system

Abstract

To detect signs of phishing fraud and provide warnings to users.SOLUTION: A system according to an embodiment includes an analysis unit, a detection unit, and a provision unit. The analysis unit analyzes voice data and text data. The detection unit detects signs of phishing fraud on the basis of the data analyzed by the analysis unit. The provision unit provides a warning to a user on the basis of the signs of phishing fraud detected by the detection unit.SELECTED DRAWING: Figure 1

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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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, there is a problem that the signs of phishing fraud are not efficiently detected and warnings are not sufficiently provided to users.

[0005] The system according to an embodiment aims to detect signs of phishing fraud and provide warnings to users.

Means for Solving the Problems

[0006] The system according to an embodiment includes an analysis unit, a detection unit, and a provision unit. The analysis unit analyzes voice data and text data. The detection unit detects signs of phishing fraud based on the data analyzed by the analysis unit. The provision unit provides a warning to the user based on the signs of phishing fraud detected by the detection unit. [Effects of the Invention]

[0007] The system according to this embodiment can detect signs of phishing scams and provide warnings to users. [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 signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[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 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are 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) An embodiment of the present invention provides an AI-based phishing fraud prevention system for mobile phone carriers. This system processes voice and text data locally on the user's device, protecting the user's privacy. Next, the AI ​​analyzes the voice data to determine if it is potentially a phishing scam. Furthermore, the AI ​​analyzes the text data of emails to detect signs of phishing scams. This provides a secure communication environment and enhances user trust. For example, if a call received by a user is potentially a phishing scam, the AI ​​issues a warning to alert the user. Also, if an email shows signs of phishing scams, the AI ​​automatically isolates the email and notifies the user. In this way, the AI-based phishing fraud prevention system keeps the user's communications secure and protects them from phishing scams.

[0029] The phishing fraud prevention system according to the embodiment comprises an analysis unit, a detection unit, and a provision unit. The analysis unit analyzes audio data. Audio data includes, but is not limited to, call recordings, voice messages, and audio files. The analysis unit analyzes the audio data using a machine learning algorithm, for example, to detect signs of phishing fraud. The analysis unit can also extract specific keywords or phrases from the audio data and determine the likelihood of phishing fraud. For example, the analysis unit detects keywords such as "bank account" and "password" in the audio data to increase the likelihood of phishing fraud. Furthermore, the analysis unit can analyze sender information of the audio data and evaluate its reliability. For example, the analysis unit evaluates reliability based on the sender's phone number and voice characteristics. The detection unit detects signs of phishing fraud based on the data analyzed by the analysis unit. Signs of phishing fraud include, but are not limited to, specific keywords, link patterns, and sender information. The detection unit detects signs of phishing fraud based on, for example, the data provided by the analysis unit. Furthermore, the detection unit may use rule-based algorithms to detect signs of phishing scams. For example, the detection unit may detect signs of phishing scams based on specific keywords or link patterns. The provisioning unit provides warnings to the user based on the signs of phishing scams detected by the detection unit. Warnings may include, but are not limited to, pop-up notifications, email notifications, or voice notifications. For example, the provisioning unit may display a pop-up notification on the user's device to warn of a potential phishing scam. The provisioning unit may also send an email notification to the user to inform them of a potential phishing scam. In addition, the provisioning unit may provide warnings to the user using voice notifications. For example, the provisioning unit may play a voice message to warn of a potential phishing scam. Thus, the phishing scam prevention system according to the embodiment can keep the user's communications secure and protect them from phishing scams.

[0030] The analysis unit analyzes audio data. Audio data includes, but is not limited to, call recordings, voice messages, and audio files. For example, the analysis unit uses machine learning algorithms to analyze audio data and detect signs of phishing scams. Specifically, it analyzes the waveform and spectrum of the audio data and extracts features. These features include variations in pitch, tempo, volume, and specific frequency components. The machine learning algorithm evaluates the likelihood of a phishing scam based on these features. For example, a model trained on audio data from past phishing scams can be used to evaluate new audio data. The analysis unit can also extract specific keywords and phrases from the audio data to determine the likelihood of a phishing scam. For example, if keywords such as "bank account" or "password" are included, it is determined that there is a high probability of a phishing scam. Furthermore, the analysis unit can analyze sender information of the audio data and evaluate its trustworthiness. For example, it evaluates whether the sender is trustworthy based on the sender's phone number and voice characteristics. Voice characteristics include voice tone, accent, and speaking patterns. This allows the analysis unit to comprehensively evaluate the content of the audio data and the sender's information, enabling it to determine the possibility of a phishing scam with high accuracy.

[0031] The detection unit detects signs of phishing scams based on data analyzed by the analysis unit. These signs include, but are not limited to, specific keywords, link patterns, and sender information. For example, the detection unit detects signs of phishing scams based on data provided by the analysis unit. Specifically, it comprehensively evaluates keywords and phrases extracted by the analysis unit, sender reliability assessments, and audio data features to determine the likelihood of phishing scams. The detection unit can also use rule-based algorithms to detect signs of phishing scams. For example, rules can be set to detect signs of phishing scams based on specific keywords or link patterns. This allows the detection unit to quickly and accurately detect signs of phishing scams based on data provided by the analysis unit. Furthermore, the detection unit can learn phishing scam patterns based on past phishing scam data and detect new signs of phishing scams. For example, by using a model trained on phishing scam features using audio data from past phishing scams, new signs of phishing scams can be detected with high accuracy. This allows the detection unit to constantly adapt to the latest phishing scam techniques and protect users.

[0032] The service provider provides warnings to users based on signs of phishing scams detected by the detection unit. Warnings include, but are not limited to, pop-up notifications, email notifications, and audio notifications. For example, the service provider may display a pop-up notification on the user's device to warn of a potential phishing scam. Specifically, a warning message can be displayed on the screen while the user is on a call or playing an audio message. The service provider may also send an email notification to the user to inform them of a potential phishing scam. For example, a warning email may be sent to the user's email address to inform them of a potential phishing scam. Furthermore, the service provider may provide warnings to users using audio notifications. For example, an audio message may be played to warn of a potential phishing scam. This allows users to receive not only visual but also auditory notifications. In addition, the service provider can collect user feedback to continuously improve the accuracy and effectiveness of warnings. For example, the content and timing of warnings can be adjusted based on the user's actions and feedback after receiving a warning. This allows the service provider to provide users with prompt and appropriate warnings and protect them from phishing scams.

[0033] The phishing prevention system includes a processing unit that processes voice and text data locally. Specific methods of local processing include, but are not limited to, processing within the device and processing without using the cloud. For example, the processing unit analyzes voice and text data within the user's device to detect signs of phishing. The processing unit can also protect user privacy by processing data within the device without using the cloud. For example, the processing unit encrypts voice and text data within the device and analyzes it without transmitting it externally. This protects user privacy by processing voice and text data locally.

[0034] The phishing prevention system includes a protection unit to safeguard user privacy. Specific methods of privacy protection include, but are not limited to, data encryption, access control, and anonymization. For example, the protection unit can encrypt voice and text data to prevent unauthorized external access. It can also control access to data, ensuring only specific users can access it. For example, it can control access based on user authentication information to prevent misuse of data. Furthermore, the protection unit can anonymize data to protect users' personal information. For example, it can remove personal information from voice and text data and analyze the anonymized data. This enhances user trust by protecting user privacy.

[0035] The phishing prevention system includes an isolation unit that isolates emails when signs of phishing are detected. The isolation unit isolates emails when signs of phishing are detected. Specific methods for isolating emails include, but are not limited to, moving them to a quarantine folder and notifying the user. For example, the isolation unit moves emails showing signs of phishing to a quarantine folder and notifies the user. The isolation unit can also automatically delete emails showing signs of phishing. For example, the isolation unit deletes emails showing signs of phishing and notifies the user. Furthermore, the isolation unit can analyze emails showing signs of phishing and provide detailed information. For example, the isolation unit analyzes sender information and link patterns in emails showing signs of phishing and notifies the user. This ensures user safety by isolating emails when signs of phishing are detected.

