system

Abstract

The system according to this embodiment aims to analyze the content of conversations on social media and issue a warning to the user if there is a high possibility of fraud. [Solution] The system according to the embodiment comprises an analysis unit, a warning unit, and an advice unit. The analysis unit analyzes the content of the conversation in real time. The warning unit issues a warning to the user if the analysis unit detects a high probability of fraud. The advice unit provides advice to the user who has received a warning from the warning unit to improve their financial literacy.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, it is difficult to prevent damage caused by investment fraud using SNS, and users with low financial literacy are at risk of being defrauded.

[0005] The system according to the embodiment aims to analyze the talk content on SNS and issue a warning to the user when the possibility of fraud is high.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, a warning unit, and an advice unit. The analysis unit analyzes the content of the conversation in real time. The warning unit issues a warning to the user if the analysis unit detects a high probability of fraud. The advice unit provides advice to the user who has received a warning from the warning unit to improve their financial literacy. [Effects of the Invention]

[0007] The system according to this embodiment can analyze the content of conversations on social media and issue a warning to the user if there is a high possibility of fraud. [Brief explanation of the drawing]

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

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

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

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

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

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

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

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

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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

[0028] (Example of form 1) The fraud prevention system according to an embodiment of the present invention is a system for addressing the increase in investment fraud using social networking services (SNS). This fraud prevention system uses a generating AI to analyze the content of messages in a messaging app and issues a warning to the user if there is a high probability of fraud. First, when a user initiates a message in a messaging app, the content is analyzed in real time by the generating AI. The generating AI detects keywords and phrases that have characteristics of fraud, and if it determines that there is a high probability of fraud, it issues a warning to the user. This mechanism allows even users with low financial literacy to spot fraud and prevent them from becoming victims. For example, a user starts a message in a messaging app. Next, the generating AI analyzes the content of the message in real time. The generating AI detects keywords and phrases that have characteristics of fraud, and if it determines that there is a high probability of fraud, it issues a warning to the user. For example, if phrases such as "guaranteed high profits" or "transfer money to the designated account" are detected, the generating AI determines that there is a high probability of fraud and issues a warning to the user. This warning allows the user to recognize the risk of fraud and prevent them from becoming victims. The generating AI also provides advice to improve the user's financial literacy. For example, by providing information on basic investment knowledge and fraud tactics, users can develop the ability to spot scams themselves. In this way, utilizing generative AI can reduce the damage caused by investment scams using social media. As a result, the fraud prevention system can analyze the user's chat content in real time, issue warnings when there is a high probability of fraud, and provide advice to improve financial literacy, thereby preventing fraud before it occurs.

[0029] The fraud prevention system according to this embodiment comprises an analysis unit, a warning unit, and an advice unit. The analysis unit analyzes the content of the conversation in real time. The analysis unit analyzes the content of the conversation using, for example, a generation AI and detects keywords and phrases that have characteristics of fraud. The analysis unit can detect phrases such as, for example, "guaranteeing high profits" or "transfer money to the designated account." The analysis unit can also learn from past fraud cases using the generation AI and detect keywords and phrases that have characteristics of fraud. The warning unit issues a warning to the user if the analysis unit has detected a high probability of fraud. The warning unit can issue a warning using, for example, a pop-up notification or a message. The warning unit can, for example, display a warning message on the user's screen. The warning unit can also issue a voice warning to the user. The advice unit provides advice to the user who has received a warning from the warning unit to improve their financial literacy. The advice unit can, for example, provide information on basic knowledge about investment and fraud methods. The advice unit can, for example, provide the user with basic knowledge about investment. The advice unit can also provide the user with information on fraud methods. As a result, the fraud prevention system according to this embodiment can prevent fraud by analyzing the user's chat content in real time, issuing a warning when there is a high possibility of fraud, and providing advice to improve financial literacy.

[0030] The analysis unit analyzes the content of conversations in real time. For example, the analysis unit uses generative AI to analyze the content of conversations and detect keywords and phrases that have characteristics of fraud. Specifically, the generative AI uses natural language processing technology to analyze the content of conversations in context and identify patterns that may indicate fraud. For example, it can detect phrases such as "guaranteed high profits" or "transfer money to the specified account." These phrases are extracted from past fraud cases, and the generative AI uses these cases as training data. The generative AI understands the context of the conversation content and can evaluate the likelihood of fraud based on the context, not just by matching keywords. For example, if the phrase "guaranteed high profits" is used, it analyzes the context before and after it to determine whether there is a high probability of fraud. The generative AI can also learn from past fraud cases and detect keywords and phrases that have characteristics of fraud. This allows the analysis unit to analyze the user's conversation content in real time and respond quickly if there is a high probability of fraud. Furthermore, the analysis unit can save the results of the conversation content analysis to a database, which can be used to improve the accuracy of analysis in the future. For example, by adding newly detected fraud patterns to the database and using them as training data for the generating AI, the accuracy of the analysis can be continuously improved. This makes the analysis unit a powerful tool for always responding to the latest fraud tactics and protecting users.

[0031] The warning unit issues a warning to the user when the analysis unit detects a high probability of fraud. The warning unit can issue warnings, for example, through pop-up notifications or messages. Specifically, it displays a warning message on the user's screen to inform them of the potential for fraud. The warning message includes the characteristics and specific phrases of the detected fraud, urging the user to pay immediate attention. The warning unit can also issue voice warnings to the user. For example, it can issue a voice warning such as "This may be a scam. Please be careful" through the speaker of a smartphone or computer. This allows the user to receive a warning even if they are not looking at the screen. Furthermore, the warning unit can customize the warning method according to the user's settings. For example, if the user has a visual impairment, it can be set to prioritize voice warnings. The warning unit can also provide the optimal warning method for the user by adjusting the frequency and content of warnings. For example, if the same fraud possibility is detected repeatedly, the content of the warning can be strengthened to give the user a stronger warning. In this way, the warning unit can provide users with quick and appropriate warnings and prevent them from becoming victims of fraud.

[0032] The Advice Department provides advice to users who have received warnings from the Warning Department to improve their financial literacy. For example, the Advice Department can provide information on basic investment knowledge and fraud tactics. Specifically, it can provide users with basic investment knowledge and explain the importance of safe investment methods and risk management. The Advice Department can also provide users with information on fraud tactics. For example, based on past fraud cases, it can explain common tactics and signs of fraud, encouraging users to be vigilant against fraud. Furthermore, the Advice Department can provide educational materials and resources to improve users' financial literacy. For example, it can provide online courses, webinars, articles, and videos to allow users to learn at their own pace. The Advice Department can also track users' learning progress and provide additional advice and resources as needed. This allows the Advice Department to support users in deepening their knowledge of fraud and enhancing their self-defense capabilities. Additionally, the Advice Department can collect feedback from users and continuously improve the content and methods of the advice it provides. For example, it can revise the advice based on feedback on topics of particular interest to users and parts they found difficult to understand, providing more effective information. This allows the advisory department to play a crucial role in supporting users' financial literacy and preventing fraud.

[0033] The analysis unit can detect keywords and phrases that have characteristics of fraud. For example, it can detect keywords and phrases such as "high profit guaranteed" or "limited-time opportunity." Furthermore, the analysis unit can use a generative AI to learn from past fraud cases and detect keywords and phrases that have characteristics of fraud. For example, the analysis unit can input past fraud cases into the generative AI and train it to recognize the characteristics of fraud. This allows for highly accurate determination of the likelihood of fraud by detecting keywords and phrases that have characteristics of fraud.

[0034] The warning unit can issue warnings to the user via pop-up notifications or messages. For example, the warning unit can display a warning message on the user's screen. It can also issue voice warnings to the user. For instance, the warning unit can display a pop-up notification on the user's smartphone to inform them of the risk of fraud. Furthermore, the warning unit can also issue warnings to the user via email or SMS. This allows for immediate notification of the risk of fraud by issuing warnings via pop-up notifications or messages.

