system

Abstract

The system according to this embodiment aims to detect the risk of special fraud early and respond appropriately. [Solution] The system according to the embodiment comprises an analysis unit, a determination unit, and a linkage unit. The analysis unit analyzes the conversation content in real time. The determination unit determines the risk of fraud based on the conversation content analyzed by the analysis unit. The linkage unit shares information with police agencies, etc., if the determination unit determines that there is a risk of fraud.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's 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 and appropriately respond to the sophistication and malignancy of special fraud at an early stage.

[0005] The system according to the embodiment aims to detect the risk of special fraud at an early stage and appropriately respond to it.

Means for Solving the Problems

[0006] The system according to the embodiment includes an analysis unit, a determination unit, and a cooperation unit. The analysis unit analyzes the conversation content in real time. The determination unit determines the fraud risk based on the conversation content analyzed by the analysis unit. The cooperation unit cooperates with a police agency or the like to provide information when the determination unit determines that there is a fraud risk. [Effects of the Invention]

[0007] The system according to this embodiment can detect the risk of special fraud early and respond appropriately. [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 special fraud prevention system according to an embodiment of the present invention is a system that uses a generating AI to detect special frauds early and provides real-time information sharing to police agencies, etc. The special fraud prevention system analyzes the content of conversations in real time, and the generating AI determines the fraud risk. If a fraud risk is determined, the system shares information with police agencies, etc. in real time. This mechanism makes it possible to prevent damage from special frauds. For example, the special fraud prevention system uses a generating AI to analyze the content of a phone conversation between elderly people and detect signs of fraud. The generating AI determines the fraud risk using typical fraud patterns and sentiment analysis. For example, it can detect phrases such as "Please transfer the money" and emotions indicating anxiety or tension. Next, if the generating AI determines that there is a fraud risk, it shares information with police agencies, etc. in real time. For example, if a high fraud risk is determined, the generating AI automatically notifies the police and provides detailed information about the fraud. This information includes the content of the conversation, the fraud methods, and the victim's location information. Furthermore, the generating AI can also issue a warning to the victim. For example, if there is a high probability that the caller is a scammer, the generating AI will warn the victim that "this call may be a scam." This allows the victim to recognize the scam and prevent becoming a victim. This mechanism can prevent special fraud from occurring. It is particularly effective against the elderly and those who are vulnerable to information, and is extremely useful in today's world where fraudulent methods are becoming more sophisticated. Furthermore, by using generating AI, it is possible to quickly detect signs of fraud and respond in real time. This enables law enforcement agencies to respond quickly and prevent the escalation of fraud damage. In short, the special fraud prevention system can quickly detect signs of fraud and respond in real time.

[0029] The special fraud prevention system according to the embodiment comprises an analysis unit, a determination unit, and a coordination unit. The analysis unit analyzes the content of a conversation in real time. For example, the analysis unit converts the content of a telephone conversation into text data using speech recognition technology and analyzes the text data. The analysis unit uses a generation AI to perform typical fraud patterns and sentiment analysis. For example, the analysis unit detects phrases such as "Please transfer the money" and emotions indicating anxiety or tension. The determination unit determines the fraud risk based on the conversation content analyzed by the analysis unit. For example, the determination unit uses a generation AI to score the fraud risk and determines the fraud risk based on that score. If the determination unit determines that the fraud risk is high, it transmits the information to the coordination unit. If the determination unit determines that there is a fraud risk, the coordination unit coordinates the information with the police, etc. For example, if the coordination unit determines that the fraud risk is high, it automatically notifies the police and provides detailed information about the fraud. The coordination unit provides the police with the content of the conversation, the fraud methods, the victim's location information, etc. As a result, the special fraud prevention system according to the embodiment can quickly detect signs of fraud and respond in real time. Some or all of the above-described processes in the analysis unit, judgment unit, and coordination unit may be performed using a generation AI, or they may not be performed using a generation AI. For example, the analysis unit can input conversation content into the generation AI and have the generation AI perform typical fraud patterns and sentiment analysis. The judgment unit can make a judgment based on the fraud risk scored by the generation AI. The coordination unit can report to the police based on the information provided by the generation AI.

[0030] The analysis unit analyzes conversation content in real time. For example, the analysis unit converts telephone conversations into text data using speech recognition technology and then analyzes that text data. Specifically, the speech recognition technology uses a highly accurate speech model to quickly and accurately convert the audio of the conversation into text. This text data is input into a generative AI, which performs typical fraud patterns and sentiment analysis. The generative AI has learned from a large amount of fraud case data and can detect specific phrases and expressions related to fraud with high accuracy. For example, if phrases such as "Please transfer the money" or "Please respond immediately" are detected, the generative AI will determine that this is highly likely to be a scam. The generative AI also performs sentiment analysis, detecting emotions such as anxiety and tension from the tone and wording of the conversation. This allows the analysis unit to analyze conversation content showing signs of fraud in real time and provide basic data for a rapid response. Furthermore, the analysis unit can also detect new patterns and trends in fraud using statistical models based on past conversation data and fraud cases. This allows the analysis unit to constantly respond to the latest fraud methods and improve the accuracy and reliability of the system.

[0031] The judgment unit determines the fraud risk based on the conversation content analyzed by the analysis unit. The judgment unit scores the fraud risk, for example, using a generative AI, and determines the fraud risk based on that score. Specifically, the generative AI receives text data provided by the analysis unit as input and executes a scoring algorithm that quantifies the fraud risk. This algorithm considers typical fraud patterns and the results of sentiment analysis to evaluate the fraud risk with high accuracy. For example, if a specific phrase or emotion is detected, its risk score will be set high. Based on this score, the judgment unit determines whether the fraud risk is high or low. If the fraud risk is determined to be high, the judgment unit sends the information to the coordination unit. Furthermore, the judgment unit can continuously improve the scoring algorithm based on past judgment results and feedback. This allows the judgment unit to always use the latest information and technology to determine fraud risk with high accuracy, improving the reliability and effectiveness of the entire system.

[0032] The Liaison Department shares information with law enforcement agencies when the Judgment Department determines there is a risk of fraud. Specifically, if a high risk of fraud is determined, it automatically notifies law enforcement agencies and provides detailed information about the fraud. For example, the Liaison Department provides law enforcement agencies with information such as the content of the conversation, the fraudulent methods used, and the victim's location. This allows law enforcement agencies to respond quickly and prevent further damage. Based on the information provided by the AI ​​generation system, the Liaison Department automatically generates the content of the report and transmits the necessary information accurately and quickly. The Liaison Department also conducts follow-up after the report is made, strengthening cooperation with law enforcement agencies. For example, it can receive feedback from law enforcement agencies and use it to improve the system. Furthermore, the Liaison Department provides appropriate support to victims. For example, it can provide victims with information on the status of the report to law enforcement agencies and future actions, giving them a sense of security. As a result, the Liaison Department can respond quickly and appropriately when there is a high risk of fraud, minimizing damage.

[0033] The emotion analysis unit performs emotion analysis. The emotion analysis unit estimates emotions from conversation content, for example, by using voice tone analysis or text analysis. The emotion analysis unit estimates the user's emotions using generative AI and determines the fraud risk based on those emotions. For example, the emotion analysis unit can determine a high fraud risk if the user is feeling anxious or tense. Also, if the user is relaxed, the emotion analysis unit can analyze the conversation content with normal analytical accuracy. As a result, performing emotion analysis improves the accuracy of fraud risk determination. Some or all of the above processing in the emotion analysis unit may be performed using generative AI, or it may be performed without using generative AI. For example, the emotion analysis unit can input the conversation content into the generative AI and have the generative AI perform the emotion analysis.

[0034] The warning unit issues a warning to the victim. The warning unit issues a warning to the victim using, for example, voice warnings, text messages, or visual alerts. The warning unit uses generative AI to warn the victim if there is a high probability that the call is fraudulent. For example, if the warning unit is likely to be a fraudster, it can warn, "This call may be fraudulent." This allows the victim to recognize the fraud and prevent becoming a victim. Some or all of the above processing in the warning unit may be performed using generative AI or not. For example, the warning unit may issue a warning based on the fraud risk determined by generative AI.