[0036] The analysis unit can analyze audio data and determine whether or not it is a phishing scam. For example, the analysis unit can analyze the audio data using machine learning algorithms to detect signs of a phishing scam. For instance, the analysis unit can detect keywords such as "bank account" or "password" in the audio data, increasing the likelihood of it being a phishing scam. The analysis unit can also analyze the sender information of the audio data and evaluate its reliability. For example, the analysis unit can evaluate reliability based on the sender's phone number and voice characteristics. This allows for the early detection of phishing scams by analyzing audio data and determining the likelihood of a phishing scam.

[0037] The analysis unit can analyze text data and detect signs of phishing scams. For example, the analysis unit can analyze text data using text analysis algorithms to detect signs of phishing scams. For instance, the analysis unit can detect keywords such as "bank account" or "password" in the text data, increasing the likelihood of a phishing scam. The analysis unit can also analyze sender information in the text data and evaluate its reliability. For example, the analysis unit can evaluate reliability based on the sender's email address and link patterns. By analyzing text data and detecting signs of phishing scams, it becomes possible to prevent phishing scams.

[0038] The analysis unit can improve the accuracy of voice data analysis by referring to the user's past call history. For example, the analysis unit can improve the accuracy of voice data analysis based on the user's past call history. For example, the analysis unit can detect similar patterns based on the call history of phishing scams the user has received in the past. The analysis unit can also extract specific keywords or phrases from the user's past call history and use them in the analysis. Furthermore, the analysis unit can analyze the user's call history and prioritize the analysis of calls that are highly likely to be phishing scams. In this way, the accuracy of the analysis is improved by referring to the user's past call history.

[0039] The analysis unit can optimize its analysis algorithm by analyzing the user's email usage patterns when analyzing text data. For example, the analysis unit can optimize the text data analysis algorithm based on the user's email usage patterns. For instance, the analysis unit can learn frequently used phrases and words from the user and detect signs of phishing scams. The analysis unit can also analyze the user's email sending and receiving patterns and detect abnormal patterns. Furthermore, the analysis unit can prioritize the analysis of emails that are highly likely to be phishing scams based on the user's email usage history. In this way, the analysis algorithm is optimized by analyzing the user's email usage patterns.

[0040] The analysis unit can perform analysis based on the user's geographical location information when analyzing voice data. For example, if the user is in a specific region, the analysis unit can incorporate patterns of phishing scams that frequently occur in that region into its analysis. The analysis unit can also perform analysis considering regional languages ​​and dialects based on the user's current location. Furthermore, the analysis unit can optimize the analysis by considering the local communication environment based on the user's geographical location information. This improves the accuracy of the analysis by considering the user's geographical location information.

[0041] The analysis unit can analyze users' social media activity during text data analysis and prioritize the analysis of relevant data. For example, the analysis unit analyzes text data based on users' social media activity. For instance, the analysis unit learns phrases and words that users frequently use on social media and detects signs of phishing scams. The analysis unit can also extract specific keywords and topics from users' social media activity and utilize them in the analysis. Furthermore, the analysis unit can prioritize the analysis of text data that is highly likely to be related to phishing scams based on users' social media activity. In this way, by analyzing users' social media activity, relevant data can be prioritized for analysis.

[0042] The detection unit can improve detection accuracy by referring to past phishing scam data when detecting signs of phishing scams. For example, the detection unit can detect signs of phishing scams based on past phishing scam data. For example, the detection unit can detect similar patterns based on past phishing scam data. The detection unit can also extract specific keywords or phrases from past phishing scam data and use them for detection. Furthermore, the detection unit can analyze past phishing scam data and prioritize the detection of signs that are highly likely to be phishing scams. In this way, detection accuracy is improved by referring to past phishing scam data.

[0043] The detection unit can analyze the user's communication patterns to optimize the detection algorithm when detecting signs of phishing scams. For example, the detection unit can detect signs of phishing scams based on the user's communication patterns. For example, the detection unit can detect abnormal patterns based on the user's communication patterns. The detection unit can also extract specific keywords or phrases from the user's communication patterns and use them for detection. Furthermore, the detection unit can analyze the user's communication patterns and prioritize the detection of signs that are highly likely to be phishing scams. In this way, the detection algorithm is optimized by analyzing the user's communication patterns.

[0044] The detection unit can take the user's geographical location into consideration when detecting signs of phishing scams. For example, the detection unit can detect signs of phishing scams based on the user's geographical location. For instance, if the user is in a specific region, the detection unit will reflect the patterns of phishing scams that frequently occur in that region in its detection. The detection unit can also take into account regional languages ​​and dialects based on the user's current location. Furthermore, the detection unit can optimize detection by taking into account the local communication environment based on the user's geographical location. This improves the accuracy of detection by considering the user's geographical location.

[0045] The detection unit can analyze the user's social media activity to prioritize the detection of relevant signs when detecting signs of phishing scams. For example, the detection unit can detect signs of phishing scams based on the user's social media activity. For instance, the detection unit can learn phrases and words that the user frequently uses on social media to detect signs of phishing scams. The detection unit can also extract specific keywords and topics from the user's social media activity and utilize them in detection. Furthermore, the detection unit can prioritize the detection of signs that are highly likely to be phishing scams based on the user's social media activity. This allows for the priority detection of relevant signs by analyzing the user's social media activity.

[0046] The service provider can select the most appropriate warning method by referring to the user's past warning history when providing a warning. For example, the service provider can select a warning method based on the user's past warning history. For example, the service provider can issue similar warnings based on the warning history the user has received in the past. The service provider can also extract specific keywords or phrases from the user's past warning history and use them in warnings. Furthermore, the service provider can analyze the user's warning history and select the most effective warning method. In this way, the service provider can select the most appropriate warning method by referring to the user's past warning history.

[0047] The alert system can adjust the urgency of an alert based on the user's current situation. For example, if the user is on the move, the alert system will issue a high-urgency alert. Conversely, if the user is relaxed, the alert system can issue a low-urgency alert. Furthermore, if the user is stressed, the alert system will issue a concise and highly visible alert. By adjusting the urgency of the alert based on the user's current situation, more appropriate alerts can be provided.

[0048] The service provider can select the most appropriate warning method when issuing a warning, taking into account the user's geographical location. For example, the service provider can select a warning method based on the user's geographical location. For instance, if the user is in a specific region, the service provider can issue a warning based on patterns of phishing scams that frequently occur in that region. The service provider can also issue a warning based on the user's current location, taking into account regional languages ​​and dialects. Furthermore, the service provider can optimize the warning based on the user's geographical location, taking into account the local communication environment. This allows the service provider to select the most appropriate warning method by considering the user's geographical location.

[0049] The service provider can analyze a user's social media activity and provide relevant warnings when issuing warnings. For example, the service provider can provide warnings based on a user's social media activity. For instance, the service provider can learn phrases and words that a user frequently uses on social media and warn of signs of phishing scams. The service provider can also extract specific keywords and topics from a user's social media activity and use them in warnings. Furthermore, the service provider can prioritize issuing warnings that are highly likely to be phishing scams based on a user's social media activity. In this way, relevant warnings can be provided by analyzing a user's social media activity.

[0050] The processing unit can select the optimal processing method by referring to the user's past data processing history during data processing. For example, the processing unit can select a data processing method based on the user's past data processing history. For example, the processing unit can select a similar processing method based on the user's past data processing history. The processing unit can also extract specific keywords or phrases from the user's past data processing history and utilize them in processing. Furthermore, the processing unit can analyze the user's data processing history and select the most efficient processing method. In this way, the optimal processing method can be selected by referring to the user's past data processing history.

[0051] The processing unit can adjust processing priorities based on the user's current communication status during data processing. For example, if the user is on the move, the processing unit will prioritize high-priority data processing. If the user is relaxed, the processing unit can distribute all data processing evenly. Furthermore, if the user is stressed, the processing unit will prioritize simple data processing. By adjusting processing priorities based on the user's current communication status, more appropriate data processing becomes possible.

