system

Abstract

The system according to the embodiment aims to prevent damage from special frauds committed over the telephone. [Solution] A system according to an embodiment includes an analysis unit, a warning unit, and a termination unit. The analysis unit analyzes the content of a call. The warning unit issues a warning when a risk of fraud is detected based on the content of the call analyzed by the analysis unit. The termination unit terminates the call when a warning is issued by the warning unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem of making it difficult to prevent special frauds committed over the phone.

[0005] The system according to the embodiment aims to prevent damage from special frauds committed over the telephone. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a warning unit, and a termination unit. The analysis unit analyzes the content of the call. The warning unit issues a warning when a fraud risk is detected based on the call content analyzed by the analysis unit. The termination unit terminates the call when the warning is issued by the warning unit. [Effects of the Invention]

[0007] The system according to the embodiment can prevent special frauds committed over the phone before they occur. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A fraud prevention system according to an embodiment of the present invention is a system for preventing telephone fraud. The fraud prevention system analyzes the content of calls and issues a warning and terminates the call if there is a possibility of fraud. The fraud prevention system analyzes the content of calls, detects keywords and phrases that may be fraudulent, and issues a warning in real time. For example, if keywords such as "investment," "billing," or "solicitation" are included, the fraud prevention system issues a warning. The fraud prevention system then records the call and makes it available for later review. This allows family members or experts to review the content and determine whether there is a possibility of fraud. Furthermore, the fraud prevention system has the function of analyzing the content of calls and automatically terminating the call if there is a high possibility of fraud. This significantly reduces the risk of elderly people being involved in fraud. For example, the fraud prevention system is provided as an application that can be installed on smartphones or landlines. For example, the fraud prevention system is designed to have a simple interface and easy operation for elderly users. As a result, the fraud prevention system can prevent telephone fraud and protect the safety of elderly people. This allows the fraud prevention system to prevent special telephone frauds and protect the safety of the elderly. For example, the fraud prevention system can analyze the content of calls and issue a warning and terminate the call if there is a possibility of fraud, thereby preventing fraud before it occurs. The fraud prevention system can also record the content of calls and make them available for later review, allowing family members or experts to review the content of the call and determine whether it is a possible fraud. This can significantly reduce the risk of the elderly becoming victims of fraud.

[0029] The fraud prevention system according to the embodiment includes an analysis unit, a warning unit, and a termination unit. The analysis unit analyzes the content of the call. For example, the analysis unit converts the content of the call into text data using voice recognition technology and analyzes it using natural language processing technology. The analysis unit can also assess the risk of fraud using a machine learning algorithm. For example, the analysis unit analyzes keywords and phrases in the content of the call to assess the risk of fraud. The warning unit issues a warning when a risk of fraud is detected based on the content of the call analyzed by the analysis unit. The warning unit can issue a warning using methods such as an audio warning, a text message, or a screen display. For example, the warning unit can issue a strong warning when the risk of fraud is high. The termination unit terminates the call when a warning is issued by the warning unit. The termination unit can use, for example, a method of automatically disconnecting the call or a method of prompting the caller to end the call. For example, the termination unit can immediately end the call when the risk of fraud is high. As a result, the fraud prevention system according to the embodiment can analyze the contents of a call, and if there is a possibility of fraud, issue a warning and terminate the call, thereby preventing fraud damage before it occurs.

[0030] The fraud prevention system includes a recording unit that records the contents of a call. The recording unit records the contents of the call. The recording unit can, for example, start recording simultaneously with the start of the call. The recording unit can also use an audio file format or a text file format to save the recorded data. For example, the recording unit can save the contents of the call as an audio file so that it can be played back later. The recording unit can also save the contents of the call as text data so that it can be searched and analyzed later. In this way, by recording the contents of the call, it is possible to check them later. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can record the contents of the call, input the recorded data into a generation AI, and have the generation AI analyze the recorded data.

[0031] The fraud prevention system includes a confirmation unit that confirms the contents of the recorded call. The confirmation unit confirms the contents of the recorded call. The confirmation unit, for example, has a function of playing back the recorded data. The confirmation unit also has a function of displaying the recorded data as text data. For example, the confirmation unit can play back the recorded data and confirm the contents of the call. The confirmation unit can also display the recorded data as text data and confirm the contents of the call. In this way, by checking the contents of the recorded call, it is possible to determine whether there is a possibility of fraud. Some or all of the above-mentioned processing in the confirmation unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation unit can input the recorded data to a generation AI and have the generation AI confirm the contents of the call.

[0032] The fraud prevention system includes a providing unit that provides a database for the AI ​​to learn from. The providing unit provides the database for the AI ​​to learn from. The providing unit can provide, for example, a fraud case database or a database of call content. The providing unit can also use a relational database or a NoSQL database as the database format. For example, the providing unit provides a fraud case database so that the AI ​​can learn fraud patterns. The providing unit also provides a database of call content so that the AI ​​can improve its analysis accuracy of the call content. By providing a database for the AI ​​to learn from, the analysis accuracy can be improved. Some or all of the above-described processing in the providing unit can be performed, for example, using AI, or can be performed without using AI. For example, the providing unit can input the database to the generation AI and have the generation AI manage the database.

[0033] The analysis unit can analyze the call content using natural language processing technology. The analysis unit analyzes the call content using natural language processing technology. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit uses morphological analysis to divide words in the call content and uses grammatical analysis to analyze the sentence structure. The analysis unit can also use semantic analysis to understand the meaning of the call content and evaluate the risk of fraud. This improves the accuracy of the analysis of the call content by using natural language processing technology. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the call content to a generation AI and have the generation AI perform analysis using natural language processing technology.

[0034] The warning unit can detect keywords or phrases that pose a high risk of fraud. The warning unit detects keywords or phrases that pose a high risk of fraud. To detect keywords or phrases, for example, a specific word list or co-occurrence network analysis can be used. For example, the warning unit can use a specific word list to detect keywords included in the content of the call. The warning unit can also use co-occurrence network analysis to analyze phrases in the content of the call and evaluate the risk of fraud. This makes it possible to detect keywords or phrases that pose a high risk of fraud and issue a fraud warning. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the content of the call into a generation AI and cause the generation AI to detect keywords and phrases.

[0035] The termination unit can automatically terminate a call when the risk of fraud is high. The termination unit automatically terminates a call when the risk of fraud is high. Methods of terminating a call include, for example, automatically disconnecting the call or prompting the caller to end the call. For example, the termination unit immediately terminates the call when the risk of fraud is high. The termination unit can also terminate the call after issuing a warning when the risk of fraud is medium. This makes it possible to prevent fraud by automatically terminating a call when the risk of fraud is high. Some or all of the above-mentioned processing in the termination unit may be performed using, or without, AI, for example. For example, the termination unit can input the content of the call into a generation AI and have the generation AI make the decision to end the call.

