system

Abstract

An object of a system according to an embodiment is to detect a fraudulent act on an SNS or a chat application in real time and warn a user.SOLUTION: A system according to an embodiment includes a conversation analysis unit, a URL analysis unit, a warning unit, and a privacy protection unit. The conversation analysis unit analyzes a conversation on an SNS or a chat application. The URL analysis unit analyzes the URL. The warning unit issues a warning to the user for the suspicious conversation or URL detected by the conversation analysis unit and the URL analysis unit. The privacy protector anonymizes and encrypts the user's data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies do not adequately detect fraudulent activities on social media and chat apps in real time and warn users, so there is room for improvement.

[0005] The system according to the embodiment aims to detect fraudulent activities on social media and chat apps in real time and warn users. [Means for solving the problem]

[0006] The system according to the embodiment includes a conversation analysis unit, a URL analysis unit, a warning unit, and a privacy protection unit. The conversation analysis unit analyzes conversations on social media and chat apps. The URL analysis unit analyzes URLs. The warning unit issues a warning to the user about suspicious conversations or URLs detected by the conversation analysis unit and the URL analysis unit. The privacy protection unit anonymizes and encrypts user data. [Effects of the Invention]

[0007] The system according to the embodiment can detect fraudulent activities on social media and chat apps in real time and warn users. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0028] (Example 1) The AI ​​fraud filter system according to an embodiment of the present invention provides safe communication on platforms such as email, SNS, and LINE. This system has the ability to detect suspicious conversations and URLs and immediately warn users of the danger. As a result, the AI ​​fraud filter system can provide users with a safe communication environment and prevent fraudulent acts before they occur.

[0029] An AI fraud filter system according to an embodiment includes a conversation analysis unit, a URL analysis unit, a warning unit, and a privacy protection unit. The conversation analysis unit analyzes conversations on social media and chat apps. For example, the conversation analysis unit uses text mining technology to analyze conversation content and detect potentially fraudulent messages. The conversation analysis unit can also use natural language processing technology to understand the context of the conversation and learn potential fraudulent patterns. The URL analysis unit analyzes URLs. For example, the URL analysis unit analyzes the content of URLs to detect phishing scams and spam links. The URL analysis unit can also analyze the content of images and videos to detect potentially fraudulent visual content. The warning unit issues a warning to the user about suspicious conversations and URLs detected by the conversation analysis unit and URL analysis unit. For example, the warning unit displays a warning such as, "This message may be fraudulent. Please be careful." The warning unit can also provide specific reasons and justifications for issuing the warning, providing information in a format that is easy for the user to understand. The privacy protection unit anonymizes and encrypts user data. For example, the privacy protection unit anonymizes a user's personal information using data masking technology. The privacy protection unit also encrypts communications using AES encryption technology to reduce the risk of information leaking to third parties. As a result, the AI ​​fraud filter system according to the embodiment can provide a safe communication environment for users and prevent fraudulent activities. For example, even if a user receives a fraudulent message while using a social networking site or chat platform, the AI ​​fraud filter system can immediately issue a warning, preventing damage before it occurs. Furthermore, integrating and analyzing information from multiple platforms enables more accurate fraud detection.

[0030] The conversation analysis unit understands the context of the conversation and can learn conversation patterns that may indicate fraud. For example, the generation AI analyzes the context of the conversation and learns patterns that may indicate fraud. For example, it detects messages that emphasize urgency, such as "Please send the money quickly." The conversation analysis unit can also allow the generation AI to analyze the flow of the conversation and learn the frequency of occurrence of keywords that may indicate fraud. The conversation analysis unit can also allow the generation AI to analyze the topic of the conversation and detect changes in the topic that may indicate fraud. In this way, by learning conversation patterns that may indicate fraud, the detection accuracy can be improved.

[0031] The conversation analysis unit can refer to the user's past conversation history and detect content that deviates from normal conversation patterns. For example, the generation AI analyzes the user's past conversation history and detects content that deviates from normal conversation patterns. For example, it detects unusual language or unusual requests for money. The conversation analysis unit can also detect deviating content by having the generation AI learn normal conversation patterns based on the user's past conversation history. The conversation analysis unit can also detect abnormal behavior by having the generation AI refer to the user's past conversation history. In this way, it is possible to detect content that deviates from normal patterns by referring to the user's past conversation history.

[0032] The URL analysis unit can also analyze the content of images or videos to detect potentially fraudulent visual content. For example, the generation AI can use image recognition technology to detect potentially fraudulent visual content, such as detecting fake logos or fraudulent QR codes. The URL analysis unit can also use video analysis technology to detect potentially fraudulent visual content. The URL analysis unit can also develop algorithms for the generation AI to analyze the content of images or videos to detect potentially fraudulent visual content. This allows the generation AI to analyze the content of images or videos to detect potentially fraudulent visual content.

[0033] The URL analysis unit can also analyze conversations in different languages, enabling multilingual fraud detection. For example, the generation AI uses multilingual natural language processing technology to detect potentially fraudulent conversations in different languages. For example, it analyzes messages in English, Spanish, Chinese, etc. The generation AI can also use a translation API to analyze conversations in different languages. The generation AI can also use a multilingual language model to enable multilingual fraud detection. This allows the generation AI to analyze conversations in different languages, enabling multilingual fraud detection.