[0035] The advisory department can provide information on basic investment knowledge and fraudulent practices. For example, the advisory department can provide users with basic investment knowledge. It can also provide users with information on fraudulent practices. For example, the advisory department can provide users with information on the basics of stock investing and the relationship between risk and return. Furthermore, the advisory department can provide users with information on fraudulent practices such as Ponzi schemes and phishing scams. By providing information on basic investment knowledge and fraudulent practices, the financial literacy of users can be improved.

[0036] The generative AI is equipped with a learning unit that learns from past fraud cases. The learning unit allows the generative AI to learn from past fraud cases. For example, the learning unit can collect fraud cases from the past five years and train the generative AI with them. The learning unit can also collect fraud cases limited to a specific industry and train the generative AI with them. For example, the learning unit can collect fraud cases in the financial industry and train the generative AI with them. Furthermore, the learning unit can train the generative AI on patterns of fraud cases. For example, the learning unit can train the generative AI on fraud methods and characteristics. In this way, the accuracy of the generative AI's analysis can be improved by learning from past fraud cases.

[0037] The system includes a notification section that specifies the method for issuing a warning. This notification section can indicate the specific method for issuing a warning. For example, it can indicate the timing and format of the warning. For example, the notification section can issue a warning while the user is in a conversation. It can also issue a warning after the user has ended a conversation. For example, the notification section can display a warning message immediately after the user ends a conversation. Furthermore, the notification section can send warnings to the user via email or SMS. For example, the notification section can display a pop-up notification on the user's smartphone to inform them of the risk of fraud. This allows for effective communication of warnings to users by clearly indicating the specific method for issuing them.

[0038] The system includes a response section that provides specific steps on how users who receive a warning can avoid fraud. The response section can provide specific steps on how users who receive a warning can avoid fraud. For example, the response section can provide step-by-step guidelines for avoiding fraud. For example, the response section can make users aware of the risk of fraud and provide specific avoidance steps. For example, the response section can explain the risk of fraud to users and provide specific steps to avoid fraud. Furthermore, the response section can explain fraudulent tactics to users and provide specific countermeasures to avoid fraud. For example, the response section can explain fraudulent tactics to users and provide specific countermeasures to avoid fraud. This ensures that users can respond appropriately by providing specific steps to avoid fraud.

[0039] The analysis unit can improve the accuracy of its analysis by referring to the user's past chat history when analyzing chat content. For example, if the user has a history of being scammed in the past, the generating AI can refer to that history and rigorously analyze similar chat content. Also, if the user has engaged in safe chats in the past, the generating AI can refer to that history and maintain normal analysis accuracy. Furthermore, if the user has frequently used certain keywords in the past, the generating AI can prioritize the analysis of those keywords. In this way, the accuracy of the analysis can be improved by referring to the user's past chat history. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's past chat history into the generating AI and have the generating AI perform the improvement of analysis accuracy.

[0040] The analysis unit, when analyzing the content of a conversation, can perform context-aware analysis in addition to detecting keywords and phrases that have characteristics of fraud. For example, the analysis unit can analyze conversation content containing the phrase "guaranteeing high profits" and determine the possibility of fraud from the context. It can also analyze conversation content containing the phrase "transfer money to the designated account" and determine the possibility of fraud from the context. Furthermore, it can analyze conversation content containing the phrase "gain large profits in a short period of time" and determine the possibility of fraud from the context. By performing context-aware analysis, the possibility of fraud can be determined more accurately. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the conversation content and its context into a generating AI and have the generating AI perform context-aware analysis.

[0041] The analysis unit can improve the accuracy of its analysis by considering the user's geographical location information when analyzing the content of a conversation. For example, if the user is in a specific region, the analysis unit can consider the characteristics of scams that frequently occur in that region. Also, if the user is traveling, the analysis unit can consider the scam risk in the travel destination. Furthermore, if the user is at home, the analysis unit can maintain normal analysis accuracy. This makes it possible to perform analysis that reflects region-specific scam risks by considering the user's geographical location information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's geographical location information into a generating AI and have the generating AI perform the task of improving the analysis accuracy.

[0042] The analysis unit can analyze the user's social media activity when analyzing the content of conversations and detect the characteristics of related scams. This allows for more accurate detection of scam characteristics by analyzing the user's social media activity. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's social media activity data into a generating AI and have the generating AI perform the detection of scam characteristics.

[0043] The warning unit can select the optimal warning method by referring to the user's past warning history when issuing a warning. For example, the warning unit can select the optimal warning method based on the user's past warning history. The warning unit can also issue similar warnings based on the content of warnings the user has received in the past. Furthermore, the warning unit can select the optimal warning method based on the user's response to past warnings. In this way, the optimal warning method can be selected by referring to the user's past warning history. Some or all of the above processing in the warning unit may be performed using AI, for example, or without using AI. For example, the warning unit can input the user's past warning history into a generating AI and have the generating AI select the optimal warning method.

[0044] The warning unit can generate different warning messages depending on the characteristics of the fraud when issuing a warning. For example, in the case of a fraud that guarantees high profits, the warning unit can generate a warning message that explains the specific risks. In the case of a fraud that requires users to transfer money to a designated account, the warning unit can generate a warning message that explains the risks of the transfer. Furthermore, in the case of a fraud that promises large profits in a short period of time, the warning unit can generate a warning message that explains the realistic risks. In this way, by generating warning messages that are tailored to the characteristics of the fraud, the warning unit can convey specific risks to the user. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the characteristics of the fraud into a generation AI and have the generation AI perform the generation of different warning messages.

[0045] The warning unit can select the optimal warning method by considering the user's device information when issuing a warning. For example, if the user is using a smartphone, the warning unit can issue a warning via a pop-up notification. If the user is using a tablet, the warning unit can issue a warning optimized for a larger screen. Furthermore, if the user is using a PC, the warning unit can issue a warning via a browser notification. This allows the system to select the optimal warning method by considering the user's device information. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the user's device information into a generating AI and have the generating AI select the optimal warning method.

[0046] The warning unit can analyze the user's social media activity and issue relevant warnings when issuing warnings. This allows the warning unit to issue relevant warnings by analyzing the user's social media activity. Some or all of the above-described processes in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the user's social media activity data into a generating AI and have the generating AI issue relevant warnings.

[0047] The advice unit can provide optimal advice by referring to the user's past financial literacy history when offering advice. For example, the advice unit can provide optimal advice based on the financial literacy advice the user has received in the past. Furthermore, the advice unit can provide similar advice based on the content of advice the user has received in the past. In addition, the advice unit can provide optimal advice based on the user's response to advice they have received in the past. This allows the advice unit to provide optimal advice by referring to the user's past financial literacy history. Some or all of the above processing in the advice unit may be performed using AI, for example, or without AI. For example, the advice unit can input the user's past financial literacy history into a generating AI and have the generating AI provide optimal advice.

[0048] The advice unit can provide customized advice based on the user's current financial situation. For example, if the user inputs their current financial situation, the advice unit can provide customized advice based on that information. Furthermore, if the user inputs their past financial situation, the advice unit can provide customized advice based on that information. Additionally, if the user inputs their future financial goals, the advice unit can provide customized advice based on that information. This allows for more appropriate advice by providing customized advice based on the user's current financial situation. Some or all of the above processing in the advice unit may be performed using AI, for example, or without AI. For example, the advice unit can input the user's financial situation data into a generating AI and have the generating AI perform the task of providing customized advice.

[0049] The advice unit can provide optimal advice by considering the user's geographical location. For example, if the user is in a specific region, the advice unit can provide advice considering the characteristics of scams that frequently occur in that region. Furthermore, if the user is traveling, the advice unit can provide advice considering the scam risks in the travel destination. Additionally, if the user is at home, the advice unit can provide standard advice. This allows for advice that reflects region-specific scam risks by considering the user's geographical location. Some or all of the above processing in the advice unit may be performed using AI, for example, or without AI. For example, the advice unit can input the user's geographical location into a generating AI and have the generating AI provide optimal advice.

