system

Abstract

The system according to this embodiment aims to determine the possibility of fraudulent phone calls in real time and prevent them before they occur. [Solution] The system according to the embodiment comprises a listening unit, an analysis unit, a determination unit, and a recording unit. The listening unit listens to the content of the call. The analysis unit analyzes the content of the call listened to by the listening unit. The determination unit determines the possibility of a fraudulent call based on the talk pattern analyzed by the analysis unit. The recording unit starts recording if the determination unit determines that there is a high possibility of a fraudulent call.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of 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 is a problem that it is difficult to detect and prevent fraud calls in real time.

[0005] The system according to the embodiment aims to determine the possibility of a fraud call in real time and prevent it.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a listening unit, an analysis unit, a determination unit, and a recording unit. The listening unit listens to the content of a phone call. The analysis unit analyzes the content of the phone call listened to by the listening unit. The determination unit determines the possibility of a fraudulent call based on the talk pattern analyzed by the analysis unit. The recording unit starts recording if the determination unit determines that there is a high possibility of a fraudulent call. [Effects of the Invention]

[0007] The system according to this embodiment can determine the possibility of a fraudulent phone call in real time and prevent it before it happens. [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, and the like. 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 fraudulent call prevention system according to an embodiment of the present invention is a telephone option service for preventing malicious fraudulent calls, which have become a social problem. The fraudulent call prevention system uses AI to listen to the content of calls from numbers other than registered phone numbers and analyze the talk patterns. If there are many similarities to fraud cases, the system determines the possibility of it being a fraudulent call based on the number of similarities. For example, if the possibility of it being a fraudulent call reaches 70%, the system informs both the caller and the recipient that "This call may be a fraudulent call, so we will start recording," and asks them to hang up. This mechanism can prevent fraud before it occurs. The fraudulent call prevention system uses AI to listen to the content of calls from numbers other than registered phone numbers. At this time, the AI ​​analyzes the content of the call in real time and extracts talk patterns. For example, it checks whether specific keywords or phrases are included. This makes it possible to determine whether there are many similarities to fraud cases. The fraudulent call prevention system uses AI to determine the possibility of it being a fraudulent call based on the number of similarities if there are many similarities to fraud cases. For example, if there are many similarities to fraud cases, it is determined that there is a high possibility that it is a fraudulent call. If the probability of a call being fraudulent reaches 70%, both the caller and the recipient are informed, "This call may be fraudulent, so we will begin recording." This allows the caller to stop their fraudulent activity and prevents the recipient from falling victim to fraud. Furthermore, since new fraudulent methods are constantly being developed, it is necessary to train the AI ​​on these new methods. For example, when a new fraud case is reported, training the AI ​​on that method allows the AI ​​to more accurately identify fraudulent calls. This improves the effectiveness of fraud prevention. Fraudulent call prevention systems can prevent fraudulent calls from becoming a problem. This is especially effective for households with elderly people who have disposable income. In addition, since the operational history can be checked from the recordings, service users can also verify the effectiveness. For example, by checking the recording of a call that was determined to have a high probability of being fraudulent, it is possible to confirm whether it was actually a fraudulent call. In this way, fraudulent call prevention systems can prevent fraud by determining the possibility of a call being fraudulent and starting recording.

[0029] The fraud prevention system according to this embodiment comprises a listening unit, an analysis unit, a determination unit, and a recording unit. The listening unit listens to the content of a call. For example, the listening unit listens to the content of a call from a number other than a registered phone number. The listening unit uses AI to analyze the content of the call in real time and extracts talk patterns. For example, it checks whether specific keywords or phrases are included. The analysis unit analyzes the content of the call listened to by the listening unit. The analysis unit uses AI to analyze the content of the call and extracts talk patterns. For example, it checks whether specific keywords or phrases are included. The determination unit determines the possibility of a fraudulent call based on the talk patterns analyzed by the analysis unit. The determination unit uses AI to determine whether there are many similarities to fraud cases. For example, if there are many similarities to fraud cases, it determines that there is a high possibility that it is a fraudulent call. The recording unit starts recording when the determination unit determines that there is a high possibility that it is a fraudulent call. The recording unit starts recording using AI. For example, if the probability of a call being a scam reaches 70%, the system will inform both the caller and the recipient that "This call may be a scam, so we will begin recording." This allows the scam call prevention system according to this embodiment to prevent fraud by determining the possibility of a call being a scam and starting recording.

[0030] The listening unit listens to the content of phone calls. For example, it listens to the content of calls from numbers other than registered phone numbers. Specifically, the listening unit captures audio data in real time as soon as a call starts and sends it to the AI. The AI ​​uses speech recognition technology to convert the content of the call into text data and then uses natural language processing technology to analyze the talk patterns. For example, it detects keywords and phrases such as "money," "transfer," and "urgent" that are often found in scam calls. This allows the listening unit to analyze the content of the call in detail and detect signs of fraud early. Furthermore, the listening unit also analyzes the sound quality and background noise of the call, and can capture the environmental sounds and sound quality characteristics unique to scam calls. For example, scam calls are often made from noisy environments, so detecting these characteristics can further increase the likelihood of fraud. The listening unit sends these analysis results to the analysis unit in real time, enabling a rapid response.

[0031] The analysis unit analyzes the content of the call recorded by the listening unit. The analysis unit uses AI to analyze the call content and extract talk patterns. Specifically, the AI ​​uses speech recognition technology to convert the call content into text data and natural language processing technology to analyze the talk patterns. For example, it checks whether specific keywords or phrases are included. Furthermore, the analysis unit can also analyze the context of the call and the speaker's emotions. For example, it analyzes the speaker's tone of voice, speed, and emotional changes to assess the likelihood of fraud. The analysis unit compares the call with a database of past fraud cases to find similarities. For example, if there are many parts that match patterns from past fraudulent calls, it determines that there is a high possibility of fraud. The analysis unit sends these analysis results to the judgment unit, providing basic data for evaluating the likelihood of fraudulent calls. Furthermore, the analysis unit continuously updates the analysis results of the call content and provides real-time feedback to the judgment unit. This allows the analysis unit to dynamically analyze the call as it progresses and detect signs of fraud early.

[0032] The judgment unit determines the likelihood of a fraudulent call based on the talk patterns analyzed by the analysis unit. The judgment unit uses AI to determine whether there are many similarities to actual fraud cases. Specifically, the AI ​​evaluates the degree of similarity of talk patterns, keywords, and phrases provided by the analysis unit and scores the likelihood of a fraudulent call. For example, if there are many similarities to actual fraud cases, it determines that there is a high possibility of a fraudulent call. Based on the scoring results, the judgment unit issues a warning if the likelihood of a fraudulent call exceeds a certain threshold. For example, if the likelihood of a fraudulent call reaches 70%, a warning message is displayed to the user, prompting them to choose whether to continue the call. Furthermore, the judgment unit continuously improves its judgment algorithm based on past judgment results and user feedback. This allows the judgment unit to improve the accuracy of fraudulent call detection and provide users with more reliable warnings.

[0033] The recording unit begins recording when the judgment unit determines that there is a high probability that the call is a scam. The recording unit uses AI to initiate recording. Specifically, when the probability of a call being a scam reaches 70%, it informs both the caller and the recipient that "This call may be a scam call, so we will begin recording." The recording unit records the conversation in high quality so that it can be used later for analysis and as evidence. The recording data is securely stored on a cloud server and can be accessed as needed. Furthermore, the recording unit can analyze the conversation in real time during recording and issue additional warnings if the signs of fraud become stronger. For example, if a new scam keyword is detected during the call, it will issue another warning and urge the user to end the call. The recording unit shares the recording data with the analysis and judgment units, contributing to the improvement of the overall system accuracy. In this way, the recording unit can play a crucial role in securing evidence of scam calls and protecting users.

[0034] The learning unit learns new tactics. The learning unit learns new tactics using AI. For example, when a new fraud case is reported, the AI ​​learns that tactic. By learning new tactics using AI, the learning unit improves the accuracy of detecting fraudulent phone calls. For example, by learning new fraud cases, the AI ​​can more accurately determine the likelihood of a phone call being fraudulent. In this way, the learning unit can improve the accuracy of detecting fraudulent phone calls by learning new tactics.

[0035] The storage unit saves the recorded data. The storage unit uses AI to save the recorded data. For example, it saves the recorded data in an audio file format. By saving the recorded data, the storage unit can review it later. For example, by saving the recorded data, it is possible to understand the reality of fraudulent phone calls. Thus, by saving the recorded data, the storage unit can review it later.

[0036] The verification unit checks the recorded data. The verification unit uses AI to check the recorded data. For example, it plays the recorded data. By checking the recorded data, the verification unit can grasp the reality of the fraudulent call. For example, by checking the recorded data, it can grasp the reality of the fraudulent call. Thus, by checking the recorded data, the verification unit can grasp the reality of the fraudulent call.

[0037] The listening unit listens to the content of calls from numbers other than registered phone numbers. The listening unit uses AI to analyze the call content in real time and extract conversation patterns. For example, it checks whether specific keywords or phrases are included. In this way, the listening unit can increase the likelihood of a call being a scam call by listening to the content of calls from numbers other than registered phone numbers.

