system

Abstract

The system according to this embodiment aims to detect signs of fraud and to implement countermeasures quickly. [Solution] The system according to the embodiment comprises an analysis unit, a determination unit, a notification unit, and a learning unit. The analysis unit analyzes facial muscles and voice tone. The determination unit determines the possibility of fraud based on the data analyzed by the analysis unit. The notification unit automatically makes a notification if the determination unit determines that there is a high possibility of fraud. The learning unit learns voice and facial expression data.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult to detect fraud and preventive measures are limited.

[0005] The system according to the embodiment aims to detect signs of fraud and implement countermeasures promptly. )]]

Means for Solving the Problems

[0006] The system according to the embodiment includes an analysis unit, a determination unit, a reporting unit, and a learning unit. The analysis unit analyzes facial muscles and voice tones. The determination unit determines the possibility of fraud based on the data analyzed by the analysis unit. The reporting unit makes an automatic report when the determination unit determines that the possibility of fraud is high. The learning unit learns voice and facial expression data. [Effects of the Invention]

[0007] The system according to this embodiment can detect signs of fraud and implement countermeasures quickly. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The fraud detection system according to an embodiment of the present invention is a technology that solves the conventional problem of fraud being difficult to detect and prevention measures being limited. The fraud detection system detects signs of fraud by analyzing facial muscles and voice tone, and by linking with an automatic notification system, it reduces fraud damage and enables rapid countermeasures. The fraud detection system uses an intercom to perform facial muscle and voice tone analysis, which is particularly effective when fraudsters use the intercom to commit fraud. For example, the fraud detection system detects signs of fraud by analyzing the movement of the facial muscles and voice tone of a fraudster speaking into the intercom. In voice tone analysis, it detects angry or tense voice tones and determines that there is a high possibility of fraud. When signs of fraud are detected, the fraud detection system links with an automatic notification system to quickly notify the police and relevant organizations. This enables the reduction of fraud damage and rapid countermeasures. In addition, the fraud detection system can use generative AI to learn voice and facial data and detect signs of fraud in real time. The generative AI can alert to the risk of fraud and prevent fraud before it occurs. This technology is particularly effective against fraudulent activities such as door-to-door sales and "ore-ore" (impersonation) scams targeting the elderly and people living alone. The fraud detection system can prevent fraudulent activities from multiple angles by combining functions such as automatic identity verification, image analysis for forgery detection, and immediate notification against wanted lists. As a result, the fraud detection system can detect signs of fraud and automatically report them, mitigating fraud losses and enabling rapid countermeasures.

[0029] The fraud detection system according to the embodiment comprises an analysis unit, a determination unit, a notification unit, and a learning unit. The analysis unit analyzes facial muscles and voice tone. The analysis unit, for example, detects the movement of facial muscles and analyzes changes in voice tone. The analysis unit can use a camera to detect the movement of muscles in specific parts of the face. The analysis unit can use a microphone to analyze the pitch, intensity, and rhythm of voice tone. The determination unit determines the likelihood of fraud based on the data analyzed by the analysis unit. The determination unit evaluates the likelihood of fraud based on the analyzed facial muscle movements and changes in voice tone. The determination unit can detect, for example, angry or tense voice tones and determine that there is a high probability of fraud. The determination unit can score the likelihood of fraud based on the analyzed data. The notification unit automatically makes a notification when the determination unit determines that there is a high probability of fraud. The notification unit can use telephone or email to notify the police or other relevant organizations. The notification unit can automatically generate notification content and make a notification quickly. The reporting unit notifies, for example, the receiving agency that there is a high probability of fraud. The learning unit learns voice and facial expression data. The learning unit can learn voice and facial expression data using, for example, generative AI. The learning unit learns voice and facial expression data to detect signs of fraud in real time. The learning unit learns voice and facial expression data to alert about the risk of fraud. As a result, the fraud detection system according to the embodiment can detect signs of fraud and automatically report them, thereby mitigating fraud damage and enabling rapid countermeasures.

[0030] The analysis unit analyzes facial muscles and voice tone. Specifically, it uses a camera and microphone to detect the movement of facial muscles and analyze changes in voice tone. The camera is high resolution and can accurately capture subtle facial movements and changes in expression. For example, it can detect the rise and fall of eyebrows, the movement of the corners of the mouth, and the tension of the muscles around the eyes. This allows the analysis unit to identify emotions such as smiles, surprise, and anger. For voice tone analysis, a high-sensitivity microphone is used to analyze the pitch, strength, rhythm, speed, and intonation of the voice in detail. For example, it can detect voice tremors, sudden changes in tone, and changes in speaking speed, and determine whether these are signs of fraud. The analysis unit processes this data in real time and immediately transmits it to the judgment unit. Furthermore, by comparing it with past data, the analysis unit can detect abnormal movements that deviate from normal patterns. This allows the analysis unit to detect signs of fraud with high accuracy and improve the reliability of the entire system.

[0031] The judgment unit determines the likelihood of fraud based on the data analyzed by the analysis unit. Specifically, the judgment unit evaluates the likelihood of fraud based on the analyzed facial muscle movements and changes in voice tone. For example, it detects angry or tense voice tones and determines that there is a high probability of fraud. The judgment unit can score the likelihood of fraud based on the analyzed data. Scoring is a numerical representation of the risk of fraud by comprehensively evaluating multiple factors. For example, it evaluates the degree of abnormality in facial muscle movements, the degree of changes in voice tone, and the consistency of what is said, and calculates an overall score. Based on this score, the judgment unit notifies the reporting unit if the likelihood of fraud exceeds a certain threshold. Furthermore, the judgment unit can improve the accuracy of its judgment by referring to past data and cases and comparing them with cases that have similar patterns. This allows the judgment unit to determine the likelihood of fraud with high accuracy and enable a rapid response.

[0032] The reporting unit automatically makes a report when the assessment unit determines that there is a high probability of fraud. Specifically, the reporting unit uses telephone and email to report to the police and other relevant agencies. The reporting unit can automatically generate report content and send it quickly. For example, the report content includes the reasons why it was determined to be highly likely to be fraud, a summary of the analyzed data, and the date and location where signs of fraud were detected. The reporting unit automatically compiles this information and sends it to the relevant agencies. Furthermore, the reporting unit not only notifies the receiving agencies of the high probability of fraud but can also provide additional information and follow up as needed. For example, if new data is analyzed after the report is made, that information can be sent as well. This allows the reporting unit to make quick and accurate reports and support a swift response by the relevant agencies.

[0033] The learning unit learns from voice and facial expression data. Specifically, the learning unit can learn from voice and facial expression data using generative AI. Based on a large amount of data, the generative AI builds a model for detecting signs of fraud in real time. For example, it learns from data of past fraud cases and extracts patterns that indicate signs of fraud. Based on these patterns, the learning unit analyzes new data in real time and alerts to fraud risks. Furthermore, the learning unit can continuously incorporate new data to improve the accuracy of the model. For example, if a new fraud method is discovered, it can learn from that data and reflect it in the model, enabling it to respond to the latest fraud methods. As a result, the learning unit can always achieve highly accurate fraud detection based on the latest information, improving the reliability and security of the entire system.

[0034] The analysis unit can analyze facial muscles and voice tone using an intercom. For example, the analysis unit can analyze the movement of a con artist's facial muscles as they speak into the intercom. For example, the analysis unit can analyze the voice tone of a con artist as they speak into the intercom. For example, the analysis unit can use the intercom's camera to detect the movement of the con artist's facial muscles. For example, the analysis unit can use the intercom's microphone to analyze changes in the con artist's voice tone. This allows for effective analysis of a con artist's facial muscles and voice tone by using an intercom. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input image data acquired by the intercom's camera into a generating AI and have the generating AI perform an analysis of facial muscle movements from the image data.

[0035] The judgment unit can detect angry and tense voice tones and determine the possibility of fraud. For example, the judgment unit analyzes the pitch, intensity, and rhythm of the voice tone to detect an angry voice tone. For example, the judgment unit analyzes the pitch, intensity, and rhythm of the voice tone to detect a tense voice tone. For example, the judgment unit detects an angry voice tone and determines that there is a high probability of fraud. For example, the judgment unit detects a tense voice tone and determines that there is a high probability of fraud. This allows for a highly accurate determination of the possibility of fraud through voice tone analysis. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input voice tone data into a generating AI and have the generating AI perform the voice tone analysis.