[0050] The advice unit can analyze the user's social media activity and provide relevant advice when offering advice. This allows the advice unit to provide relevant advice by analyzing the user's social media activity. Some or all of the above processing in the advice unit may be performed using AI, for example, or without AI. For example, the advice unit can input the user's social media activity data into a generating AI and have the generating AI provide relevant advice.

[0051] The learning unit can optimize its learning algorithm by referring to past fraud cases during the learning process. For example, the learning unit can reflect the characteristics of fraud in the learning algorithm based on past fraud cases. Furthermore, the learning unit can optimize the learning algorithm based on the success rate of past fraud cases. In addition, the learning unit can analyze patterns in past fraud cases and reflect them in the learning algorithm. This allows the learning algorithm to be optimized and analysis accuracy improved by referring to past fraud cases. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input past fraud case data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0052] The learning unit can weight the training data based on the timing of fraud cases during training. For example, the learning unit can weight the training data based on recent fraud cases. It can also weight the training data based on past fraud cases. Furthermore, the learning unit can weight the training data based on fraud cases that occurred in a concentrated period. This allows for training that reflects the latest fraud risks by weighting the training data based on the timing of fraud cases. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input data on the timing of fraud cases into a generating AI and have the generating AI perform the weighting of the training data.

[0053] The notification unit can select the optimal notification method by referring to the user's past notification history when issuing a notification. For example, the notification unit can select the optimal notification method based on the user's past notification history. The notification unit can also issue similar notifications based on the content of notifications the user has received in the past. Furthermore, the notification unit can select the optimal notification method based on the user's response to notifications they have received in the past. In this way, the optimal notification method can be selected by referring to the user's past notification history. Some or all of the above processing in the notification unit may be performed using AI, for example, or without using AI. For example, the notification unit can input the user's past notification history into a generation AI and have the generation AI perform the selection of the optimal notification method.

[0054] The notification unit can select the optimal notification method by considering the user's device information when issuing a notification. For example, if the user is using a smartphone, the notification unit can issue a pop-up notification. If the user is using a tablet, the notification unit can issue a notification optimized for a larger screen. Furthermore, if the user is using a PC, the notification unit can issue a browser notification. In this way, the optimal notification method can be selected by considering the user's device information. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input the user's device information into a generating AI and have the generating AI select the optimal notification method.

[0055] The response unit can provide the optimal response procedure by referring to the user's past response history. For example, the response unit can provide the optimal procedure based on the history of response procedures the user has received in the past. Furthermore, the response unit can provide similar procedures based on the content of response procedures the user has received in the past. In addition, the response unit can provide the optimal procedure based on the user's responses to response procedures they have received in the past. Thus, by referring to the user's past response history, the optimal procedure can be provided. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the user's past response history into a generating AI and have the generating AI execute the provision of the optimal procedure.

[0056] The response unit can provide the most appropriate response procedure by considering the user's geographical location information. For example, if the user is in a specific region, the response unit can provide a response procedure that takes into account the characteristics of scams that frequently occur in that region. Furthermore, if the user is traveling, the response unit can provide a response procedure that takes into account the scam risks of the travel destination. In addition, if the user is at home, the response unit can provide the usual response procedure. This makes it possible to provide a response procedure that reflects region-specific scam risks by considering the user's geographical location information. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the user's geographical location information into a generating AI and have the generating AI execute the provision of the most appropriate response procedure.

[0057] The response unit can analyze the user's social media activity and provide relevant procedures when providing response procedures. This allows it to provide relevant procedures by analyzing the user's social media activity. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the user's social media activity data into a generating AI and have the generating AI perform the provision of relevant response procedures.

[0058] The response unit can provide the most appropriate response procedure based on the user's financial literacy. For example, if the user has low financial literacy, the response unit can provide a detailed response procedure. If the user has high financial literacy, the response unit can provide a concise response procedure. Furthermore, if the user has moderate financial literacy, the response unit can provide a response procedure with an appropriate level of detail. By providing the most appropriate procedure based on the user's financial literacy, it becomes possible to provide a response procedure that is easy for the user to understand. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the user's financial literacy data into a generating AI and have the generating AI perform the task of providing the most appropriate response procedure.

[0059] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0060] The analysis unit can improve the accuracy of its analysis by referring to the user's past chat history when analyzing chat content. For example, if the user has a history of being scammed in the past, the generating AI can refer to that history and rigorously analyze similar chat content. Also, if the user has engaged in safe chats in the past, the generating AI can refer to that history and maintain normal analysis accuracy. Furthermore, if the user has frequently used certain keywords in the past, the generating AI can prioritize the analysis of those keywords. In this way, the accuracy of the analysis can be improved by referring to the user's past chat history. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's past chat history into the generating AI and have the generating AI perform the improvement of analysis accuracy.

[0061] The analysis unit, when analyzing the content of a conversation, can perform context-aware analysis in addition to detecting keywords and phrases that have characteristics of fraud. For example, the analysis unit can analyze conversation content containing the phrase "guaranteeing high profits" and determine the possibility of fraud from the context. It can also analyze conversation content containing the phrase "transfer money to the designated account" and determine the possibility of fraud from the context. Furthermore, it can analyze conversation content containing the phrase "gain large profits in a short period of time" and determine the possibility of fraud from the context. By performing context-aware analysis, the possibility of fraud can be determined more accurately. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the conversation content and its context into a generating AI and have the generating AI perform context-aware analysis.

[0062] The analysis unit can improve the accuracy of its analysis by considering the user's geographical location information when analyzing the content of a conversation. For example, if the user is in a specific region, the analysis unit can consider the characteristics of scams that frequently occur in that region. Also, if the user is traveling, the analysis unit can consider the scam risk in the travel destination. Furthermore, if the user is at home, the analysis unit can maintain normal analysis accuracy. This makes it possible to perform analysis that reflects region-specific scam risks by considering the user's geographical location information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's geographical location information into a generating AI and have the generating AI perform the task of improving the analysis accuracy.

[0063] The warning unit can select the optimal warning method by referring to the user's past warning history when issuing a warning. For example, the warning unit can select the optimal warning method based on the user's past warning history. The warning unit can also issue similar warnings based on the content of warnings the user has received in the past. Furthermore, the warning unit can select the optimal warning method based on the user's response to past warnings. In this way, the optimal warning method can be selected by referring to the user's past warning history. Some or all of the above processing in the warning unit may be performed using AI, for example, or without using AI. For example, the warning unit can input the user's past warning history into a generating AI and have the generating AI select the optimal warning method.

[0064] The warning unit can generate different warning messages depending on the characteristics of the fraud when issuing a warning. For example, in the case of a fraud that guarantees high profits, the warning unit can generate a warning message that explains the specific risks. In the case of a fraud that requires users to transfer money to a designated account, the warning unit can generate a warning message that explains the risks of the transfer. Furthermore, in the case of a fraud that promises large profits in a short period of time, the warning unit can generate a warning message that explains the realistic risks. In this way, by generating warning messages that are tailored to the characteristics of the fraud, the warning unit can convey specific risks to the user. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the characteristics of the fraud into a generation AI and have the generation AI perform the generation of different warning messages.

[0065] The warning unit can select the optimal warning method by considering the user's device information when issuing a warning. For example, if the user is using a smartphone, the warning unit can issue a warning via a pop-up notification. If the user is using a tablet, the warning unit can issue a warning optimized for a larger screen. Furthermore, if the user is using a PC, the warning unit can issue a warning via a browser notification. This allows the system to select the optimal warning method by considering the user's device information. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the user's device information into a generating AI and have the generating AI select the optimal warning method.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The analysis unit analyzes the conversation content in real time. The analysis unit uses a generation AI to analyze the conversation content and detect keywords and phrases that have characteristics of fraud. For example, it can detect phrases such as "we guarantee high profits" or "transfer money to the designated account." The analysis unit can also learn from past fraud cases and detect keywords and phrases that have characteristics of fraud. Step 2: The warning unit alerts the user if the analysis unit detects a high probability of fraud. The warning unit can issue warnings via pop-up notifications or messages, displaying warning messages on the user's screen. The warning unit can also issue voice warnings to the user. Step 3: The advice section provides users who have received a warning from the warning section with advice to improve their financial literacy. The advice section can provide information on basic investment knowledge and fraudulent practices. For example, it can provide users with basic investment knowledge and information on fraudulent practices.

