system

Abstract

The system according to this embodiment aims to detect telephone-based fraud in real time and respond quickly. [Solution] The system according to the embodiment comprises a monitoring unit, a judgment unit, a notification unit, a disconnection unit, and an alert unit. The monitoring unit monitors the content of a call in real time. The judgment unit determines the possibility of a special fraud based on the content of the call monitored by the monitoring unit. The notification unit notifies the user if the judgment unit determines that there is a high possibility of a special fraud. The disconnection unit automatically disconnects the call when notified by the notification unit. The alert unit sends an alert to a pre-registered contact, such as a family member, when notified by the notification unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there was a problem that it was difficult to detect special fraud by phone in real time and respond quickly.

[0005] The system according to the embodiment aims to detect special fraud by phone in real time and respond quickly.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a monitoring unit, a decision unit, a notification unit, a disconnection unit, and an alert unit. The monitoring unit monitors the content of a call in real time. The decision unit determines the possibility of a special fraud based on the content of the call monitored by the monitoring unit. The notification unit notifies the user if the decision unit determines that there is a high possibility of a special fraud. The disconnection unit automatically disconnects the call when notified by the notification unit. The alert unit sends an alert to pre-registered contacts, such as family members, when notified by the notification unit. [Effects of the Invention]

[0007] The system according to this embodiment can detect telephone-based fraud in real time and respond quickly. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The fraud prevention system according to an embodiment of the present invention is an alert function for smartphones to prevent damage from special fraud. This fraud prevention system uses a generating AI to monitor the content of a call in real time when a call is received on the user's smartphone. If the AI ​​determines that the call content is highly likely to be a special fraud, it immediately notifies the user via vibration, on-screen message, etc. Optional features include an automatic call termination function when a special fraud is detected, and a function to send alerts to pre-registered contacts such as family members. For example, when a call is received on the user's smartphone, the generating AI monitors the content in real time. The AI ​​analyzes the call content to determine if it is likely to be a special fraud. For example, it can detect phrases and speaking styles commonly used by fraudsters to increase the likelihood of fraud. Next, if the generating AI analyzes the call content and determines that it is highly likely to be a special fraud, it immediately notifies the user. Notification methods include vibration and on-screen messages. This allows the user to recognize the possibility of fraud during the call and take appropriate action. Furthermore, an optional feature is available that automatically terminates the call when a special fraud is detected. This feature reduces the risk for users to continue conversations with scammers. It also allows for alerts to be sent to pre-registered contacts, such as family members. This enables family and relevant parties to respond quickly before the user becomes a victim of fraud. This system is expected to prevent special fraud and reduce the number of fraud cases. Furthermore, since it is available as an option for smartphone users of specific telecommunications carriers, it can also contribute to the carriers' revenue. In summary, this special fraud prevention system can prevent special fraud and reduce the number of fraud cases.

[0029] The special fraud prevention system according to the embodiment comprises a monitoring unit, a judgment unit, a notification unit, a disconnection unit, and an alert unit. The monitoring unit monitors the content of a call in real time. The monitoring unit analyzes the content of a call using, for example, a generation AI, and determines the possibility of a special fraud. For example, the monitoring unit increases the likelihood of fraud by detecting phrases and speaking styles commonly used by fraudsters. The judgment unit determines the likelihood of a special fraud based on the content of the call monitored by the monitoring unit. The judgment unit analyzes the content of a call using, for example, a generation AI, and determines whether there is a high probability of a special fraud. For example, the judgment unit increases the likelihood of fraud by detecting phrases and speaking styles commonly used by fraudsters. The notification unit notifies the user if the judgment unit determines that there is a high probability of a special fraud. The notification unit notifies the user using, for example, vibration or a screen message. For example, the notification unit can notify the user with vibration. The notification unit can also notify the user with a screen message. The notification unit can also notify the user with voice. The disconnection unit automatically disconnects the call when notified by the notification unit. The disconnection unit can, for example, automatically end a call when it detects a special fraud. The disconnection unit can also be used by the user to manually end a call. Furthermore, the disconnection unit can automatically end a call when it has finished. The alert unit, when notified by the notification unit, distributes alerts to pre-registered contacts, such as family members. The alert unit can also distribute alerts to relevant parties. Furthermore, the alert unit can distribute alerts to emergency contacts. As a result, the special fraud prevention system according to this embodiment can prevent damage from special fraud and reduce the number of fraud cases.

[0030] The monitoring unit monitors call content in real time. For example, the monitoring unit uses generative AI to analyze call content and determine the possibility of a special fraud. Specifically, the generative AI uses natural language processing technology to convert call content into text and then analyzes that text. The generative AI has a learning model to detect phrases, speaking styles, specific keywords, and contexts commonly used by fraudsters. For example, if phrases such as "Please transfer the money" or "This is urgent" appear frequently, it will be determined that there is a high possibility of fraud. The generative AI can also analyze the tone of the call and the speaker's emotions. Fraudsters often speak in a tone that conveys tension or anxiety, so detecting these characteristics can further increase the likelihood of fraud. The monitoring unit transmits these analysis results to the decision-making unit in real time, enabling immediate action. Furthermore, the monitoring unit is equipped with a call recording function, which can be used later for detailed analysis and as evidence. This allows the monitoring unit to monitor call content in detail and detect signs of fraud early.

[0031] The judgment unit determines the possibility of a special fraud based on the call content monitored by the monitoring unit. The judgment unit analyzes the call content using, for example, a generative AI to determine whether there is a high probability of a special fraud. Specifically, the generative AI scores the likelihood of fraud based on the analysis results sent from the monitoring unit. The generative AI refers to a database of past fraud cases and identifies call content with similar patterns and characteristics. For example, it increases the likelihood of fraud by detecting phrases and speaking styles commonly used by fraudsters, as well as specific keywords and contexts. Furthermore, the generative AI can further increase the likelihood of fraud by analyzing the tone of the call and the speaker's emotions. Based on these analysis results, the judgment unit determines whether there is a high probability of fraud and sends the result to the notification unit. If the judgment unit determines that there is a high probability of fraud, it immediately notifies the notification unit and issues a warning to the user. In addition, even if the likelihood of fraud is low, the judgment unit can record the call content and use it later for detailed analysis or as evidence. This allows the judgment unit to analyze the call content in detail and determine the likelihood of fraud with high accuracy.

[0032] The notification unit notifies the user if the judgment unit determines that there is a high probability of a special type of fraud. The notification unit notifies the user, for example, through vibration or on-screen messages. Specifically, the notification unit issues warnings to the user's smartphone or device using methods such as vibration, on-screen messages, and voice notifications. For example, it can notify the user with vibration. The notification unit can also notify the user with on-screen messages. For example, it can display a message such as, "This may be a scam. Please be careful." The notification unit can also notify the user with voice. For example, it can play a voice message such as, "This may be a scam. Please end the call." The notification unit can combine these notification methods to issue warnings to the user quickly and reliably. Furthermore, the notification unit can collect user feedback and continuously improve the accuracy and effectiveness of the notification content. As a result, the notification unit can issue warnings to the user quickly and reliably and prevent them from becoming victims of fraud.

[0033] The disconnection unit automatically ends a call when notified by the notification unit. For example, the disconnection unit can automatically end a call when it detects a scam. Specifically, the disconnection unit has the function of immediately ending a call when it receives a signal from the notification unit. For example, if it is determined that there is a high possibility of fraud, the disconnection unit will automatically end the call, protecting the user from fraud. The disconnection unit can also be used by the user to end a call manually. For example, if a user feels that there is a possibility of fraud during a call, they can end the call by pressing a button. Furthermore, the disconnection unit can also automatically end a call when it has ended. For example, it can automatically end a call if it has continued for a certain period of time or if certain conditions are met. This allows the disconnection unit to quickly end calls that are likely to be fraudulent, protecting the user from fraud.

[0034] The alert unit, upon notification from the notification unit, sends alerts to pre-registered contacts, such as family members. Specifically, if a user receives a call that is likely to be a scam, the alert unit sends an alert to pre-registered family, friends, and emergency contacts. For example, alerts can be delivered via SMS, email, or voice call. The alert unit can also deliver alerts to relevant parties. For example, it can send alerts to the user's workplace or school to encourage a quick response. The alert unit can also deliver alerts to emergency contacts. For example, it can send alerts to the police or emergency services to encourage a quick response. This allows the alert unit to quickly and reliably notify relevant parties when a user receives a call that is likely to be a scam, thereby preventing the user from becoming a victim of fraud.