[0038] The analysis unit checks whether specific keywords or phrases are included. The analysis unit uses AI to analyze the call content and extract conversation patterns. For example, it checks whether specific keywords or phrases are included. This allows the analysis unit to increase the likelihood of a call being a scam by checking for specific keywords or phrases.

[0039] The detection unit determines the possibility of a fraudulent call if there are many similarities to fraud cases. The detection unit uses AI to determine whether there are many similarities to fraud cases. For example, if there are many similarities to fraud cases, it determines that there is a high possibility that it is a fraudulent call. In this way, the detection unit can improve the accuracy of detecting fraudulent calls by determining the possibility of a fraudulent call when there are many similarities to fraud cases.

[0040] The recording unit starts recording when it determines that there is a high probability that the call is a scam. The recording unit uses AI to initiate recording. For example, if the probability of a call being a scam reaches 70%, it will inform both the caller and the recipient, "This call may be a scam, so we will start recording." In this way, the recording unit can prevent fraudulent activities by starting recording when it determines that there is a high probability that the call is a scam.

[0041] The listening unit will add a function to automatically remove background noise and other sounds when listening to the content of a call. The listening unit will use AI to automatically remove background noise and other sounds. For example, the AI ​​will remove car noises and wind noises that occur during a call in real time. The AI ​​will filter and remove indoor noises that occur during a call. The AI ​​will identify and remove other people's conversations that occur during a call. As a result, the accuracy of listening to the content of a call will be improved by removing background noise and other sounds. Some or all of the above processing in the listening unit may be performed using AI or not using AI.

[0042] The listening unit analyzes the speaker's voice tone and speed while listening to the content of a call to identify factors that increase the likelihood of fraud. The listening unit uses AI to analyze the speaker's voice tone and speed. For example, if the speaker's voice suddenly becomes higher pitched, the AI ​​identifies this as a factor that increases the likelihood of fraud. If the speaker's voice suddenly becomes faster, the AI ​​identifies this as a factor that increases the likelihood of fraud. If the speaker's voice becomes unnaturally lower pitched, the AI ​​identifies this as a factor that increases the likelihood of fraud. In this way, by analyzing the speaker's voice tone and speed, factors that increase the likelihood of fraud can be identified. Some or all of the above processing in the listening unit may be performed using AI or not.

[0043] The listening unit improves analysis accuracy by considering the speaker's geographical accent and dialect when listening to the content of a call. The listening unit uses AI to consider the speaker's geographical accent and dialect. For example, if the speaker uses Kansai dialect, the AI ​​considers the Kansai accent to improve analysis accuracy. If the speaker uses Tohoku dialect, the AI ​​considers the Tohoku accent to improve analysis accuracy. If the speaker uses Okinawan dialect, the AI ​​considers the Okinawan accent to improve analysis accuracy. In this way, analysis accuracy is improved by considering the speaker's geographical accent and dialect. Some or all of the above processing in the listening unit may be performed using AI or not using AI.

[0044] The listening unit improves listening accuracy by referring to the speaker's past call history when listening to the content of a call. The listening unit uses AI to refer to the speaker's past call history. For example, the AI ​​refers to specific phrases the speaker has used in the past to improve listening accuracy. The AI ​​refers to specific keywords the speaker has used in the past to improve listening accuracy. The AI ​​refers to specific speaking styles the speaker has used in the past to improve listening accuracy. In this way, listening accuracy is improved by referring to the speaker's past call history. Some or all of the above processing in the listening unit may be performed using AI or not using AI.

[0045] The analysis unit evaluates the importance of specific keywords and phrases during analysis, taking into account the context of the call content. The analysis unit uses AI to consider the context of the call content. For example, the AI ​​evaluates whether a specific keyword is important based on the context of the call content. The AI ​​evaluates whether a specific phrase is important based on the context of the call content. The AI ​​evaluates whether a specific topic is important based on the context of the call content. In this way, the importance of specific keywords and phrases can be evaluated by considering the context of the call content. Some or all of the above processing in the analysis unit may be performed using AI, or may not be performed using AI.

[0046] The analysis unit analyzes the speaker's tone of voice and emotions during the analysis to identify factors that increase the likelihood of fraud. The analysis unit uses AI to analyze the speaker's tone of voice and emotions. For example, if the speaker's voice suddenly becomes higher pitched, the AI ​​identifies this as a factor that increases the likelihood of fraud. If the speaker's tone of voice changes unnaturally, the AI ​​identifies this as a factor that increases the likelihood of fraud. If the emotion in the speaker's voice suddenly changes, the AI ​​identifies this as a factor that increases the likelihood of fraud. In this way, by analyzing the speaker's tone of voice and emotions, factors that increase the likelihood of fraud can be identified. Some or all of the above processing in the analysis unit may be performed using AI or not.

[0047] The analysis unit improves analysis accuracy by considering the temporal changes in the call content during analysis. The analysis unit uses AI to consider the temporal changes in the call content. For example, the AI ​​analyzes the temporal changes in the call content in real time to improve accuracy. The AI ​​compares the temporal changes in the call content with past data to improve accuracy. The AI ​​predicts the temporal changes in the call content to improve accuracy. In this way, the analysis accuracy is improved by considering the temporal changes in the call content. Some or all of the above processing in the analysis unit may be performed using AI or without AI.

[0048] The analysis unit improves analysis accuracy by referring to the speaker's past call history during analysis. The analysis unit uses AI to refer to the speaker's past call history. For example, the AI ​​refers to the speaker's past call history to improve analysis accuracy. The AI ​​extracts specific patterns from the speaker's past call history to improve analysis accuracy. The AI ​​analyzes the speaker's past call history to improve analysis accuracy. In this way, analysis accuracy is improved by referring to the speaker's past call history. Some or all of the above processing in the analysis unit may be performed using AI or without AI.

[0049] The judgment unit evaluates the likelihood of fraud by considering the context of the call content during the judgment process. The judgment unit uses AI to consider the context of the call content. For example, the AI ​​evaluates whether a particular keyword increases the likelihood of fraud based on the context of the call content. The AI ​​evaluates whether a particular phrase increases the likelihood of fraud based on the context of the call content. The AI ​​evaluates whether a particular topic increases the likelihood of fraud based on the context of the call content. This allows for a more accurate assessment of the likelihood of fraud by considering the context of the call content. Some or all of the above processing in the judgment unit may be performed using AI or not.

[0050] The judgment unit analyzes the speaker's tone of voice and emotions during the judgment process to identify factors that increase the likelihood of fraud. The judgment unit uses AI to analyze the speaker's tone of voice and emotions. For example, if the speaker's voice suddenly becomes higher pitched, the AI ​​identifies this as a factor that increases the likelihood of fraud. If the speaker's tone of voice changes unnaturally, the AI ​​identifies this as a factor that increases the likelihood of fraud. If the emotion in the speaker's voice suddenly changes, the AI ​​identifies this as a factor that increases the likelihood of fraud. In this way, by analyzing the speaker's tone of voice and emotions, factors that increase the likelihood of fraud can be identified. Some or all of the above processing in the judgment unit may be performed using AI, or it may be performed without using AI.

[0051] The judgment unit improves its judgment accuracy by considering the temporal changes in the call content during the judgment process. The judgment unit uses AI to consider the temporal changes in the call content. For example, the AI ​​analyzes the temporal changes in the call content in real time to improve accuracy. The AI ​​compares the temporal changes in the call content with past data to improve accuracy. The AI ​​predicts the temporal changes in the call content to improve accuracy. As a result, the judgment accuracy is improved by considering the temporal changes in the call content. Some or all of the above processing in the judgment unit may be performed using AI or without AI.

[0052] The judgment unit improves judgment accuracy by referring to the speaker's past call history during the judgment process. The judgment unit uses AI to refer to the speaker's past call history. For example, the AI ​​refers to the speaker's past call history to improve judgment accuracy. The AI ​​extracts specific patterns from the speaker's past call history to improve judgment accuracy. The AI ​​analyzes the speaker's past call history to improve judgment accuracy. In this way, judgment accuracy is improved by referring to the speaker's past call history. Some or all of the above processing in the judgment unit may be performed using AI or without using AI.

[0053] The recording unit will have a function that automatically highlights important parts of the call content during recording. The recording unit will use AI to automatically highlight important parts of the call content. For example, the AI ​​will automatically highlight and record important keywords in the call content. The AI ​​will automatically highlight and record important phrases in the call content. The AI ​​will automatically highlight and record important topics in the call content. This makes it easier to review the call content later by highlighting important parts. Some or all of the above processing in the recording unit may be performed using AI or not.

[0054] The recording unit will have a function to automatically remove noise from the call content during recording. The recording unit will use AI to automatically remove noise from the call content. For example, the AI ​​will remove car noises and wind noises that occur during the call in real time. The AI ​​will filter and remove indoor noises that occur during the call. The AI ​​will identify and remove other people's conversations that occur during the call. As a result, the quality of the recording will be improved by removing noise from the call content. Some or all of the above processing in the recording unit may be performed using AI or not using AI.

