System

Abstract

An object of the system according to the embodiment is to provide training for an elderly person to find a sign of fraudulent email and appropriately handle the fraudulent email.SOLUTION: A system includes a generation AI, an investigation unit, a determination unit, and an evaluation unit. The generating AI generates virtual fraud emails using the generating AI. The investigation unit investigates virtual fraud email generated by the generation AI. The determination unit determines whether the received e-mail is a fraud e-mail based on the result of the investigation by the investigation unit. The evaluation unit evaluates the result determined by the determination unit and provides feedback.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 does not adequately train seniors to recognize the signs of fraud and respond appropriately when they receive a fraudulent email, so there is room for improvement.

[0005] The system according to the embodiment aims to provide training to help elderly people to recognize the signs of fraudulent emails and respond appropriately. [Means for solving the problem]

[0006] The system according to the embodiment comprises a generation AI, an investigation unit, a judgment unit, and an evaluation unit. The generation AI generates virtual fraudulent emails using the generation AI. The investigation unit investigates the virtual fraudulent emails generated by the generation AI. The judgment unit determines whether the email is fraudulent based on the content investigated by the investigation unit. The evaluation unit evaluates the results of the judgment by the judgment unit and provides feedback. [Effects of the Invention]

[0007] The system according to the embodiment can provide training for seniors to recognize the signs of fraudulent emails and respond appropriately. [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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[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) The simulation game according to an embodiment of the present invention is a system that supports elderly people in identifying signs of fraud in email content and learning how to deal with the situation. This system involves players receiving virtual fraudulent emails created by a generative AI, investigating them, making judgments, and providing evaluations and feedback. This simulation game allows elderly people to identify signs of fraudulent emails and learn how to deal with them.

[0029] A simulation game according to an embodiment includes a generation AI, an investigation unit, a judgment unit, and an evaluation unit. The generation AI generates virtual scam emails. For example, the generation AI can learn the characteristics of scam emails and generate realistic scam emails. The generation AI generates scam emails using models such as GPT-3 and BERT. The investigation unit investigates the virtual scam emails generated by the generation AI. For example, a player checks the sender address, destination URL, and body content of the email. The investigation unit analyzes the email's header information and verifies the links. The judgment unit determines whether the email is scam based on the information investigated by the investigation unit. For example, the player comprehensively determines whether the sender address is suspicious, whether the link leads to an unknown site, or whether the body content is unnatural. The evaluation unit evaluates the judgment results and provides feedback. For example, the generation AI analyzes the areas tapped by the player and the judgment, and scores the areas where it was able to determine scams. This allows the simulation game according to an embodiment to help elderly people identify signs of scam emails and learn how to deal with them.

[0030] The generation AI can analyze a player's past game data and generate scam emails optimized for each individual player. For example, the generation AI can analyze a player's past game data and generate emails containing scam characteristics that the player missed in the past. For example, it can create emails containing specific phrases and link formats. The generation AI can also use the player's past game data to generate emails containing the scam techniques that the player is most difficult to perpetrate. For example, it can create emails containing phishing scams and fake invoices. The generation AI can also analyze a player's past game data and avoid the scam techniques that the player has previously scored high on, generating more difficult scam emails. For example, it can create emails containing cleverly disguised sender addresses and links. This allows the system to generate scam emails optimized for each player, thereby improving its learning effect.

[0031] The generation AI learns the latest fraud techniques in real time and can constantly generate new fraudulent emails. For example, the generation AI automatically collects the latest fraud techniques on the Internet and generates new fraudulent emails based on that information. For example, it creates emails incorporating newly discovered phishing techniques. The generation AI also learns the latest fraud techniques from security research institutes and news sites and generates fraudulent emails based on that information. For example, it creates emails that imitate the latest ransomware attacks. The generation AI also references a database of fraud techniques that is updated in real time and generates fraudulent emails based on that information. For example, it creates emails incorporating newly reported fraud techniques. This allows the generation of fraudulent emails that correspond to the latest fraud techniques, thereby improving the player's learning effect.

[0032] The generation AI can generate scam emails in different languages ​​and cultures, developing the ability to respond to international scam techniques. For example, the generation AI can generate scam emails in different languages, allowing players to respond to scam techniques in multiple languages. For example, it can create scam emails in English, Spanish, Chinese, etc. The generation AI can also learn about scam techniques in different cultures and generate scam emails based on that information. For example, it can create emails that incorporate scam techniques unique to a particular culture. The generation AI can also refer to a database of international scam techniques and generate scam emails based on that information. For example, it can create emails that incorporate scam techniques reported in different countries. This allows players to develop the ability to respond to scam techniques in different languages ​​and cultures.

[0033] The generation AI can also simulate voice scams and phishing sites, enabling it to handle fraud methods other than email. For example, the generation AI can simulate voice scams to help players develop their ability to respond to phone scams. For example, it can play back the scammer's voice and analyze its content. The generation AI can also simulate phishing sites to help players develop their ability to respond to fake sites. For example, it can display a fake login page and learn its characteristics. The generation AI can also simulate fraud methods other than email, enabling players to handle a variety of fraud methods. For example, it can perform simulations that incorporate SMS scams and social media scams. This makes it possible to handle fraud methods other than email.