[0035] The monitoring unit can analyze the frequency of occurrence of specific keywords and phrases in real time while monitoring call content. For example, the monitoring unit's generating AI can analyze the frequency of occurrence of keywords such as "money" and "bank transfer" to determine the possibility of fraud. The monitoring unit can also analyze the frequency of occurrence of phrases such as "hurry" and "secret" to determine the possibility of fraud. Furthermore, the monitoring unit can analyze the frequency of occurrence of keywords such as "police" and "lawyer" to determine the possibility of fraud. In this way, the likelihood of fraud can be increased by analyzing the frequency of occurrence of specific keywords and phrases. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input text data of the call content into the generating AI and have the generating AI perform the analysis of keyword and phrase frequency.

[0036] The monitoring unit can analyze background and ambient sounds during call monitoring to identify elements that increase the likelihood of fraud. For example, the monitoring unit's generating AI can identify ambient sounds that are likely to be associated with fraud (e.g., office noise) from the background sounds during a call. The monitoring unit can also use the generating AI to identify sounds that are likely to be associated with fraud (e.g., voices from other calls) from the ambient sounds during a call. Furthermore, the monitoring unit can use the generating AI to identify sounds that are likely to be associated with fraud (e.g., traffic noise) from the background sounds during a call. In this way, by analyzing background and ambient sounds, elements that increase the likelihood of fraud can be identified. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input the audio data from a call into the generating AI and have the generating AI perform the analysis of background and ambient sounds.

[0037] The monitoring unit can analyze the tone and speed of the caller's voice when monitoring the content of a call and determine the possibility of fraud. For example, the monitoring unit can determine the possibility of fraud if the generating AI detects a sudden change in the caller's voice tone. The monitoring unit can also determine the possibility of fraud if the generating AI detects a sudden increase in the caller's speaking speed. Furthermore, the monitoring unit can determine the possibility of fraud if the generating AI detects an unnaturally high pitch in the caller's voice tone. In this way, the possibility of fraud can be determined by analyzing the tone and speed of the caller's voice. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input the caller's voice data into the generating AI and have the generating AI perform an analysis of the voice tone and speed.

[0038] The monitoring unit can improve the accuracy of its monitoring by referring to the caller's past call history when monitoring call content. For example, the monitoring unit's generating AI can refer to the caller's past call history to identify patterns that are likely to be fraudulent. The monitoring unit can also refer to the caller's past call history to identify patterns that are unlikely to be fraudulent. Furthermore, the monitoring unit can improve the accuracy of its monitoring by referring to the caller's past call history. In this way, the accuracy of monitoring can be improved by referring to the caller's past call history. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input the caller's past call history data into the generating AI and have the generating AI perform the improvement of monitoring accuracy.

[0039] The judgment unit can improve the accuracy of its judgments by learning specific ways of speaking and patterns commonly used by scammers when analyzing call content. For example, the judgment unit can improve the accuracy of its judgments by having the generating AI learn phrases such as "hurry up" and "secret" that scammers often use. The judgment unit can also improve the accuracy of its judgments by having the generating AI learn keywords such as "money" and "bank transfer" that scammers often use. Furthermore, the judgment unit can improve the accuracy of its judgments by having the generating AI learn keywords such as "police" and "lawyer" that scammers often use. In this way, the accuracy of judgments can be improved by learning specific ways of speaking and patterns commonly used by scammers. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input text data of the call content into the generating AI and have the generating AI perform the learning of specific ways of speaking and patterns.

[0040] The decision unit can determine the possibility of fraud by considering the context and flow of the conversation when analyzing the content of the call. For example, the decision unit can use a generating AI to identify a flow of conversation that is likely to be fraudulent from the context of the call. The decision unit can also use a generating AI to identify a flow of conversation that is unlikely to be fraudulent from the context of the call. Furthermore, the decision unit can use a generating AI to determine the possibility of fraud from the context of the call. In this way, by considering the context and flow of the conversation, the possibility of fraud can be determined more accurately. Some or all of the above processing in the decision unit may be performed using AI, for example, or without using AI. For example, the decision unit can input text data of the call content into a generating AI and have the generating AI perform analysis of the context and flow of conversation.

[0041] The notification unit can select different notification methods depending on the urgency if there is a high probability of fraud. For example, if the probability of fraud is very high, the generating AI will notify using both vibration and a screen message. If the probability of fraud is moderate, the generating AI can also notify using only a screen message. If the probability of fraud is low, the generating AI can also notify using only vibration. This allows for more appropriate notifications by selecting the notification method according to the probability of fraud. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input probability data of the probability of fraud into the generating AI and have the generating AI select a notification method according to the urgency.

[0042] The notification unit can select the optimal notification method by referring to the user's past response history when sending a notification. For example, if the user has previously responded to a vibration notification, the generating AI will notify via vibration. The notification unit can also notify via screen message if the user has previously responded to a screen message notification. Furthermore, if the user has previously responded to an audio notification, the generating AI can notify via audio. This allows the notification unit to select the optimal notification method by referring to the user's past response history. Some or all of the above processing in the notification unit may be performed using AI, or without AI. For example, the notification unit can input the user's past response history data into the generating AI and have the generating AI select the optimal notification method.

[0043] The notification unit can select the optimal notification method based on the user's device settings and environment when a notification is sent. For example, if the user is using a smartphone, the generation AI will notify the user via a screen message. If the user is using a tablet, the generation AI can also provide a notification method optimized for a larger screen. Furthermore, if the user is using a smartwatch, the generation AI can provide a concise and highly visible notification method. This allows for more effective notifications by selecting the optimal notification method based on the user's device settings and environment. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input the user's device setting data into the generation AI and have the generation AI select the optimal notification method.

[0044] The notification unit can customize the content of notifications by considering the user's current activity status. For example, if the user is exercising, the generating AI can provide a concise and highly visible notification. If the user is working, the generating AI can provide a detailed notification. If the user is resting, the generating AI can provide a relaxing notification. This allows for the provision of more appropriate notification content by considering the user's current activity status. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input user activity data into the generating AI and have the generating AI customize the notification content.

[0045] The disconnection unit can send a warning message to the caller when the call is disconnected if there is a high probability of fraud. For example, if the probability of fraud is very high, the disconnection unit's generating AI will send a warning message to the caller. The disconnection unit can also send a warning message if the probability of fraud is moderate, or if the probability of fraud is low. This allows for the suppression of fraudulent activity by sending a warning message when there is a high probability of fraud. Some or all of the above processing in the disconnection unit may be performed using AI, for example, or without AI. For example, the disconnection unit can input probability data of the probability of fraud into the generating AI and have the generating AI execute the sending of a warning message.

[0046] The disconnection unit can select the optimal disconnection method by referring to the user's past call history when a call is disconnected. For example, if the user has previously disconnected a call immediately, the generating AI will disconnect the call immediately. Alternatively, if the user has previously disconnected a call with a slight delay, the generating AI can disconnect the call with a slight delay. Furthermore, if the user has previously not disconnected a call, the generating AI can choose not to disconnect the call. This allows the optimal disconnection method to be selected by referring to the user's past call history. Some or all of the above processing in the disconnection unit may be performed using AI, for example, or without AI. For example, the disconnection unit can input the user's past call history data into the generating AI and have the generating AI select the optimal disconnection method.

[0047] The disconnection unit can analyze the characteristics and speaking style of the caller to adjust the timing of the disconnection. For example, if the characteristics of the caller's voice indicate a potential scam, the generating AI will immediately disconnect the call. The disconnection unit can also immediately disconnect the call if the speaking style of the caller indicates a potential scam. Furthermore, the disconnection unit can choose not to disconnect the call if the characteristics of the caller's voice do not indicate a potential scam. This allows for disconnecting the call at a more appropriate time by analyzing the characteristics and speaking style of the caller. Some or all of the above processing in the disconnection unit may be performed using AI, for example, or without AI. For example, the disconnection unit can input the caller's voice data into the generating AI and have the generating AI perform an analysis of the voice characteristics and speaking style.