[0035] The analysis unit detects typical fraud patterns. The analysis unit detects typical fraud patterns using, for example, patterns based on past fraud cases or machine learning models. The analysis unit can also detect typical fraud patterns using generative AI. For example, the analysis unit can input past fraud case data into the generative AI and train it to recognize typical fraud patterns. This improves the accuracy of fraud risk assessment by detecting typical fraud patterns. Some or all of the above processing in the analysis unit may be performed using generative AI or not. For example, the analysis unit can perform analysis based on typical fraud patterns detected by the generative AI.

[0036] The liaison department provides police agencies with detailed information about the fraud. For example, the liaison department provides police agencies with the full text of the conversation and related metadata. The liaison department can also provide police agencies with detailed information about the fraud using generative AI. For example, the liaison department can provide police agencies with the conversation content and fraud methods analyzed by generative AI. This enables a swift response by providing police agencies with detailed information about the fraud. Some or all of the above processing in the liaison department may be performed using generative AI or not. For example, the liaison department can report to police agencies based on information provided by generative AI.

[0037] The warning unit issues a warning to the victim if there is a high probability of fraud. For example, the warning unit may issue a warning to the victim using voice warnings, text messages, or visual alerts if there is a high probability of fraud. The warning unit can also use generative AI to issue a warning to the victim if there is a high probability of fraud. For example, the warning unit may issue a warning such as "This call may be a scam" based on the fraud risk determined by the generative AI. This prevents fraud by warning the victim when there is a high probability of fraud. Some or all of the above processing in the warning unit may be performed using generative AI or not. For example, the warning unit may issue a warning based on the fraud risk determined by the generative AI.

[0038] The analysis unit more accurately detects signs of fraud by considering the context of the conversation. For example, the analysis unit analyzes the context before and after the conversation to detect typical patterns of fraud. The analysis unit can use generative AI to more accurately detect signs of fraud by considering the context of the conversation. For example, the analysis unit can input the context before and after the conversation into the generative AI and detect signs of fraud. This allows for more accurate detection of signs of fraud by considering the context of the conversation. Some or all of the above processing in the analysis unit may be performed using generative AI or not. For example, the analysis unit can perform analysis based on contextual information detected by the generative AI.

[0039] The analysis unit analyzes background and ambient sounds in a conversation and obtains information that reinforces the possibility of fraud. For example, the analysis unit can identify a specific location or situation from the background sounds and evaluate the possibility of fraud. The analysis unit can use a generative AI to analyze background and ambient sounds in a conversation and obtain information that reinforces the possibility of fraud. For example, the analysis unit can input background and ambient sounds into the generative AI and obtain information that reinforces the possibility of fraud. In this way, by analyzing the background and ambient sounds in a conversation, information that reinforces the possibility of fraud can be obtained. Some or all of the above processing in the analysis unit may be performed using a generative AI or not. For example, the analysis unit can perform analysis based on background and ambient sounds analyzed by a generative AI.

[0040] The analysis unit adjusts the analysis algorithm considering the language and dialect of the conversation. For example, the analysis unit identifies the language of the conversation and uses an analysis algorithm appropriate for that language. The analysis unit can use generative AI to adjust the analysis algorithm considering the language and dialect of the conversation. For example, the analysis unit can input the language and dialect of the conversation into the generative AI and adjust the analysis algorithm. This improves the accuracy of the analysis algorithm by considering the language and dialect of the conversation. Some or all of the above-described processes in the analysis unit may be performed using generative AI or not. For example, the analysis unit can perform analysis based on an analysis algorithm adjusted by generative AI.

[0041] The analysis unit analyzes the speed and tone of the conversation and obtains information to reinforce signs of fraud. For example, the analysis unit analyzes the speed of the conversation and issues a warning if there is a high probability of fraud. The analysis unit can use a generative AI to analyze the speed and tone of the conversation and obtain information to reinforce signs of fraud. For example, the analysis unit can input the speed and tone of the conversation into the generative AI and obtain information to reinforce signs of fraud. In this way, by analyzing the speed and tone of the conversation, information to reinforce signs of fraud can be obtained. Some or all of the above processing in the analysis unit may be performed using the generative AI or not. For example, the analysis unit can perform analysis based on the speed and tone analyzed by the generative AI.

[0042] The judgment unit improves the accuracy of its judgment by referring to a database of past fraud cases. The judgment unit, for example, refers to a database of past fraud cases to determine the fraud risk. The judgment unit can improve the accuracy of its judgment by referring to a database of past fraud cases using a generation AI. For example, the judgment unit can input past fraud case data into a generation AI to determine the fraud risk. This improves the accuracy of fraud risk determination by referring to a database of past fraud cases. Some or all of the above processing in the judgment unit may be performed using a generation AI or not. For example, the judgment unit can make a judgment based on past fraud case data referenced by a generation AI.

[0043] The judgment unit determines the fraud risk by considering not only the content of the conversation but also the frequency and time of the conversation. For example, the judgment unit analyzes the frequency of the conversation and determines the fraud risk. The judgment unit can use a generative AI to determine the fraud risk by considering not only the content of the conversation but also the frequency and time of the conversation. For example, the judgment unit can input the frequency and time of the conversation into the generative AI and determine the fraud risk. This improves the accuracy of fraud risk determination by considering the frequency and time of the conversation. Some or all of the above processing in the judgment unit may be performed using a generative AI or without a generative AI. For example, the judgment unit can make a determination based on the frequency and time of the conversation analyzed by the generative AI.

[0044] The judgment unit makes a judgment by considering the attribute information of the person being spoken to. For example, the judgment unit analyzes the age and gender of the person being spoken to and determines the fraud risk. The judgment unit can use a generative AI to make a judgment by considering the attribute information of the person being spoken to. For example, the judgment unit can input the attribute information of the person being spoken to into the generative AI and determine the fraud risk. This improves the accuracy of fraud risk determination by considering the attribute information of the person being spoken to. Some or all of the above processing in the judgment unit may be performed using a generative AI or not. For example, the judgment unit can make a judgment based on attribute information analyzed by a generative AI.

[0045] The judgment unit makes a judgment considering the background sounds and ambient sounds of the conversation. For example, the judgment unit analyzes the background sounds of the conversation and determines the fraud risk. The judgment unit can use a generation AI to make a judgment considering the background sounds and ambient sounds of the conversation. For example, the judgment unit can input the background sounds and ambient sounds of the conversation into the generation AI and determine the fraud risk. This improves the accuracy of fraud risk determination by considering the background sounds and ambient sounds of the conversation. Some or all of the above processing in the judgment unit may be performed using a generation AI or not. For example, the judgment unit can make a judgment based on the background sounds and ambient sounds analyzed by the generation AI.

[0046] The liaison unit will share not only detailed information about the fraud, but also the victim's location and contact information. For example, the liaison unit will share the victim's location information along with the detailed information about the fraud. The liaison unit can use generative AI to share not only detailed information about the fraud, but also the victim's location and contact information. For example, the liaison unit can provide the police with the victim's location and contact information along with the detailed information about the fraud analyzed by the generative AI. This enables a swift response by sharing the victim's location and contact information along with the detailed information about the fraud. Some or all of the above processing in the liaison unit may be performed using generative AI, or it may be performed without using generative AI. For example, the liaison unit can report to the police based on the information provided by the generative AI.

[0047] The integration unit selects the optimal integration method by referring to past integration history. The integration unit can, for example, refer to past integration history and select the optimal integration method. The integration unit can use a generating AI to refer to past integration history and select the optimal integration method. For example, the integration unit can input past integration history into the generating AI and select the optimal integration method. In this way, the optimal integration method can be selected by referring to past integration history. Some or all of the above processing in the integration unit may be performed using a generating AI, or it may be performed without using a generating AI. For example, the integration unit can select an integration method based on past integration history analyzed by a generating AI.