[0052] The processing unit can select the optimal processing method when processing data, taking into account the user's geographical location information. For example, the processing unit can select a data processing method based on the user's geographical location information. For instance, if the user is in a specific region, the processing unit will perform processing based on data processing patterns that frequently occur in that region. The processing unit can also perform processing based on the user's current location, taking into account the region's specific communication environment. Furthermore, the processing unit can optimize processing based on the user's geographical location information, taking into account the region's communication environment. In this way, the optimal processing method can be selected by considering the user's geographical location information.

[0053] The processing unit can analyze users' social media activity during data processing and prioritize the processing of relevant data. For example, the processing unit can process data based on users' social media activity. For instance, the processing unit can learn phrases and words that users frequently use on social media and utilize them in data processing. The processing unit can also extract specific keywords and topics from users' social media activity and utilize them in data processing. Furthermore, the processing unit can prioritize the processing of relevant data based on users' social media activity. This allows for the priority processing of relevant data by analyzing users' social media activity.

[0054] The protection unit can select the optimal protection method by referring to the user's past privacy protection history when protecting privacy. For example, the protection unit can select a privacy protection method based on the user's past privacy protection history. For example, the protection unit can select a similar protection method based on the user's past privacy protection history. The protection unit can also extract specific keywords or phrases from the user's past privacy protection history and use them for protection. Furthermore, the protection unit can analyze the user's privacy protection history and select the most effective protection method. In this way, the optimal protection method can be selected by referring to the user's past privacy protection history.

[0055] The protection unit can select the optimal protection method when protecting privacy, taking into account the user's geographical location. For example, the protection unit can select a privacy protection method based on the user's geographical location. For instance, if the user is in a specific region, the protection unit can provide protection based on patterns of privacy infringement that frequently occur in that region. The protection unit can also provide protection based on the user's current location, taking into account region-specific privacy protection methods. Furthermore, the protection unit can optimize protection based on the user's geographical location, taking into account the local communication environment. This allows the system to select the optimal protection method by considering the user's geographical location.

[0056] The quarantine unit can select the optimal quarantine method by referring to the user's past email quarantine history when quarantining an email. For example, the quarantine unit can select an email quarantine method based on the user's past email quarantine history. For example, the quarantine unit can quarantine similar emails based on the history of emails the user has quarantined in the past. The quarantine unit can also extract specific keywords or phrases from the user's past email quarantine history and use them for quarantine. Furthermore, the quarantine unit can analyze the user's email quarantine history and select the most effective quarantine method. In this way, the optimal quarantine method can be selected by referring to the user's past email quarantine history.

[0057] The isolation unit can select the optimal isolation method when isolating emails, taking into account the user's geographical location. For example, the isolation unit can select an email isolation method based on the user's geographical location. For instance, if the user is in a specific region, the isolation unit can isolate emails based on patterns of phishing scams that frequently occur in that region. The isolation unit can also isolate emails based on the user's current location, taking into account regional languages ​​and dialects. Furthermore, the isolation unit can isolate emails based on the user's geographical location, taking into account the regional communication environment. This allows the system to select the optimal isolation method by considering the user's geographical location.

[0058] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0059] The analysis unit can improve the accuracy of its analysis by referring to the user's past voice data during the analysis of voice data. For example, the analysis unit can detect similar patterns based on the user's past phishing scam call history. The analysis unit can also extract specific keywords and phrases from the user's past voice data and utilize them in the analysis. Furthermore, the analysis unit can analyze the user's voice data and prioritize the analysis of calls that are highly likely to be phishing scams. This improves the accuracy of the analysis by referring to the user's past voice data.

[0060] The analysis unit can perform analysis based on the user's geographical location information when analyzing voice data. For example, if the user is in a specific region, the analysis unit can incorporate patterns of phishing scams that frequently occur in that region into its analysis. Furthermore, the analysis unit can perform analysis considering regional languages ​​and dialects based on the user's current location. In addition, the analysis unit can optimize the analysis by considering the local communication environment based on the user's geographical location information. This improves the accuracy of the analysis by taking the user's geographical location information into account.

[0061] The analysis unit can optimize its analysis algorithm by analyzing the user's email usage patterns during text data analysis. For example, the analysis unit can learn frequently used phrases and words from the user to detect signs of phishing scams. It can also analyze the user's email sending and receiving patterns to detect abnormal patterns. Furthermore, based on the user's email usage history, the analysis unit can prioritize the analysis of emails that are highly likely to be phishing scams. In this way, the analysis algorithm is optimized by analyzing the user's email usage patterns.

[0062] The detection unit can improve detection accuracy by referring to past phishing scam data when detecting signs of a phishing scam. For example, the detection unit can detect similar patterns based on past phishing scam data. The detection unit can also extract specific keywords or phrases from past phishing scam data and utilize them in detection. Furthermore, the detection unit can analyze past phishing scam data and prioritize the detection of signs that are highly likely to be phishing scams. This improves detection accuracy by referring to past phishing scam data.

[0063] The system can select the most appropriate warning method by referring to the user's past warning history when issuing a warning. For example, the system can issue similar warnings based on the user's past warning history. The system can also extract specific keywords or phrases from the user's past warning history and utilize them in warnings. Furthermore, the system can analyze the user's warning history to select the most effective warning method. This allows the system to select the optimal warning method by referring to the user's past warning history.

[0064] The following briefly describes the processing flow for example form 1.

[0065] Step 1: The analysis unit analyzes the audio data. The audio data includes call recordings, voice messages, and audio files. The analysis unit uses machine learning algorithms to analyze the audio data and detect signs of phishing scams. It also extracts specific keywords and phrases from the audio data to determine the likelihood of a phishing scam. Furthermore, it analyzes sender information to evaluate its reliability. Step 2: The analysis unit analyzes the text data. This text data includes emails, chat messages, document files, etc. The analysis unit extracts specific keywords and phrases from the text data to determine the possibility of phishing scams. Furthermore, it analyzes sender information to evaluate its reliability. Step 3: The detection unit detects signs of phishing scams based on the data analyzed by the analysis unit. These signs include specific keywords, link patterns, and sender information. The detection unit uses a rule-based algorithm to detect signs of phishing scams based on the data provided by the analysis unit. Step 4: The provider unit provides a warning to the user based on the signs of phishing detected by the detection unit. Warnings may include pop-up notifications, email notifications, and voice notifications. The provider unit displays a pop-up notification on the user's device to warn of the possibility of phishing. It can also provide warnings to the user using email notifications or voice notifications.

[0066] (Example of form 2) An embodiment of the present invention provides an AI-based phishing fraud prevention system for mobile phone carriers. This system processes voice and text data locally on the user's device, protecting the user's privacy. Next, the AI ​​analyzes the voice data to determine if it is potentially a phishing scam. Furthermore, the AI ​​analyzes the text data of emails to detect signs of phishing scams. This provides a secure communication environment and enhances user trust. For example, if a call received by a user is potentially a phishing scam, the AI ​​issues a warning to alert the user. Also, if an email shows signs of phishing scams, the AI ​​automatically isolates the email and notifies the user. In this way, the AI-based phishing fraud prevention system keeps the user's communications secure and protects them from phishing scams.

[0067] The phishing fraud prevention system according to the embodiment comprises an analysis unit, a detection unit, and a provision unit. The analysis unit analyzes audio data. Audio data includes, but is not limited to, call recordings, voice messages, and audio files. The analysis unit analyzes the audio data using a machine learning algorithm, for example, to detect signs of phishing fraud. The analysis unit can also extract specific keywords or phrases from the audio data and determine the likelihood of phishing fraud. For example, the analysis unit detects keywords such as "bank account" and "password" in the audio data to increase the likelihood of phishing fraud. Furthermore, the analysis unit can analyze sender information of the audio data and evaluate its reliability. For example, the analysis unit evaluates reliability based on the sender's phone number and voice characteristics. The detection unit detects signs of phishing fraud based on the data analyzed by the analysis unit. Signs of phishing fraud include, but are not limited to, specific keywords, link patterns, and sender information. The detection unit detects signs of phishing fraud based on, for example, the data provided by the analysis unit. Furthermore, the detection unit may use rule-based algorithms to detect signs of phishing scams. For example, the detection unit may detect signs of phishing scams based on specific keywords or link patterns. The provisioning unit provides warnings to the user based on the signs of phishing scams detected by the detection unit. Warnings may include, but are not limited to, pop-up notifications, email notifications, or voice notifications. For example, the provisioning unit may display a pop-up notification on the user's device to warn of a potential phishing scam. The provisioning unit may also send an email notification to the user to inform them of a potential phishing scam. In addition, the provisioning unit may provide warnings to the user using voice notifications. For example, the provisioning unit may play a voice message to warn of a potential phishing scam. Thus, the phishing scam prevention system according to the embodiment can keep the user's communications secure and protect them from phishing scams.