[0048] The disconnection unit can select the optimal disconnection method by referring to the caller's past behavior patterns when a call is disconnected. For example, if the caller's past behavior patterns indicate a possibility of fraud, the generating AI will immediately disconnect the call. Alternatively, if the caller's past behavior patterns do not indicate a possibility of fraud, the generating AI may not disconnect the call. Furthermore, if the caller's past behavior patterns are unknown, the disconnection unit can decide whether or not to disconnect the call. In this way, the optimal disconnection method can be selected by referring to the caller's past behavior patterns. Some or all of the above processing in the disconnection unit may be performed using AI, for example, or without AI. For example, the disconnection unit can input the caller's past behavior pattern data into the generating AI and have the generating AI select the optimal disconnection method.

[0049] The alert unit can select different alert methods depending on the urgency when an alert is likely to be fraudulent. For example, if the likelihood of fraud is very high, the generating AI can deliver an alert using both vibration and a screen message. If the likelihood of fraud is moderate, the generating AI can deliver an alert using only a screen message. If the likelihood of fraud is low, the generating AI can deliver an alert using only vibration. This allows for more appropriate alerts by selecting the alert method according to the likelihood of fraud. Some or all of the above processing in the alert unit may be performed using AI, for example, or without AI. For example, the alert unit can input probability data of the likelihood of fraud into the generating AI and have the generating AI select an alert method according to the urgency.

[0050] The alert unit can select the optimal alert method by referring to the past response history of family members and relevant parties when delivering an alert. For example, if a family member has previously responded to a vibration alert, the generating AI will deliver an alert via vibration. The alert unit can also deliver an alert via screen message if a family member has previously responded to a screen message alert. Furthermore, if a family member has previously responded to an audio alert, the generating AI can deliver an audio alert. This allows the system to select the optimal alert method by referring to the past response history of family members and relevant parties. Some or all of the above processing in the alert unit may be performed using AI, for example, or without AI. For example, the alert unit can input past response history data of family members and relevant parties into the generating AI and have the generating AI select the optimal alert method.

[0051] The alert unit can select the optimal alert method based on the device settings and environment of family members and stakeholders when delivering an alert. For example, if a family member is using a smartphone, the generation AI will deliver the alert as a screen message. If a family member is using a tablet, the generation AI can also provide an alert method optimized for a larger screen. Furthermore, if a family member is using a smartwatch, the generation AI can provide a concise and highly visible alert method. This allows for more effective alerts by selecting the optimal alert method based on the device settings and environment of family members and stakeholders. Some or all of the above processing in the alert unit may be performed using AI, for example, or without AI. For example, the alert unit can input device setting data of family members and stakeholders into the generation AI and have the generation AI select the optimal alert method.

[0052] The alert unit can customize the content of alerts when they are delivered, taking into account the current activity status of family members and related parties. For example, if a family member is exercising, the AI ​​generating the alert can provide a concise and highly visible alert. The AI ​​can also provide a more detailed alert if the family member is working. Furthermore, the AI ​​can provide a relaxed alert if the family member is resting. This allows for the provision of more appropriate alert content by considering the current activity status of family members and related parties. Some or all of the above processing in the alert unit may be performed using AI, for example, or without AI. For example, the alert unit can input activity status data of family members and related parties into the AI ​​generating alert and have the AI ​​customize the alert content.

[0053] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0054] The special fraud prevention system can also be equipped with a speech recognition unit. The speech recognition unit converts the audio during a call into text and provides that text data to the monitoring unit. For example, the speech recognition unit can convert the audio during a call into text in real time, and the monitoring unit can analyze that text data to determine the possibility of fraud. The speech recognition unit can also highlight specific keywords or phrases when converting the audio during a call into text. This allows the monitoring unit to determine the possibility of fraud more quickly. Furthermore, the speech recognition unit can also analyze the tone and speed of the other party's voice when converting the audio during a call into text. This allows the monitoring unit to determine the possibility of fraud more accurately.

[0055] The special fraud prevention system may also be equipped with a location information acquisition unit. The location information acquisition unit acquires the location information of the user during a call and provides this information to the monitoring unit. For example, if the user during a call is in a specific location, the location information acquisition unit can provide this information to the monitoring unit, which can then use it as a reference when determining the possibility of fraud. The location information acquisition unit can also provide the monitoring unit with information about the user's movement if the user during the call is moving. This allows the monitoring unit to more accurately determine the possibility of fraud. Furthermore, if the user during a call enters a specific area, the location information acquisition unit can provide this information to the monitoring unit, which can then consider it as a factor that increases the likelihood of fraud.

[0056] The special fraud prevention system may also include a call history analysis unit. The call history analysis unit analyzes past call history and provides that information to the monitoring unit. For example, the call history analysis unit can identify patterns that are highly likely to be fraudulent from past call history and provide that information to the monitoring unit. It can also identify patterns that are less likely to be fraudulent from past call history and provide that information to the monitoring unit. Furthermore, the call history analysis unit can analyze the frequency of occurrence of specific keywords or phrases from past call history and provide that information to the monitoring unit. This allows the monitoring unit to more accurately determine the likelihood of fraud.

[0057] The special fraud prevention system may also include a caller recognition unit. The caller recognition unit recognizes the caller's voice and provides that information to the monitoring unit. For example, the caller recognition unit can analyze the caller's voice in real time and compare it with past call history to determine the possibility of fraud. The caller recognition unit can also analyze the characteristics of the caller's voice and provide that information to the monitoring unit. Furthermore, the caller recognition unit can analyze the tone and speed of the caller's voice and provide that information to the monitoring unit. This allows the monitoring unit to more accurately determine the possibility of fraud.

[0058] The special fraud prevention system may also be equipped with a call content storage unit. The call content storage unit records the content of conversations and stores the data. For example, the call content storage unit can record conversations in real time and provide the data to the monitoring unit, which can be used as a reference when determining the possibility of fraud. The call content storage unit can also highlight specific keywords or phrases when recording conversations. This allows the monitoring unit to determine the possibility of fraud more quickly. Furthermore, the call content storage unit can also analyze the tone and speed of the other party's voice when recording conversations. This allows the monitoring unit to determine the possibility of fraud more accurately.

[0059] The special fraud prevention system can also be equipped with a call content translation unit. The call content translation unit translates the call content in real time and provides the translated data to the monitoring unit. For example, the call content translation unit can translate the content of a call conducted in a foreign language in real time and provide the translated data to the monitoring unit, which can help determine the possibility of fraud. The call content translation unit can also highlight specific keywords or phrases when translating them. This allows the monitoring unit to determine the possibility of fraud more quickly. Furthermore, the call content translation unit can also reflect the tone and speed of the caller's voice in the translated data. This allows the monitoring unit to determine the possibility of fraud more accurately.

[0060] The special fraud prevention system may also include a call content summarization unit. The call content summarization unit summarizes the call content in real time and provides the summary data to the monitoring unit. For example, by summarizing the call content in real time and providing the summary data to the monitoring unit, the possibility of fraud can be determined. The call content summarization unit can also highlight specific keywords or phrases when summarizing. This allows the monitoring unit to determine the possibility of fraud more quickly. Furthermore, the call content summarization unit can also reflect the tone and speed of the caller's voice in the summary data. This allows the monitoring unit to determine the possibility of fraud more accurately.

[0061] The special fraud prevention system may also include a call content analysis unit. The call content analysis unit analyzes call content in real time and provides the analysis data to the monitoring unit. For example, by analyzing the call content in real time and analyzing the frequency of occurrence of specific keywords and phrases, the call content analysis unit can determine the possibility of fraud. The call content analysis unit can also analyze the tone and speed of the caller's voice and provide that information to the monitoring unit. Furthermore, the call content analysis unit can analyze the context and flow of the conversation and provide that information to the monitoring unit. This allows the monitoring unit to more accurately determine the possibility of fraud.