[0034] The warning unit can provide specific reasons and justification when issuing a warning, and provide information in a form that is easy for the user to understand. For example, the warning unit can provide specific reasons and justification when the generation AI issues a warning. For example, it can display an explanation such as, "This message matches a pattern that has been reported as fraud in the past." The warning unit can also provide reasons and justification based on detected keywords and past fraud cases when the generation AI issues a warning. The warning unit can also develop an interface to provide information in a form that is easy for the user to understand when the generation AI issues a warning. In this way, by providing specific reasons and justification when issuing a warning, it becomes easier for the user to understand.

[0035] The warning unit can refer to feedback from other users before issuing a warning to improve the reliability of the warning. For example, the warning unit refers to feedback from other users before the generation AI issues a warning. For example, a warning is issued if the same message has also been reported as fraud by other users. The warning unit can also improve the reliability of the warning by having the generation AI refer to user evaluation comments and survey results. The warning unit can also evaluate the reliability of the warning based on the number of feedbacks and evaluation scores. In this way, the reliability of the warning is improved by referring to feedback from other users.

[0036] The warning unit can use audio or visual alerts to intuitively notify the user of danger when issuing a warning. For example, when the generation AI issues a warning, the warning unit uses audio alerts to notify the user of danger. For example, the warning unit issues an audio alert such as "Caution! This message may be fraudulent." The warning unit can also use visual alerts to notify the user of danger. For example, the warning unit can display a flash message or a warning icon. The warning unit can also customize the type of audio or visual alert by the generation AI. This allows the user to intuitively notify the user of danger using audio or visual alerts.

[0037] The warning unit can refer to the user's location information when issuing a warning and warn against fraudulent methods specific to the region. For example, the warning unit can refer to the user's location information when the generation AI issues a warning. For example, the warning unit can issue a warning against fraudulent methods that are prevalent in a specific region. The warning unit can also use GPS data or IP address to obtain the user's location information and warn against fraudulent methods specific to the region. The warning unit can also use the generation AI to create a database of fraud patterns for each region and issue a warning based on the user's location information. This makes it possible to refer to the user's location information and warn against fraudulent methods specific to the region.

[0038] The Privacy Protection Department can develop protocols for securely sharing data between different platforms when anonymizing data. For example, the Privacy Protection Department can develop protocols for securely sharing data between different platforms when the Generation AI anonymizes data. For example, the Privacy Protection Department can introduce technology to anonymize and share part of the data. The Privacy Protection Department can also have the Generation AI develop a data sharing protocol to securely share data between different platforms. The Privacy Protection Department can also have the Generation AI develop a security protocol to more securely anonymize data. By developing a protocol for securely sharing data between different platforms, the Privacy Protection Department can more securely anonymize data.

[0039] The privacy protection unit can provide a function that allows a user to select the encryption level of their data when encrypting data. For example, the privacy protection unit can provide a function that allows a user to select the encryption level of their data when the generation AI encrypts data. For example, the privacy protection unit can provide options for standard encryption and strong encryption. The privacy protection unit can also have the generation AI develop a user interface that allows the user to select the encryption level. The privacy protection unit can also have the generation AI provide a choice of encryption levels so that the user can improve the security of their data. Thus, by providing a function that allows a user to select the encryption level of their data, the security of data can be improved.

[0040] The conversation analysis unit can introduce new methods to maintain data consistency and integrity when integrating data from different platforms. For example, the conversation analysis unit can introduce new methods to maintain data consistency and integrity when the generation AI integrates data from different platforms. For example, it can adopt technology to standardize data formats. The conversation analysis unit can also enable the generation AI to perform database consistency checks to maintain data consistency. The conversation analysis unit can also enable the generation AI to develop data integration algorithms to maintain data consistency. This makes it possible to improve data quality by introducing new methods to maintain data consistency and integrity when integrating data from different platforms.

[0041] The conversation analysis unit can develop algorithms that detect data correlations with high accuracy when analyzing data from different platforms. For example, the conversation analysis unit develops algorithms that detect data correlations with high accuracy when the generation AI analyzes data from different platforms. For example, the conversation analysis unit combines and analyzes social media and email data. The conversation analysis unit can also enable the generation AI to detect data correlations using correlation coefficients or regression analysis. The conversation analysis unit can also enable the generation AI to detect data correlations with high accuracy using machine learning algorithms. This allows the development of algorithms that detect data correlations with high accuracy when analyzing data from different platforms, thereby improving the accuracy of fraud detection.

[0042] The conversation analysis unit can provide a data visualization tool when integrating data from different platforms, allowing the user to intuitively understand the data. For example, the conversation analysis unit can provide a data visualization tool when the generation AI integrates data from different platforms. For example, the data can be visually displayed using graphs and charts. The conversation analysis unit can also enable the generation AI to develop a dashboard, allowing the user to intuitively understand the data. The conversation analysis unit can also enable the generation AI to provide an interactive analysis tool, allowing the user to understand the data while manipulating it. In this way, the conversation analysis unit can provide a data visualization tool when integrating data from different platforms, allowing the user to intuitively understand the data.