[0036] The reporting unit can report to the police and relevant agencies when signs of fraud are detected. For example, the reporting unit can call the police when signs of fraud are detected. For example, the reporting unit can email relevant agencies when signs of fraud are detected. For example, the reporting unit can automatically generate and send a report to the police when signs of fraud are detected. For example, the reporting unit can automatically generate and send a report to relevant agencies when signs of fraud are detected. This allows for the swift reporting of signs of fraud, thereby minimizing damage. Some or all of the above processes in the reporting unit may be performed using AI, for example, or not using AI. For example, when signs of fraud are detected, the reporting unit can input the report content into a generating AI and have the generating AI generate the report content.

[0037] The learning unit can learn voice and facial expression data and detect signs of fraud in real time. The learning unit learns voice and facial expression data, for example, using generative AI. The learning unit detects signs of fraud in real time, for example, using generative AI. The learning unit alerts to fraud risks, for example, using generative AI. The learning unit learns voice and facial expression data, for example, using generative AI and detects signs of fraud in real time. This allows for high-precision, real-time detection of signs of fraud through learning voice and facial expression data. Some or all of the above processing in the learning unit is performed using generative AI. For example, the learning unit can input voice and facial expression data into the generative AI and have the generative AI perform the detection of signs of fraud.

[0038] The reporting unit can notify the police when it detects a person registered on the wanted list. For example, the reporting unit can notify the police by phone when it detects a person registered on the wanted list. For example, the reporting unit can notify the police by email when it detects a person registered on the wanted list. For example, the reporting unit can automatically generate and send a report to the police when it detects a person registered on the wanted list. For example, the reporting unit can automatically generate and send a report to the police when it detects a person registered on the wanted list. This makes it possible to detect and arrest fraudsters early through reports based on the wanted list. Some or all of the above processes in the reporting unit may be performed using AI, for example, or without AI. For example, the reporting unit can input data on people registered on the wanted list into a generating AI and have the generating AI generate the report content.

[0039] The analysis unit can estimate the emotions of a con artist and improve the accuracy of its analysis of facial muscles and voice tone based on the estimated emotions. For example, if the analysis unit estimates the emotions of a con artist and the emotions are strong, such as anger or tension, it will analyze the subtle movements of the facial muscles. For example, if the analysis unit estimates the emotions of a con artist and the emotions are strong, such as fear or anxiety, it will analyze the subtle changes in voice tone. For example, if the analysis unit estimates the emotions of a con artist and the emotions are strong, it will comprehensively analyze both facial muscles and voice tone. This improves the accuracy of the analysis based on the emotions of the con artist, allowing for more accurate detection of signs of fraud. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the fraudster's emotional data into a generating AI and have the generating AI perform emotion estimation.

[0040] The analysis unit can analyze facial muscles and voice tone using devices other than intercoms (e.g., smartphones or wearable devices). For example, the analysis unit can use a smartphone camera to analyze the movements of a fraudster's facial muscles. For example, the analysis unit can use a wearable device's microphone to analyze the fraudster's voice tone. For example, the analysis unit can use a smart speaker to analyze the fraudster's voice tone and facial muscle movements. This increases the chances of detecting signs of fraud by using a variety of devices. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input image data acquired by a smartphone camera into a generating AI and have the generating AI perform an analysis of facial muscle movements from the image data.

[0041] The analysis unit can optimize its methods for analyzing facial muscles and voice tone by referring to the fraudster's past behavioral patterns. For example, the analysis unit may refer to the fraudster's past behavioral patterns and focus its analysis on specific facial muscle movements. For example, the analysis unit may refer to the fraudster's past behavioral patterns and focus its analysis on specific changes in voice tone. For example, the analysis unit may refer to the fraudster's past behavioral patterns and comprehensively analyze both facial muscles and voice tone. This allows the analysis method to be optimized by referring to past behavioral patterns, enabling more accurate detection of signs of fraud. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit may input data on the fraudster's past behavioral patterns into a generating AI and have the generating AI perform the behavioral pattern analysis.

[0042] The analysis unit can estimate the emotions of the con artist and determine the priority of the analysis results based on the estimated emotions. For example, if the analysis unit estimates the emotions of the con artist and the emotions of anger or tension are strong, it will set the priority of the analysis results to a high level. For example, if the analysis unit estimates the emotions of the con artist and the emotions of fear or anxiety are strong, it will set the priority of the analysis results to a medium level. For example, if the analysis unit estimates the emotions of the con artist and the emotions of calm are strong, it will set the priority of the analysis results to a low level. This allows important analysis results to be processed preferentially by determining priorities based on the emotions of the con artist. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the emotions of the con artist into a generating AI and have the generating AI perform the determination of priorities based on emotions.

[0043] The analysis unit can improve the accuracy of its analysis of facial muscles and voice tone based on the con artist's geographical location information. For example, the analysis unit considers the con artist's geographical location information to analyze trends in fraudulent activities in a specific area. For example, the analysis unit considers the con artist's geographical location information to focus on analyzing facial muscle movements in a specific area. For example, the analysis unit considers the con artist's geographical location information to focus on analyzing changes in voice tone in a specific area. This makes it possible to perform analyses that reflect region-specific trends in fraudulent activities by considering geographical location information. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data on the con artist's geographical location information into a generating AI and have the generating AI perform an analysis based on geographical location information.

[0044] The analysis unit can analyze the fraudster's social media activity and obtain relevant data when analyzing facial muscles and voice tone. For example, the analysis unit can analyze the fraudster's social media activity and analyze the movement of specific facial muscles. For example, the analysis unit can analyze the fraudster's social media activity and analyze changes in specific voice tone. For example, the analysis unit can analyze the fraudster's social media activity and comprehensively analyze both facial muscles and voice tone. This allows for a more accurate understanding of the fraudster's behavioral patterns by analyzing social media activity. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data on the fraudster's social media activity into a generating AI and have the generating AI perform the analysis of the social media activity.

[0045] The judgment unit can estimate the emotions of the con artist and adjust the criteria for judging the likelihood of fraud based on the estimated emotions. For example, if the judgment unit estimates the emotions of the con artist and the emotions of anger or tension are strong, it will judge the likelihood of fraud to be high. For example, if the emotions of the con artist estimates the emotions of the con artist and the emotions of fear or anxiety are strong, it will judge the likelihood of fraud to be moderate. For example, if the emotions of the con artist estimate the emotions of the con artist and the emotions of calmness are strong, it will judge the likelihood of fraud to be low. In this way, the likelihood of fraud can be judged more accurately by adjusting the judgment criteria based on the emotions of the con artist. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input the emotions of the con artist into a generating AI and have the generating AI perform the adjustment of the judgment criteria based on emotions.

[0046] The judgment unit can improve the accuracy of its judgment when determining the possibility of fraud based on the fraudster's past fraudulent activity history. For example, the judgment unit may refer to the fraudster's past fraudulent activity history and determine that the possibility of fraud is high. For example, the judgment unit may refer to the fraudster's past fraudulent activity history and determine that the possibility of fraud is moderate. For example, the judgment unit may refer to the fraudster's past fraudulent activity history and determine that the possibility of fraud is low. In this way, by referring to past fraudulent activity history, the judgment unit can improve the accuracy of its judgment and determine the possibility of fraud with high precision. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit may input data on the fraudster's past fraudulent activity history into a generating AI and have the generating AI perform a judgment based on the fraudulent activity history.

[0047] The judgment unit can make a judgment by considering the attribute information of the fraudster (e.g., age, gender) when determining the possibility of fraud. For example, the judgment unit can consider the attribute information of the fraudster to determine the tendency of fraudulent activity in a particular age group. For example, the judgment unit can consider the attribute information of the fraudster to determine the tendency of fraudulent activity in a particular gender. For example, the judgment unit can consider the attribute information of the fraudster to determine the tendency of fraudulent activity in a particular age group and gender. By considering the attribute information of the fraudster, the possibility of fraud can be determined more accurately. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without using AI. For example, the judgment unit can input data on the fraudster's attribute information into a generating AI and have the generating AI perform a judgment based on the attribute information.

[0048] The judgment unit can estimate the emotions of a con artist and determine a priority order for judging the likelihood of fraud based on the estimated emotions. For example, if the judgment unit estimates the emotions of a con artist and the emotions of anger or tension are strong, it will judge the likelihood of fraud as high. For example, if the emotions of a con artist estimates the emotions of a con artist and the emotions of fear or anxiety are strong, it will judge the likelihood of fraud as moderate. For example, if the emotions of a con artist estimate the emotions of a con artist and the emotions of calm are strong, it will judge the likelihood of fraud as low. In this way, important decisions can be made with priority given to them by determining the priority order based on the emotions of the con artist. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input the emotions of a con artist into a generating AI and have the generating AI perform the determination of priority based on emotions.