[0062] The special fraud prevention system may also include a call content evaluation unit. The call content evaluation unit evaluates the call content in real time and provides the evaluation data to the monitoring unit. For example, the call content evaluation unit can evaluate the call content in real time and determine whether there is a high probability of fraud. The call content evaluation unit can also evaluate the frequency of occurrence of specific keywords or phrases and provide that information to the monitoring unit. Furthermore, the call content evaluation unit can also evaluate the tone and speed of the caller's voice and provide that information to the monitoring unit. This allows the monitoring unit to more accurately determine the likelihood of fraud.

[0063] The following briefly describes the processing flow for example form 1.

[0064] Step 1: The monitoring unit monitors call content in real time. For example, it uses generation AI to analyze call content and detect phrases and speaking styles commonly used by scammers, thereby increasing the likelihood of a special type of fraud. Step 2: The judgment unit determines the possibility of a special fraud based on the call content monitored by the monitoring unit. For example, it analyzes the call content using a generation AI and detects phrases and speaking styles commonly used by fraudsters to determine whether there is a high probability of a special fraud. Step 3: The notification unit notifies the user if the judgment unit determines that there is a high probability of a special fraud. For example, the user can be notified by vibration, on-screen message, or voice. Step 4: The disconnection unit automatically ends the call when notified by the notification unit. For example, it can automatically end the call when it detects a scam. The user can also manually end the call. Step 5: The alert unit, upon receiving a notification from the notification unit, sends an alert to pre-registered contacts, such as family members. For example, alerts can be sent to family members, relevant parties, or emergency contacts.

[0065] (Example of form 2) The fraud prevention system according to an embodiment of the present invention is an alert function for smartphones to prevent damage from special fraud. This fraud prevention system uses a generating AI to monitor the content of a call in real time when a call is received on the user's smartphone. If the AI ​​determines that the call content is highly likely to be a special fraud, it immediately notifies the user via vibration, on-screen message, etc. Optional features include an automatic call termination function when a special fraud is detected, and a function to send alerts to pre-registered contacts such as family members. For example, when a call is received on the user's smartphone, the generating AI monitors the content in real time. The AI ​​analyzes the call content to determine if it is likely to be a special fraud. For example, it can detect phrases and speaking styles commonly used by fraudsters to increase the likelihood of fraud. Next, if the generating AI analyzes the call content and determines that it is highly likely to be a special fraud, it immediately notifies the user. Notification methods include vibration and on-screen messages. This allows the user to recognize the possibility of fraud during the call and take appropriate action. Furthermore, an optional feature is available that automatically terminates the call when a special fraud is detected. This feature reduces the risk for users to continue conversations with scammers. It also allows for alerts to be sent to pre-registered contacts, such as family members. This enables family and relevant parties to respond quickly before the user becomes a victim of fraud. This system is expected to prevent special fraud and reduce the number of fraud cases. Furthermore, since it is available as an option for smartphone users of specific telecommunications carriers, it can also contribute to the carriers' revenue. In summary, this special fraud prevention system can prevent special fraud and reduce the number of fraud cases.

[0066] The special fraud prevention system according to the embodiment comprises a monitoring unit, a judgment unit, a notification unit, a disconnection unit, and an alert unit. The monitoring unit monitors the content of a call in real time. The monitoring unit analyzes the content of a call using, for example, a generation AI, and determines the possibility of a special fraud. For example, the monitoring unit increases the likelihood of fraud by detecting phrases and speaking styles commonly used by fraudsters. The judgment unit determines the likelihood of a special fraud based on the content of the call monitored by the monitoring unit. The judgment unit analyzes the content of a call using, for example, a generation AI, and determines whether there is a high probability of a special fraud. For example, the judgment unit increases the likelihood of fraud by detecting phrases and speaking styles commonly used by fraudsters. The notification unit notifies the user if the judgment unit determines that there is a high probability of a special fraud. The notification unit notifies the user using, for example, vibration or a screen message. For example, the notification unit can notify the user with vibration. The notification unit can also notify the user with a screen message. The notification unit can also notify the user with voice. The disconnection unit automatically disconnects the call when notified by the notification unit. The disconnection unit can, for example, automatically end a call when it detects a special fraud. The disconnection unit can also be used by the user to manually end a call. Furthermore, the disconnection unit can automatically end a call when it has finished. The alert unit, when notified by the notification unit, distributes alerts to pre-registered contacts, such as family members. The alert unit can also distribute alerts to relevant parties. Furthermore, the alert unit can distribute alerts to emergency contacts. As a result, the special fraud prevention system according to this embodiment can prevent damage from special fraud and reduce the number of fraud cases.

[0067] The monitoring unit monitors call content in real time. For example, the monitoring unit uses generative AI to analyze call content and determine the possibility of a special fraud. Specifically, the generative AI uses natural language processing technology to convert call content into text and then analyzes that text. The generative AI has a learning model to detect phrases, speaking styles, specific keywords, and contexts commonly used by fraudsters. For example, if phrases such as "Please transfer the money" or "This is urgent" appear frequently, it will be determined that there is a high possibility of fraud. The generative AI can also analyze the tone of the call and the speaker's emotions. Fraudsters often speak in a tone that conveys tension or anxiety, so detecting these characteristics can further increase the likelihood of fraud. The monitoring unit transmits these analysis results to the decision-making unit in real time, enabling immediate action. Furthermore, the monitoring unit is equipped with a call recording function, which can be used later for detailed analysis and as evidence. This allows the monitoring unit to monitor call content in detail and detect signs of fraud early.

[0068] The judgment unit determines the possibility of a special fraud based on the call content monitored by the monitoring unit. The judgment unit analyzes the call content using, for example, a generative AI to determine whether there is a high probability of a special fraud. Specifically, the generative AI scores the likelihood of fraud based on the analysis results sent from the monitoring unit. The generative AI refers to a database of past fraud cases and identifies call content with similar patterns and characteristics. For example, it increases the likelihood of fraud by detecting phrases and speaking styles commonly used by fraudsters, as well as specific keywords and contexts. Furthermore, the generative AI can further increase the likelihood of fraud by analyzing the tone of the call and the speaker's emotions. Based on these analysis results, the judgment unit determines whether there is a high probability of fraud and sends the result to the notification unit. If the judgment unit determines that there is a high probability of fraud, it immediately notifies the notification unit and issues a warning to the user. In addition, even if the likelihood of fraud is low, the judgment unit can record the call content and use it later for detailed analysis or as evidence. This allows the judgment unit to analyze the call content in detail and determine the likelihood of fraud with high accuracy.

[0069] The notification unit notifies the user if the judgment unit determines that there is a high probability of a special type of fraud. The notification unit notifies the user, for example, through vibration or on-screen messages. Specifically, the notification unit issues warnings to the user's smartphone or device using methods such as vibration, on-screen messages, and voice notifications. For example, it can notify the user with vibration. The notification unit can also notify the user with on-screen messages. For example, it can display a message such as, "This may be a scam. Please be careful." The notification unit can also notify the user with voice. For example, it can play a voice message such as, "This may be a scam. Please end the call." The notification unit can combine these notification methods to issue warnings to the user quickly and reliably. Furthermore, the notification unit can collect user feedback and continuously improve the accuracy and effectiveness of the notification content. As a result, the notification unit can issue warnings to the user quickly and reliably and prevent them from becoming victims of fraud.

[0070] The disconnection unit automatically ends a call when notified by the notification unit. For example, the disconnection unit can automatically end a call when it detects a scam. Specifically, the disconnection unit has the function of immediately ending a call when it receives a signal from the notification unit. For example, if it is determined that there is a high possibility of fraud, the disconnection unit will automatically end the call, protecting the user from fraud. The disconnection unit can also be used by the user to end a call manually. For example, if a user feels that there is a possibility of fraud during a call, they can end the call by pressing a button. Furthermore, the disconnection unit can also automatically end a call when it has ended. For example, it can automatically end a call if it has continued for a certain period of time or if certain conditions are met. This allows the disconnection unit to quickly end calls that are likely to be fraudulent, protecting the user from fraud.

[0071] The alert unit, upon notification from the notification unit, sends alerts to pre-registered contacts, such as family members. Specifically, if a user receives a call that is likely to be a scam, the alert unit sends an alert to pre-registered family, friends, and emergency contacts. For example, alerts can be delivered via SMS, email, or voice call. The alert unit can also deliver alerts to relevant parties. For example, it can send alerts to the user's workplace or school to encourage a quick response. The alert unit can also deliver alerts to emergency contacts. For example, it can send alerts to the police or emergency services to encourage a quick response. This allows the alert unit to quickly and reliably notify relevant parties when a user receives a call that is likely to be a scam, thereby preventing the user from becoming a victim of fraud.