[0043] The conversation analysis unit updates the data in real time when analyzing data from different platforms, allowing fraud detection to be performed based on the latest information. The conversation analysis unit updates the data in real time when the generation AI analyzes data from different platforms. For example, it collects and analyzes data from social media and emails in real time. The conversation analysis unit can also update the data in real time using streaming data processing technology by the generation AI. The conversation analysis unit can also perform fraud detection based on the latest information using a real-time database by the generation AI. This allows data to be updated in real time when analyzing data from different platforms, allowing fraud detection to be performed based on the latest information.

[0044] The conversation analysis unit learns the user's communication patterns and can issue a warning if they deviate from the normal pattern. For example, the generation AI can learn the user's communication patterns and issue a warning if they deviate from the normal pattern. For example, it can detect unusual language or unusual requests for money. The conversation analysis unit can also enable the generation AI to detect deviations based on the user's communication patterns. The conversation analysis unit can also enable the generation AI to analyze the user's communication patterns and detect abnormal behavior. This allows the generation AI to learn the user's communication patterns and issue a warning if they deviate from the normal pattern.

[0045] The conversation analysis unit can analyze the user's communication history, compare it with past fraud cases, and issue a warning. For example, the generation AI can analyze the user's communication history, compare it with past fraud cases, and issue a warning. For example, it can detect content that matches previously reported fraud messages. The conversation analysis unit can also have the generation AI refer to a database of fraud cases and compare it with the user's communication history. The conversation analysis unit can also have the generation AI analyze the user's communication history based on a list of fraud patterns. This allows the generation AI to analyze the user's communication history, compare it with past fraud cases, and issue a warning.

[0046] The conversation analysis unit can monitor the user's communication environment and automatically take measures if an abnormality is detected. For example, the conversation analysis unit can have the generation AI monitor the user's communication environment and automatically take measures if an abnormality is detected. For example, the conversation analysis unit can automatically block messages that may be fraudulent. The conversation analysis unit can also have the generation AI monitor the user's network environment and take measures if an abnormality is detected. The conversation analysis unit can also have the generation AI monitor the apps the user is using and take measures if an abnormality is detected. This makes it possible to monitor the user's communication environment and automatically take measures if an abnormality is detected.

[0047] The conversation analysis unit can analyze the user's communication environment and automatically suggest optimal security settings. For example, the conversation analysis unit can use a generation AI to analyze the user's communication environment and automatically suggest optimal security settings. For example, the conversation analysis unit can customize security settings according to the user's usage. The conversation analysis unit can also use a generation AI to analyze the user's behavioral history and suggest optimal security settings. The conversation analysis unit can also use a generation AI to evaluate security risks and suggest optimal security settings. This makes it possible to analyze the user's communication environment and automatically suggest optimal security settings.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The AI ​​fraud filter system can further include a behavioral analysis unit that analyzes a user's behavioral history. The behavioral analysis unit can, for example, analyze which platforms a user uses at what times of day and issue a warning if the user deviates from their normal behavioral patterns. For example, a warning can be issued if there is access from a platform that the user does not normally use late at night. The behavioral analysis unit can also analyze a user's click patterns and scrolling behavior to detect abnormal behavior. This allows the system to learn a user's behavioral patterns and issue a warning if the user deviates from their normal patterns.

[0050] The AI ​​fraud filter system can further include a device analysis unit that analyzes user device information. The device analysis unit can analyze, for example, the type of device and OS version used by the user and issue a warning if the access is not from a normal device. For example, if a user who normally uses a smartphone suddenly accesses the site from a PC, a warning can be issued. The device analysis unit can also analyze the device's IP address and geographic location information to detect abnormal access. This allows the system to analyze user device information and detect abnormal access.

[0051] The AI ​​fraud filter system may further include a network analysis unit that analyzes the user's network environment. The network analysis unit may, for example, analyze the security level of the Wi-Fi network to which the user is connected and warn of access from an unsecured network. For example, it may issue a warning if access is made from a public Wi-Fi network. The network analysis unit may also analyze the user's network traffic and detect abnormal data transfers. This allows the system to analyze the user's network environment and warn of access from an unsecured network.

[0052] The AI ​​fraud filter system can further include a social graph analysis unit that analyzes a user's social graph. The social graph analysis unit can, for example, analyze a user's friend relationships and follower network and issue a warning if there is a deviation from normal communication patterns. For example, it can issue a warning if a user suddenly receives a message from someone with whom the user does not normally communicate. The social graph analysis unit can also analyze changes in friend relationships and the addition of new followers to detect abnormal behavior. This allows the system to analyze a user's social graph and detect abnormal communication.

[0053] The AI ​​fraud filter system can further include an activity log analysis unit that analyzes a user's activity log. The activity log analysis unit can, for example, analyze what applications a user uses and how frequently, and issue a warning if the activity deviates from the normal activity pattern. For example, a warning can be issued if an application that is not normally used suddenly becomes frequently used. The activity log analysis unit can also analyze a user's login history and operation history to detect abnormal activity. This makes it possible to analyze a user's activity log and detect abnormal activity.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The conversation analysis unit analyzes conversations on social media and chat apps. For example, it uses text mining technology to analyze the content of conversations and detect potentially fraudulent messages. It can also use natural language processing technology to understand the context of the conversation and learn patterns that may indicate fraud. Step 2: The URL analyzer analyzes the URL. For example, it analyzes the content of the URL to detect phishing scams and spam links. It can also analyze the content of images and videos to detect potentially fraudulent visual content. Step 3: The warning unit issues a warning to the user about suspicious conversations or URLs detected by the conversation analysis unit and URL analysis unit. For example, it displays a warning such as "This message may be fraudulent. Please be careful." It can also provide specific reasons and justifications for issuing a warning, providing information in a format that is easy for the user to understand. Step 4: The privacy protection department anonymizes and encrypts the user's data. For example, it uses data masking technology to anonymize the user's personal information. It also uses AES encryption technology to encrypt communications, reducing the risk of data leaks to third parties.