[0068] The analysis unit analyzes audio data. Audio data includes, but is not limited to, call recordings, voice messages, and audio files. For example, the analysis unit uses machine learning algorithms to analyze audio data and detect signs of phishing scams. Specifically, it analyzes the waveform and spectrum of the audio data and extracts features. These features include variations in pitch, tempo, volume, and specific frequency components. The machine learning algorithm evaluates the likelihood of a phishing scam based on these features. For example, a model trained on audio data from past phishing scams can be used to evaluate new audio data. The analysis unit can also extract specific keywords and phrases from the audio data to determine the likelihood of a phishing scam. For example, if keywords such as "bank account" or "password" are included, it is determined that there is a high probability of a phishing scam. Furthermore, the analysis unit can analyze sender information of the audio data and evaluate its trustworthiness. For example, it evaluates whether the sender is trustworthy based on the sender's phone number and voice characteristics. Voice characteristics include voice tone, accent, and speaking patterns. This allows the analysis unit to comprehensively evaluate the content of the audio data and the sender's information, enabling it to determine the possibility of a phishing scam with high accuracy.

[0069] The detection unit detects signs of phishing scams based on data analyzed by the analysis unit. These signs include, but are not limited to, specific keywords, link patterns, and sender information. For example, the detection unit detects signs of phishing scams based on data provided by the analysis unit. Specifically, it comprehensively evaluates keywords and phrases extracted by the analysis unit, sender reliability assessments, and audio data features to determine the likelihood of phishing scams. The detection unit can also use rule-based algorithms to detect signs of phishing scams. For example, rules can be set to detect signs of phishing scams based on specific keywords or link patterns. This allows the detection unit to quickly and accurately detect signs of phishing scams based on data provided by the analysis unit. Furthermore, the detection unit can learn phishing scam patterns based on past phishing scam data and detect new signs of phishing scams. For example, by using a model trained on phishing scam features using audio data from past phishing scams, new signs of phishing scams can be detected with high accuracy. This allows the detection unit to constantly adapt to the latest phishing scam techniques and protect users.

[0070] The service provider provides warnings to users based on signs of phishing scams detected by the detection unit. Warnings include, but are not limited to, pop-up notifications, email notifications, and audio notifications. For example, the service provider may display a pop-up notification on the user's device to warn of a potential phishing scam. Specifically, a warning message can be displayed on the screen while the user is on a call or playing an audio message. The service provider may also send an email notification to the user to inform them of a potential phishing scam. For example, a warning email may be sent to the user's email address to inform them of a potential phishing scam. Furthermore, the service provider may provide warnings to users using audio notifications. For example, an audio message may be played to warn of a potential phishing scam. This allows users to receive not only visual but also auditory notifications. In addition, the service provider can collect user feedback to continuously improve the accuracy and effectiveness of warnings. For example, the content and timing of warnings can be adjusted based on the user's actions and feedback after receiving a warning. This allows the service provider to provide users with prompt and appropriate warnings and protect them from phishing scams.

[0071] The phishing prevention system includes a processing unit that processes voice and text data locally. Specific methods of local processing include, but are not limited to, processing within the device and processing without using the cloud. For example, the processing unit analyzes voice and text data within the user's device to detect signs of phishing. The processing unit can also protect user privacy by processing data within the device without using the cloud. For example, the processing unit encrypts voice and text data within the device and analyzes it without transmitting it externally. This protects user privacy by processing voice and text data locally.

[0072] The phishing prevention system includes a protection unit to safeguard user privacy. Specific methods of privacy protection include, but are not limited to, data encryption, access control, and anonymization. For example, the protection unit can encrypt voice and text data to prevent unauthorized external access. It can also control access to data, ensuring only specific users can access it. For example, it can control access based on user authentication information to prevent misuse of data. Furthermore, the protection unit can anonymize data to protect users' personal information. For example, it can remove personal information from voice and text data and analyze the anonymized data. This enhances user trust by protecting user privacy.

[0073] The phishing prevention system includes an isolation unit that isolates emails when signs of phishing are detected. The isolation unit isolates emails when signs of phishing are detected. Specific methods for isolating emails include, but are not limited to, moving them to a quarantine folder and notifying the user. For example, the isolation unit moves emails showing signs of phishing to a quarantine folder and notifies the user. The isolation unit can also automatically delete emails showing signs of phishing. For example, the isolation unit deletes emails showing signs of phishing and notifies the user. Furthermore, the isolation unit can analyze emails showing signs of phishing and provide detailed information. For example, the isolation unit analyzes sender information and link patterns in emails showing signs of phishing and notifies the user. This ensures user safety by isolating emails when signs of phishing are detected.

[0074] The analysis unit can analyze audio data and determine whether or not it is a phishing scam. For example, the analysis unit can analyze the audio data using machine learning algorithms to detect signs of a phishing scam. For instance, the analysis unit can detect keywords such as "bank account" or "password" in the audio data, increasing the likelihood of it being a phishing scam. The analysis unit can also analyze the sender information of the audio data and evaluate its reliability. For example, the analysis unit can evaluate reliability based on the sender's phone number and voice characteristics. This allows for the early detection of phishing scams by analyzing audio data and determining the likelihood of a phishing scam.

[0075] The analysis unit can analyze text data and detect signs of phishing scams. For example, the analysis unit can analyze text data using text analysis algorithms to detect signs of phishing scams. For instance, the analysis unit can detect keywords such as "bank account" or "password" in the text data, increasing the likelihood of a phishing scam. The analysis unit can also analyze sender information in the text data and evaluate its reliability. For example, the analysis unit can evaluate reliability based on the sender's email address and link patterns. By analyzing text data and detecting signs of phishing scams, it becomes possible to prevent phishing scams.

[0076] The analysis unit can estimate the user's emotions and adjust the method of analyzing the audio data based on the estimated emotions. For example, the analysis unit can estimate the user's emotions using voice tone analysis or facial recognition. For example, the analysis unit can analyze the user's voice tone to determine whether they are tense or relaxed. The analysis unit can also capture the user's facial expressions with a camera and estimate emotions using a facial recognition algorithm. For example, the analysis unit can analyze changes in the user's facial expressions and calculate an emotion score. Furthermore, the analysis unit can adjust the method of analyzing the audio data based on the user's emotions. For example, if the user is tense, the analysis unit can quickly analyze the audio data and provide results immediately. If the user is relaxed, the analysis unit can perform a more detailed analysis and provide more information. Furthermore, if the user is stressed, the analysis unit can summarize the analysis results concisely to avoid burdening the user. In this way, adjusting the method of analyzing audio data based on the user's emotions enables more appropriate analysis. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0077] The analysis unit can improve the accuracy of voice data analysis by referring to the user's past call history. For example, the analysis unit can improve the accuracy of voice data analysis based on the user's past call history. For example, the analysis unit can detect similar patterns based on the call history of phishing scams the user has received in the past. The analysis unit can also extract specific keywords or phrases from the user's past call history and use them in the analysis. Furthermore, the analysis unit can analyze the user's call history and prioritize the analysis of calls that are highly likely to be phishing scams. In this way, the accuracy of the analysis is improved by referring to the user's past call history.

