System

Abstract

An object of a system according to an embodiment is to prevent damage from special fraud.SOLUTION: A system includes a voice analysis unit, an image analysis unit, a communication analysis unit, and a determination unit. The sound analysis unit analyzes sound. The image analysis unit analyzes an image. The communication analysis unit analyzes communication. The determination unit determines the possibility of fraud on the basis of analysis results obtained by the voice analysis unit, the image analysis unit, and the communication analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, there was a problem that the methods of special fraud were becoming more diverse and there was a lack of effective means to prevent damage.

[0005] The system according to the embodiment aims to prevent damage caused by special fraud. [Means for solving the problem]

[0006] The system according to the embodiment includes an audio analysis unit, an image analysis unit, a communication analysis unit, and a determination unit. The audio analysis unit analyzes audio. The image analysis unit analyzes images. The communication analysis unit analyzes communications. The determination unit determines the possibility of fraud based on the analysis results obtained by the audio analysis unit, image analysis unit, and communication analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can prevent damage caused by special fraud. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention utilizes generative AI to prevent fraudulent activities. This system includes a voice analysis unit, an image analysis unit, a communication analysis unit, and a judgment unit, which work together to determine the likelihood of fraud. For example, to combat telephone fraud, the voice analysis unit analyzes keywords and tone of voice in conversations to determine the likelihood of fraud. Next, to combat smartphone fraud, the image analysis unit analyzes the validity of the text and source of emails and websites to determine the likelihood of fraud. Furthermore, to combat face-to-face fraud, an image analysis unit using a door phone or surveillance camera analyzes the content of conversations, facial features, and clothing to determine the likelihood of fraud. Finally, to combat written fraud, an image analysis unit using a smartphone camera analyzes the text written on postcards and faxes to determine the likelihood of fraud. This allows for the prevention of fraudulent activities. For example, to combat telephone fraud, the voice analysis unit analyzes keywords and tone of voice in conversations to determine the likelihood of fraud. Next, as a countermeasure against smartphone-based fraud, the image analysis unit analyzes the validity of the wording and source of emails and websites to determine the possibility of fraud. Furthermore, as a countermeasure against face-to-face fraud, the image analysis unit using door phones and surveillance cameras analyzes the content of conversations, facial features, and clothing to determine the possibility of fraud. Finally, as a countermeasure against written fraud, the image analysis unit using smartphone cameras analyzes the wording on postcards and faxes to determine the possibility of fraud. In this way, the system can prevent damage from special frauds.

[0029] The fraud prevention system according to the embodiment includes a voice analysis unit, an image analysis unit, a communication analysis unit, and a determination unit. The voice analysis unit analyzes keywords and tone of voice in telephone conversations. For example, the voice analysis unit extracts keywords from the conversations and determines whether fraud is likely. The voice analysis unit can also analyze tone of voice to detect emotions such as tension or impatience. The voice analysis unit can also convert the conversations into text and analyze it using voice recognition technology. The image analysis unit analyzes images from smartphones or door phones. For example, the image analysis unit can identify people using facial recognition technology to determine whether fraud is likely. The image analysis unit can also analyze clothing and backgrounds to detect suspicious behavior. The image analysis unit can also extract and analyze text within images using image recognition technology. The communication analysis unit analyzes the content of emails and website communications. For example, the communication analysis unit analyzes the body of emails and website content to determine whether fraud is likely. The communication analysis unit can also analyze the IP address and domain information of the sender to evaluate trustworthiness. The communication analysis unit can also analyze communication protocols and detect fraudulent communications. The judgment unit determines the possibility of fraud by integrating the analysis results obtained by the voice analysis unit, image analysis unit, and communication analysis unit. For example, the judgment unit comprehensively evaluates each analysis result and determines the possibility of fraud. The judgment unit can also refer to past fraud case data to improve the accuracy of the judgment. The judgment unit can also evaluate the reliability of the analysis results and adjust the accuracy of the judgment. As a result, the fraud prevention system according to the embodiment can prevent damage from special frauds by determining the possibility of fraud by combining voice analysis, image analysis, and communication analysis.

[0030] Furthermore, the fraud prevention system is equipped with a police coordination section that works with the police to input the learning information necessary for judgment. The police coordination section works with the police to input the learning information necessary for judgment. For example, the police coordination section collects past fraud case data provided by the police and inputs it into the system. The police coordination section can also establish information sharing protocols with the police and exchange information in real time. The police coordination section can also define coordination procedures with the police to ensure quick and accurate information transmission. In this way, by working with the police and inputting accurate learning information, the accuracy of fraud judgment is improved.

[0031] Furthermore, the fraud prevention system includes a data collection unit that collects various types of data. The data collection unit collects various types of data. For example, the data collection unit collects voice data, image data, communication data, etc. The data collection unit can also collect data in real time using sensors and cameras. The data collection unit can also accumulate past data and use it for analysis. In this way, by collecting various types of data, it is possible to comprehensively obtain information necessary for determining fraud.

[0032] Furthermore, the fraud prevention system includes a data providing unit that provides the analysis results. The data providing unit provides the analysis results. For example, the data providing unit notifies the user of the analysis results. The data providing unit can also report the analysis results to relevant organizations. The data providing unit can also store the analysis results in a database so that they can be referenced later. In this way, by providing the analysis results, information can be quickly communicated to the user and relevant organizations.

[0033] The voice analysis unit can analyze keywords and tone of voice in telephone conversations. For example, the voice analysis unit extracts keywords from telephone conversations and determines the possibility of fraud. For example, the voice analysis unit detects keywords such as "Please transfer money." The voice analysis unit can also analyze tone of voice to detect emotions such as tension or impatience. For example, the voice analysis unit analyzes tone and pitch of voice to estimate emotions. The voice analysis unit can also convert the conversation content into text using voice recognition technology and analyze it. For example, the voice analysis unit converts the conversation content into text data using voice recognition software and extracts keywords. In this way, by analyzing the conversation content and tone of voice, the possibility of fraud can be determined with high accuracy.

[0034] The image analysis unit can analyze images from smartphones and door phones. For example, the image analysis unit analyzes images from smartphones and door phones to determine the possibility of fraud. For example, the image analysis unit uses facial recognition technology to identify people and determine the possibility of fraud. The image analysis unit can also analyze clothing and background to detect suspicious features. For example, the image analysis unit analyzes clothing and background in an image to detect signs of fraud. The image analysis unit can also extract and analyze text from an image using image recognition technology. For example, the image analysis unit uses OCR technology to extract text from an image and determine the possibility of fraud. This makes it possible to determine the possibility of face-to-face fraud by analyzing images from smartphones and door phones.

[0035] The communication analysis unit can analyze the content of emails and website communications. For example, the communication analysis unit analyzes the content of emails and website communications to determine the possibility of fraud. For example, the communication analysis unit analyzes the body of an email or the content of a website to determine the possibility of fraud. The communication analysis unit can also analyze the IP address and domain information of the sender to evaluate trustworthiness. For example, the communication analysis unit analyzes the IP address of the sender to detect suspicious senders. The communication analysis unit can also analyze communication protocols to detect fraudulent communications. For example, the communication analysis unit analyzes communication protocols such as HTTP and HTTPS to detect fraudulent communications. This makes it possible to determine the possibility of online fraud by analyzing the content of emails and website communications.

[0036] The judgment unit can determine the possibility of fraud by integrating the analysis results obtained by the audio analysis unit, image analysis unit, and communication analysis unit. The judgment unit, for example, integrates the analysis results obtained by the audio analysis unit, image analysis unit, and communication analysis unit to determine the possibility of fraud. For example, the judgment unit comprehensively evaluates each analysis result to determine the possibility of fraud. The judgment unit can also refer to past fraud case data to improve the accuracy of the judgment. For example, the judgment unit refers to past fraud case data to learn fraud patterns. The judgment unit can also evaluate the reliability of the analysis results and adjust the accuracy of the judgment. For example, the judgment unit evaluates the reliability of each analysis result and prioritizes highly reliable results in the judgment. In this way, by integrating multiple analysis results, the possibility of fraud can be more accurately determined.

[0037] The audio analysis unit can analyze background sounds of a conversation during audio analysis to determine the possibility of fraud. For example, the audio analysis unit can analyze background sounds of a conversation during audio analysis to determine the possibility of fraud. For example, the audio analysis unit can detect environmental sounds that are likely to be fraudulent (e.g., noise in a public place) from the background sounds while the generation AI is talking. The audio analysis unit can also detect environmental sounds that are unlikely to be fraudulent (e.g., quiet sounds in a household) from the background sounds while the generation AI is talking. The audio analysis unit can also detect sounds associated with specific fraudulent methods (e.g., other people's voices) from the background sounds while the generation AI is talking. This allows for a more accurate determination of the possibility of fraud by analyzing the background sounds of a conversation.

[0038] The voice analysis unit can adjust the importance of keywords by taking into account the context of the conversation during voice analysis. For example, the voice analysis unit adjusts the importance of keywords by taking into account the context of the conversation during voice analysis. For example, the voice analysis unit allows the generation AI to analyze the context of the conversation and increase the importance of keywords related to fraud. The voice analysis unit can also allow the generation AI to analyze the context of the conversation and decrease the importance of keywords not related to fraud. The voice analysis unit can also allow the generation AI to analyze the context of the conversation and adjust the importance of specific phrases and expressions. This allows the importance of keywords related to fraud to be appropriately adjusted by taking into account the context of the conversation.

[0039] The voice analysis unit can analyze the speed of speech and pauses during voice analysis to determine the possibility of fraud. For example, the voice analysis unit can analyze the speed of speech and pauses during voice analysis to determine the possibility of fraud. For example, the voice analysis unit can have the generation AI analyze the speed of speech and determine that fraud is highly likely if it is abnormally fast. The voice analysis unit can also analyze the pauses in the speech and determine that fraud is highly likely if there are many unnatural pauses. The voice analysis unit can also have the generation AI comprehensively analyze the speed of speech and pauses to determine the possibility of fraud. In this way, by analyzing the speed of speech and pauses, the possibility of fraud can be more accurately determined.

[0040] The speech analysis unit can improve the accuracy of analysis by taking into account the language and dialect of the conversation during speech analysis. For example, the speech analysis unit improves the accuracy of analysis by taking into account the language and dialect of the conversation during speech analysis. For example, in the speech analysis unit, the generation AI automatically detects the language of the conversation and performs analysis specialized for that language. In addition, the speech analysis unit can also detect the dialect of the conversation and perform analysis specialized for that dialect. In addition, the speech analysis unit can perform multilingual analysis by the generation AI, and can accurately analyze conversations in different languages ​​and dialects. In this way, by taking into account the language and dialect of the conversation, the accuracy of analysis can be improved.