[0055] The recording unit improves recording accuracy by considering the temporal changes in the content of the call during recording. The recording unit uses AI to consider the temporal changes in the content of the call. For example, the AI ​​analyzes the temporal changes in the content of the call in real time to improve recording accuracy. The AI ​​compares the temporal changes in the content of the call with past data to improve recording accuracy. The AI ​​predicts the temporal changes in the content of the call to improve recording accuracy. In this way, recording accuracy is improved by considering the temporal changes in the content of the call. Some or all of the above processing in the recording unit may be performed using AI or without using AI.

[0056] The recording unit improves recording accuracy by referring to the speaker's past call history during recording. The recording unit uses AI to refer to the speaker's past call history. For example, the AI ​​refers to the speaker's past call history to improve recording accuracy. The AI ​​extracts specific patterns from the speaker's past call history to improve recording accuracy. The AI ​​analyzes the speaker's past call history to improve recording accuracy. In this way, recording accuracy is improved by referring to the speaker's past call history. Some or all of the above processing in the recording unit may be performed using AI or not using AI.

[0057] The learning unit optimizes its learning algorithm by referring to past fraud cases during the learning process. The learning unit uses AI to refer to past fraud cases. For example, the AI ​​refers to past fraud cases and optimizes the learning algorithm. The AI ​​extracts specific patterns from past fraud cases and optimizes the learning algorithm. The AI ​​analyzes past fraud cases and optimizes the learning algorithm. In this way, the learning algorithm is optimized by referring to past fraud cases. Some or all of the above processes in the learning unit may be performed using AI or not using AI.

[0058] The learning unit weights the training data during training, taking into account the temporal changes in the content of the call. The learning unit uses AI to consider the temporal changes in the content of the call. For example, the AI ​​analyzes the temporal changes in the content of the call in real time and weights the training data. The AI ​​compares the temporal changes in the content of the call with past data and weights the training data. The AI ​​predicts the temporal changes in the content of the call and weights the training data. In this way, the weighting of the training data is optimized by taking into account the temporal changes in the content of the call. Some or all of the above processes in the learning unit may be performed using AI or without using AI.

[0059] The storage unit adds a function to automatically highlight important parts of the call content when saving. The storage unit uses AI to automatically highlight important parts of the call content. For example, the AI ​​automatically highlights and saves important keywords in the call content. The AI ​​automatically highlights and saves important phrases in the call content. The AI ​​automatically highlights and saves important topics in the call content. This makes it easier to review the call content later by highlighting important parts. Some or all of the above processing in the storage unit may be performed using AI or not.

[0060] The storage unit improves storage accuracy by considering the temporal changes in call content during storage. The storage unit uses AI to consider the temporal changes in call content. For example, the AI ​​analyzes the temporal changes in call content in real time to improve storage accuracy. The AI ​​compares the temporal changes in call content with past data to improve storage accuracy. The AI ​​predicts the temporal changes in call content to improve storage accuracy. In this way, storage accuracy is improved by considering the temporal changes in call content. Some or all of the above processing in the storage unit may be performed using AI or without AI.

[0061] The verification unit adds a function to automatically highlight important parts of the call content during verification. The verification unit uses AI to automatically highlight important parts of the call content. For example, the AI ​​automatically highlights and displays important keywords in the call content. The AI ​​automatically highlights and displays important phrases in the call content. The AI ​​automatically highlights and displays important topics in the call content. This makes it easier to review the call content later by highlighting important parts. Some or all of the above processing in the verification unit may be performed using AI or not.

[0062] The verification unit improves verification accuracy by considering the temporal changes in the call content during verification. The verification unit uses AI to consider the temporal changes in the call content. For example, the AI ​​analyzes the temporal changes in the call content in real time to improve verification accuracy. The AI ​​compares the temporal changes in the call content with past data to improve verification accuracy. The AI ​​predicts the temporal changes in the call content to improve verification accuracy. In this way, verification accuracy is improved by considering the temporal changes in the call content. Some or all of the above processing in the verification unit may be performed using AI or without using AI.

[0063] The verification unit improves verification accuracy by referring to the speaker's past call history during verification. The verification unit uses AI to refer to the speaker's past call history. For example, the AI ​​refers to the speaker's past call history to improve verification accuracy. The AI ​​extracts specific patterns from the speaker's past call history to improve verification accuracy. The AI ​​analyzes the speaker's past call history to improve verification accuracy. In this way, verification accuracy is improved by referring to the speaker's past call history. Some or all of the above processing in the verification unit may be performed using AI or without using AI.

[0064] The verification unit improves verification accuracy by considering the temporal changes in the call content during verification. The verification unit uses AI to consider the temporal changes in the call content. For example, the AI ​​analyzes the temporal changes in the call content in real time to improve verification accuracy. The AI ​​compares the temporal changes in the call content with past data to improve verification accuracy. The AI ​​predicts the temporal changes in the call content to improve verification accuracy. In this way, verification accuracy is improved by considering the temporal changes in the call content. Some or all of the above processing in the verification unit may be performed using AI or without using AI.

[0065] The verification unit adds a function to automatically highlight important parts of the call content during verification. The verification unit uses AI to automatically highlight important parts of the call content. For example, the AI ​​automatically highlights and displays important keywords in the call content. The AI ​​automatically highlights and displays important phrases in the call content. The AI ​​automatically highlights and displays important topics in the call content. This makes it easier to review the call content later by highlighting important parts. Some or all of the above processing in the verification unit may be performed using AI or not.

[0066] The verification unit improves verification accuracy by referring to the speaker's past call history during verification. The verification unit uses AI to refer to the speaker's past call history. For example, the AI ​​refers to the speaker's past call history to improve verification accuracy. The AI ​​extracts specific patterns from the speaker's past call history to improve verification accuracy. The AI ​​analyzes the speaker's past call history to improve verification accuracy. In this way, verification accuracy is improved by referring to the speaker's past call history. Some or all of the above processing in the verification unit may be performed using AI or without using AI.

[0067] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0068] The fraud prevention system can also include a notification unit. This unit automatically sends notifications to user-specified contacts when it determines a call is likely to be fraudulent. For example, by registering the contact information of family and friends, the system can send warning messages to these contacts when a call is deemed likely to be fraudulent. The notification unit can also send push notifications to the user's smartphone, allowing the user to receive real-time warnings about fraudulent calls. Furthermore, the notification unit can send detailed reports to the user's email address, allowing the user to review the details of the fraudulent call later.

[0069] The fraud prevention system can also include a feedback unit. This feedback unit allows users to provide feedback on the fraud detection results. For example, if a call identified as fraudulent by the user turns out not to be fraudulent, the user can provide this information to the feedback unit. Similarly, if a call that was not identified as fraudulent by the user turns out to be fraudulent, the user can provide feedback. This allows the feedback unit to collect user feedback and use it as training data for the AI, thereby improving the accuracy of fraud detection.

[0070] The fraud prevention system can also include a translation unit. This unit translates call content in real time and provides it to the user. For example, if a fraud call comes in in a foreign language, the translation unit can translate the call into the user's native language. The translation unit can also translate the user's statements into the foreign language and convey them to the caller. This allows users to deal with fraud calls despite language barriers. Furthermore, the translation unit can save a history of call translations for later review.

[0071] The fraud prevention system can also be equipped with a voice conversion unit. This unit can convert the user's voice before transmitting it to the other party. For example, if a user wants to change their voice, the voice conversion unit can convert the user's voice to a different voice before transmitting it to the other party. The voice conversion unit can also convert the user's voice to a male or female voice, allowing the user to conceal their voice during calls. Furthermore, the voice conversion unit can apply voice conversion to recorded call data.

[0072] The fraud prevention system may also include a call summarization function. This function automatically summarizes the call content and provides it to the user. For example, if a user wants to quickly review a long call, the summarization function can summarize the call and provide it to the user. The summarization function can also extract key points from the call and provide them to the user, allowing the user to quickly grasp the main points of the call. Furthermore, the summarization function can save the summary data for later review.

[0073] The following briefly describes the processing flow for example form 1.

[0074] Step 1: The listening unit listens to the content of the call. For example, it listens to the content of calls from numbers other than registered phone numbers. The listening unit uses AI to analyze the call content in real time and extracts talk patterns. For example, it checks whether specific keywords or phrases are included. Step 2: The analysis unit analyzes the call content recorded by the listening unit. The analysis unit uses AI to analyze the call content and extract talk patterns. For example, it checks whether specific keywords or phrases are included. Step 3: The judgment unit determines the likelihood of a fraudulent call based on the talk pattern analyzed by the analysis unit. The judgment unit uses AI to determine if there are many similarities to actual fraud cases. For example, if there are many similarities to actual fraud cases, it determines that there is a high possibility that it is a fraudulent call. Step 4: The recording unit starts recording if the judgment unit determines that there is a high probability that the call is a scam. The recording unit uses AI to start recording. For example, if the probability of it being a scam reaches 70%, it will inform both the caller and the recipient, "This call may be a scam, so we will start recording."