[0068] (Example of form 2) The fraud prevention system according to an embodiment of the present invention is a system for addressing the increase in investment fraud using social networking services (SNS). This fraud prevention system uses a generating AI to analyze the content of messages in a messaging app and issues a warning to the user if there is a high probability of fraud. First, when a user initiates a message in a messaging app, the content is analyzed in real time by the generating AI. The generating AI detects keywords and phrases that have characteristics of fraud, and if it determines that there is a high probability of fraud, it issues a warning to the user. This mechanism allows even users with low financial literacy to spot fraud and prevent them from becoming victims. For example, a user starts a message in a messaging app. Next, the generating AI analyzes the content of the message in real time. The generating AI detects keywords and phrases that have characteristics of fraud, and if it determines that there is a high probability of fraud, it issues a warning to the user. For example, if phrases such as "guaranteed high profits" or "transfer money to the designated account" are detected, the generating AI determines that there is a high probability of fraud and issues a warning to the user. This warning allows the user to recognize the risk of fraud and prevent them from becoming victims. The generating AI also provides advice to improve the user's financial literacy. For example, by providing information on basic investment knowledge and fraud tactics, users can develop the ability to spot scams themselves. In this way, utilizing generative AI can reduce the damage caused by investment scams using social media. As a result, the fraud prevention system can analyze the user's chat content in real time, issue warnings when there is a high probability of fraud, and provide advice to improve financial literacy, thereby preventing fraud before it occurs.

[0069] The fraud prevention system according to this embodiment comprises an analysis unit, a warning unit, and an advice unit. The analysis unit analyzes the content of the conversation in real time. The analysis unit analyzes the content of the conversation using, for example, a generation AI and detects keywords and phrases that have characteristics of fraud. The analysis unit can detect phrases such as, for example, "guaranteeing high profits" or "transfer money to the designated account." The analysis unit can also learn from past fraud cases using the generation AI and detect keywords and phrases that have characteristics of fraud. The warning unit issues a warning to the user if the analysis unit has detected a high probability of fraud. The warning unit can issue a warning using, for example, a pop-up notification or a message. The warning unit can, for example, display a warning message on the user's screen. The warning unit can also issue a voice warning to the user. The advice unit provides advice to the user who has received a warning from the warning unit to improve their financial literacy. The advice unit can, for example, provide information on basic knowledge about investment and fraud methods. The advice unit can, for example, provide the user with basic knowledge about investment. The advice unit can also provide the user with information on fraud methods. As a result, the fraud prevention system according to this embodiment can prevent fraud by analyzing the user's chat content in real time, issuing a warning when there is a high possibility of fraud, and providing advice to improve financial literacy.

[0070] The analysis unit analyzes the content of conversations in real time. For example, the analysis unit uses generative AI to analyze the content of conversations and detect keywords and phrases that have characteristics of fraud. Specifically, the generative AI uses natural language processing technology to analyze the content of conversations in context and identify patterns that may indicate fraud. For example, it can detect phrases such as "guaranteed high profits" or "transfer money to the specified account." These phrases are extracted from past fraud cases, and the generative AI uses these cases as training data. The generative AI understands the context of the conversation content and can evaluate the likelihood of fraud based on the context, not just by matching keywords. For example, if the phrase "guaranteed high profits" is used, it analyzes the context before and after it to determine whether there is a high probability of fraud. The generative AI can also learn from past fraud cases and detect keywords and phrases that have characteristics of fraud. This allows the analysis unit to analyze the user's conversation content in real time and respond quickly if there is a high probability of fraud. Furthermore, the analysis unit can save the results of the conversation content analysis to a database, which can be used to improve the accuracy of analysis in the future. For example, by adding newly detected fraud patterns to the database and using them as training data for the generating AI, the accuracy of the analysis can be continuously improved. This makes the analysis unit a powerful tool for always responding to the latest fraud tactics and protecting users.

[0071] The warning unit issues a warning to the user when the analysis unit detects a high probability of fraud. The warning unit can issue warnings, for example, through pop-up notifications or messages. Specifically, it displays a warning message on the user's screen to inform them of the potential for fraud. The warning message includes the characteristics and specific phrases of the detected fraud, urging the user to pay immediate attention. The warning unit can also issue voice warnings to the user. For example, it can issue a voice warning such as "This may be a scam. Please be careful" through the speaker of a smartphone or computer. This allows the user to receive a warning even if they are not looking at the screen. Furthermore, the warning unit can customize the warning method according to the user's settings. For example, if the user has a visual impairment, it can be set to prioritize voice warnings. The warning unit can also provide the optimal warning method for the user by adjusting the frequency and content of warnings. For example, if the same fraud possibility is detected repeatedly, the content of the warning can be strengthened to give the user a stronger warning. In this way, the warning unit can provide users with quick and appropriate warnings and prevent them from becoming victims of fraud.

[0072] The Advice Department provides advice to users who have received warnings from the Warning Department to improve their financial literacy. For example, the Advice Department can provide information on basic investment knowledge and fraud tactics. Specifically, it can provide users with basic investment knowledge and explain the importance of safe investment methods and risk management. The Advice Department can also provide users with information on fraud tactics. For example, based on past fraud cases, it can explain common tactics and signs of fraud, encouraging users to be vigilant against fraud. Furthermore, the Advice Department can provide educational materials and resources to improve users' financial literacy. For example, it can provide online courses, webinars, articles, and videos to allow users to learn at their own pace. The Advice Department can also track users' learning progress and provide additional advice and resources as needed. This allows the Advice Department to support users in deepening their knowledge of fraud and enhancing their self-defense capabilities. Additionally, the Advice Department can collect feedback from users and continuously improve the content and methods of the advice it provides. For example, it can revise the advice based on feedback on topics of particular interest to users and parts they found difficult to understand, providing more effective information. This allows the advisory department to play a crucial role in supporting users' financial literacy and preventing fraud.

[0073] The analysis unit can detect keywords and phrases that have characteristics of fraud. For example, it can detect keywords and phrases such as "high profit guaranteed" or "limited-time opportunity." Furthermore, the analysis unit can use a generative AI to learn from past fraud cases and detect keywords and phrases that have characteristics of fraud. For example, the analysis unit can input past fraud cases into the generative AI and train it to recognize the characteristics of fraud. This allows for highly accurate determination of the likelihood of fraud by detecting keywords and phrases that have characteristics of fraud.

[0074] The warning unit can issue warnings to the user via pop-up notifications or messages. For example, the warning unit can display a warning message on the user's screen. It can also issue voice warnings to the user. For instance, the warning unit can display a pop-up notification on the user's smartphone to inform them of the risk of fraud. Furthermore, the warning unit can also issue warnings to the user via email or SMS. This allows for immediate notification of the risk of fraud by issuing warnings via pop-up notifications or messages.

[0075] The advisory department can provide information on basic investment knowledge and fraudulent practices. For example, the advisory department can provide users with basic investment knowledge. It can also provide users with information on fraudulent practices. For example, the advisory department can provide users with information on the basics of stock investing and the relationship between risk and return. Furthermore, the advisory department can provide users with information on fraudulent practices such as Ponzi schemes and phishing scams. By providing information on basic investment knowledge and fraudulent practices, the financial literacy of users can be improved.

[0076] The generative AI is equipped with a learning unit that learns from past fraud cases. The learning unit allows the generative AI to learn from past fraud cases. For example, the learning unit can collect fraud cases from the past five years and train the generative AI with them. The learning unit can also collect fraud cases limited to a specific industry and train the generative AI with them. For example, the learning unit can collect fraud cases in the financial industry and train the generative AI with them. Furthermore, the learning unit can train the generative AI on patterns of fraud cases. For example, the learning unit can train the generative AI on fraud methods and characteristics. In this way, the accuracy of the generative AI's analysis can be improved by learning from past fraud cases.