[0048] The liaison unit will share not only detailed information about the fraud, but also information about the victim's attributes. For example, the liaison unit will share the victim's age and gender along with the detailed information about the fraud. The liaison unit can use generative AI to share not only detailed information about the fraud, but also information about the victim's attributes. For example, the liaison unit can provide police agencies with detailed information about the fraud analyzed by generative AI, along with information about the victim's attributes. This enables a swift response by sharing information about the victim's attributes along with detailed information about the fraud. Some or all of the above processing in the liaison unit may be performed using generative AI, or it may be performed without using generative AI. For example, the liaison unit can report to police agencies based on information provided by generative AI.

[0049] The collaboration unit collaborates with the police by sharing detailed information about the fraud, including background sounds and ambient sounds from the conversation. For example, the collaboration unit can share background sounds from the conversation along with detailed information about the fraud. The collaboration unit can use generative AI to collaborate with the police by sharing background sounds and ambient sounds from the conversation, in addition to detailed information about the fraud. For example, the collaboration unit can provide police agencies with background sounds and ambient sounds from the conversation along with detailed information about the fraud analyzed by the generative AI. This enables a rapid response by collaborating background sounds and ambient sounds from the conversation along with detailed information about the fraud. Some or all of the above processing in the collaboration unit may be performed using generative AI or not. For example, the collaboration unit can report to police agencies based on information provided by the generative AI.

[0050] The sentiment analysis unit improves the accuracy of its analysis by referring to the user's past emotional history. For example, the sentiment analysis unit accurately analyzes the current emotion by referring to past conversation data and emotional change patterns. The sentiment analysis unit can improve the accuracy of its analysis by referring to the user's past emotional history using generative AI. For example, the sentiment analysis unit can input past emotional history into the generative AI and accurately analyze the current emotion. This improves the accuracy of sentiment analysis by referring to the user's past emotional history. Some or all of the above processing in the sentiment analysis unit may be performed using generative AI or not. For example, the sentiment analysis unit can perform analysis based on past emotional history analyzed by generative AI.

[0051] The emotion analysis unit detects emotional changes more accurately by considering the context of the conversation. For example, the emotion analysis unit analyzes the context before and after the conversation to detect emotional changes. The emotion analysis unit can use generative AI to detect emotional changes more accurately by considering the context of the conversation. For example, the emotion analysis unit can input the context before and after the conversation into the generative AI and detect emotional changes. This allows for more accurate detection of emotional changes by considering the context of the conversation. Some or all of the above processing in the emotion analysis unit may be performed using generative AI or not. For example, the emotion analysis unit can detect emotional changes based on contextual information analyzed by the generative AI.

[0052] The emotion analysis unit detects changes in emotion by considering the speed and tone of the conversation. For example, the emotion analysis unit analyzes the speed of the conversation and detects changes in emotion. The emotion analysis unit can use generative AI to detect changes in emotion by considering the speed and tone of the conversation. For example, the emotion analysis unit can input the speed and tone of the conversation into the generative AI and detect changes in emotion. This allows for more accurate detection of changes in emotion by considering the speed and tone of the conversation. Some or all of the above processing in the emotion analysis unit may be performed using generative AI or not. For example, the emotion analysis unit can detect changes in emotion based on the speed and tone analyzed by the generative AI.

[0053] The warning unit selects the optimal warning method by referring to past warning history. The warning unit can, for example, refer to past warning history and select the optimal warning method. The warning unit can use a generation AI to refer to past warning history and select the optimal warning method. For example, the warning unit can input past warning history into the generation AI and select the optimal warning method. This allows the optimal warning method to be selected by referring to past warning history. Some or all of the above processing in the warning unit may be performed using a generation AI or without a generation AI. For example, the warning unit can select a warning method based on past warning history analyzed by a generation AI.

[0054] The warning unit provides not only the content of the warning but also specific countermeasures. For example, if there is a high probability of fraud, the warning unit will provide specific countermeasures along with the warning. The warning unit can also provide specific countermeasures in addition to the content of the warning using a generation AI. For example, the warning unit can provide countermeasures against fraudulent methods analyzed by the generation AI. This allows for the prevention of damage by providing specific countermeasures along with the content of the warning. Some or all of the above processing in the warning unit may be performed using a generation AI or not. For example, the warning unit can issue a warning based on countermeasures provided by a generation AI.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The analysis unit can analyze not only the content of conversations in real time, but also background and ambient sounds. For example, the analysis unit can identify specific locations and situations from the background sounds heard during a conversation and assess the likelihood of fraud. The analysis unit can use generative AI to analyze background and ambient sounds and obtain information that reinforces the likelihood of fraud. In this way, by analyzing background and ambient sounds, information that reinforces the likelihood of fraud can be obtained. Some or all of the above processing in the analysis unit may be performed using generative AI, or it may be performed without using generative AI. For example, the analysis unit can perform analysis based on background and ambient sounds analyzed by generative AI.

[0057] The analysis unit can more accurately detect signs of fraud by considering the context of the conversation. For example, the analysis unit can analyze the context before and after the conversation and detect typical patterns of fraud. The analysis unit can more accurately detect signs of fraud by considering the context of the conversation using generative AI. This allows for more accurate detection of signs of fraud by considering the context of the conversation. Some or all of the above-described processes in the analysis unit may be performed using generative AI or not. For example, the analysis unit can perform analysis based on contextual information detected by generative AI.

[0058] The collaboration unit can share not only detailed information about the fraud, but also the victim's location and contact information. For example, the collaboration unit can share the victim's location information along with detailed information about the fraud. The collaboration unit can use generative AI to share not only detailed information about the fraud, but also the victim's location and contact information. This enables a rapid response by sharing the victim's location and contact information along with detailed information about the fraud. Some or all of the above processing in the collaboration unit may be performed using generative AI, or it may be performed without using generative AI. For example, the collaboration unit can report to police agencies based on information provided by generative AI.

[0059] The judgment unit can determine fraud risk by considering not only the content of the conversation but also the frequency and time of the conversation. For example, the judgment unit can analyze the frequency of the conversation and determine fraud risk. The judgment unit can use generative AI to determine fraud risk by considering not only the content of the conversation but also the frequency and time of the conversation. This improves the accuracy of fraud risk determination by considering the frequency and time of the conversation. Some or all of the above processing in the judgment unit may be performed using generative AI or without generative AI. For example, the judgment unit can make a determination based on the frequency and time of the conversation analyzed by generative AI.

[0060] The integration unit can select the optimal integration method by referring to past integration history. For example, the integration unit can select the optimal integration method by referring to past integration history. The integration unit can select the optimal integration method by referring to past integration history using a generation AI. This allows the optimal integration method to be selected by referring to past integration history. Some or all of the above processing in the integration unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the integration unit can select an integration method based on past integration history analyzed by a generation AI.

[0061] The warning unit can provide not only the content of the warning but also specific countermeasures. For example, if there is a high probability of fraud, the warning unit can provide specific countermeasures along with the warning. The warning unit can also provide specific countermeasures along with the content of the warning using a generation AI. This allows for the prevention of damage by providing specific countermeasures along with the content of the warning. Some or all of the above processing in the warning unit may be performed using a generation AI or not. For example, the warning unit can issue a warning based on countermeasures provided by a generation AI.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The analysis unit analyzes the conversation content in real time. For example, the analysis unit converts the content of a phone conversation into text data using speech recognition technology, and then analyzes that text data. The analysis unit uses generative AI to analyze typical patterns of fraud and emotions. For example, it detects phrases such as "Please transfer the money" and emotions indicating anxiety or tension. Step 2: The judgment unit determines the fraud risk based on the conversation content analyzed by the analysis unit. The judgment unit scores the fraud risk using a generation AI and determines the fraud risk based on that score. If the fraud risk is determined to be high, it sends the information to the cooperation unit. Step 3: The Liaison Unit shares information with police agencies, etc., if the Judgment Unit determines that there is a risk of fraud. If the Liaison Unit determines that there is a high risk of fraud, it automatically notifies the police and provides detailed information about the fraud. The Liaison Unit provides the police with information such as the content of the conversation, the fraudulent methods, and the victim's location.