[0075] (Example of form 2) The fraudulent call prevention system according to an embodiment of the present invention is a telephone option service for preventing malicious fraudulent calls, which have become a social problem. The fraudulent call prevention system uses AI to listen to the content of calls from numbers other than registered phone numbers and analyze the talk patterns. If there are many similarities to fraud cases, the system determines the possibility of it being a fraudulent call based on the number of similarities. For example, if the possibility of it being a fraudulent call reaches 70%, the system informs both the caller and the recipient that "This call may be a fraudulent call, so we will start recording," and asks them to hang up. This mechanism can prevent fraud before it occurs. The fraudulent call prevention system uses AI to listen to the content of calls from numbers other than registered phone numbers. At this time, the AI ​​analyzes the content of the call in real time and extracts talk patterns. For example, it checks whether specific keywords or phrases are included. This makes it possible to determine whether there are many similarities to fraud cases. The fraudulent call prevention system uses AI to determine the possibility of it being a fraudulent call based on the number of similarities if there are many similarities to fraud cases. For example, if there are many similarities to fraud cases, it is determined that there is a high possibility that it is a fraudulent call. If the probability of a call being fraudulent reaches 70%, both the caller and the recipient are informed, "This call may be fraudulent, so we will begin recording." This allows the caller to stop their fraudulent activity and prevents the recipient from falling victim to fraud. Furthermore, since new fraudulent methods are constantly being developed, it is necessary to train the AI ​​on these new methods. For example, when a new fraud case is reported, training the AI ​​on that method allows the AI ​​to more accurately identify fraudulent calls. This improves the effectiveness of fraud prevention. Fraudulent call prevention systems can prevent fraudulent calls from becoming a problem. This is especially effective for households with elderly people who have disposable income. In addition, since the operational history can be checked from the recordings, service users can also verify the effectiveness. For example, by checking the recording of a call that was determined to have a high probability of being fraudulent, it is possible to confirm whether it was actually a fraudulent call. In this way, fraudulent call prevention systems can prevent fraud by determining the possibility of a call being fraudulent and starting recording.

[0076] The fraud prevention system according to this embodiment comprises a listening unit, an analysis unit, a determination unit, and a recording unit. The listening unit listens to the content of a call. For example, the listening unit listens to the content of a call from a number other than a registered phone number. The listening unit uses AI to analyze the content of the call in real time and extracts talk patterns. For example, it checks whether specific keywords or phrases are included. The analysis unit analyzes the content of the call listened to by the listening unit. The analysis unit uses AI to analyze the content of the call and extracts talk patterns. For example, it checks whether specific keywords or phrases are included. The determination unit determines the possibility of a fraudulent call based on the talk patterns analyzed by the analysis unit. The determination unit uses AI to determine whether there are many similarities to fraud cases. For example, if there are many similarities to fraud cases, it determines that there is a high possibility that it is a fraudulent call. The recording unit starts recording when the determination unit determines that there is a high possibility that it is a fraudulent call. The recording unit starts recording using AI. For example, if the probability of a call being a scam reaches 70%, the system will inform both the caller and the recipient that "This call may be a scam, so we will begin recording." This allows the scam call prevention system according to this embodiment to prevent fraud by determining the possibility of a call being a scam and starting recording.

[0077] The listening unit listens to the content of phone calls. For example, it listens to the content of calls from numbers other than registered phone numbers. Specifically, the listening unit captures audio data in real time as soon as a call starts and sends it to the AI. The AI ​​uses speech recognition technology to convert the content of the call into text data and then uses natural language processing technology to analyze the talk patterns. For example, it detects keywords and phrases such as "money," "transfer," and "urgent" that are often found in scam calls. This allows the listening unit to analyze the content of the call in detail and detect signs of fraud early. Furthermore, the listening unit also analyzes the sound quality and background noise of the call, and can capture the environmental sounds and sound quality characteristics unique to scam calls. For example, scam calls are often made from noisy environments, so detecting these characteristics can further increase the likelihood of fraud. The listening unit sends these analysis results to the analysis unit in real time, enabling a rapid response.

[0078] The analysis unit analyzes the content of the call recorded by the listening unit. The analysis unit uses AI to analyze the call content and extract talk patterns. Specifically, the AI ​​uses speech recognition technology to convert the call content into text data and natural language processing technology to analyze the talk patterns. For example, it checks whether specific keywords or phrases are included. Furthermore, the analysis unit can also analyze the context of the call and the speaker's emotions. For example, it analyzes the speaker's tone of voice, speed, and emotional changes to assess the likelihood of fraud. The analysis unit compares the call with a database of past fraud cases to find similarities. For example, if there are many parts that match patterns from past fraudulent calls, it determines that there is a high possibility of fraud. The analysis unit sends these analysis results to the judgment unit, providing basic data for evaluating the likelihood of fraudulent calls. Furthermore, the analysis unit continuously updates the analysis results of the call content and provides real-time feedback to the judgment unit. This allows the analysis unit to dynamically analyze the call as it progresses and detect signs of fraud early.

[0079] The judgment unit determines the likelihood of a fraudulent call based on the talk patterns analyzed by the analysis unit. The judgment unit uses AI to determine whether there are many similarities to actual fraud cases. Specifically, the AI ​​evaluates the degree of similarity of talk patterns, keywords, and phrases provided by the analysis unit and scores the likelihood of a fraudulent call. For example, if there are many similarities to actual fraud cases, it determines that there is a high possibility of a fraudulent call. Based on the scoring results, the judgment unit issues a warning if the likelihood of a fraudulent call exceeds a certain threshold. For example, if the likelihood of a fraudulent call reaches 70%, a warning message is displayed to the user, prompting them to choose whether to continue the call. Furthermore, the judgment unit continuously improves its judgment algorithm based on past judgment results and user feedback. This allows the judgment unit to improve the accuracy of fraudulent call detection and provide users with more reliable warnings.

[0080] The recording unit begins recording when the judgment unit determines that there is a high probability that the call is a scam. The recording unit uses AI to initiate recording. Specifically, when the probability of a call being a scam reaches 70%, it informs both the caller and the recipient that "This call may be a scam call, so we will begin recording." The recording unit records the conversation in high quality so that it can be used later for analysis and as evidence. The recording data is securely stored on a cloud server and can be accessed as needed. Furthermore, the recording unit can analyze the conversation in real time during recording and issue additional warnings if the signs of fraud become stronger. For example, if a new scam keyword is detected during the call, it will issue another warning and urge the user to end the call. The recording unit shares the recording data with the analysis and judgment units, contributing to the improvement of the overall system accuracy. In this way, the recording unit can play a crucial role in securing evidence of scam calls and protecting users.

[0081] The learning unit learns new tactics. The learning unit learns new tactics using AI. For example, when a new fraud case is reported, the AI ​​learns that tactic. By learning new tactics using AI, the learning unit improves the accuracy of detecting fraudulent phone calls. For example, by learning new fraud cases, the AI ​​can more accurately determine the likelihood of a phone call being fraudulent. In this way, the learning unit can improve the accuracy of detecting fraudulent phone calls by learning new tactics.

[0082] The storage unit saves the recorded data. The storage unit uses AI to save the recorded data. For example, it saves the recorded data in an audio file format. By saving the recorded data, the storage unit can review it later. For example, by saving the recorded data, it is possible to understand the reality of fraudulent phone calls. Thus, by saving the recorded data, the storage unit can review it later.

[0083] The verification unit checks the recorded data. The verification unit uses AI to check the recorded data. For example, it plays the recorded data. By checking the recorded data, the verification unit can grasp the reality of the fraudulent call. For example, by checking the recorded data, it can grasp the reality of the fraudulent call. Thus, by checking the recorded data, the verification unit can grasp the reality of the fraudulent call.

[0084] The listening unit listens to the content of calls from numbers other than registered phone numbers. The listening unit uses AI to analyze the call content in real time and extract conversation patterns. For example, it checks whether specific keywords or phrases are included. In this way, the listening unit can increase the likelihood of a call being a scam call by listening to the content of calls from numbers other than registered phone numbers.

[0085] The analysis unit checks whether specific keywords or phrases are included. The analysis unit uses AI to analyze the call content and extract conversation patterns. For example, it checks whether specific keywords or phrases are included. This allows the analysis unit to increase the likelihood of a call being a scam by checking for specific keywords or phrases.

[0086] The detection unit determines the possibility of a fraudulent call if there are many similarities to fraud cases. The detection unit uses AI to determine whether there are many similarities to fraud cases. For example, if there are many similarities to fraud cases, it determines that there is a high possibility that it is a fraudulent call. In this way, the detection unit can improve the accuracy of detecting fraudulent calls by determining the possibility of a fraudulent call when there are many similarities to fraud cases.

[0087] The recording unit starts recording when it determines that there is a high probability that the call is a scam. The recording unit uses AI to initiate recording. For example, if the probability of a call being a scam reaches 70%, it will inform both the caller and the recipient, "This call may be a scam, so we will start recording." In this way, the recording unit can prevent fraudulent activities by starting recording when it determines that there is a high probability that the call is a scam.

