to a wide range of fraud methods, the fraud detection unit allows the generation AI to analyze fraud patterns from different industries and fields. For example, it utilizes a database of fraud cases for each industry. This allows it to consider fraud patterns from different industries and fields, enabling it to respond to a wide range of fraud methods.

[0095] The fraud detection unit allows the generation AI to take into account fraud patterns in different languages ​​or cultural spheres when conducting analysis, enabling fraud detection from a global perspective. For example, the generation AI can take into account fraud patterns in different languages ​​or cultural spheres when conducting analysis, enabling fraud detection from a global perspective. For example, developing a fraud detection algorithm that supports multiple languages. The fraud detection unit also learns fraud patterns in different cultural spheres, and the generation AI analyzes the content of messages and phone calls. For example, it takes into account fraud methods commonly used in particular cultural spheres. The fraud detection unit also allows the generation AI to analyze fraud patterns in different languages ​​and cultural spheres in order to detect fraud from a global perspective. For example, it can utilize an international fraud case database. This allows for fraud detection from a global perspective, taking into account fraud patterns in different languages ​​and cultural spheres.

[0096] The fraud detection unit can use the emotion estimation function to estimate the emotional state of a fraudster from the content of a message or phone call and determine the possibility of fraud. For example, the emotion estimation function can be used to estimate the emotional state of a fraudster from the content of a message or phone call and determine the possibility of fraud. For example, if the fraudster shows signs of impatience or tension, it can determine that there is a high risk of fraud. The fraud detection unit also analyzes the emotional state of a fraudster and builds a system in which the generative AI evaluates the possibility of fraud. For example, if the fraudster shows signs of anxiety or anger, it can issue a warning. The fraud detection unit also uses the emotion estimation function to analyze the emotional state of a fraudster in real time and determine the possibility of fraud. For example, if the fraudster is not calm, it can determine that there is a high risk of fraud. This allows the possibility of fraud to be determined with high accuracy by estimating the emotional state of a fraudster.

[0097] The fraud detection unit can use the emotion estimation function to analyze the user's emotional response to a message or phone call received and determine the possibility of fraud. For example, the emotion estimation function can be used to analyze the user's emotional response to a message or phone call received and determine the possibility of fraud. For example, if the user shows signs of surprise or anxiety, it can determine that there is a high risk of fraud. The fraud detection unit can also analyze the user's emotional response in real time and build a system to evaluate the possibility of fraud. For example, if the user shows signs of fear, it can intensify the warning. The fraud detection unit can also use the emotion estimation function to analyze the user's emotional response in real time and determine the possibility of fraud. For example, if the user shows signs of confusion or impatience, it can determine that there is a high risk of fraud. In this way, the possibility of fraud can be determined with high accuracy by analyzing the user's emotional response to a message or phone call received.

[0098] The warning unit uses the emotion estimation function to generate a warning message according to the user's emotional state, thereby enabling more effective warnings. For example, the emotion estimation function is used to generate a warning message according to the user's emotional state. For example, if the user is feeling anxious, a warning message that reassures the user is issued. The warning unit also analyzes the user's emotional state in real time, and a generation AI is used to build a system that generates an optimal warning message. For example, if the user is feeling impatient, a warning urging the user to stay calm is issued. The warning unit also uses the emotion estimation function to generate a warning message according to the user's emotional state, thereby enabling more effective warnings. For example, if the user is feeling angry, a warning message urging the user to stay calm is issued. In this way, by generating a warning message according to the user's emotional state, more effective warnings can be provided.

[0099] The warning unit can use the emotion estimation function to analyze the emotional reaction of the user when they receive the warning message and evaluate the effectiveness of the warning. For example, the emotion estimation function can be used to analyze the emotional reaction of the user when they receive the warning message and evaluate the effectiveness of the warning. For example, the emotion estimation function can be used to monitor emotional changes after the user receives the warning. The warning unit can also analyze the emotional reaction of the user in real time and build a system to evaluate the effectiveness of the warning message. For example, the emotion score can be analyzed after the user receives the warning. The warning unit can also use the emotion estimation function to analyze the emotional reaction of the user and evaluate the effectiveness of the warning. For example, the emotion estimation function can be used to check whether the user has calmed down after receiving the warning. In this way, the effectiveness of the warning can be evaluated by analyzing the emotional reaction of the user when they receive the warning message.

[0100] When the generation AI issues a warning, the warning unit can also send a notification to the user's family or friends, encouraging support from those around them. For example, a system can be constructed in which, when the generation AI issues a warning, a notification is also sent to the user's family and friends. For example, if the user receives a fraudulent message, a warning is also sent to family members. The warning unit also sends notifications to the user's family and friends, encouraging support from those around them. For example, if the user is at risk of fraud, a message is sent to the family warning them to be careful. The warning unit also sends notifications to the user's family and friends when the generation AI issues a warning, thereby strengthening support from those around them. For example, if the user receives a fraudulent message, a warning is also sent to friends. This makes it possible to encourage support from those around them by sending notifications to the user's family and friends.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The message analysis unit uses the generation AI to analyze the contents of the message or phone call. For example, the generation AI may use a text generation AI (e.g., LLM) to analyze the contents of the message or phone call. The generation AI may also use voice recognition technology to convert the contents of the phone call into text and analyze that text. Furthermore, the generation AI may also analyze the contents of the message or phone call using natural language processing technology. This makes it possible to analyze the meaning of the text data and extract important information. Step 2: The fraud detection unit detects signs of fraud from the content analyzed by the message analysis unit. For example, the fraud detection unit can determine signs of fraud by detecting specific keywords or phrases. It can also analyze the message context and sender information to comprehensively determine the possibility of fraud. It can also determine signs of fraud by detecting abnormal behavioral patterns. Step 3: The warning unit issues a warning message to the user based on the fraud signs detected by the fraud detection unit. For example, the warning message may say, "This message may be fraudulent. Do not provide personal information." It can also issue audio and visual alerts. This allows the user to immediately recognize the risk of fraud and take appropriate action.

[0103] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0104] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0105] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 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.

[0108] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0109] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0110] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0112] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0113] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0114] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0115] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0116] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0117] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0118] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0119] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0123] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0124] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0125] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0127] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0128] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0129] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0130] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0131] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0132] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0133] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 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.

[0138] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0139] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0140] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0141] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0142] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0143] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0144] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0147] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0148] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0150] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0153] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0154] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0155] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0156] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0157] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0158] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0159] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0160] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0161] 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.

[0162] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0163] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0164] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific process may be a single processor.

[0165] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0166] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0167] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0168] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0169] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0170] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a message analysis unit that analyzes the contents of a message or a phone call using a generation AI; a fraud detection unit that detects signs of fraud from the content analyzed by the message analysis unit; a warning unit that issues a warning message to a user based on the indication of fraud detected by the fraud detection unit. A system characterized by:

2. The message analysis unit In addition to analyzing the messages or phone calls, also analyze other communication channels such as social media and email.

2. The system of claim 1.

3. The fraud detection unit Analyze the entire context, not just specific keywords or phrases, to comprehensively assess the likelihood of fraud 2. The system of claim 1.

4. The warning unit When issuing a warning, the AI ​​generates the most appropriate warning message by taking into account the user's past behavioral history or reaction patterns.

2. The system of claim 1.

5. The generated AI is Analyzing the emotional state of the user when reporting the fraud and evaluating the credibility of the report.

2. The system of claim 1.

Images