[0064] (Example of form 2) The special fraud prevention system according to an embodiment of the present invention is a system that uses a generating AI to detect special frauds early and provides real-time information sharing to police agencies, etc. The special fraud prevention system analyzes the content of conversations in real time, and the generating AI determines the fraud risk. If a fraud risk is determined, the system shares information with police agencies, etc. in real time. This mechanism makes it possible to prevent damage from special frauds. For example, the special fraud prevention system uses a generating AI to analyze the content of a phone conversation between elderly people and detect signs of fraud. The generating AI determines the fraud risk using typical fraud patterns and sentiment analysis. For example, it can detect phrases such as "Please transfer the money" and emotions indicating anxiety or tension. Next, if the generating AI determines that there is a fraud risk, it shares information with police agencies, etc. in real time. For example, if a high fraud risk is determined, the generating AI automatically notifies the police and provides detailed information about the fraud. This information includes the content of the conversation, the fraud methods, and the victim's location information. Furthermore, the generating AI can also issue a warning to the victim. For example, if there is a high probability that the caller is a scammer, the generating AI will warn the victim that "this call may be a scam." This allows the victim to recognize the scam and prevent becoming a victim. This mechanism can prevent special fraud from occurring. It is particularly effective against the elderly and those who are vulnerable to information, and is extremely useful in today's world where fraudulent methods are becoming more sophisticated. Furthermore, by using generating AI, it is possible to quickly detect signs of fraud and respond in real time. This enables law enforcement agencies to respond quickly and prevent the escalation of fraud damage. In short, the special fraud prevention system can quickly detect signs of fraud and respond in real time.

[0065] The special fraud prevention system according to the embodiment comprises an analysis unit, a determination unit, and a coordination unit. The analysis unit analyzes the content of a conversation in real time. For example, the analysis unit converts the content of a telephone conversation into text data using speech recognition technology and analyzes the text data. The analysis unit uses a generation AI to perform typical fraud patterns and sentiment analysis. For example, the analysis unit detects phrases such as "Please transfer the money" and emotions indicating anxiety or tension. The determination unit determines the fraud risk based on the conversation content analyzed by the analysis unit. For example, the determination unit uses a generation AI to score the fraud risk and determines the fraud risk based on that score. If the determination unit determines that the fraud risk is high, it transmits the information to the coordination unit. If the determination unit determines that there is a fraud risk, the coordination unit coordinates the information with the police, etc. For example, if the coordination unit determines that the fraud risk is high, it automatically notifies the police and provides detailed information about the fraud. The coordination unit provides the police with the content of the conversation, the fraud methods, the victim's location information, etc. As a result, the special fraud prevention system according to the embodiment can quickly detect signs of fraud and respond in real time. Some or all of the above-described processes in the analysis unit, judgment unit, and coordination unit may be performed using a generation AI, or they may not be performed using a generation AI. For example, the analysis unit can input conversation content into the generation AI and have the generation AI perform typical fraud patterns and sentiment analysis. The judgment unit can make a judgment based on the fraud risk scored by the generation AI. The coordination unit can report to the police based on the information provided by the generation AI.

[0066] The analysis unit analyzes conversation content in real time. For example, the analysis unit converts telephone conversations into text data using speech recognition technology and then analyzes that text data. Specifically, the speech recognition technology uses a highly accurate speech model to quickly and accurately convert the audio of the conversation into text. This text data is input into a generative AI, which performs typical fraud patterns and sentiment analysis. The generative AI has learned from a large amount of fraud case data and can detect specific phrases and expressions related to fraud with high accuracy. For example, if phrases such as "Please transfer the money" or "Please respond immediately" are detected, the generative AI will determine that this is highly likely to be a scam. The generative AI also performs sentiment analysis, detecting emotions such as anxiety and tension from the tone and wording of the conversation. This allows the analysis unit to analyze conversation content showing signs of fraud in real time and provide basic data for a rapid response. Furthermore, the analysis unit can also detect new patterns and trends in fraud using statistical models based on past conversation data and fraud cases. This allows the analysis unit to constantly respond to the latest fraud methods and improve the accuracy and reliability of the system.

[0067] The judgment unit determines the fraud risk based on the conversation content analyzed by the analysis unit. The judgment unit scores the fraud risk, for example, using a generative AI, and determines the fraud risk based on that score. Specifically, the generative AI receives text data provided by the analysis unit as input and executes a scoring algorithm that quantifies the fraud risk. This algorithm considers typical fraud patterns and the results of sentiment analysis to evaluate the fraud risk with high accuracy. For example, if a specific phrase or emotion is detected, its risk score will be set high. Based on this score, the judgment unit determines whether the fraud risk is high or low. If the fraud risk is determined to be high, the judgment unit sends the information to the coordination unit. Furthermore, the judgment unit can continuously improve the scoring algorithm based on past judgment results and feedback. This allows the judgment unit to always use the latest information and technology to determine fraud risk with high accuracy, improving the reliability and effectiveness of the entire system.

[0068] The Liaison Department shares information with law enforcement agencies when the Judgment Department determines there is a risk of fraud. Specifically, if a high risk of fraud is determined, it automatically notifies law enforcement agencies and provides detailed information about the fraud. For example, the Liaison Department provides law enforcement agencies with information such as the content of the conversation, the fraudulent methods used, and the victim's location. This allows law enforcement agencies to respond quickly and prevent further damage. Based on the information provided by the AI ​​generation system, the Liaison Department automatically generates the content of the report and transmits the necessary information accurately and quickly. The Liaison Department also conducts follow-up after the report is made, strengthening cooperation with law enforcement agencies. For example, it can receive feedback from law enforcement agencies and use it to improve the system. Furthermore, the Liaison Department provides appropriate support to victims. For example, it can provide victims with information on the status of the report to law enforcement agencies and future actions, giving them a sense of security. As a result, the Liaison Department can respond quickly and appropriately when there is a high risk of fraud, minimizing damage.

[0069] The emotion analysis unit performs emotion analysis. The emotion analysis unit estimates emotions from conversation content, for example, by using voice tone analysis or text analysis. The emotion analysis unit estimates the user's emotions using generative AI and determines the fraud risk based on those emotions. For example, the emotion analysis unit can determine a high fraud risk if the user is feeling anxious or tense. Also, if the user is relaxed, the emotion analysis unit can analyze the conversation content with normal analytical accuracy. As a result, performing emotion analysis improves the accuracy of fraud risk determination. Some or all of the above processing in the emotion analysis unit may be performed using generative AI, or it may be performed without using generative AI. For example, the emotion analysis unit can input the conversation content into the generative AI and have the generative AI perform the emotion analysis.

[0070] The warning unit issues a warning to the victim. The warning unit issues a warning to the victim using, for example, voice warnings, text messages, or visual alerts. The warning unit uses generative AI to warn the victim if there is a high probability that the call is fraudulent. For example, if the warning unit is likely to be a fraudster, it can warn, "This call may be fraudulent." This allows the victim to recognize the fraud and prevent becoming a victim. Some or all of the above processing in the warning unit may be performed using generative AI or not. For example, the warning unit may issue a warning based on the fraud risk determined by generative AI.

[0071] The analysis unit detects typical fraud patterns. The analysis unit detects typical fraud patterns using, for example, patterns based on past fraud cases or machine learning models. The analysis unit can also detect typical fraud patterns using generative AI. For example, the analysis unit can input past fraud case data into the generative AI and train it to recognize typical fraud patterns. This improves the accuracy of fraud risk assessment by detecting typical fraud patterns. Some or all of the above processing in the analysis unit may be performed using generative AI or not. For example, the analysis unit can perform analysis based on typical fraud patterns detected by the generative AI.