[0088] The listening unit estimates the user's emotions and adjusts the accuracy of the call content based on the estimated emotions. The listening unit uses AI to estimate the user's emotions and adjusts the accuracy of the call content. For example, if the user is nervous, the AI ​​enhances noise cancellation to improve the accuracy of the call content. If the user is relaxed, the AI ​​sets the call content listening accuracy to normal mode. If the user is in a hurry, the AI ​​quickly adjusts the call content listening accuracy to prioritize important information. This allows the listening unit to acquire more accurate call content by adjusting the accuracy of the call content based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0089] The listening unit will add a function to automatically remove background noise and other sounds when listening to the content of a call. The listening unit will use AI to automatically remove background noise and other sounds. For example, the AI ​​will remove car noises and wind noises that occur during a call in real time. The AI ​​will filter and remove indoor noises that occur during a call. The AI ​​will identify and remove other people's conversations that occur during a call. As a result, the accuracy of listening to the content of a call will be improved by removing background noise and other sounds. Some or all of the above processing in the listening unit may be performed using AI or not using AI.

[0090] The listening unit analyzes the speaker's voice tone and speed while listening to the content of a call to identify factors that increase the likelihood of fraud. The listening unit uses AI to analyze the speaker's voice tone and speed. For example, if the speaker's voice suddenly becomes higher pitched, the AI ​​identifies this as a factor that increases the likelihood of fraud. If the speaker's voice suddenly becomes faster, the AI ​​identifies this as a factor that increases the likelihood of fraud. If the speaker's voice becomes unnaturally lower pitched, the AI ​​identifies this as a factor that increases the likelihood of fraud. In this way, by analyzing the speaker's voice tone and speed, factors that increase the likelihood of fraud can be identified. Some or all of the above processing in the listening unit may be performed using AI or not.

[0091] The listening unit estimates the user's emotions and determines listening priorities based on the estimated emotions. The listening unit uses AI to estimate the user's emotions and determine listening priorities. For example, if the user is nervous, the AI ​​prioritizes listening to important conversation content. If the user is relaxed, the AI ​​prioritizes listening to normal conversation content. If the user is in a hurry, the AI ​​quickly prioritizes listening to important conversation content. In this way, by determining listening priorities based on the user's emotions, important conversation content can be prioritized. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0092] The listening unit improves analysis accuracy by considering the speaker's geographical accent and dialect when listening to the content of a call. The listening unit uses AI to consider the speaker's geographical accent and dialect. For example, if the speaker uses Kansai dialect, the AI ​​considers the Kansai accent to improve analysis accuracy. If the speaker uses Tohoku dialect, the AI ​​considers the Tohoku accent to improve analysis accuracy. If the speaker uses Okinawan dialect, the AI ​​considers the Okinawan accent to improve analysis accuracy. In this way, analysis accuracy is improved by considering the speaker's geographical accent and dialect. Some or all of the above processing in the listening unit may be performed using AI or not using AI.

[0093] The listening unit improves listening accuracy by referring to the speaker's past call history when listening to the content of a call. The listening unit uses AI to refer to the speaker's past call history. For example, the AI ​​refers to specific phrases the speaker has used in the past to improve listening accuracy. The AI ​​refers to specific keywords the speaker has used in the past to improve listening accuracy. The AI ​​refers to specific speaking styles the speaker has used in the past to improve listening accuracy. In this way, listening accuracy is improved by referring to the speaker's past call history. Some or all of the above processing in the listening unit may be performed using AI or not using AI.

[0094] The analysis unit estimates the user's emotions and adjusts the analysis algorithm based on the estimated emotions. The analysis unit uses AI to estimate the user's emotions and adjust the analysis algorithm. For example, if the user is nervous, the AI ​​quickly adjusts the analysis algorithm to prioritize the analysis of important information. If the user is relaxed, the AI ​​sets the analysis algorithm to normal mode. If the user is in a hurry, the AI ​​quickly adjusts the analysis algorithm to prioritize the analysis of important information. This allows for the prioritization of important information by adjusting the analysis algorithm based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0095] The analysis unit evaluates the importance of specific keywords and phrases during analysis, taking into account the context of the call content. The analysis unit uses AI to consider the context of the call content. For example, the AI ​​evaluates whether a specific keyword is important based on the context of the call content. The AI ​​evaluates whether a specific phrase is important based on the context of the call content. The AI ​​evaluates whether a specific topic is important based on the context of the call content. In this way, the importance of specific keywords and phrases can be evaluated by considering the context of the call content. Some or all of the above processing in the analysis unit may be performed using AI, or may not be performed using AI.

[0096] The analysis unit analyzes the speaker's tone of voice and emotions during the analysis to identify factors that increase the likelihood of fraud. The analysis unit uses AI to analyze the speaker's tone of voice and emotions. For example, if the speaker's voice suddenly becomes higher pitched, the AI ​​identifies this as a factor that increases the likelihood of fraud. If the speaker's tone of voice changes unnaturally, the AI ​​identifies this as a factor that increases the likelihood of fraud. If the emotion in the speaker's voice suddenly changes, the AI ​​identifies this as a factor that increases the likelihood of fraud. In this way, by analyzing the speaker's tone of voice and emotions, factors that increase the likelihood of fraud can be identified. Some or all of the above processing in the analysis unit may be performed using AI or not.

[0097] The analysis unit estimates the user's emotions and adjusts the display method of the analysis results based on the estimated emotions. The analysis unit uses AI to estimate the user's emotions and adjusts the display method of the analysis results. For example, if the user is nervous, the AI ​​provides a simple and easy-to-read display method. If the user is relaxed, the AI ​​provides a display method that includes detailed information. If the user is in a hurry, the AI ​​provides a concise display method. By adjusting the display method of the analysis results based on the user's emotions, a highly easy-to-read display is possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0098] The analysis unit improves analysis accuracy by considering the temporal changes in the call content during analysis. The analysis unit uses AI to consider the temporal changes in the call content. For example, the AI ​​analyzes the temporal changes in the call content in real time to improve accuracy. The AI ​​compares the temporal changes in the call content with past data to improve accuracy. The AI ​​predicts the temporal changes in the call content to improve accuracy. In this way, the analysis accuracy is improved by considering the temporal changes in the call content. Some or all of the above processing in the analysis unit may be performed using AI or without AI.

[0099] The analysis unit improves analysis accuracy by referring to the speaker's past call history during analysis. The analysis unit uses AI to refer to the speaker's past call history. For example, the AI ​​refers to the speaker's past call history to improve analysis accuracy. The AI ​​extracts specific patterns from the speaker's past call history to improve analysis accuracy. The AI ​​analyzes the speaker's past call history to improve analysis accuracy. In this way, analysis accuracy is improved by referring to the speaker's past call history. Some or all of the above processing in the analysis unit may be performed using AI or without AI.

[0100] The judgment unit estimates the user's emotions and adjusts the criteria for determining the likelihood of a scam call based on the estimated emotions. The judgment unit uses AI to estimate the user's emotions and adjusts the criteria for determining the likelihood of a scam call. For example, if the user is nervous, the AI ​​tightens the criteria for determining the likelihood of a scam call. If the user is relaxed, the AI ​​sets the criteria for determining the likelihood of a scam call to normal. If the user is in a hurry, the AI ​​quickly adjusts the criteria for determining the likelihood of a scam call. This allows for more accurate judgment by adjusting the criteria for determining the likelihood of a scam call based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0101] The judgment unit evaluates the likelihood of fraud by considering the context of the call content during the judgment process. The judgment unit uses AI to consider the context of the call content. For example, the AI ​​evaluates whether a particular keyword increases the likelihood of fraud based on the context of the call content. The AI ​​evaluates whether a particular phrase increases the likelihood of fraud based on the context of the call content. The AI ​​evaluates whether a particular topic increases the likelihood of fraud based on the context of the call content. This allows for a more accurate assessment of the likelihood of fraud by considering the context of the call content. Some or all of the above processing in the judgment unit may be performed using AI or not.

[0102] The judgment unit analyzes the speaker's tone of voice and emotions during the judgment process to identify factors that increase the likelihood of fraud. The judgment unit uses AI to analyze the speaker's tone of voice and emotions. For example, if the speaker's voice suddenly becomes higher pitched, the AI ​​identifies this as a factor that increases the likelihood of fraud. If the speaker's tone of voice changes unnaturally, the AI ​​identifies this as a factor that increases the likelihood of fraud. If the emotion in the speaker's voice suddenly changes, the AI ​​identifies this as a factor that increases the likelihood of fraud. In this way, by analyzing the speaker's tone of voice and emotions, factors that increase the likelihood of fraud can be identified. Some or all of the above processing in the judgment unit may be performed using AI, or it may be performed without using AI.

[0103] The judgment unit estimates the user's emotions and adjusts the display method of the judgment result based on the estimated user emotions. The judgment unit uses AI to estimate the user's emotions and adjusts the display method of the judgment result. For example, if the user is nervous, the AI ​​provides a simple and highly visible display method. If the user is relaxed, the AI ​​provides a display method that includes detailed information. If the user is in a hurry, the AI ​​provides a display method that gets straight to the point. By adjusting the display method of the judgment result based on the user's emotions, a highly visible display becomes possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0104] The judgment unit improves its judgment accuracy by considering the temporal changes in the call content during the judgment process. The judgment unit uses AI to consider the temporal changes in the call content. For example, the AI ​​analyzes the temporal changes in the call content in real time to improve accuracy. The AI ​​compares the temporal changes in the call content with past data to improve accuracy. The AI ​​predicts the temporal changes in the call content to improve accuracy. As a result, the judgment accuracy is improved by considering the temporal changes in the call content. Some or all of the above processing in the judgment unit may be performed using AI or without AI.