[0049] The judgment unit can improve the accuracy of its judgment when determining the possibility of fraud based on the geographical location information of the fraudster. For example, the judgment unit considers the geographical location information of the fraudster and determines the tendency of fraudulent activity in a particular area. For example, the judgment unit considers the geographical location information of the fraudster and determines the tendency of fraudulent activity in a particular area. For example, the judgment unit considers the geographical location information of the fraudster and determines the tendency of fraudulent activity in a particular area. This makes it possible to make judgments that reflect region-specific trends in fraudulent activity by considering geographical location information. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without using AI. For example, the judgment unit can input data on the geographical location information of the fraudster into a generating AI and have the generating AI perform a judgment based on geographical location information.

[0050] The judgment unit can improve the accuracy of its judgment when determining the likelihood of fraud based on the fraudster's relevant literature. For example, the judgment unit may refer to the fraudster's relevant literature and determine that the likelihood of fraud is high. For example, the judgment unit may refer to the fraudster's relevant literature and determine that the likelihood of fraud is moderate. For example, the judgment unit may refer to the fraudster's relevant literature and determine that the likelihood of fraud is low. In this way, by referring to relevant literature, the likelihood of fraud can be determined more accurately. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit may input data on the fraudster's relevant literature into a generating AI and have the generating AI perform a judgment based on the relevant literature.

[0051] The reporting unit can estimate the emotions of the fraudster and adjust the content of the report based on the estimated emotions. For example, if the reporting unit estimates the emotions of the fraudster and the feelings of anger or tension are strong, it will describe the content of the report in detail. For example, if the reporting unit estimates the emotions of the fraudster and the feelings of fear or anxiety are strong, it will describe the content of the report concisely. For example, if the reporting unit estimates the emotions of the fraudster and the feelings of calmness are strong, it will describe the content of the report comprehensively. This improves the accuracy of the report by adjusting the content of the report based on the emotions of the fraudster. Some or all of the above processing in the reporting unit may be performed using AI, for example, or not using AI. For example, the reporting unit can input the fraudster's emotion data into a generating AI and have the generating AI perform the adjustment of the report content based on emotions.

[0052] The reporting unit can optimize the content of a report by referring to the fraudster's past fraudulent activity history when a report is made. For example, the reporting unit may refer to the fraudster's past fraudulent activity history and describe the report in detail. For example, the reporting unit may refer to the fraudster's past fraudulent activity history and describe the report concisely. For example, the reporting unit may refer to the fraudster's past fraudulent activity history and describe the report comprehensively. By referring to the past fraudulent activity history, the reporting unit optimizes the content of the report and improves the accuracy of the report. Some or all of the above processing in the reporting unit may be performed using AI, for example, or without AI. For example, the reporting unit may input data on the fraudster's past fraudulent activity history into a generating AI and have the generating AI perform the optimization of the report content based on the fraudulent activity history.

[0053] The reporting unit can adjust the urgency of a report based on the current actions of the fraudster when a report is made. For example, the reporting unit may set the urgency to high, considering the fraudster's current actions. For example, the reporting unit may set the urgency to medium, considering the fraudster's current actions. For example, the reporting unit may set the urgency to low, considering the fraudster's current actions. This allows for reporting at an appropriate level of urgency by adjusting the urgency based on the current actions. Some or all of the above processing in the reporting unit may be performed using AI, for example, or without AI. For example, the reporting unit may input data on the fraudster's current actions into a generating AI and have the generating AI perform the adjustment of the urgency based on the actions.

[0054] The reporting unit can estimate the emotions of the fraudster and determine the priority of reporting based on the estimated emotions. For example, if the reporting unit estimates the emotions of the fraudster and the emotions of anger or tension are strong, it will set the reporting priority high. For example, if the reporting unit estimates the emotions of the fraudster and the emotions of fear or anxiety are strong, it will set the reporting priority to a medium level. For example, if the reporting unit estimates the emotions of the fraudster and the emotions of calm are strong, it will set the reporting priority to a low level. This allows important reports to be given priority by determining priorities based on the emotions of the fraudster. Some or all of the above processing in the reporting unit may be performed using AI, for example, or not using AI. For example, the reporting unit can input fraudster emotion data into a generating AI and have the generating AI perform the determination of reporting priorities based on emotions.

[0055] The reporting unit can optimize the content of a report based on the geographical location information of the fraudster. For example, the reporting unit may describe the content of the report in detail, taking into account the geographical location information of the fraudster. For example, the reporting unit may describe the content of the report concisely, taking into account the geographical location information of the fraudster. For example, the reporting unit may describe the content of the report comprehensively, taking into account the geographical location information of the fraudster. This makes it possible to report frauds that reflect the trends of fraudulent activities specific to a region by taking geographical location information into consideration. Some or all of the above processing in the reporting unit may be performed using AI, for example, or without using AI. For example, the reporting unit may input data on the geographical location information of the fraudster into a generating AI and have the generating AI perform the optimization of the report content based on geographical location information.

[0056] The reporting department can analyze the fraudster's social media activity to supplement the reported information at the time of reporting. For example, the reporting department can analyze the fraudster's social media activity and describe the reported information in detail. For example, the reporting department can analyze the fraudster's social media activity and describe the reported information concisely. For example, the reporting department can analyze the fraudster's social media activity and describe the reported information comprehensively. In this way, analyzing social media activity supplements the reported information and improves the accuracy of the report. Some or all of the above processing in the reporting department may be performed using AI, for example, or not using AI. For example, the reporting department can input data on the fraudster's social media activity into a generating AI and have the generating AI perform the task of supplementing the reported information based on the social media activity.

[0057] The learning unit can estimate the emotions of a con artist and select training data based on the estimated emotions. For example, if the learning unit estimates the emotions of a con artist and finds that the emotions of anger or tension are strong, it will select training data related to those emotions. For example, if the learning unit estimates the emotions of a con artist and finds that the emotions of fear or anxiety are strong, it will select training data related to those emotions. For example, if the learning unit estimates the emotions of a con artist and finds that the emotions of calmness are strong, it will select training data related to that emotion. This improves the accuracy of learning by selecting training data based on the emotions of the con artist. Some or all of the above processing in the learning unit is performed using a generative AI. For example, the learning unit can input the emotions of a con artist into a generative AI and have the generative AI perform the selection of training data based on those emotions.

[0058] The learning unit can optimize its learning algorithm by referring to past fraud data during training. For example, the learning unit can optimize the learning algorithm by referring to past fraud data. The learning unit can improve the learning algorithm by referring to past fraud data. The learning unit can adjust the learning algorithm by referring to past fraud data. As a result, by referring to past fraud data, the learning algorithm is optimized and the accuracy of learning is improved. Some or all of the above processes in the learning unit are performed using a generative AI. For example, the learning unit can input past fraud data into the generative AI and have the generative AI perform the optimization of the learning algorithm.

[0059] The learning unit can perform learning while considering the attribute information of fraudsters (e.g., age, gender). For example, the learning unit can consider the attribute information of fraudsters and learn the tendencies of fraudulent activities in a specific age group. For example, the learning unit can consider the attribute information of fraudsters and learn the tendencies of fraudulent activities in a specific gender. For example, the learning unit can consider the attribute information of fraudsters and learn the tendencies of fraudulent activities in a specific age group and gender. This improves the accuracy of learning by considering the attribute information of fraudsters. Some or all of the above processing in the learning unit is performed using a generative AI. For example, the learning unit can input fraudster attribute information data into the generative AI and have the generative AI perform learning based on the attribute information.

[0060] The learning unit can estimate the emotions of the con artist and adjust the learning frequency based on the estimated emotions. For example, if the learning unit estimates the emotions of the con artist and the emotions of anger or tension are strong, it will set the learning frequency high. For example, if the learning unit estimates the emotions of the con artist and the emotions of fear or anxiety are strong, it will set the learning frequency to a medium level. For example, if the learning unit estimates the emotions of the con artist and the emotions of calm are strong, it will set the learning frequency to a low level. This improves the efficiency of learning by adjusting the learning frequency based on the emotions of the con artist. Some or all of the above processing in the learning unit is performed using a generative AI. For example, the learning unit can input the emotions of the con artist into the generative AI and have the generative AI perform the adjustment of the learning frequency based on the emotions.