[0077] The system includes a notification section that specifies the method for issuing a warning. This notification section can indicate the specific method for issuing a warning. For example, it can indicate the timing and format of the warning. For example, the notification section can issue a warning while the user is in a conversation. It can also issue a warning after the user has ended a conversation. For example, the notification section can display a warning message immediately after the user ends a conversation. Furthermore, the notification section can send warnings to the user via email or SMS. For example, the notification section can display a pop-up notification on the user's smartphone to inform them of the risk of fraud. This allows for effective communication of warnings to users by clearly indicating the specific method for issuing them.

[0078] The system includes a response section that provides specific steps on how users who receive a warning can avoid fraud. The response section can provide specific steps on how users who receive a warning can avoid fraud. For example, the response section can provide step-by-step guidelines for avoiding fraud. For example, the response section can make users aware of the risk of fraud and provide specific avoidance steps. For example, the response section can explain the risk of fraud to users and provide specific steps to avoid fraud. Furthermore, the response section can explain fraudulent tactics to users and provide specific countermeasures to avoid fraud. For example, the response section can explain fraudulent tactics to users and provide specific countermeasures to avoid fraud. This ensures that users can respond appropriately by providing specific steps to avoid fraud.

[0079] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated emotions. For example, if the user is feeling anxious, the generation AI can improve the accuracy of the analysis, allowing for a more rigorous detection of potential fraud. If the user is relaxed, the generation AI can maintain a normal level of accuracy, avoiding excessive warnings. Furthermore, if the user is agitated, the generation AI can adjust the accuracy of the analysis to a moderate level, issuing appropriate warnings. This allows for more appropriate analysis results by adjusting the accuracy of the analysis based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, or not. For example, the analysis unit can input user emotion data into the generation AI and have the generation AI perform emotion-based adjustments to the analysis accuracy.

[0080] The analysis unit can improve the accuracy of its analysis by referring to the user's past chat history when analyzing chat content. For example, if the user has a history of being scammed in the past, the generating AI can refer to that history and rigorously analyze similar chat content. Also, if the user has engaged in safe chats in the past, the generating AI can refer to that history and maintain normal analysis accuracy. Furthermore, if the user has frequently used certain keywords in the past, the generating AI can prioritize the analysis of those keywords. In this way, the accuracy of the analysis can be improved by referring to the user's past chat history. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's past chat history into the generating AI and have the generating AI perform the improvement of analysis accuracy.

[0081] The analysis unit, when analyzing the content of a conversation, can perform context-aware analysis in addition to detecting keywords and phrases that have characteristics of fraud. For example, the analysis unit can analyze conversation content containing the phrase "guaranteeing high profits" and determine the possibility of fraud from the context. It can also analyze conversation content containing the phrase "transfer money to the designated account" and determine the possibility of fraud from the context. Furthermore, it can analyze conversation content containing the phrase "gain large profits in a short period of time" and determine the possibility of fraud from the context. By performing context-aware analysis, the possibility of fraud can be determined more accurately. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the conversation content and its context into a generating AI and have the generating AI perform context-aware analysis.

[0082] The analysis unit can estimate the user's emotions and adjust how the analysis results are displayed based on the estimated emotions. For example, if the user is feeling anxious, the analysis unit can display the analysis results in detail and clearly communicate the risk of fraud. If the user is relaxed, the analysis unit can display the analysis results concisely and avoid excessive warnings. Furthermore, if the user is agitated, the analysis unit can display the analysis results with a moderate level of detail and issue appropriate warnings. By adjusting how the analysis results are displayed based on the user's emotions, it becomes possible to display the results in a way that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's emotion data into the generative AI and have the generative AI adjust how the analysis results are displayed based on the emotions.

[0083] The analysis unit can improve the accuracy of its analysis by considering the user's geographical location information when analyzing the content of a conversation. For example, if the user is in a specific region, the analysis unit can consider the characteristics of scams that frequently occur in that region. Also, if the user is traveling, the analysis unit can consider the scam risk in the travel destination. Furthermore, if the user is at home, the analysis unit can maintain normal analysis accuracy. This makes it possible to perform analysis that reflects region-specific scam risks by considering the user's geographical location information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's geographical location information into a generating AI and have the generating AI perform the task of improving the analysis accuracy.

[0084] The analysis unit can analyze the user's social media activity when analyzing the content of conversations and detect the characteristics of related scams. This allows for more accurate detection of scam characteristics by analyzing the user's social media activity. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's social media activity data into a generating AI and have the generating AI perform the detection of scam characteristics.

[0085] The warning unit can estimate the user's emotions and adjust the way the warning is expressed based on those emotions. For example, if the user is feeling anxious, the warning unit can explain the warning in detail and clearly communicate the risk of fraud. If the user is relaxed, the warning unit can deliver the warning concisely and avoid excessive warnings. Furthermore, if the user is agitated, the warning unit can deliver the warning with a moderate level of detail and issue an appropriate warning. This allows for warnings that are easier for the user to understand by adjusting the way the warning is expressed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the warning unit may be performed using AI or not. For example, the warning unit can input user emotion data into a generative AI and have the generative AI adjust the way the warning is expressed based on those emotions.

[0086] The warning unit can select the optimal warning method by referring to the user's past warning history when issuing a warning. For example, the warning unit can select the optimal warning method based on the user's past warning history. The warning unit can also issue similar warnings based on the content of warnings the user has received in the past. Furthermore, the warning unit can select the optimal warning method based on the user's response to past warnings. In this way, the optimal warning method can be selected by referring to the user's past warning history. Some or all of the above processing in the warning unit may be performed using AI, for example, or without using AI. For example, the warning unit can input the user's past warning history into a generating AI and have the generating AI select the optimal warning method.

[0087] The warning unit can generate different warning messages depending on the characteristics of the fraud when issuing a warning. For example, in the case of a fraud that guarantees high profits, the warning unit can generate a warning message that explains the specific risks. In the case of a fraud that requires users to transfer money to a designated account, the warning unit can generate a warning message that explains the risks of the transfer. Furthermore, in the case of a fraud that promises large profits in a short period of time, the warning unit can generate a warning message that explains the realistic risks. In this way, by generating warning messages that are tailored to the characteristics of the fraud, the warning unit can convey specific risks to the user. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the characteristics of the fraud into a generation AI and have the generation AI perform the generation of different warning messages.

[0088] The warning unit can estimate the user's emotions and adjust the timing of warnings based on the estimated emotions. For example, if the user is feeling anxious, the warning unit can issue a warning immediately. If the user is relaxed, the warning unit can issue a warning at an appropriate time. Furthermore, if the user is excited, the warning unit can wait until the user calms down before issuing a warning. In this way, by adjusting the timing of warnings based on the user's emotions, warnings can be issued at an appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the warning unit may be performed using AI, or not using AI. For example, the warning unit can input user emotion data into the generative AI and have the generative AI adjust the timing of warnings based on emotions.

[0089] The warning unit can select the optimal warning method by considering the user's device information when issuing a warning. For example, if the user is using a smartphone, the warning unit can issue a warning via a pop-up notification. If the user is using a tablet, the warning unit can issue a warning optimized for a larger screen. Furthermore, if the user is using a PC, the warning unit can issue a warning via a browser notification. This allows the system to select the optimal warning method by considering the user's device information. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the user's device information into a generating AI and have the generating AI select the optimal warning method.

[0090] The warning unit can analyze the user's social media activity and issue relevant warnings when issuing warnings. This allows the warning unit to issue relevant warnings by analyzing the user's social media activity. Some or all of the above-described processes in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the user's social media activity data into a generating AI and have the generating AI issue relevant warnings.

[0091] The advice unit can estimate the user's emotions and adjust the way it expresses advice based on those emotions. For example, if the user is feeling anxious, the advice unit can provide detailed advice to reassure them. If the user is relaxed, the advice unit can provide concise advice and avoid providing excessive information. Furthermore, if the user is agitated, the advice unit can provide advice to help them calm down. By adjusting the way advice is expressed based on the user's emotions, it becomes possible to provide advice that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the advice unit may be performed using AI, or not using AI. For example, the advice unit can input user emotion data into the generative AI and have the generative AI adjust the way advice is expressed based on those emotions.