[0105] The judgment unit improves judgment accuracy by referring to the speaker's past call history during the judgment process. The judgment unit uses AI to refer to the speaker's past call history. For example, the AI ​​refers to the speaker's past call history to improve judgment accuracy. The AI ​​extracts specific patterns from the speaker's past call history to improve judgment accuracy. The AI ​​analyzes the speaker's past call history to improve judgment accuracy. In this way, judgment accuracy is improved by referring to the speaker's past call history. Some or all of the above processing in the judgment unit may be performed using AI or without using AI.

[0106] The recording unit estimates the user's emotions and adjusts the recording start time based on the estimated emotions. The recording unit uses AI to estimate the user's emotions and adjust the recording start time. For example, if the user is nervous, the AI ​​starts recording quickly. If the user is relaxed, the AI ​​starts recording at the normal time. If the user is in a hurry, the AI ​​starts recording quickly and prioritizes recording important information. This allows for the rapid recording of important information by adjusting the recording start time based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0107] The recording unit will have a function that automatically highlights important parts of the call content during recording. The recording unit will use AI to automatically highlight important parts of the call content. For example, the AI ​​will automatically highlight and record important keywords in the call content. The AI ​​will automatically highlight and record important phrases in the call content. The AI ​​will automatically highlight and record important topics in the call content. This makes it easier to review the call content later by highlighting important parts. Some or all of the above processing in the recording unit may be performed using AI or not.

[0108] The recording unit will have a function to automatically remove noise from the call content during recording. The recording unit will use AI to automatically remove noise from the call content. For example, the AI ​​will remove car noises and wind noises that occur during the call in real time. The AI ​​will filter and remove indoor noises that occur during the call. The AI ​​will identify and remove other people's conversations that occur during the call. As a result, the quality of the recording will be improved by removing noise from the call content. Some or all of the above processing in the recording unit may be performed using AI or not using AI.

[0109] The recording unit estimates the user's emotions and determines recording priorities based on the estimated emotions. The recording unit uses AI to estimate the user's emotions and determine recording priorities. For example, if the user is nervous, the AI ​​prioritizes recording important conversation content. If the user is relaxed, the AI ​​prioritizes recording normal conversation content. If the user is in a hurry, the AI ​​quickly prioritizes recording important conversation content. In this way, important conversation content can be prioritized by determining recording priorities based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0110] The recording unit improves recording accuracy by considering the temporal changes in the content of the call during recording. The recording unit uses AI to consider the temporal changes in the content of the call. For example, the AI ​​analyzes the temporal changes in the content of the call in real time to improve recording accuracy. The AI ​​compares the temporal changes in the content of the call with past data to improve recording accuracy. The AI ​​predicts the temporal changes in the content of the call to improve recording accuracy. In this way, recording accuracy is improved by considering the temporal changes in the content of the call. Some or all of the above processing in the recording unit may be performed using AI or without using AI.

[0111] The recording unit improves recording accuracy by referring to the speaker's past call history during recording. The recording unit uses AI to refer to the speaker's past call history. For example, the AI ​​refers to the speaker's past call history to improve recording accuracy. The AI ​​extracts specific patterns from the speaker's past call history to improve recording accuracy. The AI ​​analyzes the speaker's past call history to improve recording accuracy. In this way, recording accuracy is improved by referring to the speaker's past call history. Some or all of the above processing in the recording unit may be performed using AI or not using AI.

[0112] The learning unit estimates the user's emotions and selects training data based on the estimated emotions. The learning unit uses AI to estimate the user's emotions and select training data. For example, if the user is nervous, the AI ​​prioritizes learning important fraud cases. If the user is relaxed, the AI ​​learns typical fraud cases. If the user is in a hurry, the AI ​​quickly learns important fraud cases. This allows for prioritizing learning of important fraud cases by selecting training data based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0113] The learning unit optimizes its learning algorithm by referring to past fraud cases during the learning process. The learning unit uses AI to refer to past fraud cases. For example, the AI ​​refers to past fraud cases and optimizes the learning algorithm. The AI ​​extracts specific patterns from past fraud cases and optimizes the learning algorithm. The AI ​​analyzes past fraud cases and optimizes the learning algorithm. In this way, the learning algorithm is optimized by referring to past fraud cases. Some or all of the above processes in the learning unit may be performed using AI or not using AI.

[0114] The learning unit estimates the user's emotions and adjusts the learning frequency based on the estimated emotions. The learning unit uses AI to estimate the user's emotions and adjust the learning frequency. For example, if the user is nervous, the AI ​​increases the learning frequency. If the user is relaxed, the AI ​​sets the learning frequency to normal. If the user is in a hurry, the AI ​​quickly adjusts the learning frequency. This allows for efficient learning by adjusting the learning frequency based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0115] The learning unit weights the training data during training, taking into account the temporal changes in the content of the call. The learning unit uses AI to consider the temporal changes in the content of the call. For example, the AI ​​analyzes the temporal changes in the content of the call in real time and weights the training data. The AI ​​compares the temporal changes in the content of the call with past data and weights the training data. The AI ​​predicts the temporal changes in the content of the call and weights the training data. In this way, the weighting of the training data is optimized by taking into account the temporal changes in the content of the call. Some or all of the above processes in the learning unit may be performed using AI or without using AI.

[0116] The storage unit estimates the user's emotions and selects data to save based on the estimated emotions. The storage unit uses AI to estimate the user's emotions and select data to save. For example, if the user is nervous, the AI ​​prioritizes saving important call content. If the user is relaxed, the AI ​​saves normal call content. If the user is in a hurry, the AI ​​quickly saves important call content. In this way, by selecting data to save based on the user's emotions, important call content can be saved preferentially. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0117] The storage unit adds a function to automatically highlight important parts of the call content when saving. The storage unit uses AI to automatically highlight important parts of the call content. For example, the AI ​​automatically highlights and saves important keywords in the call content. The AI ​​automatically highlights and saves important phrases in the call content. The AI ​​automatically highlights and saves important topics in the call content. This makes it easier to review the call content later by highlighting important parts. Some or all of the above processing in the storage unit may be performed using AI or not.

[0118] The storage unit estimates the user's emotions and determines the priority of saved data based on the estimated emotions. The storage unit uses AI to estimate the user's emotions and determine the priority of saved data. For example, if the user is nervous, the AI ​​prioritizes saving important call content. If the user is relaxed, the AI ​​prioritizes saving normal call content. If the user is in a hurry, the AI ​​quickly prioritizes saving important call content. In this way, important call content can be saved preferentially by determining the priority of saved data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0119] The storage unit improves storage accuracy by considering the temporal changes in call content during storage. The storage unit uses AI to consider the temporal changes in call content. For example, the AI ​​analyzes the temporal changes in call content in real time to improve storage accuracy. The AI ​​compares the temporal changes in call content with past data to improve storage accuracy. The AI ​​predicts the temporal changes in call content to improve storage accuracy. In this way, storage accuracy is improved by considering the temporal changes in call content. Some or all of the above processing in the storage unit may be performed using AI or without AI.

[0120] The verification unit estimates the user's emotions and adjusts the display method of the verification data based on the estimated user emotions. The verification unit uses AI to estimate the user's emotions and adjusts the display method of the verification data. For example, if the user is nervous, the AI ​​provides a simple and highly visible display method. If the user is relaxed, the AI ​​provides a display method that includes detailed information. If the user is in a hurry, the AI ​​provides a display method that gets straight to the point. By adjusting the display method of the verification data based on the user's emotions, a highly visible display becomes possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0121] The verification unit adds a function to automatically highlight important parts of the call content during verification. The verification unit uses AI to automatically highlight important parts of the call content. For example, the AI ​​automatically highlights and displays important keywords in the call content. The AI ​​automatically highlights and displays important phrases in the call content. The AI ​​automatically highlights and displays important topics in the call content. This makes it easier to review the call content later by highlighting important parts. Some or all of the above processing in the verification unit may be performed using AI or not.

[0122] The verification unit estimates the user's emotions and determines the priority of verification data based on the estimated user emotions. The verification unit uses AI to estimate the user's emotions and determine the priority of verification data. For example, if the user is nervous, the AI ​​will prioritize displaying important call content. If the user is relaxed, the AI ​​will prioritize displaying normal call content. If the user is in a hurry, the AI ​​will quickly prioritize displaying important call content. In this way, by prioritizing verification data based on the user's emotions, important call content can be displayed preferentially. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0123] The verification unit improves verification accuracy by considering the temporal changes in the call content during verification. The verification unit uses AI to consider the temporal changes in the call content. For example, the AI ​​analyzes the temporal changes in the call content in real time to improve verification accuracy. The AI ​​compares the temporal changes in the call content with past data to improve verification accuracy. The AI ​​predicts the temporal changes in the call content to improve verification accuracy. In this way, verification accuracy is improved by considering the temporal changes in the call content. Some or all of the above processing in the verification unit may be performed using AI or without using AI.