[0072] The liaison department provides police agencies with detailed information about the fraud. For example, the liaison department provides police agencies with the full text of the conversation and related metadata. The liaison department can also provide police agencies with detailed information about the fraud using generative AI. For example, the liaison department can provide police agencies with the conversation content and fraud methods analyzed by generative AI. This enables a swift response by providing police agencies with detailed information about the fraud. Some or all of the above processing in the liaison department may be performed using generative AI or not. For example, the liaison department can report to police agencies based on information provided by generative AI.

[0073] The warning unit issues a warning to the victim if there is a high probability of fraud. For example, the warning unit may issue a warning to the victim using voice warnings, text messages, or visual alerts if there is a high probability of fraud. The warning unit can also use generative AI to issue a warning to the victim if there is a high probability of fraud. For example, the warning unit may issue a warning such as "This call may be a scam" based on the fraud risk determined by the generative AI. This prevents fraud by warning the victim when there is a high probability of fraud. Some or all of the above processing in the warning unit may be performed using generative AI or not. For example, the warning unit may issue a warning based on the fraud risk determined by the generative AI.

[0074] The analysis unit estimates the user's emotions and adjusts the accuracy of the analysis based on the estimated emotions. The analysis unit estimates the user's emotions from the conversation content, for example, using voice tone analysis or text analysis. The analysis unit can use generative AI to estimate the user's emotions and adjust the accuracy of the analysis based on those emotions. For example, if the user is feeling anxious, the generative AI will detect the emotion and analyze the signs of fraud more rigorously. Also, if the user is relaxed, the generative AI will detect the emotion and analyze the conversation content with normal analysis accuracy. By adjusting the accuracy of the analysis based on the user's emotions, the accuracy of fraud risk determination is improved. Emotion estimation is achieved using an emotion estimation function, such as 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 generative AI or not. For example, the analysis unit can input the conversation content into the generative AI and have the generative AI perform emotion estimation.

[0075] The analysis unit more accurately detects signs of fraud by considering the context of the conversation. For example, the analysis unit analyzes the context before and after the conversation to detect typical patterns of fraud. The analysis unit can use generative AI to more accurately detect signs of fraud by considering the context of the conversation. For example, the analysis unit can input the context before and after the conversation into the generative AI and detect signs of fraud. This allows for more accurate detection of signs of fraud by considering the context of the conversation. Some or all of the above processing in the analysis unit may be performed using generative AI or not. For example, the analysis unit can perform analysis based on contextual information detected by the generative AI.

[0076] The analysis unit analyzes background and ambient sounds in a conversation and obtains information that reinforces the possibility of fraud. For example, the analysis unit can identify a specific location or situation from the background sounds and evaluate the possibility of fraud. The analysis unit can use a generative AI to analyze background and ambient sounds in a conversation and obtain information that reinforces the possibility of fraud. For example, the analysis unit can input background and ambient sounds into the generative AI and obtain information that reinforces the possibility of fraud. In this way, by analyzing the background and ambient sounds in a conversation, information that reinforces the possibility of fraud can be obtained. Some or all of the above processing in the analysis unit may be performed using a generative AI or not. For example, the analysis unit can perform analysis based on background and ambient sounds analyzed by a generative AI.

[0077] The analysis unit estimates the user's emotions and determines the analysis priority based on the estimated emotions. The analysis unit estimates the user's emotions from the conversation content, for example, using voice tone analysis or text analysis. The analysis unit can use generative AI to estimate the user's emotions and determine the analysis priority based on those emotions. For example, if the user is feeling anxious, the generative AI will detect the emotion and prioritize the analysis of conversations that are likely to be fraudulent. Conversely, if the user is relaxed, the generative AI will detect the emotion and the analysis unit can analyze the conversation content with the normal priority. This improves the accuracy of fraud risk assessment by determining the analysis priority based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI 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 generative AI or not. For example, the analysis unit can input the conversation content into the generative AI and have the generative AI perform emotion estimation.

[0078] The analysis unit adjusts the analysis algorithm considering the language and dialect of the conversation. For example, the analysis unit identifies the language of the conversation and uses an analysis algorithm appropriate for that language. The analysis unit can use generative AI to adjust the analysis algorithm considering the language and dialect of the conversation. For example, the analysis unit can input the language and dialect of the conversation into the generative AI and adjust the analysis algorithm. This improves the accuracy of the analysis algorithm by considering the language and dialect of the conversation. Some or all of the above-described processes in the analysis unit may be performed using generative AI or not. For example, the analysis unit can perform analysis based on an analysis algorithm adjusted by generative AI.

[0079] The analysis unit analyzes the speed and tone of the conversation and obtains information to reinforce signs of fraud. For example, the analysis unit analyzes the speed of the conversation and issues a warning if there is a high probability of fraud. The analysis unit can use a generative AI to analyze the speed and tone of the conversation and obtain information to reinforce signs of fraud. For example, the analysis unit can input the speed and tone of the conversation into the generative AI and obtain information to reinforce signs of fraud. In this way, by analyzing the speed and tone of the conversation, information to reinforce signs of fraud can be obtained. Some or all of the above processing in the analysis unit may be performed using the generative AI or not. For example, the analysis unit can perform analysis based on the speed and tone analyzed by the generative AI.

[0080] The judgment unit estimates the user's emotions and adjusts the judgment criteria based on the estimated emotions. The judgment unit estimates the user's emotions from the conversation content, for example, by using voice tone analysis or text analysis. The judgment unit can use generative AI to estimate the user's emotions and adjust the judgment criteria based on those emotions. For example, if the user is feeling anxious, the judgment unit's generative AI will detect the emotion and tighten the fraud risk criteria. Also, if the user is relaxed, the judgment unit's generative AI will detect the emotion and determine the fraud risk using normal criteria. In this way, the accuracy of fraud risk determination is improved by adjusting the judgment criteria based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the judgment unit may be performed using or without the generative AI. For example, the judgment unit can input the conversation content into the generative AI and have the generative AI perform emotion estimation.

[0081] The judgment unit improves the accuracy of its judgment by referring to a database of past fraud cases. The judgment unit, for example, refers to a database of past fraud cases to determine the fraud risk. The judgment unit can improve the accuracy of its judgment by referring to a database of past fraud cases using a generation AI. For example, the judgment unit can input past fraud case data into a generation AI to determine the fraud risk. This improves the accuracy of fraud risk determination by referring to a database of past fraud cases. Some or all of the above processing in the judgment unit may be performed using a generation AI or not. For example, the judgment unit can make a judgment based on past fraud case data referenced by a generation AI.

[0082] The judgment unit determines the fraud risk by considering not only the content of the conversation but also the frequency and time of the conversation. For example, the judgment unit analyzes the frequency of the conversation and determines the fraud risk. The judgment unit can use a generative AI to determine the fraud risk by considering not only the content of the conversation but also the frequency and time of the conversation. For example, the judgment unit can input the frequency and time of the conversation into the generative AI and determine the fraud risk. This improves the accuracy of fraud risk determination by considering the frequency and time of the conversation. Some or all of the above processing in the judgment unit may be performed using a generative AI or without a generative AI. For example, the judgment unit can make a determination based on the frequency and time of the conversation analyzed by the generative AI.

[0083] The judgment unit estimates the user's emotions and determines the priority of judgments based on the estimated emotions. The judgment unit estimates the user's emotions from the conversation content, for example, by using voice tone analysis or text analysis. The judgment unit can use generative AI to estimate the user's emotions and determine the priority of judgments based on those emotions. For example, if the user is feeling anxious, the generative AI will detect the emotion and prioritize judging conversations with a high risk of fraud. Also, if the user is relaxed, the generative AI will detect the emotion and the judgment unit can determine the fraud risk with the normal priority. This improves the accuracy of fraud risk judgment by determining the priority of judgments based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the judgment unit may be performed using the generative AI or not. For example, the judgment unit can input the conversation content into the generative AI and have the generative AI perform emotion estimation.