[0056] (Example 2) The AI ​​fraud filter system according to an embodiment of the present invention provides safe communication on platforms such as email, SNS, and LINE. This system has the ability to detect suspicious conversations and URLs and immediately warn users of the danger. As a result, the AI ​​fraud filter system can provide users with a safe communication environment and prevent fraudulent acts before they occur.

[0057] An AI fraud filter system according to an embodiment includes a conversation analysis unit, a URL analysis unit, a warning unit, and a privacy protection unit. The conversation analysis unit analyzes conversations on social media and chat apps. For example, the conversation analysis unit uses text mining technology to analyze conversation content and detect potentially fraudulent messages. The conversation analysis unit can also use natural language processing technology to understand the context of the conversation and learn potential fraudulent patterns. The URL analysis unit analyzes URLs. For example, the URL analysis unit analyzes the content of URLs to detect phishing scams and spam links. The URL analysis unit can also analyze the content of images and videos to detect potentially fraudulent visual content. The warning unit issues a warning to the user about suspicious conversations and URLs detected by the conversation analysis unit and URL analysis unit. For example, the warning unit displays a warning such as, "This message may be fraudulent. Please be careful." The warning unit can also provide specific reasons and justifications for issuing the warning, providing information in a format that is easy for the user to understand. The privacy protection unit anonymizes and encrypts user data. For example, the privacy protection unit anonymizes a user's personal information using data masking technology. The privacy protection unit also encrypts communications using AES encryption technology to reduce the risk of information leaking to third parties. As a result, the AI ​​fraud filter system according to the embodiment can provide a safe communication environment for users and prevent fraudulent activities. For example, even if a user receives a fraudulent message while using a social networking site or chat platform, the AI ​​fraud filter system can immediately issue a warning, preventing damage before it occurs. Furthermore, integrating and analyzing information from multiple platforms enables more accurate fraud detection.

[0058] The conversation analysis unit understands the context of the conversation and can learn conversation patterns that may indicate fraud. For example, the generation AI analyzes the context of the conversation and learns patterns that may indicate fraud. For example, it detects messages that emphasize urgency, such as "Please send the money quickly." The conversation analysis unit can also allow the generation AI to analyze the flow of the conversation and learn the frequency of occurrence of keywords that may indicate fraud. The conversation analysis unit can also allow the generation AI to analyze the topic of the conversation and detect changes in the topic that may indicate fraud. In this way, by learning conversation patterns that may indicate fraud, the detection accuracy can be improved.

[0059] The conversation analysis unit can refer to the user's past conversation history and detect content that deviates from normal conversation patterns. For example, the generation AI analyzes the user's past conversation history and detects content that deviates from normal conversation patterns. For example, it detects unusual language or unusual requests for money. The conversation analysis unit can also detect deviating content by having the generation AI learn normal conversation patterns based on the user's past conversation history. The conversation analysis unit can also detect abnormal behavior by having the generation AI refer to the user's past conversation history. In this way, it is possible to detect content that deviates from normal patterns by referring to the user's past conversation history.

[0060] The conversation analysis unit can use the emotion estimation function to detect conversations in which the user's emotions change suddenly and warn of the possibility of fraud. The conversation analysis unit, for example, uses the emotion estimation function to detect conversations in which the user's emotions change suddenly. For example, it detects messages that show sudden anger or anxiety. The conversation analysis unit can also use the emotion estimation function to analyze the user's emotion score and detect sudden changes. The conversation analysis unit can also use the emotion estimation function to analyze the user's emotional tone and detect sudden changes. This makes it possible to detect conversations in which the user's emotions change suddenly and warn of the possibility of fraud.

[0061] The URL analysis unit can also analyze the content of images or videos to detect potentially fraudulent visual content. For example, the generation AI can use image recognition technology to detect potentially fraudulent visual content, such as detecting fake logos or fraudulent QR codes. The URL analysis unit can also use video analysis technology to detect potentially fraudulent visual content. The URL analysis unit can also develop algorithms for the generation AI to analyze the content of images or videos to detect potentially fraudulent visual content. This allows the generation AI to analyze the content of images or videos to detect potentially fraudulent visual content.

[0062] The URL analysis unit can also analyze conversations in different languages, enabling multilingual fraud detection. For example, the generation AI uses multilingual natural language processing technology to detect potentially fraudulent conversations in different languages. For example, it analyzes messages in English, Spanish, Chinese, etc. The generation AI can also use a translation API to analyze conversations in different languages. The generation AI can also use a multilingual language model to enable multilingual fraud detection. This allows the generation AI to analyze conversations in different languages, enabling multilingual fraud detection.