[0124] The verification unit improves verification accuracy by referring to the speaker's past call history during verification. The verification unit uses AI to refer to the speaker's past call history. For example, the AI ​​refers to the speaker's past call history to improve verification accuracy. The AI ​​extracts specific patterns from the speaker's past call history to improve verification accuracy. The AI ​​analyzes the speaker's past call history to improve verification accuracy. In this way, verification accuracy is improved by referring to the speaker's past call history. Some or all of the above processing in the verification unit may be performed using AI or without using AI.

[0125] The verification unit improves verification accuracy by considering the temporal changes in the call content during verification. The verification unit uses AI to consider the temporal changes in the call content. For example, the AI ​​analyzes the temporal changes in the call content in real time to improve verification accuracy. The AI ​​compares the temporal changes in the call content with past data to improve verification accuracy. The AI ​​predicts the temporal changes in the call content to improve verification accuracy. In this way, verification accuracy is improved by considering the temporal changes in the call content. Some or all of the above processing in the verification unit may be performed using AI or without using AI.

[0126] The verification unit adds a function to automatically highlight important parts of the call content during verification. The verification unit uses AI to automatically highlight important parts of the call content. For example, the AI ​​automatically highlights and displays important keywords in the call content. The AI ​​automatically highlights and displays important phrases in the call content. The AI ​​automatically highlights and displays important topics in the call content. This makes it easier to review the call content later by highlighting important parts. Some or all of the above processing in the verification unit may be performed using AI or not.

[0127] The verification unit estimates the user's emotions and determines the priority of verification data based on the estimated user emotions. The verification unit uses AI to estimate the user's emotions and determine the priority of verification data. For example, if the user is nervous, the AI ​​will prioritize displaying important call content. If the user is relaxed, the AI ​​will prioritize displaying normal call content. If the user is in a hurry, the AI ​​will quickly prioritize displaying important call content. In this way, by prioritizing verification data based on the user's emotions, important call content can be displayed preferentially. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0128] The verification unit estimates the user's emotions and adjusts the display method of the verification data based on the estimated user emotions. The verification unit uses AI to estimate the user's emotions and adjusts the display method of the verification data. For example, if the user is nervous, the AI ​​provides a simple and highly visible display method. If the user is relaxed, the AI ​​provides a display method that includes detailed information. If the user is in a hurry, the AI ​​provides a display method that gets straight to the point. By adjusting the display method of the verification data based on the user's emotions, a highly visible display becomes possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0129] The verification unit improves verification accuracy by referring to the speaker's past call history during verification. The verification unit uses AI to refer to the speaker's past call history. For example, the AI ​​refers to the speaker's past call history to improve verification accuracy. The AI ​​extracts specific patterns from the speaker's past call history to improve verification accuracy. The AI ​​analyzes the speaker's past call history to improve verification accuracy. In this way, verification accuracy is improved by referring to the speaker's past call history. Some or all of the above processing in the verification unit may be performed using AI or without using AI.

[0130] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0131] The fraud prevention system can also include a notification unit. This unit automatically sends notifications to user-specified contacts when it determines a call is likely to be fraudulent. For example, by registering the contact information of family and friends, the system can send warning messages to these contacts when a call is deemed likely to be fraudulent. The notification unit can also send push notifications to the user's smartphone, allowing the user to receive real-time warnings about fraudulent calls. Furthermore, the notification unit can send detailed reports to the user's email address, allowing the user to review the details of the fraudulent call later.

[0132] The fraud prevention system can also include a feedback unit. This feedback unit allows users to provide feedback on the fraud detection results. For example, if a call identified as fraudulent by the user turns out not to be fraudulent, the user can provide this information to the feedback unit. Similarly, if a call that was not identified as fraudulent by the user turns out to be fraudulent, the user can provide feedback. This allows the feedback unit to collect user feedback and use it as training data for the AI, thereby improving the accuracy of fraud detection.

[0133] The fraud prevention system can also include a translation unit. This unit translates call content in real time and provides it to the user. For example, if a fraud call comes in in a foreign language, the translation unit can translate the call into the user's native language. The translation unit can also translate the user's statements into the foreign language and convey them to the caller. This allows users to deal with fraud calls despite language barriers. Furthermore, the translation unit can save a history of call translations for later review.

[0134] The fraud prevention system can also be equipped with a voice conversion unit. This unit can convert the user's voice before transmitting it to the other party. For example, if a user wants to change their voice, the voice conversion unit can convert the user's voice to a different voice before transmitting it to the other party. The voice conversion unit can also convert the user's voice to a male or female voice, allowing the user to conceal their voice during calls. Furthermore, the voice conversion unit can apply voice conversion to recorded call data.

[0135] The fraud prevention system may also include a call summarization function. This function automatically summarizes the call content and provides it to the user. For example, if a user wants to quickly review a long call, the summarization function can summarize the call and provide it to the user. The summarization function can also extract key points from the call and provide them to the user, allowing the user to quickly grasp the main points of the call. Furthermore, the summarization function can save the summary data for later review.

[0136] The fraud prevention system can also be equipped with an emotion analysis unit. The emotion analysis unit estimates the user's emotions from the call content and adjusts the accuracy of the call content analysis based on the estimated emotions. For example, if the user is angry, the emotion analysis unit can emphasize certain keywords to improve the accuracy of the call content analysis. Conversely, if the user is sad, the emotion analysis unit can set the accuracy of the call content analysis to normal mode. In this way, the emotion analysis unit can adjust the accuracy of the call content analysis based on the user's emotions, enabling more accurate analysis of the call content.

[0137] The fraud prevention system can also be equipped with an emotional feedback unit. This unit allows users to provide feedback on their emotions after a call. For example, users can input emotions such as "I felt relieved" or "I felt anxious" after a call. This allows the emotional feedback unit to collect user emotional data and use it as training data for the AI. This improves the accuracy of fraud detection. Furthermore, the emotional feedback unit can analyze the user's emotional data and provide appropriate advice to the user.

[0138] The fraud prevention system can also include an emotion notification unit. This unit estimates the user's emotions and sends notifications based on those estimates. For example, if the user is feeling stressed, the emotion notification unit can send a notification to the user's family or friends requesting support. Conversely, if the user is relaxed, the emotion notification unit can be configured not to send notifications. This allows the emotion notification unit to enhance the user's sense of security by sending appropriate notifications based on their emotions.

[0139] The fraud prevention system can also be equipped with an emotion recording unit. This unit records the user's emotions during a call, allowing for later review. For example, if the user was tense during the call, this emotion can be recorded and reviewed later. Similarly, if the user was relaxed during the call, this can also be recorded. This allows the emotion recording unit to accumulate user emotion data, which can then be used as training data for AI. This improves the accuracy of fraud detection.

[0140] The fraud prevention system may also include an emotional assistance unit. This unit estimates the user's emotions and provides assistance during the call based on those estimates. For example, if the user is feeling tense, the emotional assistance unit can offer advice to help them relax. Similarly, if the user is feeling anxious, the emotional assistance unit can provide reassuring messages. This allows the emotional assistance unit to improve the user's call experience by providing appropriate assistance based on their emotions.

[0141] The following briefly describes the processing flow for example form 2.

[0142] Step 1: The listening unit listens to the content of the call. For example, it listens to the content of calls from numbers other than registered phone numbers. The listening unit uses AI to analyze the call content in real time and extracts talk patterns. For example, it checks whether specific keywords or phrases are included. Step 2: The analysis unit analyzes the call content recorded by the listening unit. The analysis unit uses AI to analyze the call content and extract talk patterns. For example, it checks whether specific keywords or phrases are included. Step 3: The judgment unit determines the likelihood of a fraudulent call based on the talk pattern analyzed by the analysis unit. The judgment unit uses AI to determine if there are many similarities to actual fraud cases. For example, if there are many similarities to actual fraud cases, it determines that there is a high possibility that it is a fraudulent call. Step 4: The recording unit starts recording if the judgment unit determines that there is a high probability that the call is a scam. The recording unit uses AI to start recording. For example, if the probability of it being a scam reaches 70%, it will inform both the caller and the recipient, "This call may be a scam, so we will start recording."

[0143] 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.

[0144] 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.

[0145] 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.

[0146] Each of the multiple elements described above, including the listening unit, analysis unit, determination unit, recording unit, learning unit, storage unit, and verification unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the listening unit listens to the content of a call using the microphone 38B of the smart device 14 and analyzes it in real time using the control unit 46A. The analysis unit analyzes the content of a call using the identification processing unit 290 of the data processing unit 12 and extracts talk patterns. The determination unit determines the possibility of a fraudulent call using the identification processing unit 290 of the data processing unit 12. The recording unit starts recording using the control unit 46A of the smart device 14. The learning unit learns new tactics using the identification processing unit 290 of the data processing unit 12. The storage unit saves the recorded data in the database 24 of the data processing unit 12. The verification unit plays back the recorded data using the output device 40 of the smart device 14. 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.

[0147] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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).