[0092] The advice unit can provide optimal advice by referring to the user's past financial literacy history when offering advice. For example, the advice unit can provide optimal advice based on the financial literacy advice the user has received in the past. Furthermore, the advice unit can provide similar advice based on the content of advice the user has received in the past. In addition, the advice unit can provide optimal advice based on the user's response to advice they have received in the past. This allows the advice unit to provide optimal advice by referring to the user's past financial literacy history. Some or all of the above processing in the advice unit may be performed using AI, for example, or without AI. For example, the advice unit can input the user's past financial literacy history into a generating AI and have the generating AI provide optimal advice.

[0093] The advice unit can provide customized advice based on the user's current financial situation. For example, if the user inputs their current financial situation, the advice unit can provide customized advice based on that information. Furthermore, if the user inputs their past financial situation, the advice unit can provide customized advice based on that information. Additionally, if the user inputs their future financial goals, the advice unit can provide customized advice based on that information. This allows for more appropriate advice by providing customized advice based on the user's current financial situation. Some or all of the above processing in the advice unit may be performed using AI, for example, or without AI. For example, the advice unit can input the user's financial situation data into a generating AI and have the generating AI perform the task of providing customized advice.

[0094] The advice unit can estimate the user's emotions and adjust the timing of advice based on the estimated emotions. For example, if the user is feeling anxious, the advice unit can provide advice immediately. If the user is relaxed, the advice unit can provide advice at an appropriate time. Furthermore, if the user is agitated, the advice unit can wait until the user calms down before providing advice. In this way, by adjusting the timing of advice based on the user's emotions, advice can be provided at an appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the advice unit may be performed using AI or not using AI. For example, the advice unit can input user emotion data into the generative AI and have the generative AI adjust the timing of advice based on emotions.

[0095] The advice unit can provide optimal advice by considering the user's geographical location. For example, if the user is in a specific region, the advice unit can provide advice considering the characteristics of scams that frequently occur in that region. Furthermore, if the user is traveling, the advice unit can provide advice considering the scam risks in the travel destination. Additionally, if the user is at home, the advice unit can provide standard advice. This allows for advice that reflects region-specific scam risks by considering the user's geographical location. Some or all of the above processing in the advice unit may be performed using AI, for example, or without AI. For example, the advice unit can input the user's geographical location into a generating AI and have the generating AI provide optimal advice.

[0096] The advice unit can analyze the user's social media activity and provide relevant advice when offering advice. This allows the advice unit to provide relevant advice by analyzing the user's social media activity. Some or all of the above processing in the advice unit may be performed using AI, for example, or without AI. For example, the advice unit can input the user's social media activity data into a generating AI and have the generating AI provide relevant advice.

[0097] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is feeling anxious, the learning unit can select detailed training data about fraud. If the user is relaxed, the learning unit can select training data about general fraud. Furthermore, if the user is excited, the learning unit can select training data that emphasizes the risks of fraud. This allows for more effective learning by selecting training data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI, for example, or not using AI. For example, the learning unit can input user emotion data into a generative AI and have the generative AI perform the selection of training data based on emotions.

[0098] The learning unit can optimize its learning algorithm by referring to past fraud cases during the learning process. For example, the learning unit can reflect the characteristics of fraud in the learning algorithm based on past fraud cases. Furthermore, the learning unit can optimize the learning algorithm based on the success rate of past fraud cases. In addition, the learning unit can analyze patterns in past fraud cases and reflect them in the learning algorithm. This allows the learning algorithm to be optimized and analysis accuracy improved by referring to past fraud cases. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input past fraud case data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0099] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is feeling anxious, the learning unit can increase the learning frequency. If the user is relaxed, the learning unit can maintain a normal learning frequency. Furthermore, if the user is excited, the learning unit can adjust the learning frequency to a moderate level. This allows for effective learning by adjusting the learning frequency based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the learning frequency based on emotions.

[0100] The learning unit can weight the training data based on the timing of fraud cases during training. For example, the learning unit can weight the training data based on recent fraud cases. It can also weight the training data based on past fraud cases. Furthermore, the learning unit can weight the training data based on fraud cases that occurred in a concentrated period. This allows for training that reflects the latest fraud risks by weighting the training data based on the timing of fraud cases. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input data on the timing of fraud cases into a generating AI and have the generating AI perform the weighting of the training data.

[0101] The notification unit can estimate the user's emotions and adjust the way notifications are presented based on those emotions. For example, if the user is feeling anxious, the notification unit can provide a detailed notification to reassure them. If the user is relaxed, the notification unit can provide a concise notification to avoid overwhelming them with information. Furthermore, if the user is agitated, the notification unit can provide a notification to help them calm down. By adjusting the way notifications are presented based on the user's emotions, it becomes possible to provide notifications that are easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using AI, or not using AI. For example, the notification unit can input user emotion data into a generative AI and have the generative AI adjust the way notifications are presented based on those emotions.

[0102] The notification unit can select the optimal notification method by referring to the user's past notification history when issuing a notification. For example, the notification unit can select the optimal notification method based on the user's past notification history. The notification unit can also issue similar notifications based on the content of notifications the user has received in the past. Furthermore, the notification unit can select the optimal notification method based on the user's response to notifications they have received in the past. In this way, the optimal notification method can be selected by referring to the user's past notification history. Some or all of the above processing in the notification unit may be performed using AI, for example, or without using AI. For example, the notification unit can input the user's past notification history into a generation AI and have the generation AI perform the selection of the optimal notification method.

[0103] The notification unit can estimate the user's emotions and adjust the timing of notifications based on the estimated emotions. For example, if the user is feeling anxious, the notification unit can issue a notification immediately. If the user is relaxed, the notification unit can issue a notification at an appropriate time. Furthermore, if the user is excited, the notification unit can wait until the user calms down before issuing a notification. In this way, by adjusting the timing of notifications based on the user's emotions, notifications can be issued at an appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using AI, or not using AI. For example, the notification unit can input user emotion data into a generative AI and have the generative AI adjust the timing of notifications based on emotions.

[0104] The notification unit can select the optimal notification method by considering the user's device information when issuing a notification. For example, if the user is using a smartphone, the notification unit can issue a pop-up notification. If the user is using a tablet, the notification unit can issue a notification optimized for a larger screen. Furthermore, if the user is using a PC, the notification unit can issue a browser notification. In this way, the optimal notification method can be selected by considering the user's device information. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input the user's device information into a generating AI and have the generating AI select the optimal notification method.

[0105] The response unit can estimate the user's emotions and adjust the way the response procedures are presented based on the estimated emotions. For example, if the user is feeling anxious, the response unit can provide detailed response procedures to reassure them. If the user is relaxed, the response unit can provide concise response procedures to avoid excessive information. Furthermore, if the user is agitated, the response unit can provide response procedures to help them calm down. By adjusting the way the response procedures are presented based on the user's emotions, it becomes possible to create response procedures that are easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the response unit may be performed using AI, for example, or not using AI. For example, the response unit can input user emotion data into the generative AI and have the generative AI adjust the way the response procedures are presented based on the emotion.

[0106] The response unit can provide the optimal response procedure by referring to the user's past response history. For example, the response unit can provide the optimal procedure based on the history of response procedures the user has received in the past. Furthermore, the response unit can provide similar procedures based on the content of response procedures the user has received in the past. In addition, the response unit can provide the optimal procedure based on the user's responses to response procedures they have received in the past. Thus, by referring to the user's past response history, the optimal procedure can be provided. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the user's past response history into a generating AI and have the generating AI execute the provision of the optimal procedure.