[0041] The voice analysis unit can perform voice analysis while taking into account attribute information of the participants in the conversation. For example, the voice analysis unit performs voice analysis while taking into account attribute information of the participants in the conversation. For example, the voice analysis unit performs analysis while the generation AI takes into account the age and gender of the participants in the conversation. The voice analysis unit can also perform analysis while the generation AI takes into account the occupation and background information of the participants in the conversation. The voice analysis unit can also perform analysis while the generation AI takes into account the past speech history of the participants in the conversation. In this way, by taking into account attribute information of the participants in the conversation, the accuracy of the analysis can be improved.

[0042] The voice analysis unit translates the content of the conversation in real time during voice analysis, making it possible to detect fraud in different languages. For example, the voice analysis unit translates the content of the conversation in real time during voice analysis, making it possible to detect fraud in different languages. For example, the voice analysis unit allows the generation AI to translate the content of the conversation in real time and determine the possibility of fraud. The voice analysis unit can also translate conversations in different languages ​​using the generation AI to detect keywords related to fraud. The voice analysis unit can also perform multilingual translation and detect fraudulent methods in different languages. This makes it possible to detect fraud in different languages ​​by translating the content of the conversation in real time.

[0043] The image analysis unit can analyze the background information of the image during image analysis to determine the possibility of fraud. For example, the image analysis unit can analyze the background information of the image during image analysis to determine the possibility of fraud. For example, the image analysis unit can have the generation AI analyze the background information of the image to detect an environment where fraud is more likely (e.g., a public place). The image analysis unit can also have the generation AI analyze the background information of the image to detect an environment where fraud is less likely (e.g., within the home). The image analysis unit can also have the generation AI analyze the background information of the image to detect backgrounds associated with specific fraudulent methods (e.g., specific locations). This allows for more accurate determination of the possibility of fraud by analyzing the background information of the image.

[0044] The image analysis unit can analyze the movement of objects in the image during image analysis to determine the possibility of fraud. For example, the image analysis unit can analyze the movement of objects in the image during image analysis to determine the possibility of fraud. For example, the image analysis unit can have a generating AI analyze the movement of objects in the image, detect unnatural movements, and determine the possibility of fraud. The image analysis unit can also have a generating AI analyze the movement of objects in the image, detect specific movements (e.g., hand movements), and determine the possibility of fraud. The image analysis unit can also have a generating AI analyze the movement of objects in the image, analyze the movement patterns, and determine the possibility of fraud. This allows for a more accurate determination of the possibility of fraud by analyzing the movement of objects in the image.

[0045] The image analysis unit can improve analysis accuracy by taking into account the resolution and quality of the image during image analysis. For example, the image analysis unit can improve analysis accuracy by having the generation AI automatically adjust the image resolution to improve analysis accuracy. The image analysis unit can also have the generation AI evaluate the image quality and maintain analysis accuracy even for low-quality images. The image analysis unit can also have the generation AI comprehensively evaluate the image resolution and quality to perform optimal analysis. This makes it possible to improve analysis accuracy by taking into account the image resolution and quality.

[0046] The image analysis unit can analyze text information in an image during image analysis to determine the possibility of fraud. For example, the image analysis unit can analyze text information in an image during image analysis to determine the possibility of fraud. For example, the image analysis unit can have the generation AI analyze the text information in an image to detect keywords related to fraud. The image analysis unit can also have the generation AI analyze the text information in an image to determine the validity of the sender. The image analysis unit can also have the generation AI analyze the text information in an image to detect specific phrases or expressions to determine the possibility of fraud. This allows for more accurate determination of the possibility of fraud by analyzing the text information in an image.

[0047] The image analysis unit can analyze the color tone and brightness of the image during image analysis to determine the possibility of fraud. For example, the image analysis unit can analyze the color tone and brightness of the image during image analysis to determine the possibility of fraud. For example, the image analysis unit can have the generation AI analyze the color tone of the image and detect unnatural color tones to determine the possibility of fraud. The image analysis unit can also have the generation AI analyze the brightness of the image and detect unnatural brightness to determine the possibility of fraud. The image analysis unit can also have the generation AI comprehensively analyze the color tone and brightness of the image to determine the possibility of fraud. This allows for a more accurate determination of the possibility of fraud by analyzing the color tone and brightness of the image.

[0048] The communication analysis unit can analyze the communication metadata during communication analysis to determine the possibility of fraud. For example, the communication analysis unit can analyze the communication metadata during communication analysis to determine the possibility of fraud. For example, in the communication analysis unit, the generation AI analyzes the communication metadata and detects the source IP address and domain information to determine the possibility of fraud. The communication analysis unit can also analyze the communication metadata and analyze the communication timestamp and frequency to determine the possibility of fraud. The communication analysis unit can also comprehensively analyze the communication metadata and determine the possibility of fraud. This allows for a more accurate determination of the possibility of fraud by analyzing the communication metadata.

[0049] The communication analysis unit can analyze the frequency and patterns of communications during communication analysis to determine the possibility of fraud. For example, the communication analysis unit can analyze the frequency and patterns of communications during communication analysis to determine the possibility of fraud. For example, the communication analysis unit can have the generation AI analyze the frequency of communications, detect abnormally high frequencies of communications, and determine the possibility of fraud. The communication analysis unit can also have the generation AI analyze the patterns of communications, detect communications that are concentrated in specific time periods, and determine the possibility of fraud. The communication analysis unit can also have the generation AI comprehensively analyze the frequency and patterns of communications to determine the possibility of fraud. In this way, by analyzing the frequency and patterns of communications, the possibility of fraud can be determined more accurately.

[0050] The communication analysis unit can analyze the encryption state of the communication during communication analysis to determine the possibility of fraud. For example, the communication analysis unit can analyze the encryption state of the communication during communication analysis to determine the possibility of fraud. For example, in the communication analysis unit, the generation AI can analyze the encryption state of the communication, detect unencrypted communication, and determine the possibility of fraud. The communication analysis unit can also analyze the encryption protocol of the communication, detect an unauthorized protocol, and determine the possibility of fraud. The communication analysis unit can also comprehensively analyze the encryption state of the communication and determine the possibility of fraud. In this way, by analyzing the encryption state of the communication, the possibility of fraud can be more accurately determined.

[0051] The communication analysis unit can improve the accuracy of analysis by taking into account geographical information of the sender and receiver of the communication when analyzing the communication. For example, the communication analysis unit improves the accuracy of analysis by taking into account geographical information of the sender and receiver of the communication when analyzing the communication. For example, in the communication analysis unit, the generation AI analyzes the geographical information of the sender of the communication to detect communication from a suspicious location. The communication analysis unit can also analyze the geographical information of the receiver of the communication to detect communication to a suspicious location. The communication analysis unit can also comprehensively analyze the geographical information of the sender and receiver of the communication to determine the possibility of fraud. In this way, the analysis accuracy can be improved by taking into account geographical information of the sender and receiver of the communication.

[0052] The communication analysis unit translates the content of the communication in real time during communication analysis, making it possible to detect fraud in different languages. For example, the communication analysis unit translates the content of the communication in real time during communication analysis, making it possible to detect fraud in different languages. For example, the communication analysis unit has a generation AI that translates the content of the communication in real time to determine the possibility of fraud. The communication analysis unit can also have a generation AI that translates communications in different languages ​​and detect keywords related to fraud. The communication analysis unit can also have a generation AI that performs multilingual translation to detect fraudulent methods in different languages. This makes it possible to detect fraud in different languages ​​by translating the content of the communication in real time.

[0053] The communication analysis unit can analyze the communication protocol and format during communication analysis to determine the possibility of fraud. For example, the communication analysis unit can analyze the communication protocol and format during communication analysis to determine the possibility of fraud. For example, the communication analysis unit can have the generation AI analyze the communication protocol, detect an unauthorized protocol, and determine the possibility of fraud. The communication analysis unit can also have the generation AI analyze the communication format, detect an unnatural format, and determine the possibility of fraud. The communication analysis unit can also have the generation AI comprehensively analyze the communication protocol and format to determine the possibility of fraud. This allows for a more accurate determination of the possibility of fraud by analyzing the communication protocol and format.

[0054] The judgment unit can improve the accuracy of judgment by referring to past fraud case data when making a judgment. The judgment unit can improve the accuracy of judgment by referring to past fraud case data when making a judgment. For example, the judgment unit has the generation AI refer to past fraud case data to judge the possibility of fraud. The judgment unit can also have the generation AI analyze past fraud case data and detect specific patterns to judge the possibility of fraud. The judgment unit can also have the generation AI comprehensively refer to past fraud case data to improve the accuracy of judgment. In this way, by referring to past fraud case data, the accuracy of judgment can be improved.

[0055] The judgment unit can make a judgment taking into account the interrelationships of the analysis results when making a judgment. For example, the judgment unit makes a judgment taking into account the interrelationships of the analysis results when making a judgment. For example, the judgment unit determines the possibility of fraud by having the generation AI comprehensively analyze the results of voice analysis, image analysis, and communication analysis. The judgment unit can also determine the possibility of fraud by having the generation AI evaluate the interrelationships of each analysis result. The judgment unit can also make the most reliable judgment by having the generation AI consider the interrelationships of the analysis results. In this way, by considering the interrelationships of the analysis results, the possibility of fraud can be more accurately determined.

[0056] The judgment unit can evaluate the reliability of the analysis results at the time of judgment and adjust the accuracy of the judgment. For example, the judgment unit evaluates the reliability of the analysis results at the time of judgment and adjusts the accuracy of the judgment. For example, the judgment unit has the generation AI evaluate the reliability of each analysis result and prioritize highly reliable results in the judgment. The judgment unit can also have the generation AI comprehensively evaluate the reliability of the analysis results and adjust the accuracy of the judgment. The judgment unit can also exclude analysis results with low reliability and make the most reliable judgment. In this way, the accuracy of the judgment can be adjusted by evaluating the reliability of the analysis results.

[0057] The judgment unit can make a judgment by taking into consideration the time series data of the analysis results when making a judgment. For example, the judgment unit makes a judgment by taking into consideration the time series data of the analysis results when making a judgment. For example, the judgment unit has the generation AI analyze the time series data of the analysis results and determine the possibility of fraud. The judgment unit can also have the generation AI refer to past time series data and detect specific patterns to determine the possibility of fraud. The judgment unit can also have the generation AI comprehensively consider the time series data and make the most reliable judgment. In this way, by taking into consideration the time series data of the analysis results, the possibility of fraud can be more accurately determined.