[0084] The judgment unit makes a judgment by considering the attribute information of the person being spoken to. For example, the judgment unit analyzes the age and gender of the person being spoken to and determines the fraud risk. The judgment unit can use a generative AI to make a judgment by considering the attribute information of the person being spoken to. For example, the judgment unit can input the attribute information of the person being spoken to into the generative AI and determine the fraud risk. This improves the accuracy of fraud risk determination by considering the attribute information of the person being spoken to. Some or all of the above processing in the judgment unit may be performed using a generative AI or not. For example, the judgment unit can make a judgment based on attribute information analyzed by a generative AI.

[0085] The judgment unit makes a judgment considering the background sounds and ambient sounds of the conversation. For example, the judgment unit analyzes the background sounds of the conversation and determines the fraud risk. The judgment unit can use a generation AI to make a judgment considering the background sounds and ambient sounds of the conversation. For example, the judgment unit can input the background sounds and ambient sounds of the conversation into the generation AI and determine the fraud risk. This improves the accuracy of fraud risk determination by considering the background sounds and ambient sounds of the conversation. Some or all of the above processing in the judgment unit may be performed using a generation AI or not. For example, the judgment unit can make a judgment based on the background sounds and ambient sounds analyzed by the generation AI.

[0086] The collaboration unit estimates the user's emotions and adjusts the timing of collaboration based on the estimated emotions. The collaboration unit estimates the user's emotions from the conversation content, for example, by using voice tone analysis or text analysis. The collaboration unit can use generative AI to estimate the user's emotions and adjust the timing of collaboration based on those emotions. For example, if the user is feeling anxious, the collaboration unit's generative AI will detect the emotion and quickly collaborate on information. Also, if the user is relaxed, the collaboration unit's generative AI will detect the emotion and collaborate on information at the normal timing. This allows for a quick response by adjusting the timing of collaboration based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the collaboration unit may be performed using generative AI or not. For example, the collaboration unit can input the conversation content into the generative AI and have the generative AI perform emotion estimation.

[0087] The liaison unit will share not only detailed information about the fraud, but also the victim's location and contact information. For example, the liaison unit will share the victim's location information along with the detailed information about the fraud. The liaison unit can use generative AI to share not only detailed information about the fraud, but also the victim's location and contact information. For example, the liaison unit can provide the police with the victim's location and contact information along with the detailed information about the fraud analyzed by the generative AI. This enables a swift response by sharing the victim's location and contact information along with the detailed information about the fraud. Some or all of the above processing in the liaison unit may be performed using generative AI, or it may be performed without using generative AI. For example, the liaison unit can report to the police based on the information provided by the generative AI.

[0088] The integration unit selects the optimal integration method by referring to past integration history. The integration unit can, for example, refer to past integration history and select the optimal integration method. The integration unit can use a generating AI to refer to past integration history and select the optimal integration method. For example, the integration unit can input past integration history into the generating AI and select the optimal integration method. In this way, the optimal integration method can be selected by referring to past integration history. Some or all of the above processing in the integration unit may be performed using a generating AI, or it may be performed without using a generating AI. For example, the integration unit can select an integration method based on past integration history analyzed by a generating AI.

[0089] The collaboration unit estimates the user's emotions and determines the priority of collaboration based on the estimated emotions. The collaboration unit estimates the user's emotions from the conversation content, for example, by using voice tone analysis or text analysis. The collaboration unit can use generative AI to estimate the user's emotions and determine the priority of collaboration based on those emotions. For example, if the user is feeling anxious, the generative AI will detect the emotion and prioritize the collaboration of information with a high risk of fraud. Conversely, if the user is relaxed, the generative AI will detect the emotion and the collaboration unit can collaborate with information with the normal priority. This enables a rapid response by determining the priority of collaboration based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the collaboration unit may be performed using generative AI or not. For example, the collaboration unit can input the conversation content into the generative AI and have the generative AI perform emotion estimation.

[0090] The liaison unit will share not only detailed information about the fraud, but also information about the victim's attributes. For example, the liaison unit will share the victim's age and gender along with the detailed information about the fraud. The liaison unit can use generative AI to share not only detailed information about the fraud, but also information about the victim's attributes. For example, the liaison unit can provide police agencies with detailed information about the fraud analyzed by generative AI, along with information about the victim's attributes. This enables a swift response by sharing information about the victim's attributes along with detailed information about the fraud. Some or all of the above processing in the liaison unit may be performed using generative AI, or it may be performed without using generative AI. For example, the liaison unit can report to police agencies based on information provided by generative AI.

[0091] The collaboration unit collaborates with the police by sharing detailed information about the fraud, including background sounds and ambient sounds from the conversation. For example, the collaboration unit can share background sounds from the conversation along with detailed information about the fraud. The collaboration unit can use generative AI to collaborate with the police by sharing background sounds and ambient sounds from the conversation, in addition to detailed information about the fraud. For example, the collaboration unit can provide police agencies with background sounds and ambient sounds from the conversation along with detailed information about the fraud analyzed by the generative AI. This enables a rapid response by collaborating background sounds and ambient sounds from the conversation along with detailed information about the fraud. Some or all of the above processing in the collaboration unit may be performed using generative AI or not. For example, the collaboration unit can report to police agencies based on information provided by the generative AI.

[0092] The sentiment analysis unit improves the accuracy of its analysis by referring to the user's past emotional history. For example, the sentiment analysis unit accurately analyzes the current emotion by referring to past conversation data and emotional change patterns. The sentiment analysis unit can improve the accuracy of its analysis by referring to the user's past emotional history using generative AI. For example, the sentiment analysis unit can input past emotional history into the generative AI and accurately analyze the current emotion. This improves the accuracy of sentiment analysis by referring to the user's past emotional history. Some or all of the above processing in the sentiment analysis unit may be performed using generative AI or not. For example, the sentiment analysis unit can perform analysis based on past emotional history analyzed by generative AI.

[0093] The emotion analysis unit detects emotional changes more accurately by considering the context of the conversation. For example, the emotion analysis unit analyzes the context before and after the conversation to detect emotional changes. The emotion analysis unit can use generative AI to detect emotional changes more accurately by considering the context of the conversation. For example, the emotion analysis unit can input the context before and after the conversation into the generative AI and detect emotional changes. This allows for more accurate detection of emotional changes by considering the context of the conversation. Some or all of the above processing in the emotion analysis unit may be performed using generative AI or not. For example, the emotion analysis unit can detect emotional changes based on contextual information analyzed by the generative AI.

[0094] The sentiment analysis unit determines the priority of analysis based on the user's emotions. The sentiment analysis unit estimates the user's emotions from the conversation content, for example, using voice tone analysis or text analysis. The sentiment analysis unit can use generative AI to estimate the user's emotions and determine the priority of analysis based on those emotions. For example, if the user is feeling anxious, the sentiment analysis unit will prioritize the analysis. Conversely, if the user is relaxed, the sentiment analysis unit can perform the analysis with the normal priority. This improves the accuracy of sentiment analysis by prioritizing analysis based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, 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 sentiment analysis unit may be performed using generative AI, or not. For example, the sentiment analysis unit can input the conversation content into a generative AI and have the generative AI perform emotion estimation.

[0095] The emotion analysis unit detects changes in emotion by considering the speed and tone of the conversation. For example, the emotion analysis unit analyzes the speed of the conversation and detects changes in emotion. The emotion analysis unit can use generative AI to detect changes in emotion by considering the speed and tone of the conversation. For example, the emotion analysis unit can input the speed and tone of the conversation into the generative AI and detect changes in emotion. This allows for more accurate detection of changes in emotion by considering the speed and tone of the conversation. Some or all of the above processing in the emotion analysis unit may be performed using generative AI or not. For example, the emotion analysis unit can detect changes in emotion based on the speed and tone analyzed by the generative AI.