[0061] The learning unit can weight the training data based on the timing of fraudulent activity during training. For example, the learning unit considers the timing of fraudulent activity when weighting the training data. For example, the learning unit considers the timing of fraudulent activity when weighting the training data. For example, the learning unit considers the timing of fraudulent activity when weighting the training data when weighting the training data when weighting the training data is optimized. This improves the accuracy of training through weighting based on the timing of fraudulent activity. Some or all of the above processing in the learning unit is performed using a generative AI. For example, the learning unit can input data on the timing of fraudulent activity into the generative AI and have the generative AI perform weighting based on the timing of occurrence.

[0062] The learning unit can improve its learning accuracy by referring to relevant literature on con artists during the learning process. For example, the learning unit can refer to relevant literature on con artists to improve learning accuracy. For example, the learning unit can refer to relevant literature on con artists to improve learning accuracy. For example, the learning unit can refer to relevant literature on con artists to adjust learning accuracy. In this way, the accuracy of learning is improved by referring to relevant literature. Some or all of the above processing in the learning unit is performed using a generative AI. For example, the learning unit can input data on relevant literature on con artists into the generative AI and have the generative AI perform learning based on the relevant literature.

[0063] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0064] The analysis unit can monitor the fraudster's behavior patterns in real time and detect abnormal behavior. For example, the analysis unit will issue an alert if the fraudster deviates from their normal behavior patterns. If the fraudster is frequently active during a particular time period, the analysis unit will focus its monitoring on that time period. If the fraudster is frequently active in a particular location, the analysis unit will focus its monitoring on activities in that location. By monitoring the fraudster's behavior patterns in real time, signs of fraud can be detected early.

[0065] When signs of fraud are detected, the reporting department can optimize the report by referring to the fraudster's past activity history. For example, the reporting department can refer to the fraudster's past activity history and add detailed information to the report. The reporting department can refer to the fraudster's past activity history and summarize the report concisely. The reporting department can refer to the fraudster's past activity history and describe the report comprehensively. In this way, by referring to past activity history, the report can be optimized and the accuracy of the report can be improved.

[0066] The analysis unit can detect signs of fraud by taking into account the geographical location of the fraudster. For example, if the analysis unit frequently operates in a particular area, it will focus its monitoring on that area. If the analysis unit frequently operates during a particular time period, it will focus its monitoring on that time period. If the analysis unit observes unusual behavior at a particular location, it will focus its analysis on the activity at that location. By taking geographical location information into account, it is possible to detect signs of fraud more accurately.

[0067] When signs of fraud are detected, the reporting department can analyze the fraudster's social media activity to supplement the reported information. For example, the reporting department can analyze the fraudster's social media activity and add detailed information to the reported information. The reporting department can analyze the fraudster's social media activity and summarize the reported information concisely. The reporting department can analyze the fraudster's social media activity and provide a comprehensive description of the reported information. In this way, analyzing social media activity can supplement the reported information and improve the accuracy of the report.

[0068] The analysis unit can optimize its methods for analyzing facial muscles and voice tone by referring to the con artist's past behavioral patterns. For example, the analysis unit can refer to the con artist's past behavioral patterns and focus on analyzing specific facial muscle movements. The analysis unit can refer to the con artist's past behavioral patterns and focus on analyzing specific changes in voice tone. The analysis unit can refer to the con artist's past behavioral patterns and comprehensively analyze both facial muscles and voice tone. This allows the analysis method to be optimized by referring to past behavioral patterns, enabling more accurate detection of signs of fraud.

[0069] The following briefly describes the processing flow for example form 1.

[0070] Step 1: The analysis unit analyzes facial muscles and voice tone. For example, the analysis unit detects the movement of facial muscles and analyzes changes in voice tone. The analysis unit can use a camera to detect the movement of muscles in specific parts of the face and a microphone to analyze the pitch, intensity, and rhythm of voice tone. Step 2: The judgment unit determines the likelihood of fraud based on the data analyzed by the analysis unit. The judgment unit evaluates the likelihood of fraud based on the analyzed facial muscle movements and changes in voice tone, and if it detects angry or tense voice tones, it determines that there is a high possibility of fraud. The judgment unit can score the likelihood of fraud based on the analyzed data. Step 3: The reporting unit automatically makes a report if the assessment unit determines that there is a high probability of fraud. The reporting unit can use telephone or email to report to the police and other relevant agencies. The reporting unit can automatically generate the content of the report and submit it quickly. The reporting unit notifies the receiving agency that there is a high probability of fraud. Step 4: The learning unit learns voice and facial expression data. The learning unit can learn voice and facial expression data using generative AI. The learning unit learns voice and facial expression data to detect signs of fraud in real time. The learning unit learns voice and facial expression data to alert about the risk of fraud.

[0071] (Example of form 2) The fraud detection system according to an embodiment of the present invention is a technology that solves the conventional problem of fraud being difficult to detect and prevention measures being limited. The fraud detection system detects signs of fraud by analyzing facial muscles and voice tone, and by linking with an automatic notification system, it reduces fraud damage and enables rapid countermeasures. The fraud detection system uses an intercom to perform facial muscle and voice tone analysis, which is particularly effective when fraudsters use the intercom to commit fraud. For example, the fraud detection system detects signs of fraud by analyzing the movement of the facial muscles and voice tone of a fraudster speaking into the intercom. In voice tone analysis, it detects angry or tense voice tones and determines that there is a high possibility of fraud. When signs of fraud are detected, the fraud detection system links with an automatic notification system to quickly notify the police and relevant organizations. This enables the reduction of fraud damage and rapid countermeasures. In addition, the fraud detection system can use generative AI to learn voice and facial data and detect signs of fraud in real time. The generative AI can alert to the risk of fraud and prevent fraud before it occurs. This technology is particularly effective against fraudulent activities such as door-to-door sales and "ore-ore" (impersonation) scams targeting the elderly and people living alone. The fraud detection system can prevent fraudulent activities from multiple angles by combining functions such as automatic identity verification, image analysis for forgery detection, and immediate notification against wanted lists. As a result, the fraud detection system can detect signs of fraud and automatically report them, mitigating fraud losses and enabling rapid countermeasures.

[0072] The fraud detection system according to the embodiment comprises an analysis unit, a determination unit, a notification unit, and a learning unit. The analysis unit analyzes facial muscles and voice tone. The analysis unit, for example, detects the movement of facial muscles and analyzes changes in voice tone. The analysis unit can use a camera to detect the movement of muscles in specific parts of the face. The analysis unit can use a microphone to analyze the pitch, intensity, and rhythm of voice tone. The determination unit determines the likelihood of fraud based on the data analyzed by the analysis unit. The determination unit evaluates the likelihood of fraud based on the analyzed facial muscle movements and changes in voice tone. The determination unit can detect, for example, angry or tense voice tones and determine that there is a high probability of fraud. The determination unit can score the likelihood of fraud based on the analyzed data. The notification unit automatically makes a notification when the determination unit determines that there is a high probability of fraud. The notification unit can use telephone or email to notify the police or other relevant organizations. The notification unit can automatically generate notification content and make a notification quickly. The reporting unit notifies, for example, the receiving agency that there is a high probability of fraud. The learning unit learns voice and facial expression data. The learning unit can learn voice and facial expression data using, for example, generative AI. The learning unit learns voice and facial expression data to detect signs of fraud in real time. The learning unit learns voice and facial expression data to alert about the risk of fraud. As a result, the fraud detection system according to the embodiment can detect signs of fraud and automatically report them, thereby mitigating fraud damage and enabling rapid countermeasures.

[0073] The analysis unit analyzes facial muscles and voice tone. Specifically, it uses a camera and microphone to detect the movement of facial muscles and analyze changes in voice tone. The camera is high resolution and can accurately capture subtle facial movements and changes in expression. For example, it can detect the rise and fall of eyebrows, the movement of the corners of the mouth, and the tension of the muscles around the eyes. This allows the analysis unit to identify emotions such as smiles, surprise, and anger. For voice tone analysis, a high-sensitivity microphone is used to analyze the pitch, strength, rhythm, speed, and intonation of the voice in detail. For example, it can detect voice tremors, sudden changes in tone, and changes in speaking speed, and determine whether these are signs of fraud. The analysis unit processes this data in real time and immediately transmits it to the judgment unit. Furthermore, by comparing it with past data, the analysis unit can detect abnormal movements that deviate from normal patterns. This allows the analysis unit to detect signs of fraud with high accuracy and improve the reliability of the entire system.