[0036] The analysis unit can analyze background sounds of a call and identify factors that increase the likelihood of fraud. The analysis unit can analyze background sounds of a call and identify factors that increase the likelihood of fraud. Analysis of background sounds can include, for example, noise reduction, speech recognition, and acoustic analysis. For example, the analysis unit can identify environmental sounds that are likely to be fraudulent (e.g., call center-like sounds) from the background sounds heard during a call. The analysis unit can also identify environmental sounds that are unlikely to be fraudulent (e.g., household sounds) from the background sounds heard during a call. Furthermore, the analysis unit can detect specific sounds (e.g., other people's voices) from the background sounds heard during a call and evaluate the likelihood of fraud. In this way, factors that increase the likelihood of fraud can be identified by analyzing the background sounds of a call. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input background sound data to a generation AI and cause the generation AI to analyze the background sound.

[0037] The analysis unit can perform analysis taking into account the time of the call and the caller's past call history. The analysis unit performs analysis taking into account the time of the call and the caller's past call history. Methods that take the time of the call into account include, for example, risk assessment for each time period and analysis of past call history. For example, if a call is made late at night, the analysis unit determines that there is a high possibility of fraud and improves the accuracy of the analysis. The analysis unit can also analyze the caller's past call history to identify patterns that are likely to be fraudulent. Furthermore, the analysis unit can identify time periods when there is a high possibility of fraud (e.g., daytime on weekdays) based on the time of the call and adjust the accuracy of the analysis. This allows for a more accurate assessment of the possibility of fraud by taking into account the time of the call and the caller's past call history. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input call time period data and call history data into a generation AI and have the generation AI perform the analysis.

[0038] The analysis unit can analyze the caller's voice tone and speed to evaluate the possibility of fraud. The analysis unit can analyze the caller's voice tone and speed to evaluate the possibility of fraud. Methods for analyzing voice tone and speed include, for example, a voice analysis algorithm and extraction of acoustic features. For example, if the caller's voice tone suddenly changes, the analysis unit can determine that there is a high possibility of fraud and increase the accuracy of the analysis. The analysis unit can also determine that there is a high possibility of fraud and increase the accuracy of the analysis if the caller's speaking speed is abnormally fast. Furthermore, the analysis unit can determine that there is a high possibility of fraud and increase the accuracy of the analysis if the caller's voice tone and speed are not constant. In this way, the possibility of fraud can be evaluated by analyzing the caller's voice tone and speed. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the caller's voice tone and speed data into a generation AI and have the generation AI perform the analysis.

[0039] The analysis unit can perform analysis taking into account the caller's geographic location information. The analysis unit performs analysis taking into account the caller's geographic location information. Methods for taking into account geographic location information include, for example, GPS data and location information services. For example, if the caller is in an area where fraud is prevalent, the analysis unit determines that there is a high possibility of fraud and increases the accuracy of the analysis. Alternatively, if the caller is in a safe area, the analysis unit can analyze the call content with normal analysis accuracy. Furthermore, the analysis unit can identify areas where there is a high possibility of fraud based on the caller's geographic location information and adjust the accuracy of the analysis. This allows for a more accurate assessment of the possibility of fraud by taking into account the caller's geographic location information. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the caller's geographic location information data into a generation AI and have the generation AI perform the analysis.

[0040] The analysis unit can analyze the caller's social media activity to assess the possibility of fraud. The analysis unit can analyze the caller's social media activity to assess the possibility of fraud. Analysis of social media activity includes, for example, analysis of posted content and analysis of followers. For example, the analysis unit can analyze the caller's social media posts to identify patterns that are likely to be fraud. The analysis unit can also analyze the caller's social media friendships to identify relationships that are likely to be fraud. Furthermore, the analysis unit can analyze the frequency of the caller's social media activity to assess the possibility of fraud. In this way, the possibility of fraud can be assessed by analyzing the caller's social media activity. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the caller's social media data into a generation AI and have the generation AI perform the analysis.

[0041] The analysis unit can customize the analysis method by reflecting the caller's past feedback. The analysis unit customizes the analysis method by reflecting the caller's past feedback. Reflecting feedback includes, for example, analyzing user ratings and comments. For example, the analysis unit customizes the analysis method based on feedback provided by the caller in the past. The analysis unit can also identify patterns that are likely to be fraudulent from the caller's past feedback and adjust the analysis method. Furthermore, the analysis unit can improve the accuracy of the analysis by reflecting the caller's past feedback. In this way, the analysis method can be customized and accuracy can be improved by reflecting the caller's past feedback. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the caller's feedback data into a generation AI and have the generation AI customize the analysis method.

[0042] The warning unit can adjust the intensity of the warning based on the level of the possibility of fraud. The warning unit adjusts the intensity of the warning based on the level of the possibility of fraud. Methods for adjusting the intensity of the warning include, for example, adjusting the volume or emphasizing the message. For example, the warning unit issues a strong warning when the possibility of fraud is high. The warning unit can also issue a normal warning when the possibility of fraud is medium. Furthermore, the warning unit can also issue a mild warning when the possibility of fraud is low. In this way, by adjusting the intensity of the warning based on the level of the possibility of fraud, an appropriate warning can be issued. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input fraud possibility data to the generation AI and have the generation AI adjust the intensity of the warning.

[0043] The warning unit can display different warning messages depending on the category of the call content. The warning unit displays different warning messages depending on the category of the call content. The displayed warning messages include messages according to categories such as investment fraud, billing fraud, and solicitation fraud. For example, in the case of investment fraud, the warning unit displays a warning message about investment. In the case of billing fraud, the warning unit can also display a warning message about billing. Furthermore, in the case of solicitation fraud, the warning unit can also display a warning message about solicitation. In this way, by displaying different warning messages depending on the category of the call content, a more specific warning can be issued. Some or all of the above-mentioned processing in the warning unit may be performed, for example, using AI, or may be performed without using AI. For example, the warning unit can input call content category data into a generation AI and cause the generation AI to display a warning message.

[0044] The warning unit can improve the accuracy of the warning by referring to the caller's past warning history. The warning unit improves the accuracy of the warning by referring to the caller's past warning history. Reference to the warning history includes, for example, the content of past warnings and the frequency of warnings. For example, the warning unit analyzes the caller's past warning history to identify patterns that are likely to be fraudulent. The warning unit can also improve the accuracy of the warning based on the caller's past warning history. Furthermore, the warning unit can also customize the warning message by referring to the caller's past warning history. In this way, the accuracy of the warning can be improved by referring to the caller's past warning history. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the caller's warning history data into the generation AI and cause the generation AI to improve the accuracy of the warning.

[0045] The warning unit can determine the priority of the warning based on the time period of the call. The warning unit determines the priority of the warning based on the time period of the call. Methods for determining the priority of the warning include, for example, risk assessment and consideration of the time period. For example, the warning unit sets a high priority of the warning for a late-night call. The warning unit can also issue a warning with normal priority for a daytime call. Furthermore, the warning unit can set a medium priority of the warning for an early-morning call. In this way, by determining the priority of the warning based on the time period of the call, it is possible to issue a warning with an appropriate priority. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input call time period data to a generation AI and cause the generation AI to determine the priority of the warning.