[0072] The monitoring unit can estimate the emotions of the user during a call and adjust the accuracy of monitoring based on the estimated emotions. For example, if the user during a call is tense, the generating AI can detect the emotion and improve the accuracy of monitoring. The monitoring unit can also detect the emotion of the user during a call when they are relaxed and return the accuracy to normal. Furthermore, if the user during a call is angry, the generating AI can detect the emotion and maximize the accuracy of monitoring. This allows for more accurate monitoring by adjusting the accuracy of monitoring according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the monitoring unit may be performed using AI, or not. For example, the monitoring unit can input the voice data of the user during a call into the generating AI and have the generating AI perform emotion estimation.

[0073] The monitoring unit can analyze the frequency of occurrence of specific keywords and phrases in real time while monitoring call content. For example, the monitoring unit's generating AI can analyze the frequency of occurrence of keywords such as "money" and "bank transfer" to determine the possibility of fraud. The monitoring unit can also analyze the frequency of occurrence of phrases such as "hurry" and "secret" to determine the possibility of fraud. Furthermore, the monitoring unit can analyze the frequency of occurrence of keywords such as "police" and "lawyer" to determine the possibility of fraud. In this way, the likelihood of fraud can be increased by analyzing the frequency of occurrence of specific keywords and phrases. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input text data of the call content into the generating AI and have the generating AI perform the analysis of keyword and phrase frequency.

[0074] The monitoring unit can analyze background and ambient sounds during call monitoring to identify elements that increase the likelihood of fraud. For example, the monitoring unit's generating AI can identify ambient sounds that are likely to be associated with fraud (e.g., office noise) from the background sounds during a call. The monitoring unit can also use the generating AI to identify sounds that are likely to be associated with fraud (e.g., voices from other calls) from the ambient sounds during a call. Furthermore, the monitoring unit can use the generating AI to identify sounds that are likely to be associated with fraud (e.g., traffic noise) from the background sounds during a call. In this way, by analyzing background and ambient sounds, elements that increase the likelihood of fraud can be identified. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input the audio data from a call into the generating AI and have the generating AI perform the analysis of background and ambient sounds.

[0075] The monitoring unit can estimate the emotions of a user during a call and determine monitoring priorities based on the estimated emotions. For example, if the user during a call is tense, the generating AI can detect the emotion and increase the monitoring priority. Similarly, if the user during a call is relaxed, the generating AI can detect the emotion and return the monitoring priority to normal. Furthermore, if the user during a call is angry, the generating AI can detect the emotion and maximize the monitoring priority. This allows for more effective monitoring by determining monitoring priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the monitoring unit may be performed using AI or not. For example, the monitoring unit can input the voice data of the user during a call into the generating AI and have the generating AI perform emotion estimation.

[0076] The monitoring unit can analyze the tone and speed of the caller's voice when monitoring the content of a call and determine the possibility of fraud. For example, the monitoring unit can determine the possibility of fraud if the generating AI detects a sudden change in the caller's voice tone. The monitoring unit can also determine the possibility of fraud if the generating AI detects a sudden increase in the caller's speaking speed. Furthermore, the monitoring unit can determine the possibility of fraud if the generating AI detects an unnaturally high pitch in the caller's voice tone. In this way, the possibility of fraud can be determined by analyzing the tone and speed of the caller's voice. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input the caller's voice data into the generating AI and have the generating AI perform an analysis of the voice tone and speed.

[0077] The monitoring unit can improve the accuracy of its monitoring by referring to the caller's past call history when monitoring call content. For example, the monitoring unit's generating AI can refer to the caller's past call history to identify patterns that are likely to be fraudulent. The monitoring unit can also refer to the caller's past call history to identify patterns that are unlikely to be fraudulent. Furthermore, the monitoring unit can improve the accuracy of its monitoring by referring to the caller's past call history. In this way, the accuracy of monitoring can be improved by referring to the caller's past call history. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input the caller's past call history data into the generating AI and have the generating AI perform the improvement of monitoring accuracy.

[0078] The decision unit can estimate the emotions of the user during a call and adjust the criteria for determining the likelihood of fraud based on the estimated emotions. For example, if the user during the call is tense, the decision unit's generating AI can detect the emotion and adjust the criteria to increase the likelihood of fraud. Similarly, if the user during the call is relaxed, the decision unit can have the generating AI detect the emotion and adjust the criteria to return the likelihood of fraud to normal. Furthermore, if the user during the call is angry, the decision unit can have the generating AI detect the emotion and adjust the criteria to maximize the likelihood of fraud. This allows for more accurate judgments by adjusting the criteria for determining the likelihood of fraud according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating 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 decision unit may be performed using AI, or not. For example, the decision unit can input the voice data of the user during the call into the generating AI and have the generating AI perform emotion estimation.

[0079] The judgment unit can improve the accuracy of its judgments by learning specific ways of speaking and patterns commonly used by scammers when analyzing call content. For example, the judgment unit can improve the accuracy of its judgments by having the generating AI learn phrases such as "hurry up" and "secret" that scammers often use. The judgment unit can also improve the accuracy of its judgments by having the generating AI learn keywords such as "money" and "bank transfer" that scammers often use. Furthermore, the judgment unit can improve the accuracy of its judgments by having the generating AI learn keywords such as "police" and "lawyer" that scammers often use. In this way, the accuracy of judgments can be improved by learning specific ways of speaking and patterns commonly used by scammers. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input text data of the call content into the generating AI and have the generating AI perform the learning of specific ways of speaking and patterns.

[0080] The decision unit can determine the possibility of fraud by considering the context and flow of the conversation when analyzing the content of the call. For example, the decision unit can use a generating AI to identify a flow of conversation that is likely to be fraudulent from the context of the call. The decision unit can also use a generating AI to identify a flow of conversation that is unlikely to be fraudulent from the context of the call. Furthermore, the decision unit can use a generating AI to determine the possibility of fraud from the context of the call. In this way, by considering the context and flow of the conversation, the possibility of fraud can be determined more accurately. Some or all of the above processing in the decision unit may be performed using AI, for example, or without using AI. For example, the decision unit can input text data of the call content into a generating AI and have the generating AI perform analysis of the context and flow of conversation.

[0081] The notification unit can estimate the emotions of the user during a call and adjust the notification method based on the estimated emotions. For example, if the user is tense during a call, the generation AI can detect the emotion and notify the user with vibration. The notification unit can also detect the emotion of the user when they are relaxed and notify them with a screen message. Furthermore, if the user is angry, the generation AI can detect the emotion and notify them with voice. This allows for more effective notifications by adjusting the notification method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generation AI. The generation 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 notification unit may be performed using AI, or not using AI. For example, the notification unit can input the voice data of the user during a call into the generation AI and have the generation AI perform emotion estimation.

[0082] The notification unit can select different notification methods depending on the urgency if there is a high probability of fraud. For example, if the probability of fraud is very high, the generating AI will notify using both vibration and a screen message. If the probability of fraud is moderate, the generating AI can also notify using only a screen message. If the probability of fraud is low, the generating AI can also notify using only vibration. This allows for more appropriate notifications by selecting the notification method according to the probability of fraud. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input probability data of the probability of fraud into the generating AI and have the generating AI select a notification method according to the urgency.

[0083] The notification unit can select the optimal notification method by referring to the user's past response history when sending a notification. For example, if the user has previously responded to a vibration notification, the generating AI will notify via vibration. The notification unit can also notify via screen message if the user has previously responded to a screen message notification. Furthermore, if the user has previously responded to an audio notification, the generating AI can notify via audio. This allows the notification unit to select the optimal notification method by referring to the user's past response history. Some or all of the above processing in the notification unit may be performed using AI, or without AI. For example, the notification unit can input the user's past response history data into the generating AI and have the generating AI select the optimal notification method.