[0074] The judgment unit determines the likelihood of fraud based on the data analyzed by the analysis unit. Specifically, the judgment unit evaluates the likelihood of fraud based on the analyzed facial muscle movements and changes in voice tone. For example, it detects angry or tense voice tones and determines that there is a high probability of fraud. The judgment unit can score the likelihood of fraud based on the analyzed data. Scoring is a numerical representation of the risk of fraud by comprehensively evaluating multiple factors. For example, it evaluates the degree of abnormality in facial muscle movements, the degree of changes in voice tone, and the consistency of what is said, and calculates an overall score. Based on this score, the judgment unit notifies the reporting unit if the likelihood of fraud exceeds a certain threshold. Furthermore, the judgment unit can improve the accuracy of its judgment by referring to past data and cases and comparing them with cases that have similar patterns. This allows the judgment unit to determine the likelihood of fraud with high accuracy and enable a rapid response.

[0075] The reporting unit automatically makes a report when the assessment unit determines that there is a high probability of fraud. Specifically, the reporting unit uses telephone and email to report to the police and other relevant agencies. The reporting unit can automatically generate report content and send it quickly. For example, the report content includes the reasons why it was determined to be highly likely to be fraud, a summary of the analyzed data, and the date and location where signs of fraud were detected. The reporting unit automatically compiles this information and sends it to the relevant agencies. Furthermore, the reporting unit not only notifies the receiving agencies of the high probability of fraud but can also provide additional information and follow up as needed. For example, if new data is analyzed after the report is made, that information can be sent as well. This allows the reporting unit to make quick and accurate reports and support a swift response by the relevant agencies.

[0076] The learning unit learns from voice and facial expression data. Specifically, the learning unit can learn from voice and facial expression data using generative AI. Based on a large amount of data, the generative AI builds a model for detecting signs of fraud in real time. For example, it learns from data of past fraud cases and extracts patterns that indicate signs of fraud. Based on these patterns, the learning unit analyzes new data in real time and alerts to fraud risks. Furthermore, the learning unit can continuously incorporate new data to improve the accuracy of the model. For example, if a new fraud method is discovered, it can learn from that data and reflect it in the model, enabling it to respond to the latest fraud methods. As a result, the learning unit can always achieve highly accurate fraud detection based on the latest information, improving the reliability and security of the entire system.

[0077] The analysis unit can analyze facial muscles and voice tone using an intercom. For example, the analysis unit can analyze the movement of a con artist's facial muscles as they speak into the intercom. For example, the analysis unit can analyze the voice tone of a con artist as they speak into the intercom. For example, the analysis unit can use the intercom's camera to detect the movement of the con artist's facial muscles. For example, the analysis unit can use the intercom's microphone to analyze changes in the con artist's voice tone. This allows for effective analysis of a con artist's facial muscles and voice tone by using an intercom. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input image data acquired by the intercom's camera into a generating AI and have the generating AI perform an analysis of facial muscle movements from the image data.

[0078] The judgment unit can detect angry and tense voice tones and determine the possibility of fraud. For example, the judgment unit analyzes the pitch, intensity, and rhythm of the voice tone to detect an angry voice tone. For example, the judgment unit analyzes the pitch, intensity, and rhythm of the voice tone to detect a tense voice tone. For example, the judgment unit detects an angry voice tone and determines that there is a high probability of fraud. For example, the judgment unit detects a tense voice tone and determines that there is a high probability of fraud. This allows for a highly accurate determination of the possibility of fraud through voice tone analysis. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input voice tone data into a generating AI and have the generating AI perform the voice tone analysis.

[0079] The reporting unit can report to the police and relevant agencies when signs of fraud are detected. For example, the reporting unit can call the police when signs of fraud are detected. For example, the reporting unit can email relevant agencies when signs of fraud are detected. For example, the reporting unit can automatically generate and send a report to the police when signs of fraud are detected. For example, the reporting unit can automatically generate and send a report to relevant agencies when signs of fraud are detected. This allows for the swift reporting of signs of fraud, thereby minimizing damage. Some or all of the above processes in the reporting unit may be performed using AI, for example, or not using AI. For example, when signs of fraud are detected, the reporting unit can input the report content into a generating AI and have the generating AI generate the report content.

[0080] The learning unit can learn voice and facial expression data and detect signs of fraud in real time. The learning unit learns voice and facial expression data, for example, using generative AI. The learning unit detects signs of fraud in real time, for example, using generative AI. The learning unit alerts to fraud risks, for example, using generative AI. The learning unit learns voice and facial expression data, for example, using generative AI and detects signs of fraud in real time. This allows for high-precision, real-time detection of signs of fraud through learning voice and facial expression data. Some or all of the above processing in the learning unit is performed using generative AI. For example, the learning unit can input voice and facial expression data into the generative AI and have the generative AI perform the detection of signs of fraud.

[0081] The reporting unit can notify the police when it detects a person registered on the wanted list. For example, the reporting unit can notify the police by phone when it detects a person registered on the wanted list. For example, the reporting unit can notify the police by email when it detects a person registered on the wanted list. For example, the reporting unit can automatically generate and send a report to the police when it detects a person registered on the wanted list. For example, the reporting unit can automatically generate and send a report to the police when it detects a person registered on the wanted list. This makes it possible to detect and arrest fraudsters early through reports based on the wanted list. Some or all of the above processes in the reporting unit may be performed using AI, for example, or without AI. For example, the reporting unit can input data on people registered on the wanted list into a generating AI and have the generating AI generate the report content.

[0082] The analysis unit can estimate the emotions of a con artist and improve the accuracy of its analysis of facial muscles and voice tone based on the estimated emotions. For example, if the analysis unit estimates the emotions of a con artist and the emotions are strong, such as anger or tension, it will analyze the subtle movements of the facial muscles. For example, if the analysis unit estimates the emotions of a con artist and the emotions are strong, such as fear or anxiety, it will analyze the subtle changes in voice tone. For example, if the analysis unit estimates the emotions of a con artist and the emotions are strong, it will comprehensively analyze both facial muscles and voice tone. This improves the accuracy of the analysis based on the emotions of the con artist, allowing for more accurate detection of signs of fraud. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the fraudster's emotional data into a generating AI and have the generating AI perform emotion estimation.

[0083] The analysis unit can analyze facial muscles and voice tone using devices other than intercoms (e.g., smartphones or wearable devices). For example, the analysis unit can use a smartphone camera to analyze the movements of a fraudster's facial muscles. For example, the analysis unit can use a wearable device's microphone to analyze the fraudster's voice tone. For example, the analysis unit can use a smart speaker to analyze the fraudster's voice tone and facial muscle movements. This increases the chances of detecting signs of fraud by using a variety of devices. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input image data acquired by a smartphone camera into a generating AI and have the generating AI perform an analysis of facial muscle movements from the image data.

[0084] The analysis unit can optimize its methods for analyzing facial muscles and voice tone by referring to the fraudster's past behavioral patterns. For example, the analysis unit may refer to the fraudster's past behavioral patterns and focus its analysis on specific facial muscle movements. For example, the analysis unit may refer to the fraudster's past behavioral patterns and focus its analysis on specific changes in voice tone. For example, the analysis unit may refer to the fraudster's past behavioral patterns and comprehensively analyze both facial muscles and voice tone. This allows the analysis method to be optimized by referring to past behavioral patterns, enabling more accurate detection of signs of fraud. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit may input data on the fraudster's past behavioral patterns into a generating AI and have the generating AI perform the behavioral pattern analysis.

[0085] The analysis unit can estimate the emotions of the con artist and determine the priority of the analysis results based on the estimated emotions. For example, if the analysis unit estimates the emotions of the con artist and the emotions of anger or tension are strong, it will set the priority of the analysis results to a high level. For example, if the analysis unit estimates the emotions of the con artist and the emotions of fear or anxiety are strong, it will set the priority of the analysis results to a medium level. For example, if the analysis unit estimates the emotions of the con artist and the emotions of calm are strong, it will set the priority of the analysis results to a low level. This allows important analysis results to be processed preferentially by determining priorities based on the emotions of the con artist. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the emotions of the con artist into a generating AI and have the generating AI perform the determination of priorities based on emotions.

[0086] The analysis unit can improve the accuracy of its analysis of facial muscles and voice tone based on the con artist's geographical location information. For example, the analysis unit considers the con artist's geographical location information to analyze trends in fraudulent activities in a specific area. For example, the analysis unit considers the con artist's geographical location information to focus on analyzing facial muscle movements in a specific area. For example, the analysis unit considers the con artist's geographical location information to focus on analyzing changes in voice tone in a specific area. This makes it possible to perform analyses that reflect region-specific trends in fraudulent activities by considering geographical location information. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data on the con artist's geographical location information into a generating AI and have the generating AI perform an analysis based on geographical location information.