[0046] The warning unit can adjust the order of warnings based on the relevance of the calls. The warning unit adjusts the order of warnings based on the relevance of the calls. Methods for adjusting the order of warnings include, for example, evaluating the relevance or determining the importance. For example, if there is a high possibility of investment fraud, the warning unit can issue a warning about investments as a top priority. Also, if there is a high possibility of billing fraud, the warning unit can issue a warning about billing as a top priority. Furthermore, if there is a high possibility of solicitation fraud, the warning unit can issue a warning about solicitation as a top priority. In this way, by adjusting the order of warnings based on the relevance of the calls, warnings can be issued in an appropriate order. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input call relevance data to a generation AI and have the generation AI adjust the order of warnings.

[0047] The warning unit can adjust the content of the warning according to the caller's expertise level. The warning unit adjusts the content of the warning according to the caller's expertise level. Methods for adjusting the content of the warning include, for example, survey results and past call content. For example, the warning unit provides detailed warning content when the caller has expertise. The warning unit can also provide concise warning content when the caller does not have expertise. Furthermore, the warning unit can customize the warning content according to the caller's expertise level. As a result, appropriate warning content can be provided by adjusting the warning content according to the caller's expertise level. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the caller's expertise data into a generation AI and cause the generation AI to adjust the warning content.

[0048] The termination unit can select a termination method based on the content of the call. The termination unit selects a termination method based on the content of the call. Methods for selecting a termination method include, for example, automatic disconnection and notifying the caller. For example, the termination unit immediately terminates the call if there is a high possibility of fraud. Furthermore, the termination unit can terminate the call after issuing a warning if there is a medium possibility of fraud. Furthermore, the termination unit can terminate the call in a normal manner if there is a low possibility of fraud. In this way, by selecting a termination method based on the content of the call, it is possible to terminate the call in an appropriate manner. Some or all of the above-mentioned processing in the termination unit may be performed using, for example, AI, or may be performed without using AI. For example, the termination unit can input call content data into a generation AI and have the generation AI select a termination method.

[0049] The termination unit can optimize the termination method by referring to the caller's past call termination history. The termination unit optimizes the termination method by referring to the caller's past call termination history. Reference to the call termination history includes, for example, past termination methods and termination timings. For example, the termination unit analyzes the caller's past call termination history and selects the optimal termination method. The termination unit can also identify patterns that are likely to be fraudulent based on the caller's past call termination history. Furthermore, the termination unit can customize the termination method by referring to the caller's past call termination history. In this way, the optimal termination method can be selected by referring to the caller's past call termination history. Some or all of the above-mentioned processing in the termination unit may be performed, for example, using AI, or may be performed without using AI. For example, the termination unit can input the caller's call termination history data into a generation AI and cause the generation AI to optimize the termination method.

[0050] The termination unit can improve the termination method by reflecting the caller's feedback. The termination unit improves the termination method by reflecting the caller's feedback. Reflecting the feedback includes, for example, analyzing user ratings and comments. For example, the termination unit improves the termination method based on the caller's feedback. The termination unit can also identify patterns that are likely to be fraudulent from the caller's feedback. Furthermore, the termination unit can customize the termination method by reflecting the caller's feedback. In this way, by reflecting the caller's feedback, the termination method can be improved and a more appropriate termination can be achieved. Some or all of the above-mentioned processing in the termination unit may be performed, for example, using AI or without AI. For example, the termination unit can input the caller's feedback data into a generation AI and have the generation AI execute improvements to the termination method.

[0051] The termination unit can select a termination method taking into account the geographic distribution of the call. The termination unit selects a termination method taking into account the geographic distribution of the call. Methods that take geographic distribution into account include, for example, regional risk assessment and location-based services. For example, the termination unit immediately terminates the call if the caller is in a fraud-prone area. The termination unit can also terminate the call in a normal manner if the caller is in a safe area. Furthermore, the termination unit can identify areas with a high probability of fraud based on the geographic distribution of the caller and adjust the termination method. In this way, the call can be terminated in an appropriate manner by taking into account the geographic distribution of the call. Some or all of the above-described processing in the termination unit may be performed using, for example, AI, or may be performed without using AI. For example, the termination unit can input call geographic distribution data into a generation AI and have the generation AI select a termination method.

[0052] The termination unit can optimize the termination method by referring to literature related to the call. The termination unit can optimize the termination method by referring to literature related to the call. References to related literature include, for example, academic papers and technical reports. For example, the termination unit can refer to literature related to the content of the call and select the optimal termination method. The termination unit can also identify patterns that are likely to be fraudulent from literature related to the content of the call. Furthermore, the termination unit can customize the termination method based on literature related to the content of the call. In this way, the optimal termination method can be selected by referring to literature related to the call. Some or all of the above-mentioned processing in the termination unit can be performed, for example, using AI or without AI. For example, the termination unit can input literature data related to the call into a generation AI and cause the generation AI to optimize the termination method.

[0053] The termination unit can select a termination method taking into account the market value of the call. The termination unit selects a termination method taking into account the market value of the call. Methods that take market value into account include, for example, the importance and economic value of the call content. For example, the termination unit can carefully terminate a call if the call content contains high-value information. The termination unit can also quickly terminate a call if the call content contains low-value information. Furthermore, the termination unit can customize the termination method based on the market value of the call. This makes it possible to terminate a call in an appropriate manner by taking into account the market value of the call. Some or all of the above-mentioned processing in the termination unit may be performed using, for example, AI, or may be performed without using AI. For example, the termination unit can input market value data of the call into a generation AI and have the generation AI select a termination method.

[0054] The recording unit can adjust the level of detail of the recording based on the importance of the call. The recording unit adjusts the level of detail of the recording based on the importance of the call. Methods for adjusting the level of detail of the recording include, for example, setting the sound quality and the length of the recording time. For example, the recording unit performs detailed recording when the content of the call is important. The recording unit can also perform normal recording when the content of the call is of medium importance. Furthermore, the recording unit can also perform simplified recording when the content of the call is of low importance. In this way, by adjusting the level of detail of the recording based on the importance of the call, it is possible to record with an appropriate level of detail. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input call importance data to a generation AI and have the generation AI adjust the level of detail of the recording.

[0055] The recording unit can apply different recording algorithms depending on the call category. The recording unit applies different recording algorithms depending on the call category. Application of recording algorithms includes, for example, compression algorithms and noise reduction algorithms. For example, in the case of investment fraud, the recording unit can apply a recording algorithm related to investment. In addition, in the case of billing fraud, the recording unit can also apply a recording algorithm related to billing. Furthermore, in the case of solicitation fraud, the recording unit can also apply a recording algorithm related to solicitation. In this way, by applying different recording algorithms depending on the call category, appropriate recording can be performed. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input call category data into a generation AI and have the generation AI apply the recording algorithm.