[0063] The URL analysis unit can use the emotion estimation function to analyze the emotional response of a user to a message received and assess the possibility of fraud. The URL analysis unit, for example, uses the emotion estimation function to analyze the emotional response of a user to a message received. For example, it can detect anxiety or fear when receiving the message. The URL analysis unit can also use the emotion estimation function to analyze the user's emotion score and assess the possibility of fraud. The URL analysis unit can also use the emotion estimation function to analyze the user's emotional tone and assess the possibility of fraud. In this way, the emotional response of a user to a message received can be analyzed and the possibility of fraud can be assessed.

[0064] The warning unit can provide specific reasons and justification when issuing a warning, and provide information in a form that is easy for the user to understand. For example, the warning unit can provide specific reasons and justification when the generation AI issues a warning. For example, it can display an explanation such as, "This message matches a pattern that has been reported as fraud in the past." The warning unit can also provide reasons and justification based on detected keywords and past fraud cases when the generation AI issues a warning. The warning unit can also develop an interface to provide information in a form that is easy for the user to understand when the generation AI issues a warning. In this way, by providing specific reasons and justification when issuing a warning, it becomes easier for the user to understand.

[0065] The warning unit can refer to feedback from other users before issuing a warning to improve the reliability of the warning. For example, the warning unit refers to feedback from other users before the generation AI issues a warning. For example, a warning is issued if the same message has also been reported as fraud by other users. The warning unit can also improve the reliability of the warning by having the generation AI refer to user evaluation comments and survey results. The warning unit can also evaluate the reliability of the warning based on the number of feedbacks and evaluation scores. In this way, the reliability of the warning is improved by referring to feedback from other users.

[0066] The warning unit can use the emotion estimation function to analyze the emotional reaction of the user when receiving the warning and evaluate the effectiveness of the warning. The warning unit, for example, uses the emotion estimation function to analyze the emotional reaction of the user when receiving the warning. For example, the warning unit detects surprise or anxiety when receiving the warning. The warning unit can also use the emotion estimation function to analyze the user's emotion score and evaluate the effectiveness of the warning. The warning unit can also use the emotion estimation function to analyze the user's emotional tone and evaluate the effectiveness of the warning. In this way, the emotional reaction of the user when receiving the warning can be analyzed and the effectiveness of the warning can be evaluated.

[0067] The warning unit can use audio or visual alerts to intuitively notify the user of danger when issuing a warning. For example, when the generation AI issues a warning, the warning unit uses audio alerts to notify the user of danger. For example, the warning unit issues an audio alert such as "Caution! This message may be fraudulent." The warning unit can also use visual alerts to notify the user of danger. For example, the warning unit can display a flash message or a warning icon. The warning unit can also customize the type of audio or visual alert by the generation AI. This allows the user to intuitively notify the user of danger using audio or visual alerts.

[0068] The warning unit can refer to the user's location information when issuing a warning and warn against fraudulent methods specific to the region. For example, the warning unit can refer to the user's location information when the generation AI issues a warning. For example, the warning unit can issue a warning against fraudulent methods that are prevalent in a specific region. The warning unit can also use GPS data or IP address to obtain the user's location information and warn against fraudulent methods specific to the region. The warning unit can also use the generation AI to create a database of fraud patterns for each region and issue a warning based on the user's location information. This makes it possible to refer to the user's location information and warn against fraudulent methods specific to the region.

[0069] The warning unit can use the emotion estimation function to customize the content and format of the warning based on the emotional reaction of the user when receiving the warning. The warning unit, for example, uses the emotion estimation function to analyze the emotional reaction of the user when receiving the warning and customizes the content of the warning. For example, if the user feels surprise or anxiety, a more detailed explanation is provided. The warning unit can also use the emotion estimation function to analyze the user's emotion score and customize the format of the warning. The warning unit can also use the emotion estimation function to analyze the user's emotional tone and customize the content and format of the warning. This makes it possible to customize the content and format of the warning based on the emotional reaction of the user when receiving the warning.

[0070] The privacy protection unit can use the emotion estimation function to detect emotions when a user has a privacy concern and take appropriate action. For example, the privacy protection unit can use the emotion estimation function to detect emotions when a user has a privacy concern. For example, the privacy protection unit can take action when the user feels anxiety or doubt. The privacy protection unit can also use the emotion estimation function to analyze the user's emotion score and detect privacy concerns. The privacy protection unit can also use the emotion estimation function to analyze the user's emotional tone and take appropriate action. In this way, when a user has a privacy concern, the privacy protection unit can detect the emotion and take appropriate action.

[0071] The Privacy Protection Department can develop protocols for securely sharing data between different platforms when anonymizing data. For example, the Privacy Protection Department can develop protocols for securely sharing data between different platforms when the Generation AI anonymizes data. For example, the Privacy Protection Department can introduce technology to anonymize and share part of the data. The Privacy Protection Department can also have the Generation AI develop a data sharing protocol to securely share data between different platforms. The Privacy Protection Department can also have the Generation AI develop a security protocol to more securely anonymize data. By developing a protocol for securely sharing data between different platforms, the Privacy Protection Department can more securely anonymize data.