[0087] The analysis unit can analyze the fraudster's social media activity and obtain relevant data when analyzing facial muscles and voice tone. For example, the analysis unit can analyze the fraudster's social media activity and analyze the movement of specific facial muscles. For example, the analysis unit can analyze the fraudster's social media activity and analyze changes in specific voice tone. For example, the analysis unit can analyze the fraudster's social media activity and comprehensively analyze both facial muscles and voice tone. This allows for a more accurate understanding of the fraudster's behavioral patterns by analyzing social media activity. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data on the fraudster's social media activity into a generating AI and have the generating AI perform the analysis of the social media activity.

[0088] The judgment unit can estimate the emotions of the con artist and adjust the criteria for judging the likelihood of fraud based on the estimated emotions. For example, if the judgment unit estimates the emotions of the con artist and the emotions of anger or tension are strong, it will judge the likelihood of fraud to be high. For example, if the emotions of the con artist estimates the emotions of the con artist and the emotions of fear or anxiety are strong, it will judge the likelihood of fraud to be moderate. For example, if the emotions of the con artist estimate the emotions of the con artist and the emotions of calmness are strong, it will judge the likelihood of fraud to be low. In this way, the likelihood of fraud can be judged more accurately by adjusting the judgment criteria based on the emotions of the con artist. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input the emotions of the con artist into a generating AI and have the generating AI perform the adjustment of the judgment criteria based on emotions.

[0089] The judgment unit can improve the accuracy of its judgment when determining the possibility of fraud based on the fraudster's past fraudulent activity history. For example, the judgment unit may refer to the fraudster's past fraudulent activity history and determine that the possibility of fraud is high. For example, the judgment unit may refer to the fraudster's past fraudulent activity history and determine that the possibility of fraud is moderate. For example, the judgment unit may refer to the fraudster's past fraudulent activity history and determine that the possibility of fraud is low. In this way, by referring to past fraudulent activity history, the judgment unit can improve the accuracy of its judgment and determine the possibility of fraud with high precision. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit may input data on the fraudster's past fraudulent activity history into a generating AI and have the generating AI perform a judgment based on the fraudulent activity history.

[0090] The judgment unit can make a judgment by considering the attribute information of the fraudster (e.g., age, gender) when determining the possibility of fraud. For example, the judgment unit can consider the attribute information of the fraudster to determine the tendency of fraudulent activity in a particular age group. For example, the judgment unit can consider the attribute information of the fraudster to determine the tendency of fraudulent activity in a particular gender. For example, the judgment unit can consider the attribute information of the fraudster to determine the tendency of fraudulent activity in a particular age group and gender. By considering the attribute information of the fraudster, the possibility of fraud can be determined more accurately. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without using AI. For example, the judgment unit can input data on the fraudster's attribute information into a generating AI and have the generating AI perform a judgment based on the attribute information.

[0091] The judgment unit can estimate the emotions of a con artist and determine a priority order for judging the likelihood of fraud based on the estimated emotions. For example, if the judgment unit estimates the emotions of a con artist and the emotions of anger or tension are strong, it will judge the likelihood of fraud as high. For example, if the emotions of a con artist estimates the emotions of a con artist and the emotions of fear or anxiety are strong, it will judge the likelihood of fraud as moderate. For example, if the emotions of a con artist estimate the emotions of a con artist and the emotions of calm are strong, it will judge the likelihood of fraud as low. In this way, important decisions can be made with priority given to them by determining the priority order based on the emotions of the con artist. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input the emotions of a con artist into a generating AI and have the generating AI perform the determination of priority based on emotions.

[0092] The judgment unit can improve the accuracy of its judgment when determining the possibility of fraud based on the geographical location information of the fraudster. For example, the judgment unit considers the geographical location information of the fraudster and determines the tendency of fraudulent activity in a particular area. For example, the judgment unit considers the geographical location information of the fraudster and determines the tendency of fraudulent activity in a particular area. For example, the judgment unit considers the geographical location information of the fraudster and determines the tendency of fraudulent activity in a particular area. This makes it possible to make judgments that reflect region-specific trends in fraudulent activity by considering geographical location information. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without using AI. For example, the judgment unit can input data on the geographical location information of the fraudster into a generating AI and have the generating AI perform a judgment based on geographical location information.

[0093] The judgment unit can improve the accuracy of its judgment when determining the likelihood of fraud based on the fraudster's relevant literature. For example, the judgment unit may refer to the fraudster's relevant literature and determine that the likelihood of fraud is high. For example, the judgment unit may refer to the fraudster's relevant literature and determine that the likelihood of fraud is moderate. For example, the judgment unit may refer to the fraudster's relevant literature and determine that the likelihood of fraud is low. In this way, by referring to relevant literature, the likelihood of fraud can be determined more accurately. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit may input data on the fraudster's relevant literature into a generating AI and have the generating AI perform a judgment based on the relevant literature.

[0094] The reporting unit can estimate the emotions of the fraudster and adjust the content of the report based on the estimated emotions. For example, if the reporting unit estimates the emotions of the fraudster and the feelings of anger or tension are strong, it will describe the content of the report in detail. For example, if the reporting unit estimates the emotions of the fraudster and the feelings of fear or anxiety are strong, it will describe the content of the report concisely. For example, if the reporting unit estimates the emotions of the fraudster and the feelings of calmness are strong, it will describe the content of the report comprehensively. This improves the accuracy of the report by adjusting the content of the report based on the emotions of the fraudster. Some or all of the above processing in the reporting unit may be performed using AI, for example, or not using AI. For example, the reporting unit can input the fraudster's emotion data into a generating AI and have the generating AI perform the adjustment of the report content based on emotions.

[0095] The reporting unit can optimize the content of a report by referring to the fraudster's past fraudulent activity history when a report is made. For example, the reporting unit may refer to the fraudster's past fraudulent activity history and describe the report in detail. For example, the reporting unit may refer to the fraudster's past fraudulent activity history and describe the report concisely. For example, the reporting unit may refer to the fraudster's past fraudulent activity history and describe the report comprehensively. By referring to the past fraudulent activity history, the reporting unit optimizes the content of the report and improves the accuracy of the report. Some or all of the above processing in the reporting unit may be performed using AI, for example, or without AI. For example, the reporting unit may input data on the fraudster's past fraudulent activity history into a generating AI and have the generating AI perform the optimization of the report content based on the fraudulent activity history.

[0096] The reporting unit can adjust the urgency of a report based on the current actions of the fraudster when a report is made. For example, the reporting unit may set the urgency to high, considering the fraudster's current actions. For example, the reporting unit may set the urgency to medium, considering the fraudster's current actions. For example, the reporting unit may set the urgency to low, considering the fraudster's current actions. This allows for reporting at an appropriate level of urgency by adjusting the urgency based on the current actions. Some or all of the above processing in the reporting unit may be performed using AI, for example, or without AI. For example, the reporting unit may input data on the fraudster's current actions into a generating AI and have the generating AI perform the adjustment of the urgency based on the actions.

[0097] The reporting unit can estimate the emotions of the fraudster and determine the priority of reporting based on the estimated emotions. For example, if the reporting unit estimates the emotions of the fraudster and the emotions of anger or tension are strong, it will set the reporting priority high. For example, if the reporting unit estimates the emotions of the fraudster and the emotions of fear or anxiety are strong, it will set the reporting priority to a medium level. For example, if the reporting unit estimates the emotions of the fraudster and the emotions of calm are strong, it will set the reporting priority to a low level. This allows important reports to be given priority by determining priorities based on the emotions of the fraudster. Some or all of the above processing in the reporting unit may be performed using AI, for example, or not using AI. For example, the reporting unit can input fraudster emotion data into a generating AI and have the generating AI perform the determination of reporting priorities based on emotions.

[0098] The reporting unit can optimize the content of a report based on the geographical location information of the fraudster. For example, the reporting unit may describe the content of the report in detail, taking into account the geographical location information of the fraudster. For example, the reporting unit may describe the content of the report concisely, taking into account the geographical location information of the fraudster. For example, the reporting unit may describe the content of the report comprehensively, taking into account the geographical location information of the fraudster. This makes it possible to report frauds that reflect the trends of fraudulent activities specific to a region by taking geographical location information into consideration. Some or all of the above processing in the reporting unit may be performed using AI, for example, or without using AI. For example, the reporting unit may input data on the geographical location information of the fraudster into a generating AI and have the generating AI perform the optimization of the report content based on geographical location information.