[0058] The judgment unit can evaluate the relevance of the analysis results when making a judgment and determine the priority of the judgment. For example, the judgment unit evaluates the relevance of the analysis results when making a judgment and determines the priority of the judgment. For example, the judgment unit has the generation AI evaluate the relevance of each analysis result and prioritize results that are more likely to be fraudulent. The judgment unit can also have the generation AI comprehensively evaluate the relevance of the analysis results and make the most reliable judgment. The judgment unit can also have the generation AI exclude analysis results that are less relevant and make the most reliable judgment. In this way, by evaluating the relevance of the analysis results, important analysis results can be prioritized.

[0059] The judgment unit can detect abnormal values ​​in the analysis results at the time of judgment and determine the possibility of fraud. The judgment unit, for example, detects abnormal values ​​in the analysis results at the time of judgment and determines the possibility of fraud. For example, the judgment unit has the generation AI detect abnormal values ​​in the analysis results and determine the possibility of fraud. The judgment unit can also have the generation AI analyze patterns of abnormal values ​​and determine the possibility of fraud. The judgment unit can also have the generation AI comprehensively evaluate abnormal values ​​and make the most reliable judgment. In this way, by detecting abnormal values ​​in the analysis results, the possibility of fraud can be determined more accurately.

[0060] When coordinating with the police, the police collaboration unit can refer to past collaboration history to select the optimal collaboration method. For example, when coordinating with the police, the police collaboration unit refers to past collaboration history to select the optimal collaboration method. For example, in the police collaboration unit, the generation AI refers to past collaboration history to select the optimal collaboration method. In addition, in the police collaboration unit, the generation AI can analyze past collaboration history, detect specific patterns, and select the optimal collaboration method. In addition, in the police collaboration unit, the generation AI can comprehensively refer to past collaboration history to select the most reliable collaboration method. In this way, the optimal collaboration method can be selected by referring to past collaboration history.

[0061] The police collaboration unit can take into account the time series data of the collaboration data when collaborating with the police. For example, when collaborating with the police, the police collaboration unit can take into account the time series data of the collaboration data when collaborating with the police. For example, in the police collaboration unit, the generation AI analyzes the time series data of the collaboration data and selects the optimal collaboration method. In addition, in the police collaboration unit, the generation AI can refer to past time series data, detect specific patterns, and select the optimal collaboration method. In addition, in the police collaboration unit, the generation AI can comprehensively consider the time series data and perform the most reliable collaboration. In this way, the optimal collaboration method can be selected by taking into account the time series data of the collaboration data.

[0062] When coordinating with the police, the police collaboration unit can evaluate the relevance of the linked data and determine the priority of collaboration. For example, when coordinating with the police, the police collaboration unit can evaluate the relevance of the linked data and determine the priority of collaboration. For example, in the police collaboration unit, the generation AI evaluates the relevance of the linked data and prioritizes collaboration of data that is highly likely to be fraud. In addition, in the police collaboration unit, the generation AI can comprehensively evaluate the relevance of the linked data and perform the most reliable collaboration. In addition, in the police collaboration unit, the generation AI can exclude linked data with low relevance and perform the most reliable collaboration. In this way, by evaluating the relevance of the linked data, important linked data can be processed preferentially.

[0063] The data collection unit can evaluate the reliability of the collected data when collecting data and adjust the accuracy of collection. For example, the data collection unit evaluates the reliability of the collected data when collecting data and adjusts the accuracy of collection. For example, the data collection unit has the generation AI evaluate the reliability of the collected data and prioritize collecting highly reliable data. The data collection unit can also have the generation AI comprehensively evaluate the reliability of the collected data and adjust the accuracy of collection. The data collection unit can also exclude collected data with low reliability and collect the most reliable data. In this way, the accuracy of collection can be adjusted by evaluating the reliability of the collected data.

[0064] The data collection unit can perform data collection while taking into consideration the interrelationships of the collected data. For example, the data collection unit performs data collection while taking into consideration the interrelationships of the collected data. For example, the data collection unit allows the generation AI to evaluate the interrelationships of the collected data and prioritize collecting highly relevant data. The data collection unit can also allow the generation AI to comprehensively evaluate the interrelationships of the collected data and collect the most reliable data. The data collection unit can also allow the generation AI to exclude collected data with low interrelationships and collect the most reliable data. In this way, by taking into consideration the interrelationships of the collected data, highly relevant data can be collected preferentially.

[0065] The data collection unit can perform data collection while taking into consideration the time series data of the collected data. For example, the data collection unit performs data collection while taking into consideration the time series data of the collected data. For example, in the data collection unit, the generation AI analyzes the time series data of the collected data and selects the optimal data collection method. In addition, the data collection unit can also select the optimal data collection method by having the generation AI refer to past time series data and detect specific patterns. In addition, the data collection unit can also perform data collection with the most reliable data by having the generation AI comprehensively consider the time series data. In this way, the optimal data collection method can be selected by taking into consideration the time series data of the collected data.

[0066] The data collection unit can evaluate the relevance of the collected data when collecting data and determine the priority of collection. For example, the data collection unit evaluates the relevance of the collected data when collecting data and determines the priority of collection. For example, the data collection unit has the generation AI evaluate the relevance of the collected data and prioritize collecting data that is likely to be fraudulent. The data collection unit can also have the generation AI comprehensively evaluate the relevance of the collected data and collect the most reliable data. The data collection unit can also have the generation AI exclude less relevant collected data and collect the most reliable data. In this way, by evaluating the relevance of the collected data, important data can be collected preferentially.

[0067] The data providing unit can evaluate the reliability of the provided data when providing the data and adjust the accuracy of the provision. For example, the data providing unit evaluates the reliability of the provided data when providing the data and adjusts the accuracy of the provision. For example, the data providing unit allows the generation AI to evaluate the reliability of the provided data and provide data with higher reliability as a priority. The data providing unit can also allow the generation AI to comprehensively evaluate the reliability of the provided data and adjust the accuracy of the provision. The data providing unit can also allow the generation AI to exclude provided data with lower reliability and provide the most reliable data. In this way, the accuracy of the provision can be adjusted by evaluating the reliability of the provided data.

[0068] The data providing unit can provide data while taking into consideration the interrelationships of the provided data when providing the data. For example, the data providing unit provides data while taking into consideration the interrelationships of the provided data when providing the data. For example, the data providing unit allows the generation AI to evaluate the interrelationships of the provided data and provide highly relevant data with priority. The data providing unit can also allow the generation AI to comprehensively evaluate the interrelationships of the provided data and provide the most reliable data. The data providing unit can also allow the generation AI to exclude provided data with low interrelationships and provide the most reliable data. In this way, by taking into consideration the interrelationships of the provided data, highly relevant data can be provided with priority.

[0069] The data providing unit can provide data while taking into consideration the time series data of the provided data. For example, the data providing unit provides data while taking into consideration the time series data of the provided data. For example, the data providing unit has the generation AI analyze the time series data of the provided data and select the optimal data providing method. The data providing unit can also have the generation AI refer to past time series data, detect specific patterns, and select the optimal data providing method. The data providing unit can also have the generation AI comprehensively consider the time series data and provide the most reliable data. In this way, the optimal data providing method can be selected by taking into consideration the time series data of the provided data.

[0070] The data providing unit can evaluate the relevance of the provided data when providing the data and determine the priority of provision. For example, the data providing unit evaluates the relevance of the provided data when providing the data and determines the priority of provision. For example, the data providing unit allows the generation AI to evaluate the relevance of the provided data and prioritize providing data that is likely to be fraudulent. The data providing unit can also allow the generation AI to comprehensively evaluate the relevance of the provided data and provide the most reliable data. The data providing unit can also allow the generation AI to exclude less relevant provided data and provide the most reliable data. In this way, by evaluating the relevance of the provided data, important data can be provided preferentially.

[0071] The data providing unit can provide data while taking into consideration the interrelationships of the provided data when providing the data. For example, the data providing unit provides data while taking into consideration the interrelationships of the provided data when providing the data. For example, the data providing unit allows the generation AI to evaluate the interrelationships of the provided data and provide highly relevant data with priority. The data providing unit can also allow the generation AI to comprehensively evaluate the interrelationships of the provided data and provide the most reliable data. The data providing unit can also allow the generation AI to exclude provided data with low interrelationships and provide the most reliable data. In this way, by taking into consideration the interrelationships of the provided data, highly relevant data can be provided with priority.

[0072] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0073] The fraud prevention system may further include a behavior analysis unit that analyzes a user's behavioral patterns. The behavior analysis unit collects data on the user's past behavior and determines the possibility of fraud. For example, the behavior analysis unit may detect a large transaction that the user does not normally make and determine the possibility of fraud. The behavior analysis unit may also detect access to a website that the user does not normally visit and determine the possibility of fraud. The behavior analysis unit may also analyze a user's movement patterns and detect abnormal movements to determine the possibility of fraud. In this way, by analyzing a user's behavioral patterns, the possibility of fraud can be determined more accurately.

[0074] The fraud prevention system may further include a health monitoring unit that monitors the user's health condition. The health monitoring unit collects vital data such as the user's heart rate and blood pressure, and determines the possibility of fraud. For example, the health monitoring unit may determine that there is a high possibility of fraud if the user's heart rate suddenly increases. The health monitoring unit may also determine that there is a high possibility of fraud if the user's blood pressure is abnormally high. The health monitoring unit may also analyze the user's stress level and determine the possibility of fraud. In this way, by monitoring the user's health condition, the possibility of fraud can be more accurately determined.

[0075] The fraud prevention system may further include a purchase analysis unit that analyzes a user's purchase history. The purchase analysis unit collects the user's past purchase data and determines the possibility of fraud. For example, the purchase analysis unit may detect high-priced items that the user does not normally purchase and determine the possibility of fraud. The purchase analysis unit may also detect purchases from online stores that the user does not normally use and determine the possibility of fraud. The purchase analysis unit may also analyze the user's purchasing patterns and detect abnormal purchases to determine the possibility of fraud. In this way, by analyzing the user's purchase history, the possibility of fraud can be determined more accurately.

[0076] The fraud prevention system may further include a location analysis unit that analyzes the user's location information. The location analysis unit collects the user's current location and past movement history to determine the possibility of fraud. For example, the location analysis unit may determine that there is a high possibility of fraud if the user is in a place that the user does not normally visit. The location analysis unit may also analyze the user's movement patterns and detect abnormal movements to determine the possibility of fraud. The location analysis unit may also monitor the user's location information in real time and detect abnormal movements to determine the possibility of fraud. In this way, the possibility of fraud can be more accurately determined by analyzing the user's location information.