[0056] The recording unit can improve the accuracy of the recording by referring to the caller's past recording history. The recording unit improves the accuracy of the recording by referring to the caller's past recording history. Reference to the recording history includes, for example, past recording data and recording frequency. For example, the recording unit analyzes the caller's past recording history and selects the optimal recording method. The recording unit can also improve the accuracy of the recording based on the caller's past recording history. Furthermore, the recording unit can also customize the recording method by referring to the caller's past recording history. In this way, the accuracy of the recording can be improved by referring to the caller's past recording history. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input the caller's recording history data into a generation AI and have the generation AI improve the accuracy of the recording.

[0057] The recording unit can determine the recording priority based on the time of submission of the call. The recording unit determines the recording priority based on the time of submission of the call. Methods for determining the recording priority include, for example, the importance of the call and the time of submission. For example, the recording unit sets a high recording priority for an emergency call. The recording unit can also record at a normal priority for a normal call. Furthermore, the recording unit can set a low recording priority for a non-urgent call. In this way, by determining the recording priority based on the time of submission of the call, recording can be performed at an appropriate priority. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input call submission time data to a generation AI and have the generation AI determine the recording priority.

[0058] The recording unit can adjust the order of recordings based on the relevance of the calls. The recording unit adjusts the order of recordings based on the relevance of the calls. Methods for adjusting the order of recordings include, for example, evaluating the relevance and determining the importance. For example, if there is a high possibility of investment fraud, the recording unit can give top priority to recordings related to investments. Furthermore, if there is a high possibility of billing fraud, the recording unit can also give top priority to recordings related to billing. Furthermore, if there is a high possibility of solicitation fraud, the recording unit can also give top priority to recordings related to solicitations. In this way, by adjusting the order of recordings based on the relevance of the calls, recordings can be made in an appropriate order. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input call relevance data to a generation AI and have the generation AI adjust the order of recordings.

[0059] The recording unit can adjust the use of technical terms in the recording according to the caller's level of expertise. The recording unit adjusts the use of technical terms in the recording according to the caller's level of expertise. Methods for adjusting the use of technical terms include, for example, the caller's level of expertise and the difficulty of the terminology. For example, if the caller has technical expertise, the recording unit can record using detailed technical terms. Alternatively, if the caller does not have technical expertise, the recording unit can record using concise terms. Furthermore, the recording unit can customize the technical terms in the recording according to the caller's level of expertise. In this way, by adjusting the use of technical terms in the recording according to the caller's level of expertise, it is possible to record using appropriate terminology. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without AI. For example, the recording unit can input the caller's technical expertise data into a generation AI and have the generation AI adjust the use of technical terms.

[0060] The confirmation unit can adjust the level of detail of the confirmation based on the importance of the call. The confirmation unit adjusts the level of detail of the confirmation based on the importance of the call. Methods for adjusting the level of detail of the confirmation include, for example, the depth of the confirmation content and the amount of displayed information. For example, the confirmation unit performs detailed confirmation when the call content is important. The confirmation unit can also perform normal confirmation when the call content is of medium importance. Furthermore, the confirmation unit can also perform simple confirmation when the call content is of low importance. In this way, by adjusting the level of detail of the confirmation based on the importance of the call, confirmation can be performed with an appropriate level of detail. Some or all of the above-mentioned processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input call importance data to a generation AI and cause the generation AI to adjust the level of detail of the confirmation.

[0061] The verification unit can apply different verification algorithms depending on the call category. The verification unit applies different verification algorithms depending on the call category. Examples of application of verification algorithms include data mining algorithms and machine learning algorithms. For example, in the case of investment fraud, the verification unit applies a verification algorithm related to investment. In addition, in the case of billing fraud, the verification unit can also apply a verification algorithm related to billing. Furthermore, in the case of solicitation fraud, the verification unit can also apply a verification algorithm related to solicitation. In this way, by applying different verification algorithms depending on the call category, appropriate verification can be performed. Some or all of the above-mentioned processing in the verification unit may be performed using, for example, AI, or may be performed without using AI. For example, the verification unit can input call category data into the generation AI and cause the generation AI to apply the verification algorithm.

[0062] The confirmation unit can improve the accuracy of confirmation by referring to the caller's past confirmation history. The confirmation unit improves the accuracy of confirmation by referring to the caller's past confirmation history. Reference to the confirmation history includes, for example, past confirmation data and the frequency of confirmation. For example, the confirmation unit analyzes the caller's past confirmation history and selects the optimal confirmation method. The confirmation unit can also improve the accuracy of confirmation based on the caller's past confirmation history. Furthermore, the confirmation unit can also customize the confirmation method by referring to the caller's past confirmation history. In this way, the accuracy of confirmation can be improved by referring to the caller's past confirmation history. Some or all of the above-mentioned processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input the caller's confirmation history data into the generation AI and cause the generation AI to improve the accuracy of confirmation.

[0063] The confirmation unit can determine the confirmation priority based on the time of submission of the call. The confirmation unit determines the confirmation priority based on the time of submission of the call. Methods for determining the confirmation priority include, for example, the importance of the call and the time of submission. For example, the confirmation unit sets a high confirmation priority for an emergency call. The confirmation unit can also perform confirmation with a normal priority for a normal call. Furthermore, the confirmation unit can set a low confirmation priority for a non-urgent call. In this way, by determining the confirmation priority based on the time of submission of the call, confirmation can be performed with an appropriate priority. Some or all of the above-mentioned processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input call submission time data into the generation AI and cause the generation AI to determine the confirmation priority.

[0064] The confirmation unit can adjust the order of confirmation based on the relevance of the calls. The confirmation unit adjusts the order of confirmation based on the relevance of the calls. Methods for adjusting the order of confirmation include, for example, evaluating the relevance or determining the importance. For example, if there is a high possibility of investment fraud, the confirmation unit can give top priority to confirmation related to investments. Furthermore, if there is a high possibility of billing fraud, the confirmation unit can also give top priority to confirmation related to billing. Furthermore, if there is a high possibility of solicitation fraud, the confirmation unit can also give top priority to confirmation related to solicitation. In this way, by adjusting the order of confirmation based on the relevance of the calls, confirmation can be performed in an appropriate order. Some or all of the above-mentioned processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input call relevance data to a generation AI and have the generation AI adjust the order of confirmation.

[0065] The verification unit can adjust the use of technical terms for confirmation according to the caller's level of expertise. The verification unit adjusts the use of technical terms for confirmation according to the caller's level of expertise. Methods for adjusting the use of technical terms include, for example, the caller's level of expertise and the difficulty level of terminology. For example, the verification unit can use detailed technical terms for confirmation if the caller has technical knowledge. Alternatively, the verification unit can use concise terms for confirmation if the caller does not have technical knowledge. Furthermore, the verification unit can customize the technical terms for confirmation according to the caller's level of expertise. This allows confirmation to be performed using appropriate terms by adjusting the use of technical terms for confirmation according to the caller's level of expertise. Some or all of the above-described processing in the verification unit may be performed using, for example, AI, or may be performed without AI. For example, the verification unit can input the caller's expertise data into a generation AI and cause the generation AI to adjust the use of technical terms.