[0099] The reporting department can analyze the fraudster's social media activity to supplement the reported information at the time of reporting. For example, the reporting department can analyze the fraudster's social media activity and describe the reported information in detail. For example, the reporting department can analyze the fraudster's social media activity and describe the reported information concisely. For example, the reporting department can analyze the fraudster's social media activity and describe the reported information comprehensively. In this way, analyzing social media activity supplements the reported information and improves the accuracy of the report. Some or all of the above processing in the reporting department may be performed using AI, for example, or not using AI. For example, the reporting department can input data on the fraudster's social media activity into a generating AI and have the generating AI perform the task of supplementing the reported information based on the social media activity.

[0100] The learning unit can estimate the emotions of a con artist and select training data based on the estimated emotions. For example, if the learning unit estimates the emotions of a con artist and finds that the emotions of anger or tension are strong, it will select training data related to those emotions. For example, if the learning unit estimates the emotions of a con artist and finds that the emotions of fear or anxiety are strong, it will select training data related to those emotions. For example, if the learning unit estimates the emotions of a con artist and finds that the emotions of calmness are strong, it will select training data related to that emotion. This improves the accuracy of learning by selecting training data based on the emotions of the con artist. Some or all of the above processing in the learning unit is performed using a generative AI. For example, the learning unit can input the emotions of a con artist into a generative AI and have the generative AI perform the selection of training data based on those emotions.

[0101] The learning unit can optimize its learning algorithm by referring to past fraud data during training. For example, the learning unit can optimize the learning algorithm by referring to past fraud data. The learning unit can improve the learning algorithm by referring to past fraud data. The learning unit can adjust the learning algorithm by referring to past fraud data. As a result, by referring to past fraud data, the learning algorithm is optimized and the accuracy of learning is improved. Some or all of the above processes in the learning unit are performed using a generative AI. For example, the learning unit can input past fraud data into the generative AI and have the generative AI perform the optimization of the learning algorithm.

[0102] The learning unit can perform learning while considering the attribute information of fraudsters (e.g., age, gender). For example, the learning unit can consider the attribute information of fraudsters and learn the tendencies of fraudulent activities in a specific age group. For example, the learning unit can consider the attribute information of fraudsters and learn the tendencies of fraudulent activities in a specific gender. For example, the learning unit can consider the attribute information of fraudsters and learn the tendencies of fraudulent activities in a specific age group and gender. This improves the accuracy of learning by considering the attribute information of fraudsters. Some or all of the above processing in the learning unit is performed using a generative AI. For example, the learning unit can input fraudster attribute information data into the generative AI and have the generative AI perform learning based on the attribute information.

[0103] The learning unit can estimate the emotions of the con artist and adjust the learning frequency based on the estimated emotions. For example, if the learning unit estimates the emotions of the con artist and the emotions of anger or tension are strong, it will set the learning frequency high. For example, if the learning unit estimates the emotions of the con artist and the emotions of fear or anxiety are strong, it will set the learning frequency to a medium level. For example, if the learning unit estimates the emotions of the con artist and the emotions of calm are strong, it will set the learning frequency to a low level. This improves the efficiency of learning by adjusting the learning frequency based on the emotions of the con artist. Some or all of the above processing in the learning unit is performed using a generative AI. For example, the learning unit can input the emotions of the con artist into the generative AI and have the generative AI perform the adjustment of the learning frequency based on the emotions.

[0104] The learning unit can weight the training data based on the timing of fraudulent activity during training. For example, the learning unit considers the timing of fraudulent activity when weighting the training data. For example, the learning unit considers the timing of fraudulent activity when weighting the training data. For example, the learning unit considers the timing of fraudulent activity when weighting the training data when weighting the training data when weighting the training data is optimized. This improves the accuracy of training through weighting based on the timing of fraudulent activity. Some or all of the above processing in the learning unit is performed using a generative AI. For example, the learning unit can input data on the timing of fraudulent activity into the generative AI and have the generative AI perform weighting based on the timing of occurrence.

[0105] The learning unit can improve its learning accuracy by referring to relevant literature on con artists during the learning process. For example, the learning unit can refer to relevant literature on con artists to improve learning accuracy. For example, the learning unit can refer to relevant literature on con artists to improve learning accuracy. For example, the learning unit can refer to relevant literature on con artists to adjust learning accuracy. In this way, the accuracy of learning is improved by referring to relevant literature. Some or all of the above processing in the learning unit is performed using a generative AI. For example, the learning unit can input data on relevant literature on con artists into the generative AI and have the generative AI perform learning based on the relevant literature.

[0106] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0107] The analysis unit can monitor the fraudster's behavior patterns in real time and detect abnormal behavior. For example, the analysis unit will issue an alert if the fraudster deviates from their normal behavior patterns. If the fraudster is frequently active during a particular time period, the analysis unit will focus its monitoring on that time period. If the fraudster is frequently active in a particular location, the analysis unit will focus its monitoring on activities in that location. By monitoring the fraudster's behavior patterns in real time, signs of fraud can be detected early.

[0108] The judgment unit can estimate the emotions of the con artist and evaluate the likelihood of fraud based on those estimated emotions. For example, if the judgment unit observes anger or tension, it will determine that fraud is likely. If the con artist observes fear or anxiety, it will determine that fraud is moderately likely. If the con artist observes calmness, it will determine that fraud is unlikely. This allows for a more accurate assessment of fraud likelihood based on the con artist's emotions.

[0109] When signs of fraud are detected, the reporting department can optimize the report by referring to the fraudster's past activity history. For example, the reporting department can refer to the fraudster's past activity history and add detailed information to the report. The reporting department can refer to the fraudster's past activity history and summarize the report concisely. The reporting department can refer to the fraudster's past activity history and describe the report comprehensively. In this way, by referring to past activity history, the report can be optimized and the accuracy of the report can be improved.

[0110] The learning unit can estimate the emotions of the con artist and select training data based on the estimated emotions. For example, if the learning unit indicates anger or tension, it will select training data related to those emotions. If the con artist indicates fear or anxiety, it will select training data related to those emotions. If the con artist indicates calmness, it will select training data related to that emotion. This allows for improved learning accuracy by selecting training data based on the con artist's emotions.

[0111] The analysis unit can detect signs of fraud by taking into account the geographical location of the fraudster. For example, if the analysis unit frequently operates in a particular area, it will focus its monitoring on that area. If the analysis unit frequently operates during a particular time period, it will focus its monitoring on that time period. If the analysis unit observes unusual behavior at a particular location, it will focus its analysis on the activity at that location. By taking geographical location information into account, it is possible to detect signs of fraud more accurately.

[0112] The assessment unit can estimate the emotions of the con artist and score the likelihood of fraud based on those estimated emotions. For example, the assessment unit assigns a high score if the con artist is showing emotions such as anger or tension. The assessment unit assigns a medium score if the con artist is showing emotions such as fear or anxiety. The assessment unit assigns a low score if the con artist is showing emotions such as calmness. This allows for a more accurate assessment of the likelihood of fraud by scoring based on the con artist's emotions.

[0113] When signs of fraud are detected, the reporting department can analyze the fraudster's social media activity to supplement the reported information. For example, the reporting department can analyze the fraudster's social media activity and add detailed information to the reported information. The reporting department can analyze the fraudster's social media activity and summarize the reported information concisely. The reporting department can analyze the fraudster's social media activity and provide a comprehensive description of the reported information. In this way, analyzing social media activity can supplement the reported information and improve the accuracy of the report.

[0114] The learning unit can estimate the con artist's emotions and adjust the learning frequency based on those estimates. For example, if the con artist is showing anger or tension, the learning unit will set the learning frequency high. If the con artist is showing fear or anxiety, the learning unit will set the learning frequency to a medium level. If the con artist is showing calmness, the learning unit will set the learning frequency to a low level. This allows for improved learning efficiency by adjusting the learning frequency based on the con artist's emotions.

[0115] The analysis unit can optimize its methods for analyzing facial muscles and voice tone by referring to the con artist's past behavioral patterns. For example, the analysis unit can refer to the con artist's past behavioral patterns and focus on analyzing specific facial muscle movements. The analysis unit can refer to the con artist's past behavioral patterns and focus on analyzing specific changes in voice tone. The analysis unit can refer to the con artist's past behavioral patterns and comprehensively analyze both facial muscles and voice tone. This allows the analysis method to be optimized by referring to past behavioral patterns, enabling more accurate detection of signs of fraud.

[0116] The judgment unit can estimate the emotions of the con artist and adjust the criteria for judging the likelihood of fraud based on the estimated emotions. For example, if the judgment unit shows emotions such as anger or tension, it will judge the likelihood of fraud as high. If the judgment unit shows emotions such as fear or anxiety, it will judge the likelihood of fraud as moderate. If the judgment unit shows emotions such as calmness, it will judge the likelihood of fraud as low. In this way, by adjusting the judgment criteria based on the emotions of the con artist, the likelihood of fraud can be judged more accurately.