[0077] The fraud prevention system may further include a social media analysis unit that analyzes the user's social media activity. The social media analysis unit collects data on the user's social media activity and determines the possibility of fraud. For example, the social media analysis unit may detect interactions with accounts with which the user does not normally interact and determine the possibility of fraud. The social media analysis unit may also detect content that the user does not normally post and determine the possibility of fraud. The social media analysis unit may also analyze the user's follower and friend list to detect suspicious accounts and determine the possibility of fraud. In this way, analyzing the user's social media activity can more accurately determine the possibility of fraud.

[0078] The processing flow of the first embodiment will be briefly explained below.

[0079] Step 1: The voice analysis unit analyzes keywords and tone of voice in the telephone conversation. For example, the voice analysis unit extracts keywords from the conversation and determines the possibility of fraud. The voice analysis unit can also analyze tone of voice to detect emotions such as tension or impatience. The voice analysis unit can also convert the conversation into text using voice recognition technology and analyze it. Step 2: The image analysis unit analyzes images from smartphones and doorbells. For example, the image analysis unit can use facial recognition technology to identify people and determine whether they are suspects of fraud. The image analysis unit can also analyze clothing and background to detect suspicious behavior. The image analysis unit can also use image recognition technology to extract and analyze text within the image. Step 3: The communication analysis unit analyzes the content of emails and website communications. For example, the communication analysis unit analyzes the body of an email or the content of a website to determine the possibility of fraud. The communication analysis unit can also analyze the IP address and domain information of the sender to evaluate their trustworthiness. The communication analysis unit can also analyze communication protocols to detect fraudulent communications. Step 4: The judgment unit combines the analysis results obtained by the voice analysis unit, image analysis unit, and communication analysis unit to determine the possibility of fraud. For example, the judgment unit comprehensively evaluates each analysis result and determines the possibility of fraud. The judgment unit can also refer to data on past fraud cases to improve the accuracy of its judgment. The judgment unit can also evaluate the reliability of the analysis results and adjust the accuracy of its judgment.

[0080] (Example 2) A system according to an embodiment of the present invention utilizes generative AI to prevent fraudulent activities. This system includes a voice analysis unit, an image analysis unit, a communication analysis unit, and a judgment unit, which work together to determine the likelihood of fraud. For example, to combat telephone fraud, the voice analysis unit analyzes keywords and tone of voice in conversations to determine the likelihood of fraud. Next, to combat smartphone fraud, the image analysis unit analyzes the validity of the text and source of emails and websites to determine the likelihood of fraud. Furthermore, to combat face-to-face fraud, an image analysis unit using a door phone or surveillance camera analyzes the content of conversations, facial features, and clothing to determine the likelihood of fraud. Finally, to combat written fraud, an image analysis unit using a smartphone camera analyzes the text written on postcards and faxes to determine the likelihood of fraud. This allows for the prevention of fraudulent activities. For example, to combat telephone fraud, the voice analysis unit analyzes keywords and tone of voice in conversations to determine the likelihood of fraud. Next, as a countermeasure against smartphone-based fraud, the image analysis unit analyzes the validity of the wording and source of emails and websites to determine the possibility of fraud. Furthermore, as a countermeasure against face-to-face fraud, the image analysis unit using door phones and surveillance cameras analyzes the content of conversations, facial features, and clothing to determine the possibility of fraud. Finally, as a countermeasure against written fraud, the image analysis unit using smartphone cameras analyzes the wording on postcards and faxes to determine the possibility of fraud. In this way, the system can prevent damage from special frauds.

[0081] The fraud prevention system according to the embodiment includes a voice analysis unit, an image analysis unit, a communication analysis unit, and a determination unit. The voice analysis unit analyzes keywords and tone of voice in telephone conversations. For example, the voice analysis unit extracts keywords from the conversations and determines whether fraud is likely. The voice analysis unit can also analyze tone of voice to detect emotions such as tension or impatience. The voice analysis unit can also convert the conversations into text and analyze it using voice recognition technology. The image analysis unit analyzes images from smartphones or door phones. For example, the image analysis unit can identify people using facial recognition technology to determine whether fraud is likely. The image analysis unit can also analyze clothing and backgrounds to detect suspicious behavior. The image analysis unit can also extract and analyze text within images using image recognition technology. The communication analysis unit analyzes the content of emails and website communications. For example, the communication analysis unit analyzes the body of emails and website content to determine whether fraud is likely. The communication analysis unit can also analyze the IP address and domain information of the sender to evaluate trustworthiness. The communication analysis unit can also analyze communication protocols and detect fraudulent communications. The judgment unit determines the possibility of fraud by integrating the analysis results obtained by the voice analysis unit, image analysis unit, and communication analysis unit. For example, the judgment unit comprehensively evaluates each analysis result and determines the possibility of fraud. The judgment unit can also refer to past fraud case data to improve the accuracy of the judgment. The judgment unit can also evaluate the reliability of the analysis results and adjust the accuracy of the judgment. As a result, the fraud prevention system according to the embodiment can prevent damage from special frauds by determining the possibility of fraud by combining voice analysis, image analysis, and communication analysis.

[0082] Furthermore, the fraud prevention system is equipped with a police coordination section that works with the police to input the learning information necessary for judgment. The police coordination section works with the police to input the learning information necessary for judgment. For example, the police coordination section collects past fraud case data provided by the police and inputs it into the system. The police coordination section can also establish information sharing protocols with the police and exchange information in real time. The police coordination section can also define coordination procedures with the police to ensure quick and accurate information transmission. In this way, by working with the police and inputting accurate learning information, the accuracy of fraud judgment is improved.

[0083] Furthermore, the fraud prevention system includes a data collection unit that collects various types of data. The data collection unit collects various types of data. For example, the data collection unit collects voice data, image data, communication data, etc. The data collection unit can also collect data in real time using sensors and cameras. The data collection unit can also accumulate past data and use it for analysis. In this way, by collecting various types of data, it is possible to comprehensively obtain information necessary for determining fraud.

[0084] Furthermore, the fraud prevention system includes a data providing unit that provides the analysis results. The data providing unit provides the analysis results. For example, the data providing unit notifies the user of the analysis results. The data providing unit can also report the analysis results to relevant organizations. The data providing unit can also store the analysis results in a database so that they can be referenced later. In this way, by providing the analysis results, information can be quickly communicated to the user and relevant organizations.

[0085] The voice analysis unit can analyze keywords and tone of voice in telephone conversations. For example, the voice analysis unit extracts keywords from telephone conversations and determines the possibility of fraud. For example, the voice analysis unit detects keywords such as "Please transfer money." The voice analysis unit can also analyze tone of voice to detect emotions such as tension or impatience. For example, the voice analysis unit analyzes tone and pitch of voice to estimate emotions. The voice analysis unit can also convert the conversation content into text using voice recognition technology and analyze it. For example, the voice analysis unit converts the conversation content into text data using voice recognition software and extracts keywords. In this way, by analyzing the conversation content and tone of voice, the possibility of fraud can be determined with high accuracy.

[0086] The image analysis unit can analyze images from smartphones and door phones. For example, the image analysis unit analyzes images from smartphones and door phones to determine the possibility of fraud. For example, the image analysis unit uses facial recognition technology to identify people and determine the possibility of fraud. The image analysis unit can also analyze clothing and background to detect suspicious features. For example, the image analysis unit analyzes clothing and background in an image to detect signs of fraud. The image analysis unit can also extract and analyze text from an image using image recognition technology. For example, the image analysis unit uses OCR technology to extract text from an image and determine the possibility of fraud. This makes it possible to determine the possibility of face-to-face fraud by analyzing images from smartphones and door phones.

[0087] The communication analysis unit can analyze the content of emails and website communications. For example, the communication analysis unit analyzes the content of emails and website communications to determine the possibility of fraud. For example, the communication analysis unit analyzes the body of an email or the content of a website to determine the possibility of fraud. The communication analysis unit can also analyze the IP address and domain information of the sender to evaluate trustworthiness. For example, the communication analysis unit analyzes the IP address of the sender to detect suspicious senders. The communication analysis unit can also analyze communication protocols to detect fraudulent communications. For example, the communication analysis unit analyzes communication protocols such as HTTP and HTTPS to detect fraudulent communications. This makes it possible to determine the possibility of online fraud by analyzing the content of emails and website communications.

[0088] The judgment unit can determine the possibility of fraud by integrating the analysis results obtained by the audio analysis unit, image analysis unit, and communication analysis unit. The judgment unit, for example, integrates the analysis results obtained by the audio analysis unit, image analysis unit, and communication analysis unit to determine the possibility of fraud. For example, the judgment unit comprehensively evaluates each analysis result to determine the possibility of fraud. The judgment unit can also refer to past fraud case data to improve the accuracy of the judgment. For example, the judgment unit refers to past fraud case data to learn fraud patterns. The judgment unit can also evaluate the reliability of the analysis results and adjust the accuracy of the judgment. For example, the judgment unit evaluates the reliability of each analysis result and prioritizes highly reliable results in the judgment. In this way, by integrating multiple analysis results, the possibility of fraud can be more accurately determined.

[0089] The voice analysis unit can estimate the user's emotions and adjust the analysis accuracy of the conversation content based on the estimated user emotions. The voice analysis unit, for example, estimates the user's emotions and adjusts the analysis accuracy of the conversation content based on the estimated user emotions. For example, if the user is nervous, the voice analysis unit can cause the generation AI to increase the analysis accuracy of the conversation content and more accurately determine the possibility of fraud. Also, if the user is relaxed, the voice analysis unit can cause the generation AI to set the analysis accuracy of the conversation content to a normal level and prioritize natural conversation. Also, if the user is in a hurry, the voice analysis unit can cause the generation AI to quickly analyze the conversation content and immediately determine the possibility of fraud. In this way, by adjusting the analysis accuracy according to the user's emotions, the possibility of fraud can be more accurately determined.

[0090] The audio analysis unit can analyze background sounds of a conversation during audio analysis to determine the possibility of fraud. For example, the audio analysis unit can analyze background sounds of a conversation during audio analysis to determine the possibility of fraud. For example, the audio analysis unit can detect environmental sounds that are likely to be fraudulent (e.g., noise in a public place) from the background sounds while the generation AI is talking. The audio analysis unit can also detect environmental sounds that are unlikely to be fraudulent (e.g., quiet sounds in a household) from the background sounds while the generation AI is talking. The audio analysis unit can also detect sounds associated with specific fraudulent methods (e.g., other people's voices) from the background sounds while the generation AI is talking. This allows for a more accurate determination of the possibility of fraud by analyzing the background sounds of a conversation.