[0066] The providing unit can optimize the providing algorithm by referring to past provided data. The providing unit optimizes the providing algorithm by referring to past provided data. Optimization of the providing algorithm includes, for example, a recommendation algorithm or a data mining algorithm. For example, the providing unit analyzes the effectiveness of data provided in the past and selects an optimal providing algorithm. The providing unit can also identify patterns with a high probability of fraud based on the past provided data. Furthermore, the providing unit can customize the providing algorithm by referring to the past provided data. In this way, by referring to the past provided data, the providing algorithm can be optimized and appropriate data can be provided. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input past provided data into a generation AI and cause the generation AI to optimize the providing algorithm.

[0067] The providing unit can update the provided data by reflecting the caller's feedback. The providing unit updates the provided data by reflecting the caller's feedback. Updating the provided data includes, for example, a method for reflecting the feedback and a frequency for updating the data. For example, the providing unit updates the provided data based on the caller's feedback. The providing unit can also identify patterns that are likely to be fraudulent from the caller's feedback. Furthermore, the providing unit can customize the provided data by reflecting the caller's feedback. In this way, the provided data can be updated and appropriate data can be provided by reflecting the caller's feedback. Some or all of the above-described processing in the providing unit may be performed, for example, using AI or may be performed without using AI. For example, the providing unit can input the caller's feedback data to a generating AI and cause the generating AI to update the provided data.

[0068] The providing unit can select the data to be provided taking into account the caller's current situation. The providing unit selects the data to be provided taking into account the caller's current situation. Methods for considering the current situation include, for example, the progress of the call and the caller's environment. For example, the providing unit provides concise data when the caller is on the move. The providing unit can also provide detailed data when the caller is at home. Furthermore, the providing unit can select optimal data to be provided based on the caller's current situation. This makes it possible to provide appropriate data by taking into account the caller's current situation. Some or all of the above-described processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input the caller's current situation data into the generating AI and cause the generating AI to select the data to be provided.

[0069] The providing unit can weight the provided data based on the submission time of the call. The providing unit weights the provided data based on the submission time of the call. Methods for weighting the provided data include, for example, the submission time and the importance of the data. For example, the providing unit sets a high weighting for the provided data in the case of an emergency call. The providing unit can also provide data with a normal weighting in the case of a normal call. Furthermore, the providing unit can set a low weighting for the provided data in the case of a non-urgent call. In this way, by weighting the provided data based on the submission time of the call, data can be provided with an appropriate weighting. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input call submission time data to a generation AI and cause the generation AI to weight the provided data.

[0070] The providing unit can integrate information from different data sources to enrich the provided data. The providing unit integrates information from different data sources to enrich the provided data. Integration of different data sources includes, for example, external databases and internal databases. For example, the providing unit integrates information from different data sources to enrich the provided data. The providing unit can also identify patterns with a high likelihood of fraud based on information from different data sources. Furthermore, the providing unit can customize the provided data by referring to information from different data sources. In this way, the provided data can be enriched and appropriate data can be provided by integrating information from different data sources. Some or all of the above-described processing in the providing unit may be performed, for example, using AI or without AI. For example, the providing unit can input information from different data sources to a generation AI and cause the generation AI to integrate the information.

[0071] The providing unit can optimize the provided data by referring to the caller's past behavioral history. The providing unit optimizes the provided data by referring to the caller's past behavioral history. Reference to the behavioral history includes, for example, past behavioral patterns and frequency of behavior. For example, the providing unit analyzes the caller's past behavioral history and selects optimal provided data. The providing unit can also identify patterns that are likely to be fraudulent based on the caller's past behavioral history. Furthermore, the providing unit can customize the provided data by referring to the caller's past behavioral history. In this way, by referring to the caller's past behavioral history, the provided data can be optimized and appropriate data can be provided. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the caller's behavioral history data into a generation AI and cause the generation AI to optimize the provided data.

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

[0073] The analysis unit can also analyze the tone and speed of the caller's voice to assess the possibility of fraud. For example, if the caller's tone of voice suddenly changes, it can be determined that there is a high possibility of fraud. Also, if the caller's speaking speed is abnormally fast, it can be determined that there is a high possibility of fraud. Furthermore, if the caller's tone and speed of voice are not constant, it can be determined that there is a high possibility of fraud. In this way, the possibility of fraud can be assessed by analyzing the caller's tone and speed of voice.

[0074] The verification unit can improve the accuracy of verification by referring to the caller's past verification history. For example, it can analyze past verification data and the frequency of verification to select the optimal verification method. It can also improve the accuracy of verification based on the caller's past verification history. Furthermore, it can also customize the verification method by referring to the caller's past verification history. In this way, it is possible to improve the accuracy of verification by referring to the caller's past verification history.

[0075] The analysis unit can analyze background sounds during a call and identify factors that increase the likelihood of fraud. For example, from the background sounds heard during a call, it can identify environmental sounds that are likely to be fraudulent (e.g., sounds like those in a call center). It can also identify environmental sounds that are unlikely to be fraudulent (e.g., household sounds) from the background sounds heard during a call. Furthermore, it can detect specific sounds (e.g., other people's voices) from the background sounds heard during a call and evaluate the likelihood of fraud. In this way, by analyzing the background sounds of a call, it is possible to identify factors that increase the likelihood of fraud.

[0076] The providing unit can integrate information from different data sources to enrich the provided data. For example, the providing unit can integrate information from external databases and internal databases to enrich the provided data. Furthermore, the providing unit can identify patterns that are likely to be fraudulent based on information from different data sources. Furthermore, the providing unit can refer to information from different data sources to customize the provided data. In this way, the provided data can be enriched by integrating information from different data sources, and appropriate data can be provided.

[0077] The analysis unit can perform analysis taking into account the time of the call and the caller's past call history. For example, if a call is made late at night, it can determine that there is a high possibility of fraud and improve the accuracy of the analysis. It can also analyze the caller's past call history to identify patterns that are likely to be fraudulent. Furthermore, it can identify times when fraud is more likely (e.g., daytime on weekdays) based on the time of the call and adjust the accuracy of the analysis. In this way, by taking into account the time of the call and the caller's past call history, it is possible to more accurately evaluate the possibility of fraud.

[0078] The warning unit can adjust the order of warnings based on the relevance of the call. For example, if there is a high possibility of investment fraud, a warning about investments can be issued with the highest priority. Also, if there is a high possibility of billing fraud, a warning about billing can be issued with the highest priority. Furthermore, if there is a high possibility of solicitation fraud, a warning about solicitation can be issued with the highest priority. In this way, by adjusting the order of warnings based on the relevance of the call, warnings can be issued in an appropriate order.