[0117] The following briefly describes the processing flow for example form 2.

[0118] Step 1: The analysis unit analyzes facial muscles and voice tone. For example, the analysis unit detects the movement of facial muscles and analyzes changes in voice tone. The analysis unit can use a camera to detect the movement of muscles in specific parts of the face and a microphone to analyze the pitch, intensity, and rhythm of voice tone. Step 2: The judgment unit determines the likelihood of fraud based on the data analyzed by the analysis unit. The judgment unit evaluates the likelihood of fraud based on the analyzed facial muscle movements and changes in voice tone, and if it detects angry or tense voice tones, it determines that there is a high possibility of fraud. The judgment unit can score the likelihood of fraud based on the analyzed data. Step 3: The reporting unit automatically makes a report if the assessment unit determines that there is a high probability of fraud. The reporting unit can use telephone or email to report to the police and other relevant agencies. The reporting unit can automatically generate the content of the report and submit it quickly. The reporting unit notifies the receiving agency that there is a high probability of fraud. Step 4: The learning unit learns voice and facial expression data. The learning unit can learn voice and facial expression data using generative AI. The learning unit learns voice and facial expression data to detect signs of fraud in real time. The learning unit learns voice and facial expression data to alert about the risk of fraud.

[0119] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0120] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0121] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0122] Each of the multiple elements described above, including the analysis unit, judgment unit, notification unit, and learning unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit analyzes facial muscle movements and voice tone using the camera 42 and microphone 38B of the smart device 14. The judgment unit determines the possibility of fraud based on the data analyzed by the identification processing unit 290 of the data processing unit 12. The notification unit notifies the police or relevant agencies using the communication I / F 44 of the smart device 14. The learning unit learns voice and facial expression data using the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0123] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0124] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0125] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0126] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0127] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0128] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0129] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0130] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0131] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0132] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0133] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0134] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0135] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0136] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0137] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0138] Each of the multiple elements described above, including the analysis unit, judgment unit, notification unit, and learning unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit analyzes facial muscle movements and voice tone using the camera 42 and microphone 238 of the smart glasses 214. The judgment unit determines the possibility of fraud based on the data analyzed by the identification processing unit 290 of the data processing unit 12. The notification unit notifies the police or relevant agencies using the communication I / F 44 of the smart glasses 214. The learning unit learns voice and facial expression data using the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0139] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0140] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0141] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0142] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0143] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0145] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0146] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0147] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0148] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0149] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0150] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0151] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0152] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0153] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0154] Each of the multiple elements described above, including the analysis unit, judgment unit, notification unit, and learning unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit analyzes facial muscle movements and voice tone using the camera 42 and microphone 238 of the headset terminal 314. The judgment unit determines the possibility of fraud based on the data analyzed by the identification processing unit 290 of the data processing unit 12. The notification unit notifies the police or relevant agencies using the communication I / F 44 of the headset terminal 314. The learning unit learns voice and facial expression data using the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0155] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0156] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0157] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0158] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0159] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0160] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0161] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0162] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0163] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0164] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0165] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0166] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0167] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0168] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0169] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0170] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0171] Each of the multiple elements described above, including the analysis unit, judgment unit, notification unit, and learning unit, is implemented in, for example, at least one of the robot 414 and the data processing unit 12. For example, the analysis unit analyzes facial muscle movements and voice tone using the camera 42 and microphone 238 of the robot 414. The judgment unit determines the possibility of fraud based on the data analyzed by the identification processing unit 290 of the data processing unit 12. The notification unit notifies the police or relevant agencies using the communication I / F 44 of the robot 414. The learning unit learns voice and facial expression data using the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0172] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0173] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0174] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0175] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0176] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0177] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0178] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0179] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0180] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0181] 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.

[0182] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0183] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0184] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0185] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0186] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0187] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0188] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0189] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0190] (Note 1) An analysis unit that analyzes facial muscles and voice tone, A determination unit that determines the possibility of fraud based on the data analyzed by the aforementioned analysis unit, The aforementioned determination unit determines that there is a high probability of fraud and automatically makes a notification unit, It comprises a learning unit that learns voice and facial expression data. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Using an intercom to analyze facial muscles and voice tone. The system described in Appendix 1, characterized by the features described herein. (Note 3) The determination unit, It detects angry and tense voice tones to determine the possibility of fraud. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned reporting unit, If signs of fraud are detected, report them to the police and relevant authorities. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned learning unit, It learns from voice and facial expression data to detect signs of fraud in real time. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reporting unit, If a person on the wanted list is detected, the police will be notified. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, It estimates the emotions of con artists and improves the accuracy of facial muscle and voice tone analysis based on the estimated emotions of the con artists. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, Analyze facial muscles and voice tone using devices other than the intercom. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, We optimize the analysis method of facial muscles and voice tone based on the con artist's past behavioral patterns. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, The system estimates the emotions of the con artist and prioritizes the analysis results based on the estimated emotions of the con artist. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, When analyzing facial muscles and voice tone, improve analysis accuracy based on the con artist's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, During the analysis of facial muscles and voice tone, the social media activity of the fraudster is analyzed to obtain relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 13) The determination unit, We estimate the emotions of the con artist and adjust the criteria for determining the likelihood of fraud based on the estimated emotions of the con artist. The system described in Appendix 1, characterized by the features described herein. (Note 14) The determination unit, When assessing the likelihood of fraud, we improve the accuracy of our judgment based on the fraudster's past fraudulent activity history. The system described in Appendix 1, characterized by the features described herein. (Note 15) The determination unit, When determining the likelihood of fraud, the fraudster's attribute information should be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 16) The determination unit, We estimate the emotions of the con artist and, based on those estimated emotions, determine the priority of the likelihood of fraud. The system described in Appendix 1, characterized by the features described herein. (Note 17) The determination unit, When assessing the likelihood of fraud, we improve the accuracy of our assessment based on the geographical location information of the fraudster. The system described in Appendix 1, characterized by the features described herein. (Note 18) The determination unit, When assessing the possibility of fraud, improve the accuracy of the assessment based on relevant literature on fraudsters. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned reporting unit, We estimate the emotions of the scammer and adjust the content of the report based on the estimated emotions of the scammer. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned reporting unit, When reporting a scam, the report content is optimized by referring to the scammer's past fraud history. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned reporting unit, When reporting, the urgency of the report will be adjusted based on the fraudster's current activities. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned reporting unit, The system estimates the emotions of the scammers and prioritizes reporting based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned reporting unit, When reporting a fraud, the report content is optimized based on the fraudster's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned reporting unit, When a report is filed, the report's details are supplemented by analyzing the fraudster's social media activity. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned learning unit, The system estimates the emotions of the con artists and selects training data based on these estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past fraud data. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned learning unit, During the learning process, the system takes into account the attributes of the fraudsters. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned learning unit, It estimates the emotions of the con artist and adjusts the learning frequency based on the estimated emotions of the con artist. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned learning unit, During training, the training data is weighted based on when the fraudulent activity occurred. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned learning unit, During training, we improve learning accuracy by referring to relevant literature on con artists. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0191] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An analysis unit that analyzes facial muscles and voice tone, A determination unit that determines the possibility of fraud based on the data analyzed by the aforementioned analysis unit, The aforementioned determination unit determines that there is a high probability of fraud and automatically makes a notification unit, It comprises a learning unit that learns voice and facial expression data. A system characterized by the following features.

2. The aforementioned analysis unit, Using an intercom to analyze facial muscles and voice tone. The system according to feature 1.

3. The determination unit, It detects angry and tense voice tones to determine the possibility of fraud. The system according to feature 1.

4. The aforementioned reporting unit, If signs of fraud are detected, report them to the police and relevant authorities. The system according to feature 1.

5. The aforementioned learning unit, It learns from voice and facial expression data to detect signs of fraud in real time. The system according to feature 1.

6. The aforementioned reporting unit, If a person on the wanted list is detected, the police will be notified. The system according to feature 1.

7. The aforementioned analysis unit, It estimates the emotions of con artists and improves the accuracy of facial muscle and voice tone analysis based on the estimated emotions of the con artists. The system according to feature 1.

8. The aforementioned analysis unit, Analyze facial muscles and voice tone using devices other than the intercom. The system according to feature 1.

9. The aforementioned analysis unit, We optimize the analysis method of facial muscles and voice tone based on the con artist's past behavioral patterns. The system according to feature 1.

Images