[0091] The voice analysis unit can adjust the importance of keywords by taking into account the context of the conversation during voice analysis. For example, the voice analysis unit adjusts the importance of keywords by taking into account the context of the conversation during voice analysis. For example, the voice analysis unit allows the generation AI to analyze the context of the conversation and increase the importance of keywords related to fraud. The voice analysis unit can also allow the generation AI to analyze the context of the conversation and decrease the importance of keywords not related to fraud. The voice analysis unit can also allow the generation AI to analyze the context of the conversation and adjust the importance of specific phrases and expressions. This allows the importance of keywords related to fraud to be appropriately adjusted by taking into account the context of the conversation.

[0092] The voice analysis unit can analyze the speed of speech and pauses during voice analysis to determine the possibility of fraud. For example, the voice analysis unit can analyze the speed of speech and pauses during voice analysis to determine the possibility of fraud. For example, the voice analysis unit can have the generation AI analyze the speed of speech and determine that fraud is highly likely if it is abnormally fast. The voice analysis unit can also analyze the pauses in the speech and determine that fraud is highly likely if there are many unnatural pauses. The voice analysis unit can also have the generation AI comprehensively analyze the speed of speech and pauses to determine the possibility of fraud. In this way, by analyzing the speed of speech and pauses, the possibility of fraud can be more accurately determined.

[0093] The voice analysis unit can estimate the user's emotions and determine the priority of analysis results based on the estimated user's emotions. The voice analysis unit can, for example, estimate the user's emotions and determine the priority of analysis results based on the estimated user's emotions. For example, if the user is nervous, the voice analysis unit can cause the generation AI to prioritize displaying analysis results that are more likely to be fraudulent. Also, if the user is relaxed, the voice analysis unit can cause the generation AI to prioritize displaying analysis results that are less likely to be fraudulent. Also, if the user is in a hurry, the voice analysis unit can quickly display analysis results that are more likely to be fraudulent. In this way, by determining the priority of analysis results according to the user's emotions, important analysis results can be displayed preferentially.

[0094] The speech analysis unit can improve the accuracy of analysis by taking into account the language and dialect of the conversation during speech analysis. For example, the speech analysis unit improves the accuracy of analysis by taking into account the language and dialect of the conversation during speech analysis. For example, in the speech analysis unit, the generation AI automatically detects the language of the conversation and performs analysis specialized for that language. In addition, the speech analysis unit can also detect the dialect of the conversation and perform analysis specialized for that dialect. In addition, the speech analysis unit can perform multilingual analysis by the generation AI, and can accurately analyze conversations in different languages ​​and dialects. In this way, by taking into account the language and dialect of the conversation, the accuracy of analysis can be improved.

[0095] The voice analysis unit can perform voice analysis while taking into account attribute information of the participants in the conversation. For example, the voice analysis unit performs voice analysis while taking into account attribute information of the participants in the conversation. For example, the voice analysis unit performs analysis while the generation AI takes into account the age and gender of the participants in the conversation. The voice analysis unit can also perform analysis while the generation AI takes into account the occupation and background information of the participants in the conversation. The voice analysis unit can also perform analysis while the generation AI takes into account the past speech history of the participants in the conversation. In this way, by taking into account attribute information of the participants in the conversation, the accuracy of the analysis can be improved.

[0096] The voice analysis unit translates the content of the conversation in real time during voice analysis, making it possible to detect fraud in different languages. For example, the voice analysis unit translates the content of the conversation in real time during voice analysis, making it possible to detect fraud in different languages. For example, the voice analysis unit allows the generation AI to translate the content of the conversation in real time and determine the possibility of fraud. The voice analysis unit can also translate conversations in different languages ​​using the generation AI to detect keywords related to fraud. The voice analysis unit can also perform multilingual translation and detect fraudulent methods in different languages. This makes it possible to detect fraud in different languages ​​by translating the content of the conversation in real time.

[0097] The image analysis unit can estimate the user's emotions and adjust the accuracy of the image analysis based on the estimated user emotions. The image analysis unit, for example, estimates the user's emotions and adjusts the accuracy of the image analysis based on the estimated user emotions. For example, if the user is nervous, the image analysis unit causes the generation AI to increase the accuracy of the image analysis and more accurately determine the possibility of fraud. Also, if the user is relaxed, the image analysis unit can cause the generation AI to set the accuracy of the image analysis to a normal level and perform natural image analysis. Also, if the user is in a hurry, the image analysis unit can cause the generation AI to quickly perform image analysis and immediately determine the possibility of fraud. In this way, by adjusting the accuracy of the image analysis according to the user's emotions, the possibility of fraud can be more accurately determined.

[0098] The image analysis unit can analyze the background information of the image during image analysis to determine the possibility of fraud. For example, the image analysis unit can analyze the background information of the image during image analysis to determine the possibility of fraud. For example, the image analysis unit can have the generation AI analyze the background information of the image to detect an environment where fraud is more likely (e.g., a public place). The image analysis unit can also have the generation AI analyze the background information of the image to detect an environment where fraud is less likely (e.g., within the home). The image analysis unit can also have the generation AI analyze the background information of the image to detect backgrounds associated with specific fraudulent methods (e.g., specific locations). This allows for more accurate determination of the possibility of fraud by analyzing the background information of the image.

[0099] The image analysis unit can analyze the movement of objects in the image during image analysis to determine the possibility of fraud. For example, the image analysis unit can analyze the movement of objects in the image during image analysis to determine the possibility of fraud. For example, the image analysis unit can have a generating AI analyze the movement of objects in the image, detect unnatural movements, and determine the possibility of fraud. The image analysis unit can also have a generating AI analyze the movement of objects in the image, detect specific movements (e.g., hand movements), and determine the possibility of fraud. The image analysis unit can also have a generating AI analyze the movement of objects in the image, analyze the movement patterns, and determine the possibility of fraud. This allows for a more accurate determination of the possibility of fraud by analyzing the movement of objects in the image.

[0100] The image analysis unit can improve analysis accuracy by taking into account the resolution and quality of the image during image analysis. For example, the image analysis unit can improve analysis accuracy by having the generation AI automatically adjust the image resolution to improve analysis accuracy. The image analysis unit can also have the generation AI evaluate the image quality and maintain analysis accuracy even for low-quality images. The image analysis unit can also have the generation AI comprehensively evaluate the image resolution and quality to perform optimal analysis. This makes it possible to improve analysis accuracy by taking into account the image resolution and quality.

[0101] The image analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. The image analysis unit can, for example, estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the image analysis unit can cause the generation AI to provide a simple, highly visible display method. Also, if the user is relaxed, the image analysis unit can cause the generation AI to provide a display method that includes detailed information. Also, if the user is in a hurry, the image analysis unit can cause the generation AI to provide a display method that focuses on the main points. In this way, by adjusting the display method of the analysis results according to the user's emotions, important information can be displayed appropriately.

[0102] The image analysis unit can analyze text information in an image during image analysis to determine the possibility of fraud. For example, the image analysis unit can analyze text information in an image during image analysis to determine the possibility of fraud. For example, the image analysis unit can have the generation AI analyze the text information in an image to detect keywords related to fraud. The image analysis unit can also have the generation AI analyze the text information in an image to determine the validity of the sender. The image analysis unit can also have the generation AI analyze the text information in an image to detect specific phrases or expressions to determine the possibility of fraud. This allows for more accurate determination of the possibility of fraud by analyzing the text information in an image.

[0103] The image analysis unit can analyze the color tone and brightness of the image during image analysis to determine the possibility of fraud. For example, the image analysis unit can analyze the color tone and brightness of the image during image analysis to determine the possibility of fraud. For example, the image analysis unit can have the generation AI analyze the color tone of the image and detect unnatural color tones to determine the possibility of fraud. The image analysis unit can also have the generation AI analyze the brightness of the image and detect unnatural brightness to determine the possibility of fraud. The image analysis unit can also have the generation AI comprehensively analyze the color tone and brightness of the image to determine the possibility of fraud. This allows for a more accurate determination of the possibility of fraud by analyzing the color tone and brightness of the image.

[0104] The communication analysis unit can estimate the user's emotions and adjust the analysis accuracy of the communication content based on the estimated user emotions. The communication analysis unit, for example, estimates the user's emotions and adjusts the analysis accuracy of the communication content based on the estimated user emotions. For example, if the user is nervous, the communication analysis unit causes the generation AI to increase the analysis accuracy of the communication content and more accurately determine the possibility of fraud. Also, if the user is relaxed, the communication analysis unit can cause the generation AI to set the analysis accuracy of the communication content to a normal level and perform a natural communication analysis. Also, if the user is in a hurry, the communication analysis unit can cause the generation AI to quickly analyze the communication content and immediately determine the possibility of fraud. In this way, by adjusting the analysis accuracy of the communication content according to the user's emotions, the possibility of fraud can be more accurately determined.

[0105] The communication analysis unit can analyze the communication metadata during communication analysis to determine the possibility of fraud. For example, the communication analysis unit can analyze the communication metadata during communication analysis to determine the possibility of fraud. For example, in the communication analysis unit, the generation AI analyzes the communication metadata and detects the source IP address and domain information to determine the possibility of fraud. The communication analysis unit can also analyze the communication metadata and analyze the communication timestamp and frequency to determine the possibility of fraud. The communication analysis unit can also comprehensively analyze the communication metadata and determine the possibility of fraud. This allows for a more accurate determination of the possibility of fraud by analyzing the communication metadata.

[0106] The communication analysis unit can analyze the frequency and patterns of communications during communication analysis to determine the possibility of fraud. For example, the communication analysis unit can analyze the frequency and patterns of communications during communication analysis to determine the possibility of fraud. For example, the communication analysis unit can have the generation AI analyze the frequency of communications, detect abnormally high frequencies of communications, and determine the possibility of fraud. The communication analysis unit can also have the generation AI analyze the patterns of communications, detect communications that are concentrated in specific time periods, and determine the possibility of fraud. The communication analysis unit can also have the generation AI comprehensively analyze the frequency and patterns of communications to determine the possibility of fraud. In this way, by analyzing the frequency and patterns of communications, the possibility of fraud can be determined more accurately.

[0107] The communication analysis unit can analyze the encryption state of the communication during communication analysis to determine the possibility of fraud. For example, the communication analysis unit can analyze the encryption state of the communication during communication analysis to determine the possibility of fraud. For example, in the communication analysis unit, the generation AI can analyze the encryption state of the communication, detect unencrypted communication, and determine the possibility of fraud. The communication analysis unit can also analyze the encryption protocol of the communication, detect an unauthorized protocol, and determine the possibility of fraud. The communication analysis unit can also comprehensively analyze the encryption state of the communication and determine the possibility of fraud. In this way, by analyzing the encryption state of the communication, the possibility of fraud can be more accurately determined.