[0079] The processing flow of the first embodiment will be briefly explained below.

[0080] Step 1: The analysis unit analyzes the call content. The analysis unit uses voice recognition technology to convert the call content into text data and analyzes it using natural language processing technology. The analysis unit also uses machine learning algorithms to analyze keywords and phrases in the call content and assess the risk of fraud. Step 2: The warning unit issues a warning if a fraud risk is detected based on the call content analyzed by the analysis unit. The warning unit can issue a warning by voice warning, text message, screen display, etc. If the fraud risk is high, a strong warning can be issued. Step 3: The Termination Unit terminates the call if a warning is issued by the Warning Unit. The Termination Unit can automatically disconnect the call or prompt the caller to end the call. If there is a high risk of fraud, the call can be terminated immediately.

[0081] (Example 2) A fraud prevention system according to an embodiment of the present invention is a system for preventing telephone fraud. The fraud prevention system analyzes the content of calls and issues a warning and terminates the call if there is a possibility of fraud. The fraud prevention system analyzes the content of calls, detects keywords and phrases that may be fraudulent, and issues a warning in real time. For example, if keywords such as "investment," "billing," or "solicitation" are included, the fraud prevention system issues a warning. The fraud prevention system then records the call and makes it available for later review. This allows family members or experts to review the content and determine whether there is a possibility of fraud. Furthermore, the fraud prevention system has the function of analyzing the content of calls and automatically terminating the call if there is a high possibility of fraud. This significantly reduces the risk of elderly people being involved in fraud. For example, the fraud prevention system is provided as an application that can be installed on smartphones or landlines. For example, the fraud prevention system is designed to have a simple interface and easy operation for elderly users. As a result, the fraud prevention system can prevent telephone fraud and protect the safety of elderly people. This allows the fraud prevention system to prevent special telephone frauds and protect the safety of the elderly. For example, the fraud prevention system can analyze the content of calls and issue a warning and terminate the call if there is a possibility of fraud, thereby preventing fraud before it occurs. The fraud prevention system can also record the content of calls and make them available for later review, allowing family members or experts to review the content of the call and determine whether it is a possible fraud. This can significantly reduce the risk of the elderly becoming victims of fraud.

[0082] The fraud prevention system according to the embodiment includes an analysis unit, a warning unit, and a termination unit. The analysis unit analyzes the content of the call. For example, the analysis unit converts the content of the call into text data using voice recognition technology and analyzes it using natural language processing technology. The analysis unit can also assess the risk of fraud using a machine learning algorithm. For example, the analysis unit analyzes keywords and phrases in the content of the call to assess the risk of fraud. The warning unit issues a warning when a risk of fraud is detected based on the content of the call analyzed by the analysis unit. The warning unit can issue a warning using methods such as an audio warning, a text message, or a screen display. For example, the warning unit can issue a strong warning when the risk of fraud is high. The termination unit terminates the call when a warning is issued by the warning unit. The termination unit can use, for example, a method of automatically disconnecting the call or a method of prompting the caller to end the call. For example, the termination unit can immediately end the call when the risk of fraud is high. As a result, the fraud prevention system according to the embodiment can analyze the contents of a call, and if there is a possibility of fraud, issue a warning and terminate the call, thereby preventing fraud damage before it occurs.

[0083] The fraud prevention system includes a recording unit that records the contents of a call. The recording unit records the contents of the call. The recording unit can, for example, start recording simultaneously with the start of the call. The recording unit can also use an audio file format or a text file format to save the recorded data. For example, the recording unit can save the contents of the call as an audio file so that it can be played back later. The recording unit can also save the contents of the call as text data so that it can be searched and analyzed later. In this way, by recording the contents of the call, it is possible to check them later. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can record the contents of the call, input the recorded data into a generation AI, and have the generation AI analyze the recorded data.

[0084] The fraud prevention system includes a confirmation unit that confirms the contents of the recorded call. The confirmation unit confirms the contents of the recorded call. The confirmation unit, for example, has a function of playing back the recorded data. The confirmation unit also has a function of displaying the recorded data as text data. For example, the confirmation unit can play back the recorded data and confirm the contents of the call. The confirmation unit can also display the recorded data as text data and confirm the contents of the call. In this way, by checking the contents of the recorded call, it is possible to determine whether there is a possibility of fraud. Some or all of the above-mentioned processing in the confirmation unit may be performed using AI, for example, or may be performed without using AI. For example, the confirmation unit can input the recorded data to a generation AI and have the generation AI confirm the contents of the call.

[0085] The fraud prevention system includes a providing unit that provides a database for the AI ​​to learn from. The providing unit provides the database for the AI ​​to learn from. The providing unit can provide, for example, a fraud case database or a database of call content. The providing unit can also use a relational database or a NoSQL database as the database format. For example, the providing unit provides a fraud case database so that the AI ​​can learn fraud patterns. The providing unit also provides a database of call content so that the AI ​​can improve its analysis accuracy of the call content. By providing a database for the AI ​​to learn from, the analysis accuracy can be improved. Some or all of the above-described processing in the providing unit can be performed, for example, using AI, or can be performed without using AI. For example, the providing unit can input the database to the generation AI and have the generation AI manage the database.

[0086] The analysis unit can analyze the call content using natural language processing technology. The analysis unit analyzes the call content using natural language processing technology. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit uses morphological analysis to divide words in the call content and uses grammatical analysis to analyze the sentence structure. The analysis unit can also use semantic analysis to understand the meaning of the call content and evaluate the risk of fraud. This improves the accuracy of the analysis of the call content by using natural language processing technology. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the call content to a generation AI and have the generation AI perform analysis using natural language processing technology.

[0087] The warning unit can detect keywords or phrases that pose a high risk of fraud. The warning unit detects keywords or phrases that pose a high risk of fraud. To detect keywords or phrases, for example, a specific word list or co-occurrence network analysis can be used. For example, the warning unit can use a specific word list to detect keywords included in the content of the call. The warning unit can also use co-occurrence network analysis to analyze phrases in the content of the call and evaluate the risk of fraud. This makes it possible to detect keywords or phrases that pose a high risk of fraud and issue a fraud warning. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the content of the call into a generation AI and cause the generation AI to detect keywords and phrases.

[0088] The termination unit can automatically terminate a call when the risk of fraud is high. The termination unit automatically terminates a call when the risk of fraud is high. Methods of terminating a call include, for example, automatically disconnecting the call or prompting the caller to end the call. For example, the termination unit immediately terminates the call when the risk of fraud is high. The termination unit can also terminate the call after issuing a warning when the risk of fraud is medium. This makes it possible to prevent fraud by automatically terminating a call when the risk of fraud is high. Some or all of the above-mentioned processing in the termination unit may be performed using, or without, AI, for example. For example, the termination unit can input the content of the call into a generation AI and have the generation AI make the decision to end the call.