[0072] The privacy protection unit can provide a function that allows a user to select the encryption level of their data when encrypting data. For example, the privacy protection unit can provide a function that allows a user to select the encryption level of their data when the generation AI encrypts data. For example, the privacy protection unit can provide options for standard encryption and strong encryption. The privacy protection unit can also have the generation AI develop a user interface that allows the user to select the encryption level. The privacy protection unit can also have the generation AI provide a choice of encryption levels so that the user can improve the security of their data. Thus, by providing a function that allows a user to select the encryption level of their data, the security of data can be improved.

[0073] The privacy protection unit can use the emotion estimation function to automatically adjust privacy settings based on the emotion when a user has a privacy concern. For example, the privacy protection unit can use the emotion estimation function to automatically adjust privacy settings based on the emotion when a user has a privacy concern. For example, the privacy protection unit can strengthen privacy settings when the user feels anxious. The privacy protection unit can also use the emotion estimation function to analyze the user's emotion score and automatically adjust privacy settings. The privacy protection unit can also use the emotion estimation function to analyze the user's emotional tone and automatically adjust privacy settings. In this way, when a user has a privacy concern, the privacy settings can be automatically adjusted based on the emotion.

[0074] The conversation analysis unit can introduce new methods to maintain data consistency and integrity when integrating data from different platforms. For example, the conversation analysis unit can introduce new methods to maintain data consistency and integrity when the generation AI integrates data from different platforms. For example, it can adopt technology to standardize data formats. The conversation analysis unit can also enable the generation AI to perform database consistency checks to maintain data consistency. The conversation analysis unit can also enable the generation AI to develop data integration algorithms to maintain data consistency. This makes it possible to improve data quality by introducing new methods to maintain data consistency and integrity when integrating data from different platforms.

[0075] The conversation analysis unit can develop algorithms that detect data correlations with high accuracy when analyzing data from different platforms. For example, the conversation analysis unit develops algorithms that detect data correlations with high accuracy when the generation AI analyzes data from different platforms. For example, the conversation analysis unit combines and analyzes social media and email data. The conversation analysis unit can also enable the generation AI to detect data correlations using correlation coefficients or regression analysis. The conversation analysis unit can also enable the generation AI to detect data correlations with high accuracy using machine learning algorithms. This allows the development of algorithms that detect data correlations with high accuracy when analyzing data from different platforms, thereby improving the accuracy of fraud detection.

[0076] The conversation analysis unit can use the emotion estimation function to analyze changes in a user's emotions on different platforms and assess the possibility of fraud. The conversation analysis unit can, for example, use the emotion estimation function to analyze changes in a user's emotions on different platforms and assess the possibility of fraud. For example, the conversation analysis unit can detect changes in emotions between social media and email. The conversation analysis unit can also use the emotion estimation function to analyze a user's emotion score and detect changes in emotions on different platforms. The conversation analysis unit can also use the emotion estimation function to analyze a user's emotional tone and assess the possibility of fraud. This makes it possible to analyze changes in a user's emotions on different platforms and assess the possibility of fraud.

[0077] The conversation analysis unit can provide a data visualization tool when integrating data from different platforms, allowing the user to intuitively understand the data. For example, the conversation analysis unit can provide a data visualization tool when the generation AI integrates data from different platforms. For example, the data can be visually displayed using graphs and charts. The conversation analysis unit can also enable the generation AI to develop a dashboard, allowing the user to intuitively understand the data. The conversation analysis unit can also enable the generation AI to provide an interactive analysis tool, allowing the user to understand the data while manipulating it. In this way, the conversation analysis unit can provide a data visualization tool when integrating data from different platforms, allowing the user to intuitively understand the data.

[0078] The conversation analysis unit updates the data in real time when analyzing data from different platforms, allowing fraud detection to be performed based on the latest information. The conversation analysis unit updates the data in real time when the generation AI analyzes data from different platforms. For example, it collects and analyzes data from social media and emails in real time. The conversation analysis unit can also update the data in real time using streaming data processing technology by the generation AI. The conversation analysis unit can also perform fraud detection based on the latest information using a real-time database by the generation AI. This allows data to be updated in real time when analyzing data from different platforms, allowing fraud detection to be performed based on the latest information.

[0079] The conversation analysis unit learns the user's communication patterns and can issue a warning if they deviate from the normal pattern. For example, the generation AI can learn the user's communication patterns and issue a warning if they deviate from the normal pattern. For example, it can detect unusual language or unusual requests for money. The conversation analysis unit can also enable the generation AI to detect deviations based on the user's communication patterns. The conversation analysis unit can also enable the generation AI to analyze the user's communication patterns and detect abnormal behavior. This allows the generation AI to learn the user's communication patterns and issue a warning if they deviate from the normal pattern.

[0080] The conversation analysis unit can analyze the user's communication history, compare it with past fraud cases, and issue a warning. For example, the generation AI can analyze the user's communication history, compare it with past fraud cases, and issue a warning. For example, it can detect content that matches previously reported fraud messages. The conversation analysis unit can also have the generation AI refer to a database of fraud cases and compare it with the user's communication history. The conversation analysis unit can also have the generation AI analyze the user's communication history based on a list of fraud patterns. This allows the generation AI to analyze the user's communication history, compare it with past fraud cases, and issue a warning.