[0084] The notification unit can estimate the emotions of the user during a call and adjust the timing of notifications based on the estimated emotions. For example, if the user during a call is tense, the generation AI can detect the emotion and send an immediate notification. The notification unit can also detect the emotion of the user during a call when they are relaxed and send a slightly delayed notification. Furthermore, if the user during a call is angry, the generation AI can detect the emotion and send an immediate notification. This allows for more effective notifications by adjusting the timing of notifications according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation 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 notification unit may be performed using AI, or not using AI. For example, the notification unit can input the voice data of the user during a call into the generation AI and have the generation AI perform emotion estimation.

[0085] The notification unit can select the optimal notification method based on the user's device settings and environment when a notification is sent. For example, if the user is using a smartphone, the generation AI will notify the user via a screen message. If the user is using a tablet, the generation AI can also provide a notification method optimized for a larger screen. Furthermore, if the user is using a smartwatch, the generation AI can provide a concise and highly visible notification method. This allows for more effective notifications by selecting the optimal notification method based on the user's device settings and environment. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input the user's device setting data into the generation AI and have the generation AI select the optimal notification method.

[0086] The notification unit can customize the content of notifications by considering the user's current activity status. For example, if the user is exercising, the generating AI can provide a concise and highly visible notification. If the user is working, the generating AI can provide a detailed notification. If the user is resting, the generating AI can provide a relaxing notification. This allows for the provision of more appropriate notification content by considering the user's current activity status. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input user activity data into the generating AI and have the generating AI customize the notification content.

[0087] The disconnection unit can estimate the emotions of the user during a call and adjust the timing of disconnecting the call based on the estimated emotions. For example, if the user is tense during a call, the disconnection unit's generating AI can detect the emotion and immediately disconnect the call. If the user is relaxed during a call, the disconnection unit's generating AI can detect the emotion and disconnect the call with a slight delay. If the user is angry during a call, the disconnection unit's generating AI can detect the emotion and immediately disconnect the call. This allows for more appropriate call disconnection timing by adjusting the timing according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating 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 disconnection unit may be performed using AI, or not using AI. For example, the disconnection unit can input the voice data of the user during a call into the generating AI and have the generating AI perform emotion estimation.

[0088] The disconnection unit can send a warning message to the caller when the call is disconnected if there is a high probability of fraud. For example, if the probability of fraud is very high, the disconnection unit's generating AI will send a warning message to the caller. The disconnection unit can also send a warning message if the probability of fraud is moderate, or if the probability of fraud is low. This allows for the suppression of fraudulent activity by sending a warning message when there is a high probability of fraud. Some or all of the above processing in the disconnection unit may be performed using AI, for example, or without AI. For example, the disconnection unit can input probability data of the probability of fraud into the generating AI and have the generating AI execute the sending of a warning message.

[0089] The disconnection unit can select the optimal disconnection method by referring to the user's past call history when a call is disconnected. For example, if the user has previously disconnected a call immediately, the generating AI will disconnect the call immediately. Alternatively, if the user has previously disconnected a call with a slight delay, the generating AI can disconnect the call with a slight delay. Furthermore, if the user has previously not disconnected a call, the generating AI can choose not to disconnect the call. This allows the optimal disconnection method to be selected by referring to the user's past call history. Some or all of the above processing in the disconnection unit may be performed using AI, for example, or without AI. For example, the disconnection unit can input the user's past call history data into the generating AI and have the generating AI select the optimal disconnection method.

[0090] The disconnection unit can estimate the emotions of the user during a call and determine the priority for disconnecting the call based on the estimated emotions. For example, if the user during the call is tense, the disconnection unit's generating AI can detect the emotion and increase the priority for disconnecting the call. Conversely, if the user during the call is relaxed, the disconnection unit's generating AI can detect the emotion and return the priority for disconnecting the call to normal. Furthermore, if the user during the call is angry, the disconnection unit's generating AI can detect the emotion and maximize the priority for disconnecting the call. This allows for disconnecting calls at a more appropriate time by determining the priority for disconnecting the call according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generating AI. The generating 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 disconnection unit may be performed using AI or not. For example, the disconnection unit can input the voice data of the user during the call into the generating AI and have the generating AI perform emotion estimation.

[0091] The disconnection unit can analyze the characteristics and speaking style of the caller to adjust the timing of the disconnection. For example, if the characteristics of the caller's voice indicate a potential scam, the generating AI will immediately disconnect the call. The disconnection unit can also immediately disconnect the call if the speaking style of the caller indicates a potential scam. Furthermore, the disconnection unit can choose not to disconnect the call if the characteristics of the caller's voice do not indicate a potential scam. This allows for disconnecting the call at a more appropriate time by analyzing the characteristics and speaking style of the caller. Some or all of the above processing in the disconnection unit may be performed using AI, for example, or without AI. For example, the disconnection unit can input the caller's voice data into the generating AI and have the generating AI perform an analysis of the voice characteristics and speaking style.

[0092] The disconnection unit can select the optimal disconnection method by referring to the caller's past behavior patterns when a call is disconnected. For example, if the caller's past behavior patterns indicate a possibility of fraud, the generating AI will immediately disconnect the call. Alternatively, if the caller's past behavior patterns do not indicate a possibility of fraud, the generating AI may not disconnect the call. Furthermore, if the caller's past behavior patterns are unknown, the disconnection unit can decide whether or not to disconnect the call. In this way, the optimal disconnection method can be selected by referring to the caller's past behavior patterns. Some or all of the above processing in the disconnection unit may be performed using AI, for example, or without AI. For example, the disconnection unit can input the caller's past behavior pattern data into the generating AI and have the generating AI select the optimal disconnection method.

[0093] The alert unit can estimate the emotions of the user during a call and adjust the content of the alert based on the estimated emotions. For example, if the user during a call is tense, the generation AI can detect the emotion and deliver a high-priority alert. The alert unit can also detect the emotion of the user during a call when they are relaxed and deliver a normal alert. Furthermore, if the user during a call is angry, the generation AI can detect the emotion and deliver a high-priority alert. This allows for more effective alerts by adjusting the content of the alert according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation 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 alert unit may be performed using AI, or not using AI. For example, the alert unit can input the voice data of the user during a call into the generation AI and have the generation AI perform emotion estimation.

[0094] The alert unit can select different alert methods depending on the urgency when an alert is likely to be fraudulent. For example, if the likelihood of fraud is very high, the generating AI can deliver an alert using both vibration and a screen message. If the likelihood of fraud is moderate, the generating AI can deliver an alert using only a screen message. If the likelihood of fraud is low, the generating AI can deliver an alert using only vibration. This allows for more appropriate alerts by selecting the alert method according to the likelihood of fraud. Some or all of the above processing in the alert unit may be performed using AI, for example, or without AI. For example, the alert unit can input probability data of the likelihood of fraud into the generating AI and have the generating AI select an alert method according to the urgency.

[0095] The alert unit can select the optimal alert method by referring to the past response history of family members and relevant parties when delivering an alert. For example, if a family member has previously responded to a vibration alert, the generating AI will deliver an alert via vibration. The alert unit can also deliver an alert via screen message if a family member has previously responded to a screen message alert. Furthermore, if a family member has previously responded to an audio alert, the generating AI can deliver an audio alert. This allows the system to select the optimal alert method by referring to the past response history of family members and relevant parties. Some or all of the above processing in the alert unit may be performed using AI, for example, or without AI. For example, the alert unit can input past response history data of family members and relevant parties into the generating AI and have the generating AI select the optimal alert method.

[0096] The alert unit can estimate the emotions of the user during a call and adjust the timing of alert delivery based on the estimated emotions. For example, if the user during a call is tense, the generation AI can detect the emotion and deliver an alert immediately. The alert unit can also detect the emotion of the user during a call when they are relaxed and deliver an alert with a slight delay. Furthermore, if the user during a call is angry, the generation AI can detect the emotion and deliver an alert immediately. This allows for more effective alerts by adjusting the timing of alert delivery according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generation AI. The generation 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 alert unit may be performed using AI or not. For example, the alert unit can input the voice data of the user during a call into the generation AI and have the generation AI perform emotion estimation.