[0034] The investigation unit allows the generation AI to provide detailed background information and past cases for the area the player taps. For example, when a player taps on the sender address of an email, the generation AI displays detailed background information about that address. For example, it provides information such as, "This address has been reported as a scam email in the past." When a player taps on a linked URL, the generation AI displays past cases related to that URL. For example, it provides information such as, "This URL has been reported as a phishing site." When a player taps on a specific phrase in the body of the email, the generation AI displays detailed background information about that phrase. For example, it provides information such as, "This phrase is a technique often used in scam emails." This allows for the accuracy of investigations to be improved by providing detailed background information and past cases for the area the player taps on.

[0035] In the investigation section, the generation AI can provide hints and advice in real time as the player proceeds with their investigation. For example, as the player proceeds with their investigation of an email, the generation AI provides hints in real time. For example, it displays advice such as "Check the sender address." In addition, as the player investigates a linked URL, the generation AI provides advice in real time. For example, it displays a warning such as "This URL may lead to an unknown site." In addition, as the player investigates the content of the text, the generation AI provides hints in real time. For example, it displays information such as "This phrase is a technique commonly used in fraudulent emails." This allows the accuracy of the investigation to be improved by providing hints and advice in real time as the player proceeds with their investigation.

[0036] The investigation department can expand the scope of its investigations to include not only emails but also messages on social media and chat apps. For example, the investigation department will expand the scope of its investigations to include not only emails but also messages on social media. For example, it will include messages on Facebook and Twitter. It will also expand the scope of its investigations to include messages on chat apps. For example, it will include messages on WhatsApp and LINE. It will also expand the scope of its investigations to include a variety of message formats, allowing players to respond to a variety of fraudulent methods. For example, it will include SMS and instant messages. By expanding the scope of its investigations, it will allow players to respond to a variety of fraudulent methods.

[0037] The judgment unit allows the generation AI to simulate multiple scenarios and suggest the optimal decision before the player makes a decision. For example, before the player makes a decision about an email, the generation AI simulates multiple scenarios and suggests the optimal decision. For example, it makes a suggestion such as, "It is best to ignore this email." Also, before the player makes a decision about a linked URL, the generation AI simulates multiple scenarios and suggests the optimal decision. For example, it makes a suggestion such as, "It is better not to click on this URL." Also, before the player makes a decision about the content of the text, the generation AI simulates multiple scenarios and suggests the optimal decision. For example, it makes a suggestion such as, "This phrase is likely to be a scam." This allows the accuracy of judgment to be improved by suggesting the optimal decision before the player makes a decision.

[0038] The judgment unit can add a function that allows a player to refer to the judgment results and feedback of other players when making a judgment. For example, the judgment unit adds a function that allows a player to refer to the judgment results of other players when making a judgment about an email. For example, it displays information such as "Other players have judged this email to be a scam." Furthermore, when a player makes a judgment about a linked URL, it adds a function that allows a player to refer to the feedback of other players. For example, it displays information such as "Other players have judged this URL as not being a scam." Furthermore, when a player makes a judgment about the content of the text, it adds a function that allows a player to refer to the judgment results and feedback of other players. For example, it displays information such as "Other players have judged this phrase to be a scam." This allows a player to refer to the judgment results and feedback of other players, thereby improving the accuracy of their judgment.

[0039] The judgment unit can expand the object of judgment to include not only email but also fraud methods such as telephone and door-to-door sales. For example, the judgment unit expands the object of judgment to not only email but also telephone fraud. For example, a telephone fraud scenario is simulated and the player makes the judgment. The object of judgment can also be expanded to door-to-door sales fraud. For example, a door-to-door sales scenario is simulated and the player makes the judgment. The object of judgment can also be expanded to a variety of fraud methods, allowing the player to respond to a variety of fraud methods. For example, SMS fraud and social media fraud can be included as objects of judgment. In this way, by expanding the object of judgment, the player can respond to a variety of fraud methods.

[0040] The evaluation unit can use the generation AI to analyze a player's past performance data and provide optimized feedback to each individual player. For example, the evaluation unit uses the generation AI to analyze a player's past performance data and provide optimized feedback to each individual player. For example, the evaluation unit displays feedback such as, "You have overlooked this type of fraud in the past. Be careful." Based on the player's past performance data, the generation AI also suggests specific areas for improvement. For example, it provides advice such as, "Check the URLs you link to more carefully." The generation AI also analyzes a player's past performance data and provides an optimized learning plan for each individual player. For example, it suggests, "Next time, play a scenario that specializes in phishing scams." This makes it possible to improve learning effectiveness by analyzing a player's past performance data and providing optimized feedback.