[0107] The response unit can estimate the user's emotions and adjust the timing of response procedures based on the estimated emotions. For example, if the user is feeling anxious, the response unit can immediately provide response procedures. If the user is relaxed, the response unit can provide response procedures at an appropriate time. Furthermore, if the user is agitated, the response unit can wait until the user calms down before providing response procedures. In this way, by adjusting the timing of response procedures based on the user's emotions, response procedures can be provided at an appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the response unit may be performed using AI, for example, or not using AI. For example, the response unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the timing of response procedures based on emotions.

[0108] The response unit can provide the most appropriate response procedure by considering the user's geographical location information. For example, if the user is in a specific region, the response unit can provide a response procedure that takes into account the characteristics of scams that frequently occur in that region. Furthermore, if the user is traveling, the response unit can provide a response procedure that takes into account the scam risks of the travel destination. In addition, if the user is at home, the response unit can provide the usual response procedure. This makes it possible to provide a response procedure that reflects region-specific scam risks by considering the user's geographical location information. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the user's geographical location information into a generating AI and have the generating AI execute the provision of the most appropriate response procedure.

[0109] The response unit can analyze the user's social media activity and provide relevant procedures when providing response procedures. This allows it to provide relevant procedures by analyzing the user's social media activity. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the user's social media activity data into a generating AI and have the generating AI perform the provision of relevant response procedures.

[0110] The response unit can provide the most appropriate response procedure based on the user's financial literacy. For example, if the user has low financial literacy, the response unit can provide a detailed response procedure. If the user has high financial literacy, the response unit can provide a concise response procedure. Furthermore, if the user has moderate financial literacy, the response unit can provide a response procedure with an appropriate level of detail. By providing the most appropriate procedure based on the user's financial literacy, it becomes possible to provide a response procedure that is easy for the user to understand. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the user's financial literacy data into a generating AI and have the generating AI perform the task of providing the most appropriate response procedure.

[0111] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0112] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated emotions. For example, if the user is feeling anxious, the generation AI can improve the accuracy of the analysis, allowing for a more rigorous detection of potential fraud. If the user is relaxed, the generation AI can maintain a normal level of accuracy, avoiding excessive warnings. Furthermore, if the user is agitated, the generation AI can adjust the accuracy of the analysis to a moderate level, issuing appropriate warnings. This allows for more appropriate analysis results by adjusting the accuracy of the analysis based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, or not. For example, the analysis unit can input user emotion data into the generation AI and have the generation AI perform emotion-based adjustments to the analysis accuracy.

[0113] The analysis unit can improve the accuracy of its analysis by referring to the user's past chat history when analyzing chat content. For example, if the user has a history of being scammed in the past, the generating AI can refer to that history and rigorously analyze similar chat content. Also, if the user has engaged in safe chats in the past, the generating AI can refer to that history and maintain normal analysis accuracy. Furthermore, if the user has frequently used certain keywords in the past, the generating AI can prioritize the analysis of those keywords. In this way, the accuracy of the analysis can be improved by referring to the user's past chat history. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's past chat history into the generating AI and have the generating AI perform the improvement of analysis accuracy.

[0114] The analysis unit, when analyzing the content of a conversation, can perform context-aware analysis in addition to detecting keywords and phrases that have characteristics of fraud. For example, the analysis unit can analyze conversation content containing the phrase "guaranteeing high profits" and determine the possibility of fraud from the context. It can also analyze conversation content containing the phrase "transfer money to the designated account" and determine the possibility of fraud from the context. Furthermore, it can analyze conversation content containing the phrase "gain large profits in a short period of time" and determine the possibility of fraud from the context. By performing context-aware analysis, the possibility of fraud can be determined more accurately. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the conversation content and its context into a generating AI and have the generating AI perform context-aware analysis.

[0115] The analysis unit can estimate the user's emotions and adjust how the analysis results are displayed based on the estimated emotions. For example, if the user is feeling anxious, the analysis unit can display the analysis results in detail and clearly communicate the risk of fraud. If the user is relaxed, the analysis unit can display the analysis results concisely and avoid excessive warnings. Furthermore, if the user is agitated, the analysis unit can display the analysis results with a moderate level of detail and issue appropriate warnings. By adjusting how the analysis results are displayed based on the user's emotions, it becomes possible to display the results in a way that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's emotion data into the generative AI and have the generative AI adjust how the analysis results are displayed based on the emotions.

[0116] The analysis unit can improve the accuracy of its analysis by considering the user's geographical location information when analyzing the content of a conversation. For example, if the user is in a specific region, the analysis unit can consider the characteristics of scams that frequently occur in that region. Also, if the user is traveling, the analysis unit can consider the scam risk in the travel destination. Furthermore, if the user is at home, the analysis unit can maintain normal analysis accuracy. This makes it possible to perform analysis that reflects region-specific scam risks by considering the user's geographical location information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's geographical location information into a generating AI and have the generating AI perform the task of improving the analysis accuracy.

[0117] The warning unit can estimate the user's emotions and adjust the way the warning is expressed based on those emotions. For example, if the user is feeling anxious, the warning unit can explain the warning in detail and clearly communicate the risk of fraud. If the user is relaxed, the warning unit can deliver the warning concisely and avoid excessive warnings. Furthermore, if the user is agitated, the warning unit can deliver the warning with a moderate level of detail and issue an appropriate warning. This allows for warnings that are easier for the user to understand by adjusting the way the warning is expressed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the warning unit may be performed using AI or not. For example, the warning unit can input user emotion data into a generative AI and have the generative AI adjust the way the warning is expressed based on those emotions.

[0118] The warning unit can select the optimal warning method by referring to the user's past warning history when issuing a warning. For example, the warning unit can select the optimal warning method based on the user's past warning history. The warning unit can also issue similar warnings based on the content of warnings the user has received in the past. Furthermore, the warning unit can select the optimal warning method based on the user's response to past warnings. In this way, the optimal warning method can be selected by referring to the user's past warning history. Some or all of the above processing in the warning unit may be performed using AI, for example, or without using AI. For example, the warning unit can input the user's past warning history into a generating AI and have the generating AI select the optimal warning method.

[0119] The warning unit can generate different warning messages depending on the characteristics of the fraud when issuing a warning. For example, in the case of a fraud that guarantees high profits, the warning unit can generate a warning message that explains the specific risks. In the case of a fraud that requires users to transfer money to a designated account, the warning unit can generate a warning message that explains the risks of the transfer. Furthermore, in the case of a fraud that promises large profits in a short period of time, the warning unit can generate a warning message that explains the realistic risks. In this way, by generating warning messages that are tailored to the characteristics of the fraud, the warning unit can convey specific risks to the user. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the characteristics of the fraud into a generation AI and have the generation AI perform the generation of different warning messages.

[0120] The warning unit can estimate the user's emotions and adjust the timing of warnings based on the estimated emotions. For example, if the user is feeling anxious, the warning unit can issue a warning immediately. If the user is relaxed, the warning unit can issue a warning at an appropriate time. Furthermore, if the user is excited, the warning unit can wait until the user calms down before issuing a warning. In this way, by adjusting the timing of warnings based on the user's emotions, warnings can be issued at an appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the warning unit may be performed using AI, or not using AI. For example, the warning unit can input user emotion data into the generative AI and have the generative AI adjust the timing of warnings based on emotions.

[0121] The warning unit can select the optimal warning method by considering the user's device information when issuing a warning. For example, if the user is using a smartphone, the warning unit can issue a warning via a pop-up notification. If the user is using a tablet, the warning unit can issue a warning optimized for a larger screen. Furthermore, if the user is using a PC, the warning unit can issue a warning via a browser notification. This allows the system to select the optimal warning method by considering the user's device information. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the user's device information into a generating AI and have the generating AI select the optimal warning method.

[0122] The following briefly describes the processing flow for example form 2.