[0097] The alert unit can select the optimal alert method based on the device settings and environment of family members and stakeholders when delivering an alert. For example, if a family member is using a smartphone, the generation AI will deliver the alert as a screen message. If a family member is using a tablet, the generation AI can also provide an alert method optimized for a larger screen. Furthermore, if a family member is using a smartwatch, the generation AI can provide a concise and highly visible alert method. This allows for more effective alerts by selecting the optimal alert method based on the device settings and environment of family members and stakeholders. Some or all of the above processing in the alert unit may be performed using AI, for example, or without AI. For example, the alert unit can input device setting data of family members and stakeholders into the generation AI and have the generation AI select the optimal alert method.

[0098] The alert unit can customize the content of alerts when they are delivered, taking into account the current activity status of family members and related parties. For example, if a family member is exercising, the AI ​​generating the alert can provide a concise and highly visible alert. The AI ​​can also provide a more detailed alert if the family member is working. Furthermore, the AI ​​can provide a relaxed alert if the family member is resting. This allows for the provision of more appropriate alert content by considering the current activity status of family members and related parties. Some or all of the above processing in the alert unit may be performed using AI, for example, or without AI. For example, the alert unit can input activity status data of family members and related parties into the AI ​​generating alert and have the AI ​​customize the alert content.

[0099] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0100] The special fraud prevention system can also be equipped with a speech recognition unit. The speech recognition unit converts the audio during a call into text and provides that text data to the monitoring unit. For example, the speech recognition unit can convert the audio during a call into text in real time, and the monitoring unit can analyze that text data to determine the possibility of fraud. The speech recognition unit can also highlight specific keywords or phrases when converting the audio during a call into text. This allows the monitoring unit to determine the possibility of fraud more quickly. Furthermore, the speech recognition unit can also analyze the tone and speed of the other party's voice when converting the audio during a call into text. This allows the monitoring unit to determine the possibility of fraud more accurately.

[0101] The special fraud prevention system may also be equipped with a location information acquisition unit. The location information acquisition unit acquires the location information of the user during a call and provides this information to the monitoring unit. For example, if the user during a call is in a specific location, the location information acquisition unit can provide this information to the monitoring unit, which can then use it as a reference when determining the possibility of fraud. The location information acquisition unit can also provide the monitoring unit with information about the user's movement if the user during the call is moving. This allows the monitoring unit to more accurately determine the possibility of fraud. Furthermore, if the user during a call enters a specific area, the location information acquisition unit can provide this information to the monitoring unit, which can then consider it as a factor that increases the likelihood of fraud.

[0102] The special fraud prevention system may also include an emotion estimation unit. The emotion estimation unit estimates the emotions of the user during a call and provides this information to the monitoring unit. For example, if the emotion estimation unit finds that the user is tense during the call, it can provide this information to the monitoring unit, which can then consider it as a factor that increases the likelihood of fraud. Similarly, if the user is relaxed during the call, the emotion estimation unit can provide this information to the monitoring unit, which can then consider it as a factor that lowers the likelihood of fraud. Furthermore, if the user is angry during the call, the emotion estimation unit can provide this information to the monitoring unit, which can then consider it as a factor that maximizes the likelihood of fraud. This allows the accuracy of monitoring to be adjusted according to the user's emotions.

[0103] The special fraud prevention system may also include a call history analysis unit. The call history analysis unit analyzes past call history and provides that information to the monitoring unit. For example, the call history analysis unit can identify patterns that are highly likely to be fraudulent from past call history and provide that information to the monitoring unit. It can also identify patterns that are less likely to be fraudulent from past call history and provide that information to the monitoring unit. Furthermore, the call history analysis unit can analyze the frequency of occurrence of specific keywords or phrases from past call history and provide that information to the monitoring unit. This allows the monitoring unit to more accurately determine the likelihood of fraud.

[0104] The special fraud prevention system may also include a caller recognition unit. The caller recognition unit recognizes the caller's voice and provides that information to the monitoring unit. For example, the caller recognition unit can analyze the caller's voice in real time and compare it with past call history to determine the possibility of fraud. The caller recognition unit can also analyze the characteristics of the caller's voice and provide that information to the monitoring unit. Furthermore, the caller recognition unit can analyze the tone and speed of the caller's voice and provide that information to the monitoring unit. This allows the monitoring unit to more accurately determine the possibility of fraud.

[0105] The special fraud prevention system may also be equipped with a call content storage unit. The call content storage unit records the content of conversations and stores the data. For example, the call content storage unit can record conversations in real time and provide the data to the monitoring unit, which can be used as a reference when determining the possibility of fraud. The call content storage unit can also highlight specific keywords or phrases when recording conversations. This allows the monitoring unit to determine the possibility of fraud more quickly. Furthermore, the call content storage unit can also analyze the tone and speed of the other party's voice when recording conversations. This allows the monitoring unit to determine the possibility of fraud more accurately.

[0106] The special fraud prevention system can also be equipped with a call content translation unit. The call content translation unit translates the call content in real time and provides the translated data to the monitoring unit. For example, the call content translation unit can translate the content of a call conducted in a foreign language in real time and provide the translated data to the monitoring unit, which can help determine the possibility of fraud. The call content translation unit can also highlight specific keywords or phrases when translating them. This allows the monitoring unit to determine the possibility of fraud more quickly. Furthermore, the call content translation unit can also reflect the tone and speed of the caller's voice in the translated data. This allows the monitoring unit to determine the possibility of fraud more accurately.

[0107] The special fraud prevention system may also include a call content summarization unit. The call content summarization unit summarizes the call content in real time and provides the summary data to the monitoring unit. For example, by summarizing the call content in real time and providing the summary data to the monitoring unit, the possibility of fraud can be determined. The call content summarization unit can also highlight specific keywords or phrases when summarizing. This allows the monitoring unit to determine the possibility of fraud more quickly. Furthermore, the call content summarization unit can also reflect the tone and speed of the caller's voice in the summary data. This allows the monitoring unit to determine the possibility of fraud more accurately.

[0108] The special fraud prevention system may also include a call content analysis unit. The call content analysis unit analyzes call content in real time and provides the analysis data to the monitoring unit. For example, by analyzing the call content in real time and analyzing the frequency of occurrence of specific keywords and phrases, the call content analysis unit can determine the possibility of fraud. The call content analysis unit can also analyze the tone and speed of the caller's voice and provide that information to the monitoring unit. Furthermore, the call content analysis unit can analyze the context and flow of the conversation and provide that information to the monitoring unit. This allows the monitoring unit to more accurately determine the possibility of fraud.

[0109] The special fraud prevention system may also include a call content evaluation unit. The call content evaluation unit evaluates the call content in real time and provides the evaluation data to the monitoring unit. For example, the call content evaluation unit can evaluate the call content in real time and determine whether there is a high probability of fraud. The call content evaluation unit can also evaluate the frequency of occurrence of specific keywords or phrases and provide that information to the monitoring unit. Furthermore, the call content evaluation unit can also evaluate the tone and speed of the caller's voice and provide that information to the monitoring unit. This allows the monitoring unit to more accurately determine the likelihood of fraud.

[0110] The following briefly describes the processing flow for example form 2.

[0111] Step 1: The monitoring unit monitors call content in real time. For example, it uses generation AI to analyze call content and detect phrases and speaking styles commonly used by scammers, thereby increasing the likelihood of a special type of fraud. Step 2: The judgment unit determines the possibility of a special fraud based on the call content monitored by the monitoring unit. For example, it analyzes the call content using a generation AI and detects phrases and speaking styles commonly used by fraudsters to determine whether there is a high probability of a special fraud. Step 3: The notification unit notifies the user if the judgment unit determines that there is a high probability of a special fraud. For example, the user can be notified by vibration, on-screen message, or voice. Step 4: The disconnection unit automatically ends the call when notified by the notification unit. For example, it can automatically end the call when it detects a scam. The user can also manually end the call. Step 5: The alert unit, upon receiving a notification from the notification unit, sends an alert to pre-registered contacts, such as family members. For example, alerts can be sent to family members, relevant parties, or emergency contacts.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] Each of the multiple elements described above, including the monitoring unit, decision unit, notification unit, disconnection unit, and alert unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the monitoring unit monitors the call content in real time using the camera 42 and microphone 38B of the smart device 14 and analyzes the call content using the control unit 46A. The decision unit is implemented in the identification processing unit 290 of the data processing unit 12, which analyzes the call content and determines the possibility of a special fraud. The notification unit is implemented in the control unit 46A of the smart device 14, which notifies the user via vibration or screen message. The disconnection unit is implemented in the identification processing unit 290 of the data processing unit 12, which automatically disconnects the call when a special fraud is detected. The alert unit is implemented in the control unit 46A of the smart device 14, which delivers an alert to pre-registered contacts such as family members. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0116] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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).