[0041] The evaluation unit can use the generation AI to analyze the reasons for the player's decisions and suggest specific areas for improvement. For example, the evaluation unit uses the generation AI to analyze the reasons for the player's decisions and suggest specific areas for improvement. For example, it provides feedback such as, "You didn't check the sender address enough. Be more careful next time." The generation AI also suggests detailed areas for improvement based on the player's reasons for decisions. For example, it provides advice such as, "You didn't check the destination URL enough. Be sure to check the URL domain next time." The generation AI also analyzes the reasons for the player's decisions and suggests specific areas for improvement. For example, it provides feedback such as, "You didn't check the content of the text enough. Be careful to use unnatural phrases next time." In this way, by analyzing the reasons for the player's decisions and suggesting specific areas for improvement, the learning effect can be enhanced.

[0042] The evaluation unit can provide feedback not only in the form of email, but also in the form of messages on social media or chat apps. For example, the evaluation unit can provide feedback not only in the form of email, but also in the form of messages on social media. For example, the evaluation unit can provide feedback as messages on Facebook or Twitter. The evaluation unit can also provide feedback in the form of messages on chat apps. For example, the evaluation unit can provide feedback as messages on WhatsApp or LINE. The evaluation unit can also provide feedback in a variety of message formats, allowing players to receive feedback on a variety of platforms. For example, the evaluation unit can provide feedback as an SMS or an instant message. In this way, by providing feedback in a variety of message formats, it is possible to allow players to receive feedback on a variety of platforms.

[0043] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0044] In simulation games, the AI ​​can provide hints and advice in real time as players investigate scam emails. For example, when a player checks the sender address of an email, it displays information such as "This address has been reported as a scam email in the past." When a player investigates the destination URL, it displays a warning such as "This URL has been reported as a phishing site." Furthermore, when a player investigates a specific phrase in the body of the email, it provides information such as "This phrase is a technique commonly used in scam emails." This allows the AI ​​to provide hints and advice in real time as the player progresses with their investigation, improving the accuracy of their investigation.

[0045] Simulation games can add a feature that allows players to refer to the judgments and feedback of other players when judging whether an email is fraudulent. For example, when a player judges an email, information such as "Other players have judged this email to be fraudulent" can be displayed. Also, when a player judges a linked URL, information such as "Other players have judged this URL as not being fraudulent" can be displayed. Furthermore, when a player judges the content of the text, information such as "Other players have judged this phrase to be fraudulent" can be displayed. This allows players to refer to the judgments and feedback of other players, improving the accuracy of their judgments.

[0046] In simulation games, when players investigate fraudulent emails, the AI ​​generator can provide them with detailed background information and past examples. For example, if a player taps on the sender address of an email, the AI ​​displays information such as "This address has been reported as a fraudulent email in the past." If the player taps on a linked URL, the AI ​​displays information such as "This URL has been reported as a phishing site." Furthermore, if the player taps on a specific phrase in the body of the email, the AI ​​displays information such as "This phrase is a commonly used technique in fraudulent emails." This allows the AI ​​to improve the accuracy of the investigation by providing detailed background information and past examples for the area the player taps on.

[0047] In the simulation game, when the player judges whether an email is fraudulent, the generative AI can simulate multiple scenarios and suggest the optimal decision. For example, before the player makes a judgment about the email, it makes a suggestion such as "It is best to ignore this email." Also, before the player judges the destination URL, it makes a suggestion such as "It is better not to click on this URL." Furthermore, before the player judges the content of the text, it makes a suggestion such as "This phrase is likely to be fraudulent." This allows the player to make optimal decisions before they make them, improving the accuracy of their judgments.

[0048] In simulation games, the AI ​​can provide hints and advice in real time as players investigate scam emails. For example, when a player checks the sender address of an email, it displays information such as "This address has been reported as a scam email in the past." When a player investigates the destination URL, it displays a warning such as "This URL has been reported as a phishing site." Furthermore, when a player investigates a specific phrase in the body of the email, it provides information such as "This phrase is a technique commonly used in scam emails." This allows the AI ​​to provide hints and advice in real time as the player progresses with their investigation, improving the accuracy of their investigation.

[0049] Simulation games can add a feature that allows players to refer to the judgments and feedback of other players when judging whether an email is fraudulent. For example, when a player judges an email, information such as "Other players have judged this email to be fraudulent" can be displayed. Also, when a player judges a linked URL, information such as "Other players have judged this URL as not being fraudulent" can be displayed. Furthermore, when a player judges the content of the text, information such as "Other players have judged this phrase to be fraudulent" can be displayed. This allows players to refer to the judgments and feedback of other players, improving the accuracy of their judgments.

[0050] In simulation games, when players investigate fraudulent emails, the AI ​​generator can provide them with detailed background information and past examples. For example, if a player taps on the sender address of an email, the AI ​​displays information such as "This address has been reported as a fraudulent email in the past." If the player taps on a linked URL, the AI ​​displays information such as "This URL has been reported as a phishing site." Furthermore, if the player taps on a specific phrase in the body of the email, the AI ​​displays information such as "This phrase is a commonly used technique in fraudulent emails." This allows the AI ​​to improve the accuracy of the investigation by providing detailed background information and past examples for the area the player taps on.