[0123] Step 1: The analysis unit analyzes the conversation content in real time. The analysis unit uses a generation AI to analyze the conversation content and detect keywords and phrases that have characteristics of fraud. For example, it can detect phrases such as "we guarantee high profits" or "transfer money to the designated account." The analysis unit can also learn from past fraud cases and detect keywords and phrases that have characteristics of fraud. Step 2: The warning unit alerts the user if the analysis unit detects a high probability of fraud. The warning unit can issue warnings via pop-up notifications or messages, displaying warning messages on the user's screen. The warning unit can also issue voice warnings to the user. Step 3: The advice section provides users who have received a warning from the warning section with advice to improve their financial literacy. The advice section can provide information on basic investment knowledge and fraudulent practices. For example, it can provide users with basic investment knowledge and information on fraudulent practices.

[0124] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0125] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0126] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0127] Each of the multiple elements described above, including the analysis unit, warning unit, advice unit, learning unit, notification unit, and response unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart device 14 and analyzes the content of the conversation in real time. The warning unit is implemented by the control unit 46A of the smart device 14 and issues a warning to the user. The advice unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides advice for improving financial literacy. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns past fraud cases. The notification unit is implemented by the control unit 46A of the smart device 14 and indicates the timing of the warning and the format of the notification. The response unit is implemented by the specific processing unit 290 of the data processing unit 12 and indicates specific steps to avoid fraud. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0128] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0129] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0130] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0131] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0132] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0133] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0134] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0135] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0136] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0137] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0138] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0139] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0140] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0141] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0142] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0143] Each of the multiple elements described above, including the analysis unit, warning unit, advice unit, learning unit, notification unit, and response unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart glasses 214 and analyzes the content of the conversation in real time. The warning unit is implemented by the control unit 46A of the smart glasses 214 and issues a warning to the user. The advice unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides advice for improving financial literacy. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns past fraud cases. The notification unit is implemented by the control unit 46A of the smart glasses 214 and indicates the timing of the warning and the format of the notification. The response unit is implemented by the specific processing unit 290 of the data processing unit 12 and indicates specific steps to avoid fraud. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0144] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0145] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0146] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0147] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0148] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0149] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0150] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0151] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0152] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0153] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0154] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0155] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0156] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0157] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0158] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0159] Each of the multiple elements described above, including the analysis unit, warning unit, advice unit, learning unit, notification unit, and response unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the headset terminal 314 and analyzes the content of the conversation in real time. The warning unit is implemented by the control unit 46A of the headset terminal 314 and issues a warning to the user. The advice unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides advice for improving financial literacy. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns past fraud cases. The notification unit is implemented by the control unit 46A of the headset terminal 314 and indicates the timing of the warning and the format of the notification. The response unit is implemented by the specific processing unit 290 of the data processing unit 12 and indicates specific steps to avoid fraud. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0160] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0161] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0162] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0163] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0164] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0165] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0166] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0167] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0168] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0169] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0170] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0171] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0172] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0173] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0174] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0175] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0176] Each of the multiple elements described above, including the analysis unit, warning unit, advice unit, learning unit, notification unit, and response unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the robot 414 and analyzes the content of the talk in real time. The warning unit is implemented by the control unit 46A of the robot 414 and issues a warning to the user. The advice unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides advice for improving financial literacy. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns past fraud cases. The notification unit is implemented by the control unit 46A of the robot 414 and indicates the timing of the warning and the format of the notification. The response unit is implemented by the specific processing unit 290 of the data processing unit 12 and indicates specific steps to avoid fraud. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0177] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0178] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0179] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0180] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0181] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0182] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0183] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0184] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0185] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0186] 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.

[0187] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0188] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0189] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0190] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0191] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0192] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0193] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0194] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0195] (Note 1) The analysis unit analyzes the content of the conversation in real time, A warning unit that issues a warning to the user if the analysis unit detects a high probability of fraud, The system includes an advice unit that provides advice to users who have received a warning from the warning unit, in order to improve their financial literacy. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Detects keywords and phrases that have characteristics of fraud. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned warning unit is Warnings are sent to the user via pop-up notifications or messages. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned advice section, This site provides basic knowledge about investing and information about fraudulent practices. The system described in Appendix 1, characterized by the features described herein. (Note 5) The generation AI has a learning unit that learns from past fraud cases. The system described in Appendix 1, characterized by the features described herein. (Note 6) It includes a notification section that shows the specific method for issuing a warning. The system described in Appendix 1, characterized by the features described herein. (Note 7) It includes a section that provides specific steps for users who receive a warning to avoid fraud. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, It estimates the user's emotions and adjusts the accuracy of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, When analyzing chat content, we improve the accuracy of the analysis by referring to the user's past chat history. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, When analyzing the content of a conversation, in addition to detecting keywords and phrases that have characteristics of fraud, the analysis also takes context into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, When analyzing the content of conversations, the system improves the accuracy of the analysis by taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, When analyzing the content of conversations, the system analyzes the user's social media activity and detects the characteristics of related scams. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned warning unit is The system estimates the user's emotions and adjusts the way warnings are presented based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned warning unit is When issuing a warning, the system refers to the user's past warning history to select the most appropriate warning method. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned warning unit is When issuing a warning, different warning messages are generated depending on the characteristics of the scam. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned warning unit is It estimates the user's emotions and adjusts the timing of warnings based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned warning unit is When issuing a warning, the system selects the most appropriate warning method, taking into account the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned warning unit is When issuing a warning, the system analyzes the user's social media activity and issues relevant warnings. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned advice section, It estimates the user's emotions and adjusts the way advice is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned advice section, When providing advice, we refer to the user's past financial literacy history to provide the most appropriate advice. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned advice section, When providing advice, we offer customized advice based on the user's current financial situation. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned advice section, It estimates the user's emotions and adjusts the timing of advice based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned advice section, When providing advice, we take the user's geographical location into consideration to provide the most appropriate advice. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned advice section, When providing advice, we analyze the user's social media activity and provide relevant advice. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past fraud cases. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned learning unit, During training, the training data is weighted based on the timing of fraud cases. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned notification unit, It estimates the user's emotions and adjusts the way notifications are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned notification unit, When issuing a notification, the system will refer to the user's past notification history to select the most suitable notification method. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned notification unit, It estimates the user's emotions and adjusts the timing of notifications based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned notification unit, When issuing notifications, the system selects the most suitable notification method by considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 34) The corresponding part is, The system estimates the user's emotions and adjusts the way the response procedures are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The corresponding part is, When providing troubleshooting steps, we refer to the user's past troubleshooting history to provide the most appropriate steps. The system described in Appendix 1, characterized by the features described herein. (Note 36) The corresponding part is, It estimates the user's emotions and adjusts the timing of response procedures based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 37) The corresponding part is, When providing response procedures, we will consider the user's geographical location to provide the most appropriate procedure. The system described in Appendix 1, characterized by the features described herein. (Note 38) The corresponding part is, When providing response procedures, we analyze the user's social media activity and provide relevant steps. The system described in Appendix 1, characterized by the features described herein. (Note 39) The corresponding part is, When providing response procedures, we will provide the most appropriate procedures based on the user's financial literacy. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0196] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The analysis unit analyzes the content of the conversation in real time, A warning unit that issues a warning to the user if the analysis unit detects a high probability of fraud, The system includes an advice unit that provides advice to users who have received a warning from the warning unit, in order to improve their financial literacy. A system characterized by the following features.

2. The aforementioned analysis unit, Detects keywords and phrases that have characteristics of fraud. The system according to feature 1.

3. The aforementioned warning unit is Warnings are sent to the user via pop-up notifications or messages. The system according to feature 1.

4. The aforementioned advice section, This site provides basic knowledge about investing and information about fraudulent practices. The system according to feature 1.

5. The generating AI has a learning unit that learns from past fraud cases. The system according to feature 1.

6. It includes a notification unit that shows the specific method for issuing a warning. The system according to feature 1.

7. It includes a section that provides specific steps for users who receive a warning to avoid fraud. The system according to feature 1.

8. The aforementioned analysis unit, It estimates the user's emotions and adjusts the accuracy of the analysis based on the estimated user emotions. The system according to feature 1.

9. The aforementioned analysis unit, When analyzing chat content, we refer to the user's past chat history to improve the accuracy of the analysis. The system according to feature 1.

Images