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] Each of the multiple elements described above, including the monitoring unit, decision unit, notification unit, disconnection unit, and alert unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the monitoring unit monitors the call content in real time using the camera 42 and microphone 238 of the smart glasses 214 and analyzes the call content using the control unit 46A. The decision unit is implemented in the identification processing unit 290 of the data processing unit 12, which analyzes the call content and determines the possibility of a special fraud. The notification unit is implemented in the control unit 46A of the smart glasses 214, which notifies the user with vibration or a screen message. The disconnection unit is implemented in the identification processing unit 290 of the data processing unit 12, which automatically disconnects the call when a special fraud is detected. The alert unit is implemented in the control unit 46A of the smart glasses 214, which delivers an alert to pre-registered contacts such as family members. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0132] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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).

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.).

[0144] 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.

[0145] 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.

[0146] 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.

[0147] Each of the multiple elements described above, including the monitoring unit, decision unit, notification unit, disconnection unit, and alert unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the monitoring unit monitors the call content in real time using the camera 42 and microphone 238 of the headset terminal 314 and analyzes the call content using the control unit 46A. The decision unit is implemented in the identification processing unit 290 of the data processing unit 12, which analyzes the call content and determines the possibility of a special fraud. The notification unit is implemented in the control unit 46A of the headset terminal 314, which notifies the user via vibration or on-screen message. The disconnection unit is implemented in the identification processing unit 290 of the data processing unit 12, which automatically disconnects the call when a special fraud is detected. The alert unit is implemented in the control unit 46A of the headset terminal 314, which delivers an alert to pre-registered contacts such as family members. 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.

[0148] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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).

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] Each of the multiple elements described above, including the monitoring unit, decision unit, notification unit, disconnection unit, and alert unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the monitoring unit monitors the call content in real time using the camera 42 and microphone 238 of the robot 414 and analyzes the call content using the control unit 46A. The decision unit is implemented in the identification processing unit 290 of the data processing unit 12, which analyzes the call content and determines the possibility of a special fraud. The notification unit is implemented in the control unit 46A of the robot 414, which notifies the user with vibration or a screen message. The disconnection unit is implemented in the identification processing unit 290 of the data processing unit 12, which automatically disconnects the call when a special fraud is detected. The alert unit is implemented in the control unit 46A of the robot 414, which sends an alert to pre-registered contacts such as family members. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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."

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] (Note 1) The monitoring department monitors the content of calls in real time, A determination unit that determines the possibility of special fraud based on the content of the call monitored by the aforementioned monitoring unit, A notification unit that notifies the user if the aforementioned determination unit determines that there is a high probability of a special fraud case, A disconnection unit that automatically ends the call when notified by the aforementioned notification unit, The system includes an alert unit that, when notified by the aforementioned notification unit, distributes an alert to a pre-registered contact, such as a family member. A system characterized by the following features. (Note 2) The aforementioned monitoring unit, The system estimates the user's emotions during a call and adjusts the monitoring accuracy based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned monitoring unit, When monitoring call content, the frequency of specific keywords and phrases is analyzed in real time. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned monitoring unit, When monitoring call content, the system analyzes background noise and ambient sounds to identify factors that increase the likelihood of fraud. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned monitoring unit, The system estimates the emotions of the user during a call and determines monitoring priorities based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned monitoring unit, During call monitoring, the tone and speed of the caller's voice are analyzed to determine the possibility of fraud. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned monitoring unit, When monitoring call content, the accuracy of monitoring is improved by referring to the caller's past call history. The system described in Appendix 1, characterized by the features described herein. (Note 8) The unit that makes the determination said, We estimate the emotions of users during calls and adjust the criteria for determining the likelihood of fraud based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The unit that makes the determination said, During call analysis, the system learns specific speaking styles and patterns commonly used by scammers to improve the accuracy of its judgments. The system described in Appendix 1, characterized by the features described herein. (Note 10) The unit that makes the determination said, When analyzing call content, the possibility of fraud is determined by considering the context and flow of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned notification unit, It estimates the user's emotions during a call and adjusts the notification method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned notification unit, When notifying, if there is a high probability of fraud, we will select a different notification method depending on the urgency. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned notification unit, When sending a notification, the system will refer to the user's past response history to select the most suitable notification method. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned notification unit, It estimates the user's emotions during a call and adjusts the timing of notifications based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned notification unit, When a notification is sent, the system selects the most suitable notification method based on the user's device settings and environment. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned notification unit, When sending notifications, customize the content of the notifications based on the user's current activity status. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned cut portion is The system estimates the user's emotions during a call and adjusts the timing of disconnecting the call based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned cut portion is If a call is likely to be a scam when it is disconnected, a warning message will be sent to the caller. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned cut portion is When a call is disconnected, the system refers to the user's past call history to select the most suitable disconnection method. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned cut portion is The system estimates the emotions of the user during a call and determines the priority for ending the call based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned cut portion is When ending a call, the system analyzes the characteristics and speaking style of the caller to adjust the timing of the disconnection. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned cut portion is When ending a call, the system selects the optimal disconnection method by referring to the caller's past behavioral patterns. The system described in Appendix 1, characterized by the features described herein. (Note 23) The alert unit is, The system estimates the user's emotions during a call and adjusts the content of alerts based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The alert unit is, When an alert is delivered, if there is a high probability of fraud, a different alert method will be selected depending on the urgency. The system described in Appendix 1, characterized by the features described herein. (Note 25) The alert unit is, When an alert is delivered, the system selects the most appropriate alert method by referring to the past response history of family members and stakeholders. The system described in Appendix 1, characterized by the features described herein. (Note 26) The alert unit is, The system estimates the user's emotions during a call and adjusts the timing of alert delivery based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The alert unit is, When delivering alerts, the system selects the most suitable alert method based on the device settings and environment of family members and stakeholders. The system described in Appendix 1, characterized by the features described herein. (Note 28) The alert unit is, When sending alerts, customize the content of the alerts to take into account the current activities of family members and related parties. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0184] 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. The monitoring department monitors the content of calls in real time, A determination unit that determines the possibility of special fraud based on the content of the call monitored by the aforementioned monitoring unit, A notification unit that notifies the user if the aforementioned determination unit determines that there is a high probability of a special fraud case, A disconnection unit that automatically ends the call when notified by the aforementioned notification unit, The system includes an alert unit that, when notified by the aforementioned notification unit, distributes an alert to a pre-registered contact, such as a family member. A system characterized by the following features.

2. The aforementioned monitoring unit, The system estimates the user's emotions during a call and adjusts the monitoring accuracy based on the estimated emotions. The system according to feature 1.

3. The aforementioned monitoring unit, When monitoring call content, the frequency of specific keywords and phrases is analyzed in real time. The system according to feature 1.

4. The aforementioned monitoring unit, When monitoring call content, the system analyzes background noise and ambient sounds to identify factors that increase the likelihood of fraud. The system according to feature 1.

5. The aforementioned monitoring unit, The system estimates the emotions of the user during a call and determines monitoring priorities based on the estimated emotions. The system according to feature 1.

6. The aforementioned monitoring unit, During call monitoring, the tone and speed of the caller's voice are analyzed to determine the possibility of fraud. The system according to feature 1.

7. The aforementioned monitoring unit, When monitoring call content, the accuracy of monitoring is improved by referring to the caller's past call history. The system according to feature 1.

8. The unit that makes the determination said, We estimate the emotions of users during calls and adjust the criteria for determining the likelihood of fraud based on those estimated emotions. The system according to feature 1.

9. The unit that makes the determination said, During call analysis, the system learns specific speaking styles and patterns commonly used by scammers to improve the accuracy of its judgments. The system according to feature 1.

10. The unit that makes the determination said, When analyzing call content, the possibility of fraud is determined by considering the context and flow of the conversation. The system according to feature 1.

Images