[0051] The processing flow of the first embodiment will be briefly explained below.

[0052] Step 1: The generative AI generates virtual fraudulent emails. For example, the generative AI can learn the characteristics of fraudulent emails and generate realistic fraudulent emails. For example, the generative AI uses models such as GPT-3 or BERT to generate fraudulent emails. Step 2: The investigation department investigates the virtual fraudulent email generated by the generation AI. For example, the player checks the sender address, destination URL, and content of the email. The investigation department, for example, analyzes the email header information and verifies the links. Step 3: The Judgment Department determines whether the email is fraudulent based on the content investigated by the Investigation Department. For example, the player will make a comprehensive judgment based on information such as whether the sender address is suspicious, whether the link leads to an unknown site, or whether the content of the text is unnatural. Step 4: The evaluation unit evaluates the results of the judgment unit and provides feedback. For example, the generation AI analyzes the points where the player tapped and the judgment content, and gives a score depending on the points where it was able to determine fraud.

[0053] (Example 2) The simulation game according to an embodiment of the present invention is a system that supports elderly people in identifying signs of fraud in email content and learning how to deal with the situation. This system involves players receiving virtual fraudulent emails created by a generative AI, investigating them, making judgments, and providing evaluations and feedback. This simulation game allows elderly people to identify signs of fraudulent emails and learn how to deal with them.

[0054] A simulation game according to an embodiment includes a generation AI, an investigation unit, a judgment unit, and an evaluation unit. The generation AI generates virtual scam emails. For example, the generation AI can learn the characteristics of scam emails and generate realistic scam emails. The generation AI generates scam emails using models such as GPT-3 and BERT. The investigation unit investigates the virtual scam emails generated by the generation AI. For example, a player checks the sender address, destination URL, and body content of the email. The investigation unit analyzes the email's header information and verifies the links. The judgment unit determines whether the email is scam based on the information investigated by the investigation unit. For example, the player comprehensively determines whether the sender address is suspicious, whether the link leads to an unknown site, or whether the body content is unnatural. The evaluation unit evaluates the judgment results and provides feedback. For example, the generation AI analyzes the areas tapped by the player and the judgment, and scores the areas where it was able to determine scams. This allows the simulation game according to an embodiment to help elderly people identify signs of scam emails and learn how to deal with them.

[0055] The generation AI can analyze a player's past game data and generate scam emails optimized for each individual player. For example, the generation AI can analyze a player's past game data and generate emails containing scam characteristics that the player missed in the past. For example, it can create emails containing specific phrases and link formats. The generation AI can also use the player's past game data to generate emails containing the scam techniques that the player is most difficult to perpetrate. For example, it can create emails containing phishing scams and fake invoices. The generation AI can also analyze a player's past game data and avoid the scam techniques that the player has previously scored high on, generating more difficult scam emails. For example, it can create emails containing cleverly disguised sender addresses and links. This allows the system to generate scam emails optimized for each player, thereby improving its learning effect.

[0056] The generation AI learns the latest fraud techniques in real time and can constantly generate new fraudulent emails. For example, the generation AI automatically collects the latest fraud techniques on the Internet and generates new fraudulent emails based on that information. For example, it creates emails incorporating newly discovered phishing techniques. The generation AI also learns the latest fraud techniques from security research institutes and news sites and generates fraudulent emails based on that information. For example, it creates emails that imitate the latest ransomware attacks. The generation AI also references a database of fraud techniques that is updated in real time and generates fraudulent emails based on that information. For example, it creates emails incorporating newly reported fraud techniques. This allows the generation of fraudulent emails that correspond to the latest fraud techniques, thereby improving the player's learning effect.

[0057] The generation AI can use its emotion estimation function to generate scam emails of a difficulty level that corresponds to the player's emotional state. For example, the generation AI analyzes the player's facial expressions and voice, and generates scam emails of a higher difficulty level if the player is relaxed. For example, it creates emails with complex link structures and clever sender addresses. It also uses its emotion estimation function to generate scam emails of a lower difficulty level if the player is stressed. For example, it creates emails with clearly suspicious phrases and links. It also adjusts the content of the scam email according to the player's emotional state. For example, if the player is concentrating, it generates emails with more sophisticated scamming techniques. This allows the AI ​​to generate scam emails of a higher difficulty level that correspond to the player's emotional state, thereby enhancing the learning effect.

[0058] The generation AI can generate scam emails in different languages ​​and cultures, developing the ability to respond to international scam techniques. For example, the generation AI can generate scam emails in different languages, allowing players to respond to scam techniques in multiple languages. For example, it can create scam emails in English, Spanish, Chinese, etc. The generation AI can also learn about scam techniques in different cultures and generate scam emails based on that information. For example, it can create emails that incorporate scam techniques unique to a particular culture. The generation AI can also refer to a database of international scam techniques and generate scam emails based on that information. For example, it can create emails that incorporate scam techniques reported in different countries. This allows players to develop the ability to respond to scam techniques in different languages ​​and cultures.