[0078] The analysis unit can optimize its analysis algorithm by analyzing the user's email usage patterns when analyzing text data. For example, the analysis unit can optimize the text data analysis algorithm based on the user's email usage patterns. For instance, the analysis unit can learn frequently used phrases and words from the user and detect signs of phishing scams. The analysis unit can also analyze the user's email sending and receiving patterns and detect abnormal patterns. Furthermore, the analysis unit can prioritize the analysis of emails that are highly likely to be phishing scams based on the user's email usage history. In this way, the analysis algorithm is optimized by analyzing the user's email usage patterns.

[0079] The analysis unit can estimate the user's emotions and determine the priority of text data analysis based on the estimated emotions. For example, the analysis unit can estimate the user's emotions using voice tone analysis or facial recognition. For instance, it can analyze the user's voice tone to determine whether they are tense or relaxed. It can also capture the user's facial expressions with a camera and estimate emotions using a facial recognition algorithm. For example, it can analyze changes in the user's facial expressions and calculate an emotion score. Furthermore, the analysis unit can determine the priority of text data analysis based on the user's emotions. For example, if the user is tense, the analysis unit prioritizes analyzing important text data. If the user is relaxed, the analysis unit can perform a detailed analysis and analyze all text data equally. If the user is stressed, the analysis unit performs a concise analysis and provides only essential information. This allows for more appropriate analysis by determining the priority of text data analysis based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0080] The analysis unit can perform analysis based on the user's geographical location information when analyzing voice data. For example, if the user is in a specific region, the analysis unit can incorporate patterns of phishing scams that frequently occur in that region into its analysis. The analysis unit can also perform analysis considering regional languages ​​and dialects based on the user's current location. Furthermore, the analysis unit can optimize the analysis by considering the local communication environment based on the user's geographical location information. This improves the accuracy of the analysis by considering the user's geographical location information.

[0081] The analysis unit can analyze users' social media activity during text data analysis and prioritize the analysis of relevant data. For example, the analysis unit analyzes text data based on users' social media activity. For instance, the analysis unit learns phrases and words that users frequently use on social media and detects signs of phishing scams. The analysis unit can also extract specific keywords and topics from users' social media activity and utilize them in the analysis. Furthermore, the analysis unit can prioritize the analysis of text data that is highly likely to be related to phishing scams based on users' social media activity. In this way, by analyzing users' social media activity, relevant data can be prioritized for analysis.

[0082] The detection unit can estimate the user's emotions and adjust the phishing scam detection criteria based on the estimated user emotions. For example, the detection unit can estimate the user's emotions using voice tone analysis or facial recognition. For instance, it can analyze the user's voice tone to determine whether they are tense or relaxed. Alternatively, the detection unit can capture the user's facial expressions with a camera and estimate emotions using a facial recognition algorithm. For example, it can analyze changes in the user's facial expressions and calculate an emotion score. Furthermore, the detection unit can adjust the phishing scam detection criteria based on the user's emotions. For example, if the user is tense, the detection unit can detect phishing scam signs using strict criteria. If the user is relaxed, the detection unit can detect phishing scam signs using flexible criteria. Furthermore, if the user is stressed, the detection unit can detect phishing scam signs using simple criteria. This allows for more appropriate detection by adjusting the phishing scam detection criteria based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0083] The detection unit can improve detection accuracy by referring to past phishing scam data when detecting signs of phishing scams. For example, the detection unit can detect signs of phishing scams based on past phishing scam data. For example, the detection unit can detect similar patterns based on past phishing scam data. The detection unit can also extract specific keywords or phrases from past phishing scam data and use them for detection. Furthermore, the detection unit can analyze past phishing scam data and prioritize the detection of signs that are highly likely to be phishing scams. In this way, detection accuracy is improved by referring to past phishing scam data.

[0084] The detection unit can analyze the user's communication patterns to optimize the detection algorithm when detecting signs of phishing scams. For example, the detection unit can detect signs of phishing scams based on the user's communication patterns. For example, the detection unit can detect abnormal patterns based on the user's communication patterns. The detection unit can also extract specific keywords or phrases from the user's communication patterns and use them for detection. Furthermore, the detection unit can analyze the user's communication patterns and prioritize the detection of signs that are highly likely to be phishing scams. In this way, the detection algorithm is optimized by analyzing the user's communication patterns.

[0085] The detection unit can estimate the user's emotions and adjust the display method of the phishing scam detection results based on the estimated user emotions. For example, the detection unit can estimate the user's emotions using voice tone analysis or facial recognition. For instance, it can analyze the user's voice tone to determine whether they are tense or relaxed. Alternatively, the detection unit can capture the user's facial expressions with a camera and estimate emotions using a facial recognition algorithm. For example, it can analyze changes in the user's facial expressions and calculate an emotion score. Furthermore, the detection unit can adjust the display method of the phishing scam detection results based on the user's emotions. For example, if the user is tense, the detection unit provides a concise and easily visible display. If the user is relaxed, the detection unit can also provide a display that includes detailed information. Furthermore, if the user is stressed, the detection unit provides a concise display, showing only essential information. This allows for more appropriate display by adjusting the display method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0086] The detection unit can take the user's geographical location into consideration when detecting signs of phishing scams. For example, the detection unit can detect signs of phishing scams based on the user's geographical location. For instance, if the user is in a specific region, the detection unit will reflect the patterns of phishing scams that frequently occur in that region in its detection. The detection unit can also take into account regional languages ​​and dialects based on the user's current location. Furthermore, the detection unit can optimize detection by taking into account the local communication environment based on the user's geographical location. This improves the accuracy of detection by considering the user's geographical location.

[0087] The detection unit can analyze the user's social media activity to prioritize the detection of relevant signs when detecting signs of phishing scams. For example, the detection unit can detect signs of phishing scams based on the user's social media activity. For instance, the detection unit can learn phrases and words that the user frequently uses on social media to detect signs of phishing scams. The detection unit can also extract specific keywords and topics from the user's social media activity and utilize them in detection. Furthermore, the detection unit can prioritize the detection of signs that are highly likely to be phishing scams based on the user's social media activity. This allows for the priority detection of relevant signs by analyzing the user's social media activity.

[0088] The system can estimate the user's emotions and adjust the way warnings are delivered based on those emotions. For example, the system can estimate the user's emotions using voice tone analysis or facial recognition. For instance, it can analyze the user's voice tone to determine whether they are tense or relaxed. The system can also capture the user's facial expressions with a camera and estimate their emotions using a facial recognition algorithm. For example, it can analyze changes in the user's facial expressions and calculate an emotion score. Furthermore, the system can adjust the way warnings are delivered based on the user's emotions. For example, if the user is tense, the system will issue a warning in a calm tone. If the user is relaxed, the system can issue a warning in a bright tone. Furthermore, if the user is stressed, the system will issue a concise and highly visible warning. By adjusting the way warnings are delivered based on the user's emotions, more appropriate warnings become possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0089] The service provider can select the most appropriate warning method by referring to the user's past warning history when providing a warning. For example, the service provider can select a warning method based on the user's past warning history. For example, the service provider can issue similar warnings based on the warning history the user has received in the past. The service provider can also extract specific keywords or phrases from the user's past warning history and use them in warnings. Furthermore, the service provider can analyze the user's warning history and select the most effective warning method. In this way, the service provider can select the most appropriate warning method by referring to the user's past warning history.

[0090] The alert system can adjust the urgency of an alert based on the user's current situation. For example, if the user is on the move, the alert system will issue a high-urgency alert. Conversely, if the user is relaxed, the alert system can issue a low-urgency alert. Furthermore, if the user is stressed, the alert system will issue a concise and highly visible alert. By adjusting the urgency of the alert based on the user's current situation, more appropriate alerts can be provided.

[0091] The system can estimate the user's emotions and prioritize warnings based on those emotions. For example, the system can estimate the user's emotions using voice tone analysis or facial recognition. For instance, it can analyze the user's voice tone to determine if they are tense or relaxed. Alternatively, it can capture the user's facial expressions with a camera and estimate their emotions using a facial recognition algorithm. For example, it can analyze changes in the user's facial expressions and calculate an emotion score. Furthermore, the system can prioritize warnings based on the user's emotions. For example, if the user is tense, the system will prioritize important warnings. If the user is relaxed, the system can distribute all warnings equally. If the user is stressed, the system will prioritize concise warnings. This allows for more appropriate warnings by prioritizing them based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0092] The service provider can select the most appropriate warning method when issuing a warning, taking into account the user's geographical location. For example, the service provider can select a warning method based on the user's geographical location. For instance, if the user is in a specific region, the service provider can issue a warning based on patterns of phishing scams that frequently occur in that region. The service provider can also issue a warning based on the user's current location, taking into account regional languages ​​and dialects. Furthermore, the service provider can optimize the warning based on the user's geographical location, taking into account the local communication environment. This allows the service provider to select the most appropriate warning method by considering the user's geographical location.