[0081] The conversation analysis unit can use the emotion estimation function to provide feedback based on emotions so that the user can communicate with a sense of security. The conversation analysis unit, for example, uses the emotion estimation function to provide feedback based on emotions so that the user can communicate with a sense of security. For example, if the user feels anxious, a message that gives a sense of security is displayed. The conversation analysis unit can also use the emotion estimation function to analyze the user's emotion score and provide feedback that gives a sense of security. The conversation analysis unit can also use the emotion estimation function to analyze the user's emotional tone and provide feedback that gives a sense of security. In this way, it is possible to provide feedback based on emotions so that the user can communicate with a sense of security.

[0082] The conversation analysis unit can monitor the user's communication environment and automatically take measures if an abnormality is detected. For example, the conversation analysis unit can have the generation AI monitor the user's communication environment and automatically take measures if an abnormality is detected. For example, the conversation analysis unit can automatically block messages that may be fraudulent. The conversation analysis unit can also have the generation AI monitor the user's network environment and take measures if an abnormality is detected. The conversation analysis unit can also have the generation AI monitor the apps the user is using and take measures if an abnormality is detected. This makes it possible to monitor the user's communication environment and automatically take measures if an abnormality is detected.

[0083] The conversation analysis unit can analyze the user's communication environment and automatically suggest optimal security settings. For example, the conversation analysis unit can use a generation AI to analyze the user's communication environment and automatically suggest optimal security settings. For example, the conversation analysis unit can customize security settings according to the user's usage. The conversation analysis unit can also use a generation AI to analyze the user's behavioral history and suggest optimal security settings. The conversation analysis unit can also use a generation AI to evaluate security risks and suggest optimal security settings. This makes it possible to analyze the user's communication environment and automatically suggest optimal security settings.

[0084] The conversation analysis unit can use the emotion estimation function to perform customization based on emotions so that the user can communicate with a sense of security. The conversation analysis unit, for example, can use the emotion estimation function to perform customization based on emotions so that the user can communicate with a sense of security. For example, if the user feels anxious, the conversation analysis unit can provide settings that give the user a sense of security. The conversation analysis unit can also use the emotion estimation function to analyze the user's emotion score and perform customization. The conversation analysis unit can also use the emotion estimation function to analyze the user's emotional tone and perform customization. This allows customization based on emotions so that the user can communicate with a sense of security.

[0085] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0086] The AI ​​fraud filter system can further include a behavioral analysis unit that analyzes a user's behavioral history. The behavioral analysis unit can, for example, analyze which platforms a user uses at what times of day and issue a warning if the user deviates from their normal behavioral patterns. For example, a warning can be issued if there is access from a platform that the user does not normally use late at night. The behavioral analysis unit can also analyze a user's click patterns and scrolling behavior to detect abnormal behavior. This allows the system to learn a user's behavioral patterns and issue a warning if the user deviates from their normal patterns.

[0087] The AI ​​fraud filter system can further include a device analysis unit that analyzes user device information. The device analysis unit can analyze, for example, the type of device and OS version used by the user and issue a warning if the access is not from a normal device. For example, if a user who normally uses a smartphone suddenly accesses the site from a PC, a warning can be issued. The device analysis unit can also analyze the device's IP address and geographic location information to detect abnormal access. This allows the system to analyze user device information and detect abnormal access.

[0088] The AI ​​fraud filter system may further include a network analysis unit that analyzes the user's network environment. The network analysis unit may, for example, analyze the security level of the Wi-Fi network to which the user is connected and warn of access from an unsecured network. For example, it may issue a warning if access is made from a public Wi-Fi network. The network analysis unit may also analyze the user's network traffic and detect abnormal data transfers. This allows the system to analyze the user's network environment and warn of access from an unsecured network.

[0089] The AI ​​fraud filter system can further include a social graph analysis unit that analyzes a user's social graph. The social graph analysis unit can, for example, analyze a user's friend relationships and follower network and issue a warning if there is a deviation from normal communication patterns. For example, it can issue a warning if a user suddenly receives a message from someone with whom the user does not normally communicate. The social graph analysis unit can also analyze changes in friend relationships and the addition of new followers to detect abnormal behavior. This allows the system to analyze a user's social graph and detect abnormal communication.

[0090] The AI ​​fraud filter system can further include an activity log analysis unit that analyzes a user's activity log. The activity log analysis unit can, for example, analyze what applications a user uses and how frequently, and issue a warning if the activity deviates from the normal activity pattern. For example, a warning can be issued if an application that is not normally used suddenly becomes frequently used. The activity log analysis unit can also analyze a user's login history and operation history to detect abnormal activity. This makes it possible to analyze a user's activity log and detect abnormal activity.

[0091] The conversation analysis unit can use the emotion estimation function to analyze the user's emotional response to a message received and assess the possibility of fraud. For example, it can detect anxiety or fear when receiving a message. The conversation analysis unit can also use the emotion estimation function to analyze the user's emotion score and assess the possibility of fraud. The conversation analysis unit can also use the emotion estimation function to analyze the user's emotional tone and assess the possibility of fraud. In this way, it is possible to analyze the user's emotional response to a message received and assess the possibility of fraud.