[0089] The analysis unit can estimate the caller's emotions and adjust the accuracy of the analysis based on the estimated caller's emotions. The analysis unit can estimate the caller's emotions and adjust the accuracy of the analysis based on the estimated caller's emotions. Methods for estimating the caller's emotions include, for example, voice analysis, facial expression recognition, and text analysis. For example, the analysis unit can analyze the tone and speed of the caller's voice to estimate the caller's emotions. The analysis unit can also capture the caller's facial expressions with a camera and estimate the emotions using facial expression recognition technology. Furthermore, the analysis unit can analyze text data of the call content to estimate the caller's emotions. This enables more accurate analysis by adjusting the accuracy of the analysis based on the caller's emotions. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the caller's emotional data into the generation AI and have the generation AI adjust the accuracy of the analysis.

[0090] The analysis unit can analyze background sounds of a call and identify factors that increase the likelihood of fraud. The analysis unit can analyze background sounds of a call and identify factors that increase the likelihood of fraud. Analysis of background sounds can include, for example, noise reduction, speech recognition, and acoustic analysis. For example, the analysis unit can identify environmental sounds that are likely to be fraudulent (e.g., call center-like sounds) from the background sounds heard during a call. The analysis unit can also identify environmental sounds that are unlikely to be fraudulent (e.g., household sounds) from the background sounds heard during a call. Furthermore, the analysis unit can detect specific sounds (e.g., other people's voices) from the background sounds heard during a call and evaluate the likelihood of fraud. In this way, factors that increase the likelihood of fraud can be identified by analyzing the background sounds of a call. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input background sound data to a generation AI and cause the generation AI to analyze the background sound.

[0091] The analysis unit can perform analysis taking into account the time of the call and the caller's past call history. The analysis unit performs analysis taking into account the time of the call and the caller's past call history. Methods that take the time of the call into account include, for example, risk assessment for each time period and analysis of past call history. For example, if a call is made late at night, the analysis unit determines that there is a high possibility of fraud and improves the accuracy of the analysis. The analysis unit can also analyze the caller's past call history to identify patterns that are likely to be fraudulent. Furthermore, the analysis unit can identify time periods when there is a high possibility of fraud (e.g., daytime on weekdays) based on the time of the call and adjust the accuracy of the analysis. This allows for a more accurate assessment of the possibility of fraud by taking into account the time of the call and the caller's past call history. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input call time period data and call history data into a generation AI and have the generation AI perform the analysis.

[0092] The analysis unit can analyze the caller's voice tone and speed to evaluate the possibility of fraud. The analysis unit can analyze the caller's voice tone and speed to evaluate the possibility of fraud. Methods for analyzing voice tone and speed include, for example, a voice analysis algorithm and extraction of acoustic features. For example, if the caller's voice tone suddenly changes, the analysis unit can determine that there is a high possibility of fraud and increase the accuracy of the analysis. The analysis unit can also determine that there is a high possibility of fraud and increase the accuracy of the analysis if the caller's speaking speed is abnormally fast. Furthermore, the analysis unit can determine that there is a high possibility of fraud and increase the accuracy of the analysis if the caller's voice tone and speed are not constant. In this way, the possibility of fraud can be evaluated by analyzing the caller's voice tone and speed. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the caller's voice tone and speed data into a generation AI and have the generation AI perform the analysis.

[0093] The analysis unit can estimate the caller's emotions and prioritize the analysis results based on the estimated caller's emotions. The analysis unit can estimate the caller's emotions and prioritize the analysis results based on the estimated caller's emotions. Methods for prioritizing the analysis results include, for example, emotion scores and risk assessments. For example, if the caller is nervous, the analysis unit determines that there is a high possibility of fraud and displays the analysis results with priority. The analysis unit can also display the analysis results with normal priority if the caller is relaxed. Furthermore, if the caller is angry, the analysis unit can determine that there is a high possibility of fraud and display the analysis results with top priority. In this way, by prioritizing the analysis results based on the caller's emotions, important analysis results can be displayed with priority. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input the caller's emotion data into a generation AI and have the generation AI determine the priority of the analysis results.

[0094] The analysis unit can perform analysis taking into account the caller's geographic location information. The analysis unit performs analysis taking into account the caller's geographic location information. Methods for taking into account geographic location information include, for example, GPS data and location information services. For example, if the caller is in an area where fraud is prevalent, the analysis unit determines that there is a high possibility of fraud and increases the accuracy of the analysis. Alternatively, if the caller is in a safe area, the analysis unit can analyze the call content with normal analysis accuracy. Furthermore, the analysis unit can identify areas where there is a high possibility of fraud based on the caller's geographic location information and adjust the accuracy of the analysis. This allows for a more accurate assessment of the possibility of fraud by taking into account the caller's geographic location information. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the caller's geographic location information data into a generation AI and have the generation AI perform the analysis.

[0095] The analysis unit can analyze the caller's social media activity to assess the possibility of fraud. The analysis unit can analyze the caller's social media activity to assess the possibility of fraud. Analysis of social media activity includes, for example, analysis of posted content and analysis of followers. For example, the analysis unit can analyze the caller's social media posts to identify patterns that are likely to be fraud. The analysis unit can also analyze the caller's social media friendships to identify relationships that are likely to be fraud. Furthermore, the analysis unit can analyze the frequency of the caller's social media activity to assess the possibility of fraud. In this way, the possibility of fraud can be assessed by analyzing the caller's social media activity. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the caller's social media data into a generation AI and have the generation AI perform the analysis.

[0096] The analysis unit can customize the analysis method by reflecting the caller's past feedback. The analysis unit customizes the analysis method by reflecting the caller's past feedback. Reflecting feedback includes, for example, analyzing user ratings and comments. For example, the analysis unit customizes the analysis method based on feedback provided by the caller in the past. The analysis unit can also identify patterns that are likely to be fraudulent from the caller's past feedback and adjust the analysis method. Furthermore, the analysis unit can improve the accuracy of the analysis by reflecting the caller's past feedback. In this way, the analysis method can be customized and accuracy can be improved by reflecting the caller's past feedback. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the caller's feedback data into a generation AI and have the generation AI customize the analysis method.

[0097] The warning unit can estimate the caller's emotions and adjust the way the warning is expressed based on the estimated caller's emotions. The warning unit can estimate the caller's emotions and adjust the way the warning is expressed based on the estimated caller's emotions. Adjustment of the way the warning is expressed can include, for example, a voice warning, a text message, a screen display, etc. For example, if the caller is nervous, the warning unit can issue a warning using a gentle expression. Also, if the caller is relaxed, the warning unit can issue a warning using a normal expression. Furthermore, if the caller is angry, the warning unit can issue a warning using a strong expression. In this way, by adjusting the way the warning is expressed based on the caller's emotions, a more effective warning can be issued. Some or all of the above-mentioned processing in the warning unit can be performed using, for example, AI, or without AI. For example, the warning unit can input the caller's emotion data into a generation AI and cause the generation AI to adjust the way the warning is expressed.