[0093] The service provider can analyze a user's social media activity and provide relevant warnings when issuing warnings. For example, the service provider can provide warnings based on a user's social media activity. For instance, the service provider can learn phrases and words that a user frequently uses on social media and warn of signs of phishing scams. The service provider can also extract specific keywords and topics from a user's social media activity and use them in warnings. Furthermore, the service provider can prioritize issuing warnings that are highly likely to be phishing scams based on a user's social media activity. In this way, relevant warnings can be provided by analyzing a user's social media activity.

[0094] The processing unit can estimate the user's emotions and adjust the timing of data processing based on the estimated emotions. For example, the processing unit can estimate the user's emotions using voice tone analysis or facial recognition. For instance, it can analyze the user's voice tone to determine whether they are tense or relaxed. Alternatively, it can capture the user's facial expressions with a camera and estimate emotions using a facial recognition algorithm. For example, it can analyze changes in the user's facial expressions and calculate an emotion score. Furthermore, the processing unit can adjust the timing of data processing based on the user's emotions. For example, if the user is tense, the processing unit can process the data quickly and provide immediate results. If the user is relaxed, the processing unit can perform detailed data processing to provide more information. Additionally, if the user is stressed, the processing unit can summarize the data processing results concisely to avoid burdening the user. This allows for more appropriate data processing by adjusting the timing of data processing based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0095] The processing unit can select the optimal processing method by referring to the user's past data processing history during data processing. For example, the processing unit can select a data processing method based on the user's past data processing history. For example, the processing unit can select a similar processing method based on the user's past data processing history. The processing unit can also extract specific keywords or phrases from the user's past data processing history and utilize them in processing. Furthermore, the processing unit can analyze the user's data processing history and select the most efficient processing method. In this way, the optimal processing method can be selected by referring to the user's past data processing history.

[0096] The processing unit can adjust processing priorities based on the user's current communication status during data processing. For example, if the user is on the move, the processing unit will prioritize high-priority data processing. If the user is relaxed, the processing unit can distribute all data processing evenly. Furthermore, if the user is stressed, the processing unit will prioritize simple data processing. By adjusting processing priorities based on the user's current communication status, more appropriate data processing becomes possible.

[0097] The processing unit can estimate the user's emotions and determine the priority of data processing based on the estimated emotions. For example, the processing unit can estimate the user's emotions using voice tone analysis or facial recognition. For instance, it can analyze the user's voice tone to determine whether they are tense or relaxed. Alternatively, it can capture the user's facial expressions with a camera and estimate their emotions using a facial recognition algorithm. For example, it can analyze changes in the user's facial expressions and calculate an emotion score. Furthermore, the processing unit can determine the priority of data processing based on the user's emotions. For example, if the user is tense, the processing unit prioritizes important data processing. If the user is relaxed, the processing unit can distribute all data processing evenly. Furthermore, if the user is stressed, the processing unit prioritizes simple data processing. This allows for more appropriate data processing by prioritizing data processing based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0098] The processing unit can select the optimal processing method when processing data, taking into account the user's geographical location information. For example, the processing unit can select a data processing method based on the user's geographical location information. For instance, if the user is in a specific region, the processing unit will perform processing based on data processing patterns that frequently occur in that region. The processing unit can also perform processing based on the user's current location, taking into account the region's specific communication environment. Furthermore, the processing unit can optimize processing based on the user's geographical location information, taking into account the region's communication environment. In this way, the optimal processing method can be selected by considering the user's geographical location information.

[0099] The processing unit can analyze users' social media activity during data processing and prioritize the processing of relevant data. For example, the processing unit can process data based on users' social media activity. For instance, the processing unit can learn phrases and words that users frequently use on social media and utilize them in data processing. The processing unit can also extract specific keywords and topics from users' social media activity and utilize them in data processing. Furthermore, the processing unit can prioritize the processing of relevant data based on users' social media activity. This allows for the priority processing of relevant data by analyzing users' social media activity.

[0100] The protection unit can estimate the user's emotions and adjust the privacy protection method based on the estimated emotions. For example, the protection unit can estimate the user's emotions using voice tone analysis or facial recognition. For example, the protection unit can analyze the user's voice tone to determine whether they are tense or relaxed. The protection unit can also capture the user's facial expressions with a camera and estimate emotions using a facial recognition algorithm. For example, the protection unit can analyze changes in the user's facial expressions and calculate an emotion score. Furthermore, the protection unit can adjust the privacy protection method based on the user's emotions. For example, if the user is tense, the protection unit will implement strict privacy protection. If the user is relaxed, the protection unit can implement flexible privacy protection. Furthermore, if the user is stressed, the protection unit will implement simple privacy protection. In this way, by adjusting the privacy protection method based on the user's emotions, more appropriate privacy protection becomes possible. Emotion estimation is achieved using emotion estimation functions, 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.

[0101] The protection unit can select the optimal protection method by referring to the user's past privacy protection history when protecting privacy. For example, the protection unit can select a privacy protection method based on the user's past privacy protection history. For example, the protection unit can select a similar protection method based on the user's past privacy protection history. The protection unit can also extract specific keywords or phrases from the user's past privacy protection history and use them for protection. Furthermore, the protection unit can analyze the user's privacy protection history and select the most effective protection method. In this way, the optimal protection method can be selected by referring to the user's past privacy protection history.

[0102] The protection unit can estimate the user's emotions and determine the priority of privacy protection based on the estimated emotions. For example, the protection unit can estimate the user's emotions using voice tone analysis or facial recognition. For instance, it can analyze the user's voice tone to determine whether they are tense or relaxed. It can also capture the user's facial expressions with a camera and estimate emotions using facial recognition algorithms. For example, it can analyze changes in the user's facial expressions and calculate an emotion score. Furthermore, the protection unit can determine the priority of privacy protection based on the user's emotions. For example, if the user is tense, the protection unit prioritizes important privacy protection. If the user is relaxed, the protection unit can distribute all privacy protection equally. Furthermore, if the user is stressed, the protection unit prioritizes simple privacy protection. This allows for more appropriate privacy protection by determining the priority of privacy protection based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0103] The protection unit can select the optimal protection method when protecting privacy, taking into account the user's geographical location. For example, the protection unit can select a privacy protection method based on the user's geographical location. For instance, if the user is in a specific region, the protection unit can provide protection based on patterns of privacy infringement that frequently occur in that region. The protection unit can also provide protection based on the user's current location, taking into account region-specific privacy protection methods. Furthermore, the protection unit can optimize protection based on the user's geographical location, taking into account the local communication environment. This allows the system to select the optimal protection method by considering the user's geographical location.

[0104] The isolation unit can estimate the user's emotions and adjust the email isolation method based on the estimated emotions. For example, the isolation unit can estimate the user's emotions using voice tone analysis or facial recognition. For instance, it can analyze the user's voice tone to determine whether they are tense or relaxed. It can also capture the user's facial expressions with a camera and estimate emotions using facial recognition algorithms. For example, it can analyze changes in the user's facial expressions and calculate an emotion score. Furthermore, the isolation unit can adjust the email isolation method based on the user's emotions. For example, if the user is tense, the isolation unit will quickly isolate the email and notify the user immediately. If the user is relaxed, the isolation unit can provide detailed information and explain the reason for isolation. If the user is stressed, the isolation unit will provide a concise notification, offering only essential information. This allows for more appropriate isolation by adjusting the email isolation method based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0105] The quarantine unit can select the optimal quarantine method by referring to the user's past email quarantine history when quarantining an email. For example, the quarantine unit can select an email quarantine method based on the user's past email quarantine history. For example, the quarantine unit can quarantine similar emails based on the history of emails the user has quarantined in the past. The quarantine unit can also extract specific keywords or phrases from the user's past email quarantine history and use them for quarantine. Furthermore, the quarantine unit can analyze the user's email quarantine history and select the most effective quarantine method. In this way, the optimal quarantine method can be selected by referring to the user's past email quarantine history.