[0092] The conversation analysis unit can use the emotion estimation function to detect conversations in which the user's emotions change suddenly and warn of the possibility of fraud. For example, it can detect messages that show sudden anger or anxiety. The conversation analysis unit can also use the emotion estimation function to analyze the user's emotion score and detect sudden changes. The conversation analysis unit can also use the emotion estimation function to analyze the user's emotional tone and detect sudden changes. This makes it possible to detect conversations in which the user's emotions change suddenly and warn of the possibility of fraud.

[0093] The warning unit can use the emotion estimation function to analyze the user's emotional reaction when receiving the warning and evaluate the effectiveness of the warning. For example, the warning unit can detect surprise or anxiety when receiving the warning. The warning unit can also use the emotion estimation function to analyze the user's emotion score and evaluate the effectiveness of the warning. The warning unit can also use the emotion estimation function to analyze the user's emotional tone and evaluate the effectiveness of the warning. In this way, the user's emotional reaction when receiving the warning can be analyzed and the effectiveness of the warning can be evaluated.

[0094] The privacy protection unit can use the emotion estimation function to detect emotions when a user has privacy concerns and take appropriate measures. For example, it can respond when the user feels anxiety or doubt. The privacy protection unit can also use the emotion estimation function to analyze the user's emotion score and detect privacy concerns. The privacy protection unit can also use the emotion estimation function to analyze the user's emotional tone and take appropriate measures. In this way, it can detect emotions when a user has privacy concerns and take appropriate measures.

[0095] The conversation analysis unit can use the emotion estimation function to analyze changes in a user's emotions on different platforms and assess the possibility of fraud. For example, it can detect changes in emotions between social media and email. The conversation analysis unit can also use the emotion estimation function to analyze a user's emotion score and detect changes in emotions on different platforms. The conversation analysis unit can also use the emotion estimation function to analyze a user's emotional tone and assess the possibility of fraud. This makes it possible to analyze changes in a user's emotions on different platforms and assess the possibility of fraud.

[0096] The processing flow of the second embodiment will be briefly explained below.

[0097] Step 1: The conversation analysis unit analyzes conversations on social media and chat apps. For example, it uses text mining technology to analyze the content of conversations and detect potentially fraudulent messages. It can also use natural language processing technology to understand the context of the conversation and learn patterns that may indicate fraud. Step 2: The URL analyzer analyzes the URL. For example, it analyzes the content of the URL to detect phishing scams and spam links. It can also analyze the content of images and videos to detect potentially fraudulent visual content. Step 3: The warning unit issues a warning to the user about suspicious conversations or URLs detected by the conversation analysis unit and URL analysis unit. For example, it displays a warning such as "This message may be fraudulent. Please be careful." It can also provide specific reasons and justifications for issuing a warning, providing information in a format that is easy for the user to understand. Step 4: The privacy protection department anonymizes and encrypts the user's data. For example, it uses data masking technology to anonymize the user's personal information. It also uses AES encryption technology to encrypt communications, reducing the risk of data leaks to third parties.

[0098] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0099] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0100] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0101] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0102] 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.

[0103] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0104] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0105] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0106] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0107] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0108] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0109] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0110] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0111] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0112] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0113] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0115] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0116] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0117] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0118] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0119] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0120] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0122] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0123] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0124] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0125] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0126] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0127] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0128] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0129] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0130] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0131] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0132] 7, a 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.

[0133] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0134] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0135] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0137] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0138] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0139] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0140] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0141] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0142] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0143] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0144] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0145] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0146] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0147] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0148] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0149] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0150] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0151] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0152] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0153] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0154] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0155] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0156] 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.

[0157] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0158] The hardware resource for executing a specific process can be any of the following processors: A CPU is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A dedicated electrical circuit, such as a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application-specific integrated circuit (ASIC), is a processor with a circuit configuration specifically designed to execute a specific process. Each processor has built-in or connected memory, and uses the memory to execute the specific process.

[0159] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0160] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0161] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0162] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0163] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0164] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0165] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A conversation analysis section that analyzes conversations on social media and chat apps, a URL analysis unit that analyzes a URL; a warning unit that issues a warning to a user about a suspicious conversation or URL detected by the conversation analysis unit and the URL analysis unit; a privacy protection unit that anonymizes and encrypts the user's data; A system characterized by:

2. The conversation analysis unit Using emotion estimation, the system detects conversations in which the user's emotions change suddenly and warns of potential fraud.

2. The system of claim 1.

3. The URL analysis unit It also analyzes the content of images or videos to detect potentially fraudulent visual content.

2. The system of claim 1.

4. The warning unit When issuing the warning, the reason and grounds are presented and the information is provided in a format that is easy for the user to understand.

2. The system of claim 1.

5. The privacy protection unit Using emotion estimation, when the user has a privacy concern, the emotion is detected and appropriate action is taken.

2. The system of claim 1.

6. The conversation analysis unit Using emotion estimation capabilities, the change in the user's emotions across different platforms is analyzed to assess the likelihood of fraud.

2. The system of claim 1.

7. The conversation analysis unit Using emotion estimation functionality, the user is provided with emotion-based feedback to ensure that they can communicate with confidence.

2. The system of claim 1.

8. The conversation analysis unit Using an emotion estimation function, customization based on emotions is performed so that the user can communicate with peace of mind.

2. The system of claim 1.

Images