[0096] The warning unit estimates the user's emotions and adjusts the way the warning is expressed based on those emotions. The warning unit estimates the user's emotions from the conversation content, for example, by using voice tone analysis or text analysis. The warning unit can use generative AI to estimate the user's emotions and adjust the way the warning is expressed based on those emotions. For example, if the user is feeling anxious, the warning unit will issue a warning in a calm tone. Conversely, if the user is relaxed, the warning unit can issue a warning in a normal tone. By adjusting the way the warning is expressed based on the user's emotions, more effective warnings become possible. Emotion estimation is achieved using an emotion estimation function, such as 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 warning unit may be performed using generative AI or not. For example, the warning unit can input the conversation content into a generative AI and have the generative AI perform emotion estimation.

[0097] The warning unit selects the optimal warning method by referring to past warning history. The warning unit can, for example, refer to past warning history and select the optimal warning method. The warning unit can use a generation AI to refer to past warning history and select the optimal warning method. For example, the warning unit can input past warning history into the generation AI and select the optimal warning method. This allows the optimal warning method to be selected by referring to past warning history. Some or all of the above processing in the warning unit may be performed using a generation AI or without a generation AI. For example, the warning unit can select a warning method based on past warning history analyzed by a generation AI.

[0098] The warning unit estimates the user's emotions and determines the priority of warnings based on the estimated emotions. The warning unit estimates the user's emotions from the conversation content, for example, by using voice tone analysis or text analysis. The warning unit can use generative AI to estimate the user's emotions and determine the priority of warnings based on those emotions. For example, if the user is feeling anxious, the warning unit will issue a warning with priority. Conversely, if the user is relaxed, the warning unit can issue a warning with normal priority. This allows for more effective warnings by determining the priority of warnings based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the warning unit may be performed using generative AI or not. For example, the warning unit can input the conversation content into a generative AI and have the generative AI perform emotion estimation.

[0099] The warning unit provides not only the content of the warning but also specific countermeasures. For example, if there is a high probability of fraud, the warning unit will provide specific countermeasures along with the warning. The warning unit can also provide specific countermeasures in addition to the content of the warning using a generation AI. For example, the warning unit can provide countermeasures against fraudulent methods analyzed by the generation AI. This allows for the prevention of damage by providing specific countermeasures along with the content of the warning. Some or all of the above processing in the warning unit may be performed using a generation AI or not. For example, the warning unit can issue a warning based on countermeasures provided by a generation AI.

[0100] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0101] The analysis unit can analyze not only the content of conversations in real time, but also background and ambient sounds. For example, the analysis unit can identify specific locations and situations from the background sounds heard during a conversation and assess the likelihood of fraud. The analysis unit can use generative AI to analyze background and ambient sounds and obtain information that reinforces the likelihood of fraud. In this way, by analyzing background and ambient sounds, information that reinforces the likelihood of fraud can be obtained. Some or all of the above processing in the analysis unit may be performed using generative AI, or it may be performed without using generative AI. For example, the analysis unit can perform analysis based on background and ambient sounds analyzed by generative AI.

[0102] The sentiment analysis unit can improve the accuracy of its analysis by referring to the user's past emotional history. For example, the sentiment analysis unit can accurately analyze the user's current emotions by referring to past conversation data and emotional change patterns. The sentiment analysis unit can improve the accuracy of its analysis by referring to the user's past emotional history using generative AI. This improves the accuracy of sentiment analysis by referring to the user's past emotional history. Some or all of the above-described processes in the sentiment analysis unit may be performed using generative AI or not. For example, the sentiment analysis unit can perform analysis based on past emotional history analyzed by generative AI.

[0103] The warning unit can estimate the user's emotions and adjust the way the warning is expressed based on those emotions. For example, the warning unit can estimate the user's emotions from the conversation content using speech tone analysis or text analysis. The warning unit can use generative AI to estimate the user's emotions and adjust the way the warning is expressed based on those emotions. For example, if the user is feeling anxious, the warning can be issued in a calm tone. If the user is relaxed, the warning can be issued in a normal tone. By adjusting the way the warning is expressed based on the user's emotions, more effective warnings become possible. Emotion estimation is achieved using an emotion estimation function, such as 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 warning unit may be performed using generative AI or not. For example, the warning unit can input the conversation content into the generative AI and have the generative AI perform emotion estimation.

[0104] The analysis unit can more accurately detect signs of fraud by considering the context of the conversation. For example, the analysis unit can analyze the context before and after the conversation and detect typical patterns of fraud. The analysis unit can more accurately detect signs of fraud by considering the context of the conversation using generative AI. This allows for more accurate detection of signs of fraud by considering the context of the conversation. Some or all of the above-described processes in the analysis unit may be performed using generative AI or not. For example, the analysis unit can perform analysis based on contextual information detected by generative AI.

[0105] The collaboration unit can share not only detailed information about the fraud, but also the victim's location and contact information. For example, the collaboration unit can share the victim's location information along with detailed information about the fraud. The collaboration unit can use generative AI to share not only detailed information about the fraud, but also the victim's location and contact information. This enables a rapid response by sharing the victim's location and contact information along with detailed information about the fraud. Some or all of the above processing in the collaboration unit may be performed using generative AI, or it may be performed without using generative AI. For example, the collaboration unit can report to police agencies based on information provided by generative AI.

[0106] The judgment unit can determine fraud risk by considering not only the content of the conversation but also the frequency and time of the conversation. For example, the judgment unit can analyze the frequency of the conversation and determine fraud risk. The judgment unit can use generative AI to determine fraud risk by considering not only the content of the conversation but also the frequency and time of the conversation. This improves the accuracy of fraud risk determination by considering the frequency and time of the conversation. Some or all of the above processing in the judgment unit may be performed using generative AI or without generative AI. For example, the judgment unit can make a determination based on the frequency and time of the conversation analyzed by generative AI.

[0107] The analysis unit can estimate the user's emotions and determine the priority of analysis based on the estimated emotions. For example, the analysis unit can estimate the user's emotions from the conversation content using voice tone analysis or text analysis. The analysis unit can also estimate the user's emotions using generative AI and determine the priority of analysis based on those emotions. For example, if the user is feeling anxious, the generative AI can detect the emotion and prioritize the analysis of conversations that are likely to be fraudulent. Conversely, if the user is relaxed, the generative AI can detect the emotion and analyze the conversation content with the normal priority. This improves the accuracy of fraud risk assessment by determining the priority of analysis based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using or without the generative AI. For example, the analysis unit can input the conversation content into the generative AI and have the generative AI perform emotion estimation.

[0108] The judgment unit can estimate the user's emotions and adjust the judgment criteria based on the estimated emotions. For example, the judgment unit can estimate the user's emotions from the conversation content using voice tone analysis or text analysis. The judgment unit can estimate the user's emotions using generative AI and adjust the judgment criteria based on those emotions. For example, if the user is feeling anxious, the generative AI can detect the emotion and tighten the criteria for fraud risk. Conversely, if the user is relaxed, the generative AI can detect the emotion and determine the fraud risk using the normal criteria. This improves the accuracy of fraud risk determination by adjusting the judgment criteria based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the judgment unit may be performed using or without the generative AI. For example, the judgment unit can input the conversation content into the generative AI and have the generative AI perform emotion estimation.

[0109] The integration unit can select the optimal integration method by referring to past integration history. For example, the integration unit can select the optimal integration method by referring to past integration history. The integration unit can select the optimal integration method by referring to past integration history using a generation AI. This allows the optimal integration method to be selected by referring to past integration history. Some or all of the above processing in the integration unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the integration unit can select an integration method based on past integration history analyzed by a generation AI.