[0106] The isolation unit can estimate the user's emotions and determine the priority of email isolation based on the estimated emotions. For example, the isolation unit can estimate the user's emotions using voice tone analysis or facial recognition. For instance, it can analyze the user's voice tone to determine whether they are tense or relaxed. Alternatively, the isolation unit can capture the user's facial expressions with a camera and estimate emotions using facial recognition algorithms. For example, it can analyze changes in the user's facial expressions and calculate an emotion score. Furthermore, the isolation unit can determine the priority of email isolation based on the user's emotions. For example, if the user is tense, the isolation unit will prioritize isolating important emails. If the user is relaxed, the isolation unit can isolate all emails equally. Furthermore, if the user is stressed, the isolation unit will prioritize isolating concise emails. This allows for more appropriate isolation by determining email isolation priorities based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0107] The isolation unit can select the optimal isolation method when isolating emails, taking into account the user's geographical location. For example, the isolation unit can select an email isolation method based on the user's geographical location. For instance, if the user is in a specific region, the isolation unit can isolate emails based on patterns of phishing scams that frequently occur in that region. The isolation unit can also isolate emails based on the user's current location, taking into account regional languages ​​and dialects. Furthermore, the isolation unit can isolate emails based on the user's geographical location, taking into account the regional communication environment. This allows the system to select the optimal isolation method by considering the user's geographical location.

[0108] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0109] The analysis unit can improve the accuracy of its analysis by referring to the user's past voice data during the analysis of voice data. For example, the analysis unit can detect similar patterns based on the user's past phishing scam call history. The analysis unit can also extract specific keywords and phrases from the user's past voice data and utilize them in the analysis. Furthermore, the analysis unit can analyze the user's voice data and prioritize the analysis of calls that are highly likely to be phishing scams. This improves the accuracy of the analysis by referring to the user's past voice data.

[0110] The analysis unit can perform analysis based on the user's geographical location information when analyzing voice data. For example, if the user is in a specific region, the analysis unit can incorporate patterns of phishing scams that frequently occur in that region into its analysis. Furthermore, the analysis unit can perform analysis considering regional languages ​​and dialects based on the user's current location. In addition, the analysis unit can optimize the analysis by considering the local communication environment based on the user's geographical location information. This improves the accuracy of the analysis by taking the user's geographical location information into account.

[0111] The analysis unit can estimate the user's emotions and adjust the method of analyzing the voice data based on the estimated emotions. For example, the analysis unit can analyze the user's voice tone to determine whether they are tense or relaxed. It can also capture the user's facial expressions with a camera and estimate their emotions using a facial recognition algorithm. Furthermore, if the user is experiencing stress, the analysis unit summarizes the analysis results concisely to avoid burdening the user. This allows for more appropriate analysis by adjusting the voice data analysis method based on the user's emotions.

[0112] The analysis unit can optimize its analysis algorithm by analyzing the user's email usage patterns during text data analysis. For example, the analysis unit can learn frequently used phrases and words from the user to detect signs of phishing scams. It can also analyze the user's email sending and receiving patterns to detect abnormal patterns. Furthermore, based on the user's email usage history, the analysis unit can prioritize the analysis of emails that are highly likely to be phishing scams. In this way, the analysis algorithm is optimized by analyzing the user's email usage patterns.

[0113] The analysis unit can estimate the user's emotions and determine the priority of text data analysis based on the estimated emotions. For example, the analysis unit can analyze the user's voice tone to determine whether they are tense or relaxed. It can also capture the user's facial expressions with a camera and estimate their emotions using a facial recognition algorithm. Furthermore, if the user is experiencing stress, the analysis unit performs a concise analysis, providing only essential information. This allows for more appropriate analysis by prioritizing text data analysis based on the user's emotions.

[0114] The detection unit can improve detection accuracy by referring to past phishing scam data when detecting signs of a phishing scam. For example, the detection unit can detect similar patterns based on past phishing scam data. The detection unit can also extract specific keywords or phrases from past phishing scam data and utilize them in detection. Furthermore, the detection unit can analyze past phishing scam data and prioritize the detection of signs that are highly likely to be phishing scams. This improves detection accuracy by referring to past phishing scam data.

[0115] The detection unit can estimate the user's emotions and adjust the phishing scam detection criteria based on the estimated emotions. For example, the detection unit can analyze the user's voice tone to determine whether they are tense or relaxed. It can also capture the user's facial expressions with a camera and estimate their emotions using a facial recognition algorithm. Furthermore, if the user is feeling stressed, the detection unit can detect signs of a phishing scam using simple criteria. This allows for more accurate detection by adjusting the phishing scam detection criteria based on the user's emotions.

[0116] The system can select the most appropriate warning method by referring to the user's past warning history when issuing a warning. For example, the system can issue similar warnings based on the user's past warning history. The system can also extract specific keywords or phrases from the user's past warning history and utilize them in warnings. Furthermore, the system can analyze the user's warning history to select the most effective warning method. This allows the system to select the optimal warning method by referring to the user's past warning history.

[0117] The system can estimate the user's emotions and adjust the way warnings are expressed based on those emotions. For example, it can analyze the user's voice tone to determine whether they are tense or relaxed. It can also capture the user's facial expressions with a camera and estimate their emotions using a facial recognition algorithm. Furthermore, if the user is feeling stressed, the system will issue a concise and highly visible warning. By adjusting the way warnings are expressed based on the user's emotions, more appropriate warnings can be provided.

[0118] The protection unit can estimate the user's emotions and adjust privacy protection methods based on those emotions. For example, the protection unit can analyze the user's voice tone to determine whether they are tense or relaxed. It can also capture the user's facial expressions with a camera and estimate their emotions using a facial recognition algorithm. Furthermore, if the user is experiencing stress, the protection unit will implement simpler privacy protection measures. This allows for more appropriate privacy protection by adjusting privacy protection methods based on the user's emotions.

[0119] The following briefly describes the processing flow for example form 2.

[0120] Step 1: The analysis unit analyzes the audio data. The audio data includes call recordings, voice messages, and audio files. The analysis unit uses machine learning algorithms to analyze the audio data and detect signs of phishing scams. It also extracts specific keywords and phrases from the audio data to determine the likelihood of a phishing scam. Furthermore, it analyzes sender information to evaluate its reliability. Step 2: The analysis unit analyzes the text data. This text data includes emails, chat messages, document files, etc. The analysis unit extracts specific keywords and phrases from the text data to determine the possibility of phishing scams. Furthermore, it analyzes sender information to evaluate its reliability. Step 3: The detection unit detects signs of phishing scams based on the data analyzed by the analysis unit. These signs include specific keywords, link patterns, and sender information. The detection unit uses a rule-based algorithm to detect signs of phishing scams based on the data provided by the analysis unit. Step 4: The provider unit provides a warning to the user based on the signs of phishing detected by the detection unit. Warnings may include pop-up notifications, email notifications, and voice notifications. The provider unit displays a pop-up notification on the user's device to warn of the possibility of phishing. It can also provide warnings to the user using email notifications or voice notifications.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] Each of the multiple elements described above, including the analysis unit, detection unit, provision unit, processing unit, protection unit, and isolation 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 voice data. The detection unit is implemented by the specific processing unit 290 of the data processing unit 12 and detects signs of phishing scams. The provision unit is implemented by the control unit 46A of the smart device 14 and provides warnings to the user. The processing unit is implemented by the processor 46 of the smart device 14 and processes voice data and text data locally. The protection unit is implemented by the specific processing unit 290 of the data processing unit 12 and protects the user's privacy. The isolation unit is implemented by the control unit 46A of the smart device 14 and isolates emails when signs of phishing scams are detected. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0125] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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).