[0059] The generation AI can also simulate voice scams and phishing sites, enabling it to handle fraud methods other than email. For example, the generation AI can simulate voice scams to help players develop their ability to respond to phone scams. For example, it can play back the scammer's voice and analyze its content. The generation AI can also simulate phishing sites to help players develop their ability to respond to fake sites. For example, it can display a fake login page and learn its characteristics. The generation AI can also simulate fraud methods other than email, enabling players to handle a variety of fraud methods. For example, it can perform simulations that incorporate SMS scams and social media scams. This makes it possible to handle fraud methods other than email.

[0060] The generation AI uses its emotion estimation function to generate scam emails that will make players most wary, thereby increasing their vigilance against actual scams. For example, the generation AI uses its emotion estimation function to generate scam emails that will make players most wary. For example, it creates emails with content and formats that make players feel uneasy. The generation AI also analyzes the player's emotional state to generate scam emails that will increase players' vigilance. For example, it creates emails that emphasize urgency and include phrases that stir anxiety. The generation AI also adjusts scam emails to increase vigilance based on the player's emotional response. For example, it generates emails that incorporate elements that make players feel most uneasy. This increases players' vigilance, thereby improving their ability to respond to actual scams.

[0061] The investigation unit allows the generation AI to provide detailed background information and past cases for the area the player taps. For example, when a player taps on the sender address of an email, the generation AI displays detailed background information about that address. For example, it provides information such as, "This address has been reported as a scam email in the past." When a player taps on a linked URL, the generation AI displays past cases related to that URL. For example, it provides information such as, "This URL has been reported as a phishing site." When a player taps on a specific phrase in the body of the email, the generation AI displays detailed background information about that phrase. For example, it provides information such as, "This phrase is a technique often used in scam emails." This allows for the accuracy of investigations to be improved by providing detailed background information and past cases for the area the player taps on.

[0062] In the investigation section, the generation AI can provide hints and advice in real time as the player proceeds with their investigation. For example, as the player proceeds with their investigation of an email, the generation AI provides hints in real time. For example, it displays advice such as "Check the sender address." In addition, as the player investigates a linked URL, the generation AI provides advice in real time. For example, it displays a warning such as "This URL may lead to an unknown site." In addition, as the player investigates the content of the text, the generation AI provides hints in real time. For example, it displays information such as "This phrase is a technique commonly used in fraudulent emails." This allows the accuracy of the investigation to be improved by providing hints and advice in real time as the player proceeds with their investigation.

[0063] The investigation unit can use the emotion estimation function to display a support message to alleviate the player's anxiety or doubt. For example, the investigation unit uses the emotion estimation function to display a support message when the player is feeling anxious. For example, it displays a message such as "Please remain calm and proceed with the investigation." Also, it uses the emotion estimation function to display a support message when the player is feeling doubtful. For example, it displays a message such as "This email may be a scam. Please investigate carefully." Also, it uses the emotion estimation function to display a support message to alleviate the player's anxiety. For example, it displays advice such as "Let's check the characteristics of this email." In this way, by displaying a support message to alleviate the player's anxiety or doubt, the accuracy of the investigation can be improved.

[0064] The investigation department can expand the scope of its investigations to include not only emails but also messages on social media and chat apps. For example, the investigation department will expand the scope of its investigations to include not only emails but also messages on social media. For example, it will include messages on Facebook and Twitter. It will also expand the scope of its investigations to include messages on chat apps. For example, it will include messages on WhatsApp and LINE. It will also expand the scope of its investigations to include a variety of message formats, allowing players to respond to a variety of fraudulent methods. For example, it will include SMS and instant messages. By expanding the scope of its investigations, it will allow players to respond to a variety of fraudulent methods.

[0065] The research unit can use the emotion estimation function to identify the part where the player feels most anxious and provide special support for that part. For example, the research unit can use the emotion estimation function to identify the part where the player feels most anxious and provide special support for that part. For example, the research unit can display a warning such as "This link may lead to an unknown site." The research unit can also identify the part where the player feels anxious and provide detailed information about that part. For example, the research unit can display information such as "This sender address has been reported as a scam email in the past." The research unit can also use the emotion estimation function to display a special support message for the part where the player feels most anxious. For example, the research unit can display a message such as "This phrase is a technique often used in scam emails. Please investigate carefully." This can improve the accuracy of the research by providing special support for the part where the player feels most anxious.

[0066] The judgment unit allows the generation AI to simulate multiple scenarios and suggest the optimal decision before the player makes a decision. For example, before the player makes a decision about an email, the generation AI simulates multiple scenarios and suggests the optimal decision. For example, it makes a suggestion such as, "It is best to ignore this email." Also, before the player makes a decision about a linked URL, the generation AI simulates multiple scenarios and suggests the optimal decision. For example, it makes a suggestion such as, "It is better not to click on this URL." Also, before the player makes a decision about the content of the text, the generation AI simulates multiple scenarios and suggests the optimal decision. For example, it makes a suggestion such as, "This phrase is likely to be a scam." This allows the accuracy of judgment to be improved by suggesting the optimal decision before the player makes a decision.