[0110] The warning unit can provide not only the content of the warning but also specific countermeasures. For example, if there is a high probability of fraud, the warning unit can provide specific countermeasures along with the warning. The warning unit can also provide specific countermeasures along with the content of the warning using a generation AI. This allows for the prevention of damage by providing specific countermeasures along with the content of the warning. Some or all of the above processing in the warning unit may be performed using a generation AI or not. For example, the warning unit can issue a warning based on countermeasures provided by a generation AI.

[0111] The following briefly describes the processing flow for example form 2.

[0112] Step 1: The analysis unit analyzes the conversation content in real time. For example, the analysis unit converts the content of a phone conversation into text data using speech recognition technology, and then analyzes that text data. The analysis unit uses generative AI to analyze typical patterns of fraud and emotions. For example, it detects phrases such as "Please transfer the money" and emotions indicating anxiety or tension. Step 2: The judgment unit determines the fraud risk based on the conversation content analyzed by the analysis unit. The judgment unit scores the fraud risk using a generation AI and determines the fraud risk based on that score. If the fraud risk is determined to be high, it sends the information to the cooperation unit. Step 3: The Liaison Unit shares information with police agencies, etc., if the Judgment Unit determines that there is a risk of fraud. If the Liaison Unit determines that there is a high risk of fraud, it automatically notifies the police and provides detailed information about the fraud. The Liaison Unit provides the police with information such as the content of the conversation, the fraudulent methods, and the victim's location.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] Each of the multiple elements described above, including the analysis unit, judgment unit, coordination unit, sentiment analysis unit, and warning unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit is implemented by the computer 36 of the smart device 14 and analyzes the conversation content in real time. The judgment unit is implemented by the identification processing unit 290 of the data processing unit 12 and determines the risk of fraud. The coordination unit is implemented by the communication I / F 44 of the smart device 14 and coordinates information with police agencies, etc. The sentiment analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and performs sentiment analysis. The warning unit is implemented by the output device 40 of the smart device 14 and issues a warning to the victim. 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.

[0117] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] Each of the multiple elements described above, including the analysis unit, judgment unit, coordination unit, sentiment analysis unit, and warning unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit is implemented by the computer 36 of the smart glasses 214 and analyzes the conversation content in real time. The judgment unit is implemented by the identification processing unit 290 of the data processing unit 12 and determines the risk of fraud. The coordination unit is implemented by the communication I / F 44 of the smart glasses 214 and coordinates information with police agencies, etc. The sentiment analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and performs sentiment analysis. The warning unit is implemented by the speaker 240 of the smart glasses 214 and issues a warning to the victim. 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.

[0133] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] Each of the multiple elements described above, including the analysis unit, judgment unit, coordination unit, sentiment analysis unit, and warning unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the computer 36 of the headset terminal 314 and analyzes the conversation content in real time. The judgment unit is implemented by the identification processing unit 290 of the data processing unit 12 and determines the risk of fraud. The coordination unit is implemented by the communication I / F 44 of the headset terminal 314 and coordinates information with police agencies, etc. The sentiment analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and performs sentiment analysis. The warning unit is implemented by the speaker 240 of the headset terminal 314 and issues a warning to the victim. 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.

[0149] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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).

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.).

[0162] 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.

[0163] 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.

[0164] 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.

[0165] Each of the multiple elements described above, including the analysis unit, judgment unit, coordination unit, sentiment analysis unit, and warning unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the computer 36 of the robot 414 and analyzes the content of conversation in real time. The judgment unit is implemented by the identification processing unit 290 of the data processing unit 12 and determines the risk of fraud. The coordination unit is implemented by the communication I / F 44 of the robot 414 and coordinates information with police agencies, etc. The sentiment analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and performs sentiment analysis. The warning unit is implemented by the speaker 240 of the robot 414 and issues a warning to the victim. 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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."

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] (Note 1) An analysis unit that analyzes the conversation content in real time, A determination unit that determines the risk of fraud based on the conversation content analyzed by the aforementioned analysis unit, The aforementioned determination unit determines that there is a risk of fraud, and the cooperation unit shares this information with police agencies, etc., Equipped with A system characterized by the following features. (Note 2) It is equipped with an emotion analysis department that performs emotion analysis. The system described in Appendix 1, characterized by the features described herein. (Note 3) It is equipped with a warning unit that issues a warning to the victim. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned analysis unit, Detecting typical patterns of fraud The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned linkage unit is, Provide detailed information about the fraud to the police. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned warning unit is Issue a warning to the victim if there is a high probability of fraud. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, It estimates the user's emotions and adjusts the accuracy of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, By considering the context of the conversation, signs of fraud can be detected more accurately. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, The system analyzes background and ambient sounds in conversations to obtain information that reinforces the possibility of fraud. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, It estimates the user's emotions and determines the priority of analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, The analysis algorithm is adjusted to take into account the language and dialect of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, By analyzing the speed and tone of conversation, we obtain information that reinforces signs of fraud. The system described in Appendix 1, characterized by the features described herein. (Note 13) The determination unit, It estimates the user's emotions and adjusts the criteria for judgment based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The determination unit, We improve the accuracy of our assessments by referring to a database of past fraud cases. The system described in Appendix 1, characterized by the features described herein. (Note 15) The determination unit, The risk of fraud is determined not only by the content of the conversation, but also by considering the frequency and timing of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 16) The determination unit, The system estimates the user's emotions and determines the priority of decisions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The determination unit, The determination is made by taking into account the attribute information of the person being spoken to. The system described in Appendix 1, characterized by the features described herein. (Note 18) The determination unit, The judgment is made by taking into account the background sounds and ambient sounds of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned linkage unit is, It estimates the user's emotions and adjusts the timing of interactions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned linkage unit is, We will share not only detailed information about the fraud, but also the victim's location and contact information. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned linkage unit is, Refer to past collaboration history to select the optimal collaboration method. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned linkage unit is, It estimates the user's emotions and determines the priority of collaboration based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned linkage unit is, In addition to detailed information about the fraud, the system will also share information about the victim's attributes. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned linkage unit is, In addition to detailed information about the scam, the system also integrates background sounds and ambient noise from the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned emotion analysis unit, By referencing the user's past sentiment history, we can improve the accuracy of our analysis. The system described in Appendix 2, characterized by the features described herein. (Note 26) The aforementioned emotion analysis unit, By considering the context of the conversation, emotional changes can be detected more accurately. The system described in Appendix 2, characterized by the features described herein. (Note 27) The aforementioned emotion analysis unit, Prioritize analysis based on user sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 28) The aforementioned emotion analysis unit, It detects emotional changes by considering the speed and tone of conversation. The system described in Appendix 2, characterized by the features described herein. (Note 29) The aforementioned warning unit is It estimates the user's emotions and adjusts the way warnings are expressed based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 30) The aforementioned warning unit is Refer to past warning history to select the most suitable warning method. The system described in Appendix 3, characterized by the features described herein. (Note 31) The aforementioned warning unit is It estimates the user's emotions and determines the priority of warnings based on those emotions. The system described in Appendix 3, characterized by the features described herein. (Note 32) The aforementioned warning unit is In addition to the warning content, specific countermeasures will also be provided. The system described in Appendix 3, characterized by the features described herein. [Explanation of Symbols]

[0185] 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 the conversation content in real time, A determination unit that determines the risk of fraud based on the conversation content analyzed by the aforementioned analysis unit, The aforementioned determination unit determines that there is a risk of fraud, and the cooperation unit shares this information with police agencies, etc., Equipped with A system characterized by the following features.

2. It is equipped with an emotion analysis department that performs emotion analysis. The system according to feature 1.

3. It is equipped with a warning unit that issues a warning to the victim. The system according to feature 1.

4. The aforementioned analysis unit, Detecting typical patterns of fraud The system according to feature 1.

5. The aforementioned linkage unit is, Provide detailed information about the fraud to the police. The system according to feature 1.

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

7. The aforementioned analysis unit, By considering the context of the conversation, signs of fraud can be detected more accurately. The system according to feature 1.

Images