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] Each of the multiple elements described above, including the analysis unit, detection unit, provision unit, processing unit, protection unit, and isolation 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 voice data. The detection unit is implemented by the specific processing unit 290 of the data processing unit 12 and detects signs of phishing scams. The provision unit is implemented by the control unit 46A of the smart glasses 214 and provides warnings to the user. The processing unit is implemented by the processor 46 of the smart glasses 214 and processes voice data and text data locally. The protection unit is implemented by the specific processing unit 290 of the data processing unit 12 and protects the user's privacy. The isolation unit is implemented by the control unit 46A of the smart glasses 214 and isolates emails when signs of phishing scams are detected. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0141] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.).

[0153] 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.

[0154] 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.

[0155] 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.

[0156] Each of the multiple elements described above, including the analysis unit, detection unit, provision unit, processing unit, protection unit, and isolation 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 voice data. The detection unit is implemented by the specific processing unit 290 of the data processing unit 12 and detects signs of phishing scams. The provision unit is implemented by the control unit 46A of the headset terminal 314 and provides warnings to the user. The processing unit is implemented by the processor 46 of the headset terminal 314 and processes voice data and text data locally. The protection unit is implemented by the specific processing unit 290 of the data processing unit 12 and protects the user's privacy. The isolation unit is implemented by the control unit 46A of the headset terminal 314 and isolates emails when signs of phishing scams are detected. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0157] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.).

[0170] 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.

[0171] 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.

[0172] 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.

[0173] Each of the multiple elements described above, including the analysis unit, detection unit, provision unit, processing unit, protection unit, and isolation unit, is implemented, for example, 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 voice data. The detection unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and detects signs of phishing scams. The provision unit is implemented, for example, by the control unit 46A of the robot 414 and provides warnings to the user. The processing unit is implemented, for example, by the processor 46 of the robot 414 and processes voice data and text data locally. The protection unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and protects the user's privacy. The isolation unit is implemented, for example, by the control unit 46A of the robot 414 and isolates emails when signs of phishing scams are detected. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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."

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] (Note 1) An analysis unit that analyzes audio data and text data, A detection unit that detects signs of phishing fraud based on data analyzed by the aforementioned analysis unit, A providing unit that provides a warning to the user based on the signs of phishing fraud detected by the detection unit, Equipped with system. (Note 2) It includes a processing unit that processes audio and text data locally. The system described in Appendix 1, characterized by the features described herein. (Note 3) It features a protective section to safeguard user privacy. The system described in Appendix 1, characterized by the features described herein. (Note 4) It includes a quarantine section that isolates emails if signs of phishing scams are detected. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned analysis unit, The system analyzes the audio data to determine whether or not it is a phishing scam. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, Analyze text data to detect signs of phishing scams. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, The system estimates the user's emotions and adjusts the audio data analysis method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, When analyzing voice data, we improve analysis accuracy by referring to the user's past call history. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, When analyzing text data, we analyze users' email usage patterns to optimize the analysis algorithm. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, It estimates the user's emotions and determines the priority of text data analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, When analyzing voice data, the analysis is performed based on the user's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, When analyzing text data, the system analyzes users' social media activity and prioritizes analyzing relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 13) The detection unit is We estimate user sentiment and adjust the phishing scam detection criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 14) The detection unit is When detecting signs of a phishing scam, we improve detection accuracy by referring to past phishing scam data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The detection unit is When detecting signs of a phishing scam, the system analyzes the user's communication patterns to optimize the detection algorithm. The system described in Appendix 1, characterized by the features described herein. (Note 16) The detection unit is We estimate the user's sentiment and adjust how phishing scam warnings are displayed based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 17) The detection unit is When detecting signs of a phishing scam, the system takes the user's geographical location into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 18) The detection unit is When detecting signs of a phishing scam, the system analyzes the user's social media activity to prioritize the detection of relevant signs. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned supply 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 20) The aforementioned supply unit is, When issuing a warning, the system selects the most appropriate warning method by referring to the user's past warning history. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned supply unit is, When providing a warning, adjust the urgency of the warning based on the user's current situation. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, The system estimates the user's emotions and prioritizes warnings based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, When providing a warning, the system selects the most appropriate warning method, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned supply unit is, When providing warnings, the system analyzes the user's social media activity and provides relevant warnings. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned processing unit, It estimates the user's emotions and adjusts the timing of data processing based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 26) The aforementioned processing unit, During data processing, the system selects the optimal processing method by referring to the user's past data processing history. The system described in Appendix 2, characterized by the features described herein. (Note 27) The aforementioned processing unit, During data processing, the processing priority is adjusted based on the user's current communication status. The system described in Appendix 2, characterized by the features described herein. (Note 28) The aforementioned processing unit, It estimates the user's emotions and determines the priority of data processing based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 29) The aforementioned processing unit, During data processing, the optimal processing method is selected by considering the user's geographical location information. The system described in Appendix 2, characterized by the features described herein. (Note 30) The aforementioned processing unit, During data processing, the system analyzes users' social media activity and prioritizes processing relevant data. The system described in Appendix 2, characterized by the features described herein. (Note 31) The aforementioned protective part is We estimate the user's emotions and adjust our privacy protection methods based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 32) The aforementioned protective part is When protecting privacy, the system selects the most appropriate protection method by referring to the user's past privacy protection history. The system described in Appendix 3, characterized by the features described herein. (Note 33) The aforementioned protective part is It estimates user sentiment and determines privacy protection priorities based on the estimated user sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 34) The aforementioned protective part is When protecting privacy, the optimal protection method is selected by considering the user's geographical location. The system described in Appendix 3, characterized by the features described herein. (Note 35) The aforementioned isolation section is It estimates the user's sentiment and adjusts the email quarantine method based on the estimated user sentiment. The system described in Appendix 4, characterized by the features described herein. (Note 36) The aforementioned isolation section is When quarantining an email, the system selects the optimal quarantine method by referring to the user's past email quarantine history. The system described in Appendix 4, characterized by the features described herein. (Note 37) The aforementioned isolation section is It estimates the user's sentiment and determines the email quarantine priority based on the estimated user sentiment. The system described in Appendix 4, characterized by the features described herein. (Note 38) The aforementioned isolation section is When quarantining emails, the system selects the optimal quarantine method by considering the user's geographical location. The system described in Appendix 4, characterized by the features described herein. [Explanation of Symbols]

[0193] 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. An analysis unit analyzes the audio data and text data by detecting predetermined keywords in the audio data and text data or by analyzing the sender information of the audio data and text data, A detection unit that detects signs of a phishing scam based on the audio data and text data analyzed by the analysis unit, A providing unit that provides a warning to the user based on the signs of phishing fraud detected by the detection unit, Equipped with, The aforementioned analysis unit, The method for analyzing the audio data is adjusted such that, by analyzing the user's voice tone or by capturing the user's facial expression with a camera and using a facial expression recognition algorithm, the user's emotions, including whether they are tense or relaxed, are estimated, and if the estimated emotion of the user is tense, the audio data is analyzed quickly, and if the estimated emotion of the user is relaxed, a detailed analysis is performed. The aforementioned analysis unit, During the analysis of the aforementioned text data, the system learns phrases or words frequently used by the user and optimizes the text data analysis algorithm based on the user's email usage patterns. A system characterized by the following features.

2. A processing unit that processes the audio data and the text data locally. The system according to feature 1.

3. A protection unit that encrypts the voice data and the text data and prevents unauthorized access from the outside, thereby protecting the user's privacy. The system according to feature 1.

4. The system includes a quarantine section that moves emails to a quarantine folder when signs of phishing scams are detected. The system according to feature 1.

5. The aforementioned analysis unit, Based on the estimated emotions of the user, the system prioritizes the analysis of the text data, and if the user is stressed, it prioritizes the analysis of important text data. The system according to feature 1.

6. The aforementioned analysis unit, When analyzing the aforementioned voice data, the accuracy of the analysis is improved by detecting similar patterns based on the call history of phishing scams the user has received in the past. The system according to feature 1.

Images