[0067] The judgment unit can use the emotion estimation function to measure the player's confidence level and provide additional support if the player's confidence is low. For example, the judgment unit can use the emotion estimation function to measure the player's confidence level and provide additional support if the player's confidence is low. For example, the judgment unit can display a message such as, "It seems you are not confident in your judgment of this email. Please check the detailed information." The judgment unit can also measure the player's confidence level and provide additional advice if the player's confidence is low. For example, the judgment unit can display advice such as, "This link may lead to an unknown site. Please use caution." The judgment unit can also measure the player's confidence level and display a special support message if the player's confidence is low. For example, the judgment unit can display a message such as, "This phrase is a common technique used in scam emails. Please use caution." This can improve the accuracy of judgment by measuring the player's confidence level and providing additional support if the player's confidence is low.

[0068] The judgment unit can add a function that allows a player to refer to the judgment results and feedback of other players when making a judgment. For example, the judgment unit adds a function that allows a player to refer to the judgment results of other players when making a judgment about an email. For example, it displays information such as "Other players have judged this email to be a scam." Furthermore, when a player makes a judgment about a linked URL, it adds a function that allows a player to refer to the feedback of other players. For example, it displays information such as "Other players have judged this URL as not being a scam." Furthermore, when a player makes a judgment about the content of the text, it adds a function that allows a player to refer to the judgment results and feedback of other players. For example, it displays information such as "Other players have judged this phrase to be a scam." This allows a player to refer to the judgment results and feedback of other players, thereby improving the accuracy of their judgment.

[0069] The judgment unit can expand the object of judgment to include not only email but also fraud methods such as telephone and door-to-door sales. For example, the judgment unit expands the object of judgment to not only email but also telephone fraud. For example, a telephone fraud scenario is simulated and the player makes the judgment. The object of judgment can also be expanded to door-to-door sales fraud. For example, a door-to-door sales scenario is simulated and the player makes the judgment. The object of judgment can also be expanded to a variety of fraud methods, allowing the player to respond to a variety of fraud methods. For example, SMS fraud and social media fraud can be included as objects of judgment. In this way, by expanding the object of judgment, the player can respond to a variety of fraud methods.

[0070] The judgment unit can use the emotion estimation function to identify the decision points at which the player feels the most anxious and provide special support for those points. For example, the judgment unit uses the emotion estimation function to identify the decision points at which the player feels the most anxious and provide special support for those points. For example, the judgment unit displays a warning such as "This link may lead to an unknown site." The judgment unit also identifies the decision points at which the player feels anxious and provides detailed information about those points. For example, the judgment unit displays information such as "This sender address has been reported as a scam email in the past." The judgment unit also uses the emotion estimation function to display a special support message for the decision points at which the player feels the most anxious. For example, the judgment unit displays a message such as "This phrase is a technique often used in scam emails. Please make your decision carefully." By providing special support for the decision points at which the player feels the most anxious, the accuracy of judgment can be improved.

[0071] The evaluation unit can use the generation AI to analyze a player's past performance data and provide optimized feedback to each individual player. For example, the evaluation unit uses the generation AI to analyze a player's past performance data and provide optimized feedback to each individual player. For example, the evaluation unit displays feedback such as, "You have overlooked this type of fraud in the past. Be careful." Based on the player's past performance data, the generation AI also suggests specific areas for improvement. For example, it provides advice such as, "Check the URLs you link to more carefully." The generation AI also analyzes a player's past performance data and provides an optimized learning plan for each individual player. For example, it suggests, "Next time, play a scenario that specializes in phishing scams." This makes it possible to improve learning effectiveness by analyzing a player's past performance data and providing optimized feedback.

[0072] The evaluation unit can use the generation AI to analyze the reasons for the player's decisions and suggest specific areas for improvement. For example, the evaluation unit uses the generation AI to analyze the reasons for the player's decisions and suggest specific areas for improvement. For example, it provides feedback such as, "You didn't check the sender address enough. Be more careful next time." The generation AI also suggests detailed areas for improvement based on the player's reasons for decisions. For example, it provides advice such as, "You didn't check the destination URL enough. Be sure to check the URL domain next time." The generation AI also analyzes the reasons for the player's decisions and suggests specific areas for improvement. For example, it provides feedback such as, "You didn't check the content of the text enough. Be careful to use unnatural phrases next time." In this way, by analyzing the reasons for the player's decisions and suggesting specific areas for improvement, the learning effect can be enhanced.