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] Each of the multiple elements described above, including the listening unit, analysis unit, determination unit, recording unit, learning unit, storage unit, and verification unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the listening unit listens to the content of a call using the microphone 238 of the smart glasses 214 and analyzes it in real time using the control unit 46A. The analysis unit analyzes the content of a call using the identification processing unit 290 of the data processing unit 12 and extracts talk patterns. The determination unit determines the possibility of a fraudulent call using the identification processing unit 290 of the data processing unit 12. The recording unit starts recording using the control unit 46A of the smart glasses 214. The learning unit learns new methods using the identification processing unit 290 of the data processing unit 12. The storage unit saves the recorded data in the database 24 of the data processing unit 12. The verification unit plays back the recorded data using the speaker 240 of the smart glasses 214. 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.

[0163] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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).

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] Each of the multiple elements described above, including the listening unit, analysis unit, determination unit, recording unit, learning unit, storage unit, and verification unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the listening unit listens to the content of a call using the microphone 238 of the headset terminal 314 and analyzes it in real time using the control unit 46A. The analysis unit analyzes the content of a call using the identification processing unit 290 of the data processing unit 12 and extracts talk patterns. The determination unit determines the possibility of a fraudulent call using the identification processing unit 290 of the data processing unit 12. The recording unit starts recording using the control unit 46A of the headset terminal 314. The learning unit learns new methods using the identification processing unit 290 of the data processing unit 12. The storage unit saves the recorded data in the database 24 of the data processing unit 12. The verification unit plays back the recorded data using the speaker 240 of the headset terminal 314. 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.

[0179] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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).

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.).

[0192] 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.

[0193] 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.

[0194] 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.

[0195] Each of the multiple elements described above, including the listening unit, analysis unit, determination unit, recording unit, learning unit, storage unit, and verification unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the listening unit listens to the content of a call using the microphone 238 of the robot 414 and analyzes it in real time using the control unit 46A. The analysis unit analyzes the content of a call using the identification processing unit 290 of the data processing unit 12 and extracts talk patterns. The determination unit determines the possibility of a fraudulent call using the identification processing unit 290 of the data processing unit 12. The recording unit starts recording using the control unit 46A of the robot 414. The learning unit learns new methods using the identification processing unit 290 of the data processing unit 12. The storage unit saves the recorded data in the database 24 of the data processing unit 12. The verification unit plays back the recorded data using the speaker 240 of the robot 414. 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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."

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] (Note 1) A listening unit that takes in the content of the call, An analysis unit analyzes the content of the conversation heard by the aforementioned listening unit, A determination unit that determines the possibility of a fraudulent call based on the talk pattern analyzed by the analysis unit, The system includes a recording unit that starts recording when the determination unit determines that there is a high probability that the call is a scam. A system characterized by the following features. (Note 2) It includes a learning unit for studying new techniques. The system described in Appendix 1, characterized by the features described herein. (Note 3) Equipped with a storage unit for saving recorded data. The system described in Appendix 1, characterized by the features described herein. (Note 4) It is equipped with a verification unit to check the recorded data. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned listening unit is Listen to the content of incoming calls from numbers other than registered phone numbers. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, Check if it contains specific keywords or phrases. The system described in Appendix 1, characterized by the features described herein. (Note 7) The determination unit, Determining the likelihood of a phone call being a scam based on numerous similarities to previous fraud cases. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned recording unit is Recording will begin if the call is determined to be highly likely to be a scam call. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned listening unit is It estimates the user's emotions and adjusts the accuracy of call content recognition based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned listening unit is Add a feature that automatically removes background noise and other sounds when listening to phone calls. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned listening unit is During the recording of the call, the tone and speed of the speaker's voice are analyzed to identify factors that increase the likelihood of fraud. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned listening unit is The system estimates the user's emotions and determines the priority of interviews based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned listening unit is When listening to call content, the system improves analysis accuracy by taking into account the speaker's geographical accent and dialect. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned listening unit is When listening to the content of a call, the system improves listening accuracy by referring to the speaker's past call history. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, It estimates the user's emotions and adjusts the analysis algorithm based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, During analysis, the importance of specific keywords and phrases is evaluated by considering the context of the call content. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During the analysis, the speaker's tone of voice and emotions are analyzed to identify factors that increase the likelihood of fraud. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, During analysis, we improve the accuracy of the analysis by taking into account the temporal changes in the content of the call. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned analysis unit, During analysis, the speaker's past call history is referenced to improve analysis accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 21) The determination unit, The system estimates the user's emotions and adjusts the criteria for determining the likelihood of a fraudulent call based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The determination unit, When making a determination, the likelihood of fraud is assessed by considering the context of the call content. The system described in Appendix 1, characterized by the features described herein. (Note 23) The determination unit, During the assessment, the speaker's tone of voice and emotions are analyzed to identify factors that increase the likelihood of fraud. The system described in Appendix 1, characterized by the features described herein. (Note 24) The determination unit, The system estimates the user's emotions and adjusts how the judgment results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The determination unit, When making a judgment, the accuracy of the judgment is improved by taking into account the temporal changes in the content of the call. The system described in Appendix 1, characterized by the features described herein. (Note 26) The determination unit, During the assessment process, the speaker's past call history is referenced to improve the accuracy of the assessment. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned recording unit is It estimates the user's emotions and adjusts the recording start time based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned recording unit is Add a feature that automatically highlights important parts of a call during recording. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned recording unit is Add a feature to automatically remove noise from call content during recording. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned recording unit is It estimates the user's emotions and determines the priority of recordings based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned recording unit is During recording, the system improves recording accuracy by taking into account the temporal changes in the content of the call. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned recording unit is During recording, the system improves recording accuracy by referencing the speaker's past call history. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past fraud cases. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 36) The aforementioned learning unit, During training, the training data is weighted to take into account the temporal changes in the content of the call. The system described in Appendix 2, characterized by the features described herein. (Note 37) The aforementioned storage unit is The system estimates the user's emotions and selects data to store based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned storage unit is Add a feature that automatically highlights important parts of the call content when saving. The system described in Appendix 3, characterized by the features described herein. (Note 39) The aforementioned storage unit is It estimates the user's emotions and determines the priority of stored data based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 40) The aforementioned storage unit is When saving, the accuracy of saving is improved by taking into account the temporal changes in the call content. The system described in Appendix 3, characterized by the features described herein. (Note 41) The aforementioned verification unit is It estimates the user's emotions and adjusts how confirmation data is displayed based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 42) The aforementioned verification unit is Add a feature that automatically highlights important parts of the call content during review. The system described in Appendix 4, characterized by the features described herein. (Note 43) The aforementioned verification unit is The system estimates the user's emotions and prioritizes confirmation data based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 44) The aforementioned verification unit is During verification, we improve verification accuracy by taking into account the temporal changes in the call content. The system described in Appendix 4, characterized by the features described herein. (Note 45) The aforementioned verification unit is During verification, the accuracy of the verification is improved by referring to the speaker's past call history. The system described in Appendix 4, characterized by the features described herein. (Note 46) The aforementioned verification unit is During verification, we improve verification accuracy by taking into account the temporal changes in the call content. The system described in Appendix 4, characterized by the features described herein. (Note 47) The aforementioned verification unit is Add a feature that automatically highlights important parts of the call content during review. The system described in Appendix 4, characterized by the features described herein. (Note 48) The aforementioned verification unit is The system estimates the user's emotions and prioritizes confirmation data based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 49) The aforementioned verification unit is It estimates the user's emotions and adjusts how confirmation data is displayed based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 50) The aforementioned verification unit is During verification, the accuracy of the verification is improved by referring to the speaker's past call history. The system described in Appendix 4, characterized by the features described herein. [Explanation of Symbols]

[0215] 10, 210, 310, 410 data processing systems 12 data processing devices 14 smart devices 214 smart glasses 314 headset-type terminals 414 robots

Claims

1. A listening unit that takes in the content of the call, An analysis unit analyzes the content of the conversation heard by the aforementioned listening unit, A determination unit that determines the possibility of a fraudulent call based on the talk pattern analyzed by the analysis unit, The system includes a recording unit that starts recording when the determination unit determines that there is a high probability that the call is a scam. A system characterized by the following features.

2. It includes a learning unit for studying new techniques. The system according to feature 1.

3. Equipped with a storage unit for saving recorded data. The system according to feature 1.

4. It is equipped with a verification unit to check the recorded data. The system according to feature 1.

5. The aforementioned listening unit is Listen to the content of incoming calls from numbers other than registered phone numbers. The system according to feature 1.

6. The aforementioned analysis unit, Check if it contains specific keywords or phrases. The system according to feature 1.

7. The determination unit, Determining the likelihood of a phone call being a scam based on numerous similarities to previous fraud cases. The system according to feature 1.

8. The aforementioned recording unit is Recording will begin if the call is determined to be highly likely to be a scam call. The system according to feature 1.

9. The aforementioned listening unit is It estimates the user's emotions and adjusts the accuracy of call content recognition based on the estimated emotions. The system according to feature 1.

10. The aforementioned listening unit is Add a feature that automatically removes background noise and other sounds when listening to phone calls. The system according to feature 1.

Images