[0108] The communication analysis unit can estimate the user's emotions and determine the priority of analysis results based on the estimated user's emotions. The communication analysis unit, for example, estimates the user's emotions and determines the priority of analysis results based on the estimated user's emotions. For example, if the user is nervous, the communication analysis unit can cause the generation AI to preferentially display analysis results that are likely to be fraud. Also, if the user is relaxed, the communication analysis unit can cause the generation AI to preferentially display analysis results that are unlikely to be fraud. Also, if the user is in a hurry, the communication analysis unit can cause the generation AI to quickly display analysis results that are likely to be fraud. In this way, by determining the priority of analysis results according to the user's emotions, important analysis results can be preferentially displayed.

[0109] The communication analysis unit can improve the accuracy of analysis by taking into account geographical information of the sender and receiver of the communication when analyzing the communication. For example, the communication analysis unit improves the accuracy of analysis by taking into account geographical information of the sender and receiver of the communication when analyzing the communication. For example, in the communication analysis unit, the generation AI analyzes the geographical information of the sender of the communication to detect communication from a suspicious location. The communication analysis unit can also analyze the geographical information of the receiver of the communication to detect communication to a suspicious location. The communication analysis unit can also comprehensively analyze the geographical information of the sender and receiver of the communication to determine the possibility of fraud. In this way, the analysis accuracy can be improved by taking into account geographical information of the sender and receiver of the communication.

[0110] The communication analysis unit translates the content of the communication in real time during communication analysis, making it possible to detect fraud in different languages. For example, the communication analysis unit translates the content of the communication in real time during communication analysis, making it possible to detect fraud in different languages. For example, the communication analysis unit has a generation AI that translates the content of the communication in real time to determine the possibility of fraud. The communication analysis unit can also have a generation AI that translates communications in different languages ​​and detect keywords related to fraud. The communication analysis unit can also have a generation AI that performs multilingual translation to detect fraudulent methods in different languages. This makes it possible to detect fraud in different languages ​​by translating the content of the communication in real time.

[0111] The communication analysis unit can analyze the communication protocol and format during communication analysis to determine the possibility of fraud. For example, the communication analysis unit can analyze the communication protocol and format during communication analysis to determine the possibility of fraud. For example, the communication analysis unit can have the generation AI analyze the communication protocol, detect an unauthorized protocol, and determine the possibility of fraud. The communication analysis unit can also have the generation AI analyze the communication format, detect an unnatural format, and determine the possibility of fraud. The communication analysis unit can also have the generation AI comprehensively analyze the communication protocol and format to determine the possibility of fraud. This allows for a more accurate determination of the possibility of fraud by analyzing the communication protocol and format.

[0112] The judgment unit can estimate the user's emotions and adjust the judgment criteria based on the estimated user emotions. The judgment unit, for example, estimates the user's emotions and adjusts the judgment criteria based on the estimated user emotions. For example, if the user is nervous, the judgment unit causes the generation AI to set the judgment criteria stricter and more strictly judge the possibility of fraud. Also, if the user is relaxed, the judgment unit can cause the generation AI to set the judgment criteria at a normal level and make a natural judgment. Also, if the user is in a hurry, the judgment unit can cause the generation AI to quickly set the judgment criteria and immediately judge the possibility of fraud. In this way, by adjusting the judgment criteria according to the user's emotions, the possibility of fraud can be more accurately judged.

[0113] The judgment unit can improve the accuracy of judgment by referring to past fraud case data when making a judgment. The judgment unit can improve the accuracy of judgment by referring to past fraud case data when making a judgment. For example, the judgment unit has the generation AI refer to past fraud case data to judge the possibility of fraud. The judgment unit can also have the generation AI analyze past fraud case data and detect specific patterns to judge the possibility of fraud. The judgment unit can also have the generation AI comprehensively refer to past fraud case data to improve the accuracy of judgment. In this way, by referring to past fraud case data, the accuracy of judgment can be improved.

[0114] The judgment unit can make a judgment taking into account the interrelationships of the analysis results when making a judgment. For example, the judgment unit makes a judgment taking into account the interrelationships of the analysis results when making a judgment. For example, the judgment unit determines the possibility of fraud by having the generation AI comprehensively analyze the results of voice analysis, image analysis, and communication analysis. The judgment unit can also determine the possibility of fraud by having the generation AI evaluate the interrelationships of each analysis result. The judgment unit can also make the most reliable judgment by having the generation AI consider the interrelationships of the analysis results. In this way, by considering the interrelationships of the analysis results, the possibility of fraud can be more accurately determined.

[0115] The judgment unit can evaluate the reliability of the analysis results at the time of judgment and adjust the accuracy of the judgment. For example, the judgment unit evaluates the reliability of the analysis results at the time of judgment and adjusts the accuracy of the judgment. For example, the judgment unit has the generation AI evaluate the reliability of each analysis result and prioritize highly reliable results in the judgment. The judgment unit can also have the generation AI comprehensively evaluate the reliability of the analysis results and adjust the accuracy of the judgment. The judgment unit can also exclude analysis results with low reliability and make the most reliable judgment. In this way, the accuracy of the judgment can be adjusted by evaluating the reliability of the analysis results.

[0116] The determination unit can estimate the user's emotions and adjust the display method of the determination result based on the estimated user's emotions. The determination unit, for example, estimates the user's emotions and adjusts the display method of the determination result based on the estimated user's emotions. For example, if the user is nervous, the determination unit causes the generation AI to provide a simple, highly visible display method. Furthermore, if the user is relaxed, the determination unit can also cause the generation AI to provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the determination unit can also cause the generation AI to provide a display method that focuses on the main points. In this way, by adjusting the display method of the determination result according to the user's emotions, important information can be displayed appropriately.

[0117] The judgment unit can make a judgment by taking into consideration the time series data of the analysis results when making a judgment. For example, the judgment unit makes a judgment by taking into consideration the time series data of the analysis results when making a judgment. For example, the judgment unit has the generation AI analyze the time series data of the analysis results and determine the possibility of fraud. The judgment unit can also have the generation AI refer to past time series data and detect specific patterns to determine the possibility of fraud. The judgment unit can also have the generation AI comprehensively consider the time series data and make the most reliable judgment. In this way, by taking into consideration the time series data of the analysis results, the possibility of fraud can be more accurately determined.

[0118] The judgment unit can evaluate the relevance of the analysis results when making a judgment and determine the priority of the judgment. For example, the judgment unit evaluates the relevance of the analysis results when making a judgment and determines the priority of the judgment. For example, the judgment unit has the generation AI evaluate the relevance of each analysis result and prioritize results that are more likely to be fraudulent. The judgment unit can also have the generation AI comprehensively evaluate the relevance of the analysis results and make the most reliable judgment. The judgment unit can also have the generation AI exclude analysis results that are less relevant and make the most reliable judgment. In this way, by evaluating the relevance of the analysis results, important analysis results can be prioritized.

[0119] The judgment unit can detect abnormal values ​​in the analysis results at the time of judgment and determine the possibility of fraud. The judgment unit, for example, detects abnormal values ​​in the analysis results at the time of judgment and determines the possibility of fraud. For example, the judgment unit has the generation AI detect abnormal values ​​in the analysis results and determine the possibility of fraud. The judgment unit can also have the generation AI analyze patterns of abnormal values ​​and determine the possibility of fraud. The judgment unit can also have the generation AI comprehensively evaluate abnormal values ​​and make the most reliable judgment. In this way, by detecting abnormal values ​​in the analysis results, the possibility of fraud can be determined more accurately.

[0120] The police collaboration unit can estimate the user's emotions and adjust the method of collaboration with the police based on the estimated user's emotions. The police collaboration unit, for example, estimates the user's emotions and adjusts the method of collaboration with the police based on the estimated user's emotions. For example, if the user is nervous, the police collaboration unit can quickly collaborate with the police and immediately report the possibility of fraud. Also, if the user is relaxed, the police collaboration unit can also collaborate with the police through normal procedures and report the possibility of fraud. Also, if the user is in a hurry, the police collaboration unit can quickly collaborate with the police and immediately report the possibility of fraud. In this way, by adjusting the method of collaboration with the police according to the user's emotions, fast and appropriate collaboration is possible.

[0121] When coordinating with the police, the police collaboration unit can refer to past collaboration history to select the optimal collaboration method. For example, when coordinating with the police, the police collaboration unit refers to past collaboration history to select the optimal collaboration method. For example, in the police collaboration unit, the generation AI refers to past collaboration history to select the optimal collaboration method. In addition, in the police collaboration unit, the generation AI can analyze past collaboration history, detect specific patterns, and select the optimal collaboration method. In addition, in the police collaboration unit, the generation AI can comprehensively refer to past collaboration history to select the most reliable collaboration method. In this way, the optimal collaboration method can be selected by referring to past collaboration history.

[0122] The collaboration unit with police can estimate the user's emotions and adjust the display method of the collaboration results based on the estimated user's emotions. The collaboration unit with police, for example, can estimate the user's emotions and adjust the display method of the collaboration results based on the estimated user's emotions. For example, if the user is nervous, the collaboration unit with police can have the generation AI provide a simple, highly visible display method. Also, if the user is relaxed, the collaboration unit with police can have the generation AI provide a display method that includes detailed information. Also, if the user is in a hurry, the collaboration unit with police can have the generation AI provide a display method that focuses on the main points. In this way, by adjusting the display method of the collaboration results according to the user's emotions, important information can be displayed appropriately.

[0123] The police collaboration unit can take into account the time series data of the collaboration data when collaborating with the police. For example, when collaborating with the police, the police collaboration unit can take into account the time series data of the collaboration data when collaborating with the police. For example, in the police collaboration unit, the generation AI analyzes the time series data of the collaboration data and selects the optimal collaboration method. In addition, in the police collaboration unit, the generation AI can refer to past time series data, detect specific patterns, and select the optimal collaboration method. In addition, in the police collaboration unit, the generation AI can comprehensively consider the time series data and perform the most reliable collaboration. In this way, the optimal collaboration method can be selected by taking into account the time series data of the collaboration data.

[0124] When coordinating with the police, the police collaboration unit can evaluate the relevance of the linked data and determine the priority of collaboration. For example, when coordinating with the police, the police collaboration unit can evaluate the relevance of the linked data and determine the priority of collaboration. For example, in the police collaboration unit, the generation AI evaluates the relevance of the linked data and prioritizes collaboration of data that is highly likely to be fraud. In addition, in the police collaboration unit, the generation AI can comprehensively evaluate the relevance of the linked data and perform the most reliable collaboration. In addition, in the police collaboration unit, the generation AI can exclude linked data with low relevance and perform the most reliable collaboration. In this way, by evaluating the relevance of the linked data, important linked data can be processed preferentially.