[0073] The evaluation unit uses the emotion estimation function to provide feedback according to the player's emotional state, thereby increasing their motivation to learn. The evaluation unit, for example, uses the emotion estimation function to provide feedback according to the player's emotional state. For example, if the player is feeling anxious, a message such as "Try to play more relaxedly next time" is displayed. In addition, based on the player's emotional state, the generation AI provides feedback to increase their motivation to learn. For example, if the player is confident, a message such as "That was a great decision. Let's keep it up" is displayed. In addition, the emotion estimation function is used to provide feedback according to the player's emotional state, thereby increasing their motivation to learn. For example, if the player is feeling stressed, a suggestion such as "Let's start with an easier scenario next time" is displayed. In this way, by providing feedback according to the player's emotional state, it is possible to increase their motivation to learn.

[0074] The evaluation unit can provide feedback not only in the form of email, but also in the form of messages on social media or chat apps. For example, the evaluation unit can provide feedback not only in the form of email, but also in the form of messages on social media. For example, the evaluation unit can provide feedback as messages on Facebook or Twitter. The evaluation unit can also provide feedback in the form of messages on chat apps. For example, the evaluation unit can provide feedback as messages on WhatsApp or LINE. The evaluation unit can also provide feedback in a variety of message formats, allowing players to receive feedback on a variety of platforms. For example, the evaluation unit can provide feedback as an SMS or an instant message. In this way, by providing feedback in a variety of message formats, it is possible to allow players to receive feedback on a variety of platforms.

[0075] The evaluation unit uses the emotion estimation function to provide feedback that will inspire the player with the most positive emotions, further increasing their motivation to learn. The evaluation unit, for example, uses the emotion estimation function to provide feedback that will inspire the player with the most positive emotions. For example, it displays a message such as, "Great decision. Let's keep it up." The generation AI also provides positive feedback based on the player's emotional state. For example, if the player is confident, it displays a message such as, "Your decision is accurate. Let's move on to the next level." The emotion estimation function also provides feedback that will inspire the player with the most positive emotions, further increasing their motivation to learn. For example, if the player feels a sense of accomplishment, it displays a message such as, "Your score is great. Let's do our best on the next challenge." This allows the evaluation unit to provide feedback that will inspire the player with the most positive emotions, further increasing their motivation to learn.

[0076] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0077] In simulation games, the AI ​​can provide hints and advice in real time as players investigate scam emails. For example, when a player checks the sender address of an email, it displays information such as "This address has been reported as a scam email in the past." When a player investigates the destination URL, it displays a warning such as "This URL has been reported as a phishing site." Furthermore, when a player investigates a specific phrase in the body of the email, it provides information such as "This phrase is a technique commonly used in scam emails." This allows the AI ​​to provide hints and advice in real time as the player progresses with their investigation, improving the accuracy of their investigation.

[0078] Simulation games can add a feature that allows players to refer to the judgments and feedback of other players when judging whether an email is fraudulent. For example, when a player judges an email, information such as "Other players have judged this email to be fraudulent" can be displayed. Also, when a player judges a linked URL, information such as "Other players have judged this URL as not being fraudulent" can be displayed. Furthermore, when a player judges the content of the text, information such as "Other players have judged this phrase to be fraudulent" can be displayed. This allows players to refer to the judgments and feedback of other players, improving the accuracy of their judgments.

[0079] In simulation games, when players investigate fraudulent emails, the AI ​​generator can provide them with detailed background information and past examples. For example, if a player taps on the sender address of an email, the AI ​​displays information such as "This address has been reported as a fraudulent email in the past." If the player taps on a linked URL, the AI ​​displays information such as "This URL has been reported as a phishing site." Furthermore, if the player taps on a specific phrase in the body of the email, the AI ​​displays information such as "This phrase is a commonly used technique in fraudulent emails." This allows the AI ​​to improve the accuracy of the investigation by providing detailed background information and past examples for the area the player taps on.

[0080] In the simulation game, when the player judges whether an email is fraudulent, the generative AI can simulate multiple scenarios and suggest the optimal decision. For example, before the player makes a judgment about the email, it makes a suggestion such as "It is best to ignore this email." Also, before the player judges the destination URL, it makes a suggestion such as "It is better not to click on this URL." Furthermore, before the player judges the content of the text, it makes a suggestion such as "This phrase is likely to be fraudulent." This allows the player to make optimal decisions before they make them, improving the accuracy of their judgments.

[0081] When a player investigates a fraudulent email, the simulation game can use the emotion estimation function to display support messages to alleviate the player's anxiety and doubt. For example, if the player feels anxious, a message such as "Remain calm and continue your investigation" is displayed. Alternatively, if the player feels suspicious, a message such as "This email may be fraudulent. Please investigate carefully" is displayed. Furthermore, advice such as "Let's check the characteristics of this email" is displayed to alleviate the player's anxiety. In this way, by displaying support messages to alleviate the player's anxiety and doubt, the accuracy of the investigation can be improved.