[0125] The data collection unit can estimate the user's emotions and adjust the data collection method based on the estimated user's emotions. The data collection unit, for example, estimates the user's emotions and adjusts the data collection method based on the estimated user's emotions. For example, if the user is nervous, the data collection unit causes the generation AI to simplify the data collection method and collect data quickly. Also, if the user is relaxed, the data collection unit can cause the generation AI to collect detailed data and increase accuracy. Also, if the user is in a hurry, the data collection unit can cause the generation AI to speed up the data collection method and collect data immediately. This makes it possible to adjust the data collection method according to the user's emotions, thereby enabling fast and appropriate data collection.

[0126] The data collection unit can evaluate the reliability of the collected data when collecting data and adjust the accuracy of collection. For example, the data collection unit evaluates the reliability of the collected data when collecting data and adjusts the accuracy of collection. For example, the data collection unit has the generation AI evaluate the reliability of the collected data and prioritize collecting highly reliable data. The data collection unit can also have the generation AI comprehensively evaluate the reliability of the collected data and adjust the accuracy of collection. The data collection unit can also exclude collected data with low reliability and collect the most reliable data. In this way, the accuracy of collection can be adjusted by evaluating the reliability of the collected data.

[0127] The data collection unit can perform data collection while taking into consideration the interrelationships of the collected data. For example, the data collection unit performs data collection while taking into consideration the interrelationships of the collected data. For example, the data collection unit allows the generation AI to evaluate the interrelationships of the collected data and prioritize collecting highly relevant data. The data collection unit can also allow the generation AI to comprehensively evaluate the interrelationships of the collected data and collect the most reliable data. The data collection unit can also allow the generation AI to exclude collected data with low interrelationships and collect the most reliable data. In this way, by taking into consideration the interrelationships of the collected data, highly relevant data can be collected preferentially.

[0128] The data collection unit can estimate the user's emotions and determine the priority of collected data based on the estimated user's emotions. The data collection unit, for example, estimates the user's emotions and determines the priority of collected data based on the estimated user's emotions. For example, if the user is nervous, the data collection unit causes the generation AI to preferentially collect data that is likely to be fraudulent. Also, if the user is relaxed, the data collection unit can cause the generation AI to preferentially collect data that is unlikely to be fraudulent. Also, if the user is in a hurry, the data collection unit can cause the generation AI to quickly collect data that is likely to be fraudulent. In this way, by determining the priority of collected data according to the user's emotions, important data can be collected preferentially.

[0129] The data collection unit can perform data collection while taking into consideration the time series data of the collected data. For example, the data collection unit performs data collection while taking into consideration the time series data of the collected data. For example, in the data collection unit, the generation AI analyzes the time series data of the collected data and selects the optimal data collection method. In addition, the data collection unit can also select the optimal data collection method by having the generation AI refer to past time series data and detect specific patterns. In addition, the data collection unit can also perform data collection with the most reliable data by having the generation AI comprehensively consider the time series data. In this way, the optimal data collection method can be selected by taking into consideration the time series data of the collected data.

[0130] The data collection unit can evaluate the relevance of the collected data when collecting data and determine the priority of collection. For example, the data collection unit evaluates the relevance of the collected data when collecting data and determines the priority of collection. For example, the data collection unit has the generation AI evaluate the relevance of the collected data and prioritize collecting data that is likely to be fraudulent. The data collection unit can also have the generation AI comprehensively evaluate the relevance of the collected data and collect the most reliable data. The data collection unit can also have the generation AI exclude less relevant collected data and collect the most reliable data. In this way, by evaluating the relevance of the collected data, important data can be collected preferentially.

[0131] The data providing unit can estimate the user's emotions and adjust the method of providing data based on the estimated user's emotions. The data providing unit, for example, estimates the user's emotions and adjusts the method of providing data based on the estimated user's emotions. For example, if the user is nervous, the data providing unit can cause the generation AI to simplify the method of providing data and provide data quickly. Also, if the user is relaxed, the data providing unit can cause the generation AI to provide detailed data and increase accuracy. Also, if the user is in a hurry, the data providing unit can cause the generation AI to speed up the method of providing data and provide data immediately. In this way, by adjusting the method of providing data according to the user's emotions, it is possible to provide data quickly and appropriately.

[0132] The data providing unit can evaluate the reliability of the provided data when providing the data and adjust the accuracy of the provision. For example, the data providing unit evaluates the reliability of the provided data when providing the data and adjusts the accuracy of the provision. For example, the data providing unit allows the generation AI to evaluate the reliability of the provided data and provide data with higher reliability as a priority. The data providing unit can also allow the generation AI to comprehensively evaluate the reliability of the provided data and adjust the accuracy of the provision. The data providing unit can also allow the generation AI to exclude provided data with lower reliability and provide the most reliable data. In this way, the accuracy of the provision can be adjusted by evaluating the reliability of the provided data.

[0133] The data providing unit can provide data while taking into consideration the interrelationships of the provided data when providing the data. For example, the data providing unit provides data while taking into consideration the interrelationships of the provided data when providing the data. For example, the data providing unit allows the generation AI to evaluate the interrelationships of the provided data and provide highly relevant data with priority. The data providing unit can also allow the generation AI to comprehensively evaluate the interrelationships of the provided data and provide the most reliable data. The data providing unit can also allow the generation AI to exclude provided data with low interrelationships and provide the most reliable data. In this way, by taking into consideration the interrelationships of the provided data, highly relevant data can be provided with priority.

[0134] The data providing unit can estimate the user's emotions and determine the priority of the provided data based on the estimated user's emotions. The data providing unit, for example, estimates the user's emotions and determines the priority of the provided data based on the estimated user's emotions. For example, if the user is nervous, the data providing unit can cause the generation AI to preferentially provide data that is likely to be fraudulent. Also, if the user is relaxed, the data providing unit can cause the generation AI to preferentially provide data that is unlikely to be fraudulent. Also, if the user is in a hurry, the data providing unit can cause the generation AI to quickly provide data that is likely to be fraudulent. In this way, by determining the priority of the provided data according to the user's emotions, important data can be preferentially provided.

[0135] The data providing unit can provide data while taking into consideration the time series data of the provided data. For example, the data providing unit provides data while taking into consideration the time series data of the provided data. For example, the data providing unit has the generation AI analyze the time series data of the provided data and select the optimal data providing method. The data providing unit can also have the generation AI refer to past time series data, detect specific patterns, and select the optimal data providing method. The data providing unit can also have the generation AI comprehensively consider the time series data and provide the most reliable data. In this way, the optimal data providing method can be selected by taking into consideration the time series data of the provided data.

[0136] The data providing unit can evaluate the relevance of the provided data when providing the data and determine the priority of provision. For example, the data providing unit evaluates the relevance of the provided data when providing the data and determines the priority of provision. For example, the data providing unit allows the generation AI to evaluate the relevance of the provided data and prioritize providing data that is likely to be fraudulent. The data providing unit can also allow the generation AI to comprehensively evaluate the relevance of the provided data and provide the most reliable data. The data providing unit can also allow the generation AI to exclude less relevant provided data and provide the most reliable data. In this way, by evaluating the relevance of the provided data, important data can be provided preferentially.

[0137] The data providing unit can provide data while taking into consideration the interrelationships of the provided data when providing the data. For example, the data providing unit provides data while taking into consideration the interrelationships of the provided data when providing the data. For example, the data providing unit allows the generation AI to evaluate the interrelationships of the provided data and provide highly relevant data with priority. The data providing unit can also allow the generation AI to comprehensively evaluate the interrelationships of the provided data and provide the most reliable data. The data providing unit can also allow the generation AI to exclude provided data with low interrelationships and provide the most reliable data. In this way, by taking into consideration the interrelationships of the provided data, highly relevant data can be provided with priority. === Hard Collateral 1-1 === Each of the above-described elements, including the voice analysis unit, image analysis unit, communication analysis unit, judgment unit, police collaboration unit, data collection unit, and data provision unit, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the voice analysis unit collects telephone conversation content using the microphone 38B of the smart device 14, which is analyzed by the specific processing unit 290 of the data processing device 12. For example, the image analysis unit collects images using the camera 42 of the smart device 14, which is analyzed by the specific processing unit 290 of the data processing device 12. For example, the communication analysis unit collects communication content via the communication I / F 44 of the smart device 14, which is analyzed by the specific processing unit 290 of the data processing device 12. For example, the judgment unit is implemented by the specific processing unit 290 of the data processing device 12 and integrates the results of each analysis to determine the possibility of fraud. For example, the police collaboration unit is implemented by the specific processing unit 290 of the data processing device 12, which collects data provided by the police and inputs it into the system. For example, the data collection unit collects data using various sensors and cameras of the smart device 14, and the data is analyzed by the specific processing unit 290 of the data processing device 12. For example, the data provision unit notifies the user of the analysis results using the output device 40 of the smart device 14, and the specific processing unit 290 of the data processing device 12 reports the results to relevant organizations. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned voice analysis unit, image analysis unit, communication analysis unit, judgment unit, police collaboration unit, data collection unit, and data provision unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the voice analysis unit collects telephone conversation content using the microphone 238 of the smart glasses 214, which is analyzed by the specific processing unit 290 of the data processing device 12. For example, the image analysis unit collects images using the camera 42 of the smart glasses 214, which is analyzed by the specific processing unit 290 of the data processing device 12. For example, the communication analysis unit collects communication content via the communication I / F 44 of the smart glasses 214, which is analyzed by the specific processing unit 290 of the data processing device 12. For example, the judgment unit is realized by the specific processing unit 290 of the data processing device 12 and integrates the results of each analysis to determine the possibility of fraud. For example, the police collaboration unit is realized by the specific processing unit 290 of the data processing device 12, which collects data provided by the police and inputs it into the system. For example, the data collection unit collects data using various sensors and cameras of the smart glasses 214, and the data is analyzed by the specific processing unit 290 of the data processing device 12. For example, the data provision unit notifies the user of the analysis results using the speaker 240 of the smart glasses 214, and the specific processing unit 290 of the data processing device 12 reports the results to relevant organizations. === Hard Collateral 1-3 === Each of the multiple elements, including the voice analysis unit, image analysis unit, communication analysis unit, judgment unit, police collaboration unit, data collection unit, and data provision unit, is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the voice analysis unit collects telephone conversation content using the microphone 238 of the headset terminal 314, and the collected content is analyzed by the specific processing unit 290 of the data processing device 12. For example, the image analysis unit collects images using the camera 42 of the headset terminal 314, and the collected images are analyzed by the specific processing unit 290 of the data processing device 12. For example, the communication analysis unit collects communication content via the communication I / F 44 of the headset terminal 314, and the collected images are analyzed by the specific processing unit 290 of the data processing device 12. For example, the judgment unit is realized by the specific processing unit 290 of the data processing device 12 and integrates the results of each analysis to determine the possibility of fraud. For example, the police collaboration unit is realized by the specific processing unit 290 of the data processing device 12, and collects data provided by the police and inputs it into the system. For example, the data collection unit collects data using various sensors and cameras of the headset terminal 314, and the data is analyzed by the specific processing unit 290 of the data processing device 12. For example, the data provision unit notifies the user of the analysis results using the display 343 of the headset terminal 314, and the specific processing unit 290 of the data processing device 12 reports the results to relevant organizations. === Hard Collateral 1-4 === Each of the multiple elements, including the voice analysis unit, image analysis unit, communication analysis unit, judgment unit, police collaboration unit, data collection unit, and data provision unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the voice analysis unit collects telephone conversation content using the microphone 238 of the robot 414, which is analyzed by the specific processing unit 290 of the data processing device 12. For example, the image analysis unit collects images using the camera 42 of the robot 414, which is analyzed by the specific processing unit 290 of the data processing device 12. For example, the communication analysis unit collects communication content via the communication I / F 44 of the robot 414, which is analyzed by the specific processing unit 290 of the data processing device 12. For example, the judgment unit is realized by the specific processing unit 290 of the data processing device 12 and integrates the results of each analysis to determine the possibility of fraud. For example, the police collaboration unit is realized by the specific processing unit 290 of the data processing device 12, which collects data provided by the police and inputs it into the system. For example, the data collection unit collects data using various sensors and cameras of the robot 414, and the data is analyzed by the specific processing unit 290 of the data processing device 12. For example, the data provision unit notifies the user of the analysis results using the speaker 240 of the robot 414, and the specific processing unit 290 of the data processing device 12 reports the results to relevant organizations.

[0138] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0139] The fraud prevention system may further include a behavior analysis unit that analyzes a user's behavioral patterns. The behavior analysis unit collects data on the user's past behavior and determines the possibility of fraud. For example, the behavior analysis unit may detect a large transaction that the user does not normally make and determine the possibility of fraud. The behavior analysis unit may also detect access to a website that the user does not normally visit and determine the possibility of fraud. The behavior analysis unit may also analyze a user's movement patterns and detect abnormal movements to determine the possibility of fraud. In this way, by analyzing a user's behavioral patterns, the possibility of fraud can be determined more accurately.

[0140] The fraud prevention system may further include a warning adjustment unit that estimates the user's emotions and adjusts the content of the warning message based on the estimated user emotions. For example, if the user is nervous, the warning adjustment unit may cause the generation AI to provide a concise and clear warning message. Alternatively, if the user is relaxed, the warning adjustment unit may cause the generation AI to provide a warning message that includes detailed information. Alternatively, if the user is in a hurry, the warning adjustment unit may cause the generation AI to provide a warning message that is quickly understandable. This allows for the provision of effective warnings by adjusting the content of the warning message according to the user's emotions.

[0141] The fraud prevention system may further include a health monitoring unit that monitors the user's health condition. The health monitoring unit collects vital data such as the user's heart rate and blood pressure, and determines the possibility of fraud. For example, the health monitoring unit may determine that there is a high possibility of fraud if the user's heart rate suddenly increases. The health monitoring unit may also determine that there is a high possibility of fraud if the user's blood pressure is abnormally high. The health monitoring unit may also analyze the user's stress level and determine the possibility of fraud. In this way, by monitoring the user's health condition, the possibility of fraud can be more accurately determined.

[0142] The fraud prevention system may further include a notification unit that estimates the user's emotions and notifies the user of possible fraud in real time based on the estimated user emotions. For example, if the user is nervous, the generation AI may immediately notify the user of possible fraud. Alternatively, if the user is relaxed, the notification unit may notify the user of possible fraud using a normal notification method. Alternatively, if the user is in a hurry, the notification unit may notify the user of possible fraud quickly. This allows for a rapid response by notifying the user of possible fraud in real time according to the user's emotions.

[0143] The fraud prevention system may further include an interface adjustment unit that estimates a user's emotions and adjusts the system interface based on the estimated user emotions. For example, when the user is nervous, the generation AI may provide a simple and intuitive interface. When the user is relaxed, the interface adjustment unit may also provide an interface that includes detailed information. When the user is in a hurry, the interface adjustment unit may also provide an interface that can be operated quickly. This makes it possible to improve usability by adjusting the system interface according to the user's emotions.

[0144] The fraud prevention system may further include a purchase analysis unit that analyzes a user's purchase history. The purchase analysis unit collects the user's past purchase data and determines the possibility of fraud. For example, the purchase analysis unit may detect high-priced items that the user does not normally purchase and determine the possibility of fraud. The purchase analysis unit may also detect purchases from online stores that the user does not normally use and determine the possibility of fraud. The purchase analysis unit may also analyze the user's purchasing patterns and detect abnormal purchases to determine the possibility of fraud. In this way, by analyzing the user's purchase history, the possibility of fraud can be determined more accurately.

[0145] The fraud prevention system may further include a speed adjustment unit that estimates the user's emotions and adjusts the system's operating speed based on the estimated user's emotions. For example, if the user is nervous, the speed adjustment unit may cause the generation AI to speed up the system's operating speed, enabling a quick response. Alternatively, if the user is relaxed, the speed adjustment unit may cause the generation AI to set the system's operating speed to a normal level, prioritizing natural operation. Alternatively, if the user is in a hurry, the speed adjustment unit may cause the generation AI to further speed up the system's operating speed, enabling an immediate response. This allows the system's operating speed to be adjusted according to the user's emotions, enabling a quick and appropriate response.

[0146] The fraud prevention system may further include a location analysis unit that analyzes the user's location information. The location analysis unit collects the user's current location and past movement history to determine the possibility of fraud. For example, the location analysis unit may determine that there is a high possibility of fraud if the user is in a place that the user does not normally visit. The location analysis unit may also analyze the user's movement patterns and detect abnormal movements to determine the possibility of fraud. The location analysis unit may also monitor the user's location information in real time and detect abnormal movements to determine the possibility of fraud. In this way, the possibility of fraud can be more accurately determined by analyzing the user's location information.

[0147] The fraud prevention system may further include a notification adjustment unit that estimates the user's emotions and adjusts the system's notification method based on the estimated user emotions. For example, if the user is nervous, the notification adjustment unit may cause the generation AI to immediately notify the user of a possible fraud. Alternatively, if the user is relaxed, the notification adjustment unit may cause the generation AI to notify the user of a possible fraud using a standard notification method. Alternatively, if the user is in a hurry, the notification adjustment unit may cause the generation AI to quickly notify the user of a possible fraud. This allows for prompt and appropriate notification by adjusting the notification method according to the user's emotions.

[0148] The fraud prevention system may further include a social media analysis unit that analyzes the user's social media activity. The social media analysis unit collects data on the user's social media activity and determines the possibility of fraud. For example, the social media analysis unit may detect interactions with accounts with which the user does not normally interact and determine the possibility of fraud. The social media analysis unit may also detect content that the user does not normally post and determine the possibility of fraud. The social media analysis unit may also analyze the user's follower and friend list to detect suspicious accounts and determine the possibility of fraud. In this way, analyzing the user's social media activity can more accurately determine the possibility of fraud.

[0149] The processing flow of the second embodiment will be briefly explained below.

[0150] Step 1: The voice analysis unit analyzes keywords and tone of voice in the telephone conversation. For example, the voice analysis unit extracts keywords from the conversation and determines the possibility of fraud. The voice analysis unit can also analyze tone of voice to detect emotions such as tension or impatience. The voice analysis unit can also convert the conversation into text using voice recognition technology and analyze it. Step 2: The image analysis unit analyzes images from smartphones and doorbells. For example, the image analysis unit can use facial recognition technology to identify people and determine whether they are suspects of fraud. The image analysis unit can also analyze clothing and background to detect suspicious behavior. The image analysis unit can also use image recognition technology to extract and analyze text within the image. Step 3: The communication analysis unit analyzes the content of emails and website communications. For example, the communication analysis unit analyzes the body of an email or the content of a website to determine the possibility of fraud. The communication analysis unit can also analyze the IP address and domain information of the sender to evaluate their trustworthiness. The communication analysis unit can also analyze communication protocols to detect fraudulent communications. Step 4: The judgment unit combines the analysis results obtained by the voice analysis unit, image analysis unit, and communication analysis unit to determine the possibility of fraud. For example, the judgment unit comprehensively evaluates each analysis result and determines the possibility of fraud. The judgment unit can also refer to data on past fraud cases to improve the accuracy of its judgment. The judgment unit can also evaluate the reliability of the analysis results and adjust the accuracy of its judgment.

[0151] 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.

[0152] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<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.

[0153] 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.

[0154] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0155] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0165] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0166] 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.

[0167] 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.

[0168] 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 AI 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.

[0169] 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.

[0170] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0171] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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).

[0177] 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.

[0178] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0179] 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.

[0180] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0181] 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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0182] 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.

[0183] 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.

[0184] 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 AI 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.

[0185] 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.

[0186] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0187] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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).

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0198] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. 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 the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0199] 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.

[0200] 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.

[0201] 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 AI 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.

[0202] 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.

[0203] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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).

[0208] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0209] 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."

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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, in order to avoid confusion and to 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.

[0221] 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.

[0222] [Explanation of symbols]

[0223] 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 voice analysis unit that analyzes voice; an image analysis unit that analyzes an image; a communication analysis unit that analyzes communication; a determination unit that determines the possibility of fraud based on the analysis results obtained by the voice analysis unit, the image analysis unit, and the communication analysis unit; Equipped with A system characterized by:

2. We have a police cooperation department, Cooperate with the police to input the learning information necessary for making decisions 2. The system of claim 1.

3. Equipped with a data collection unit, Collect various data 2. The system of claim 1.

4. A data providing unit is provided, Providing analysis results 2. The system of claim 1.

5. The voice analysis unit Analyzing keywords and tone of voice in telephone conversations 2. The system of claim 1.

6. The image analysis unit Analyzing images from smartphones and door phones 2. The system of claim 1.

7. The communication analysis unit Analyzing email and website communications 2. The system of claim 1.

8. The determination unit The analysis results obtained by the voice analysis unit, the image analysis unit, and the communication analysis unit are integrated to determine the possibility of fraud.

2. The system of claim 1.

9. The voice analysis unit Estimate the user's emotions and adjust the accuracy of conversation analysis based on the estimated user emotions.

2. The system of claim 1.

10. The voice analysis unit During voice analysis, background sounds of conversations are analyzed to determine the possibility of fraud.

2. The system of claim 1.

Images