[0082] When a player judges a scam email, the simulation game uses emotion estimation to measure the player's confidence and can provide additional support if the player's confidence is low. For example, it displays a message such as, "It seems you are not confident in judging this email. Please check the detailed information." The simulation game also measures the player's confidence and provides additional advice if the player's confidence is low. For example, it displays advice such as, "This link may lead to an unknown site. Please use caution." Furthermore, it measures the player's confidence and displays a special support message if the player's confidence is low. For example, it displays a message such as, "This phrase is a common technique used in scam emails. Please use caution." This allows the game to measure the player's confidence and provide additional support if the player's confidence is low, thereby improving the accuracy of their judgment.

[0083] When a player investigates a scam email, the simulation game can use emotion estimation to identify the parts that make the player feel most anxious and provide special support for those parts. For example, a warning such as "This link may lead to an unknown site" can be displayed. The simulation game can also identify the parts that make the player feel anxious and provide detailed information about those parts. For example, it can display information such as "This sender address has been reported as a scam email in the past." Furthermore, it can display special support messages for the parts that make the player feel most anxious. For example, it can display a message such as "This phrase is a common technique used in scam emails. Please investigate carefully." This can improve the accuracy of the investigation by providing special support for the parts that make the player feel most anxious.

[0084] In simulation games, the AI ​​can provide hints and advice in real time as players investigate scam emails. For example, when a player checks the sender address of an email, it displays information such as "This address has been reported as a scam email in the past." When a player investigates the destination URL, it displays a warning such as "This URL has been reported as a phishing site." Furthermore, when a player investigates a specific phrase in the body of the email, it provides information such as "This phrase is a technique commonly used in scam emails." This allows the AI ​​to provide hints and advice in real time as the player progresses with their investigation, improving the accuracy of their investigation.

[0085] Simulation games can add a feature that allows players to refer to the judgments and feedback of other players when judging whether an email is fraudulent. For example, when a player judges an email, information such as "Other players have judged this email to be fraudulent" can be displayed. Also, when a player judges a linked URL, information such as "Other players have judged this URL as not being fraudulent" can be displayed. Furthermore, when a player judges the content of the text, information such as "Other players have judged this phrase to be fraudulent" can be displayed. This allows players to refer to the judgments and feedback of other players, improving the accuracy of their judgments.

[0086] In simulation games, when players investigate fraudulent emails, the AI ​​generator can provide them with detailed background information and past examples. For example, if a player taps on the sender address of an email, the AI ​​displays information such as "This address has been reported as a fraudulent email in the past." If the player taps on a linked URL, the AI ​​displays information such as "This URL has been reported as a phishing site." Furthermore, if the player taps on a specific phrase in the body of the email, the AI ​​displays information such as "This phrase is a commonly used technique in fraudulent emails." This allows the AI ​​to improve the accuracy of the investigation by providing detailed background information and past examples for the area the player taps on.

[0087] The processing flow of the second embodiment will be briefly explained below.

[0088] Step 1: The generative AI generates virtual fraudulent emails. For example, the generative AI can learn the characteristics of fraudulent emails and generate realistic fraudulent emails. For example, the generative AI uses models such as GPT-3 or BERT to generate fraudulent emails. Step 2: The investigation department investigates the virtual fraudulent email generated by the generation AI. For example, the player checks the sender address, destination URL, and content of the email. The investigation department, for example, analyzes the email header information and verifies the links. Step 3: The Judgment Department determines whether the email is fraudulent based on the content investigated by the Investigation Department. For example, the player will make a comprehensive judgment based on information such as whether the sender address is suspicious, whether the link leads to an unknown site, or whether the content of the text is unnatural. Step 4: The evaluation unit evaluates the results of the judgment unit and provides feedback. For example, the generation AI analyzes the points where the player tapped and the judgment content, and gives a score depending on the points where it was able to determine fraud.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0093] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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).

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0102] 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. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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).

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0117] In the headset type terminal 314, 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 headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0133] In the robot 414, 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. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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."

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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]

[0156] 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 generation AI that generates virtual fraudulent emails using a generation AI; An investigation department that investigates the virtual fraudulent emails generated by the generation AI; a determination unit that determines whether the email is fraudulent based on the content investigated by the investigation unit; an evaluation unit that evaluates the result determined by the determination unit and provides feedback; A system characterized by:

2. The generated AI is Analyzes the player's past game data and generates the scam emails optimized for each individual player.

2. The system of claim 1.

3. The generated AI is Learns the latest fraud techniques in real time and constantly generates new fraudulent emails 2. The system of claim 1.

4. The generated AI is Generate the fraudulent email with a difficulty level that corresponds to the player's emotional state 2. The system of claim 1.

5. The generated AI is Generate fraudulent emails in different languages ​​and cultures to develop the ability to respond to international fraud techniques.

2. The system of claim 1.

6. The generated AI is We will also conduct simulations of voice fraud and phishing sites to enable us to respond to fraud methods other than email.

2. The system of claim 1.

7. The generated AI is Generate the scam email that will most likely make players wary, and increase their vigilance against actual scams 2. The system of claim 1.

8. The research department When the player taps on something, the generative AI provides detailed background information and past examples.

2. The system of claim 1.

Images