[0098] The warning unit can adjust the intensity of the warning based on the level of the possibility of fraud. The warning unit adjusts the intensity of the warning based on the level of the possibility of fraud. Methods for adjusting the intensity of the warning include, for example, adjusting the volume or emphasizing the message. For example, the warning unit issues a strong warning when the possibility of fraud is high. The warning unit can also issue a normal warning when the possibility of fraud is medium. Furthermore, the warning unit can also issue a mild warning when the possibility of fraud is low. In this way, by adjusting the intensity of the warning based on the level of the possibility of fraud, an appropriate warning can be issued. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input fraud possibility data to the generation AI and have the generation AI adjust the intensity of the warning.

[0099] The warning unit can display different warning messages depending on the category of the call content. The warning unit displays different warning messages depending on the category of the call content. The displayed warning messages include messages according to categories such as investment fraud, billing fraud, and solicitation fraud. For example, in the case of investment fraud, the warning unit displays a warning message about investment. In the case of billing fraud, the warning unit can also display a warning message about billing. Furthermore, in the case of solicitation fraud, the warning unit can also display a warning message about solicitation. In this way, by displaying different warning messages depending on the category of the call content, a more specific warning can be issued. Some or all of the above-mentioned processing in the warning unit may be performed, for example, using AI, or may be performed without using AI. For example, the warning unit can input call content category data into a generation AI and cause the generation AI to display a warning message.

[0100] The warning unit can improve the accuracy of the warning by referring to the caller's past warning history. The warning unit improves the accuracy of the warning by referring to the caller's past warning history. Reference to the warning history includes, for example, the content of past warnings and the frequency of warnings. For example, the warning unit analyzes the caller's past warning history to identify patterns that are likely to be fraudulent. The warning unit can also improve the accuracy of the warning based on the caller's past warning history. Furthermore, the warning unit can also customize the warning message by referring to the caller's past warning history. In this way, the accuracy of the warning can be improved by referring to the caller's past warning history. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the caller's warning history data into the generation AI and cause the generation AI to improve the accuracy of the warning.

[0101] The warning unit can estimate the emotion of the caller and adjust the timing of the warning based on the estimated emotion of the caller. The warning unit can estimate the emotion of the caller and adjust the timing of the warning based on the estimated emotion of the caller. Methods for adjusting the timing of the warning include, for example, the progress of the call and the caller's reaction. For example, the warning unit issues a warning early if the caller is nervous. The warning unit can also issue a warning at a normal timing if the caller is relaxed. Furthermore, the warning unit can also issue a warning immediately if the caller is angry. In this way, by adjusting the timing of the warning based on the emotion of the caller, the warning can be issued at an appropriate timing. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input emotion data of the caller to a generation AI and cause the generation AI to adjust the timing of the warning.

[0102] The warning unit can determine the priority of the warning based on the time period of the call. The warning unit determines the priority of the warning based on the time period of the call. Methods for determining the priority of the warning include, for example, risk assessment and consideration of the time period. For example, the warning unit sets a high priority of the warning for a late-night call. The warning unit can also issue a warning with normal priority for a daytime call. Furthermore, the warning unit can set a medium priority of the warning for an early-morning call. In this way, by determining the priority of the warning based on the time period of the call, it is possible to issue a warning with an appropriate priority. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input call time period data to a generation AI and cause the generation AI to determine the priority of the warning.

[0103] The warning unit can adjust the order of warnings based on the relevance of the calls. The warning unit adjusts the order of warnings based on the relevance of the calls. Methods for adjusting the order of warnings include, for example, evaluating the relevance or determining the importance. For example, if there is a high possibility of investment fraud, the warning unit can issue a warning about investments as a top priority. Also, if there is a high possibility of billing fraud, the warning unit can issue a warning about billing as a top priority. Furthermore, if there is a high possibility of solicitation fraud, the warning unit can issue a warning about solicitation as a top priority. In this way, by adjusting the order of warnings based on the relevance of the calls, warnings can be issued in an appropriate order. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input call relevance data to a generation AI and have the generation AI adjust the order of warnings.

[0104] The warning unit can adjust the content of the warning according to the caller's expertise level. The warning unit adjusts the content of the warning according to the caller's expertise level. Methods for adjusting the content of the warning include, for example, survey results and past call content. For example, the warning unit provides detailed warning content when the caller has expertise. The warning unit can also provide concise warning content when the caller does not have expertise. Furthermore, the warning unit can customize the warning content according to the caller's expertise level. As a result, appropriate warning content can be provided by adjusting the warning content according to the caller's expertise level. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the caller's expertise data into a generation AI and cause the generation AI to adjust the warning content.

[0105] The termination unit can estimate the emotion of the caller and adjust the timing of the call end based on the estimated emotion of the caller. The termination unit can estimate the emotion of the caller and adjust the timing of the call end based on the estimated emotion of the caller. Methods for adjusting the timing of the call end include, for example, the progress of the call and the caller's reaction. For example, the termination unit can end the call early if the caller is nervous. Furthermore, the termination unit can end the call at a normal timing if the caller is relaxed. Furthermore, the termination unit can immediately end the call if the caller is angry. In this way, by adjusting the timing of the call end based on the emotion of the caller, the call can be ended at an appropriate timing. Some or all of the above-mentioned processing in the termination unit may be performed using, for example, AI, or may be performed without using AI. For example, the termination unit can input emotion data of the caller into a generation AI and cause the generation AI to adjust the timing of the call end.

[0106] The termination unit can select a termination method based on the content of the call. The termination unit selects a termination method based on the content of the call. Methods for selecting a termination method include, for example, automatic disconnection and notifying the caller. For example, the termination unit immediately terminates the call if there is a high possibility of fraud. Furthermore, the termination unit can terminate the call after issuing a warning if there is a medium possibility of fraud. Furthermore, the termination unit can terminate the call in a normal manner if there is a low possibility of fraud. In this way, by selecting a termination method based on the content of the call, it is possible to terminate the call in an appropriate manner. Some or all of the above-mentioned processing in the termination unit may be performed using, for example, AI, or may be performed without using AI. For example, the termination unit can input call content data into a generation AI and have the generation AI select a termination method.

[0107] The termination unit can optimize the termination method by referring to the caller's past call termination history. The termination unit optimizes the termination method by referring to the caller's past call termination history. Reference to the call termination history includes, for example, past termination methods and termination timings. For example, the termination unit analyzes the caller's past call termination history and selects the optimal termination method. The termination unit can also identify patterns that are likely to be fraudulent based on the caller's past call termination history. Furthermore, the termination unit can customize the termination method by referring to the caller's past call termination history. In this way, the optimal termination method can be selected by referring to the caller's past call termination history. Some or all of the above-mentioned processing in the termination unit may be performed, for example, using AI, or may be performed without using AI. For example, the termination unit can input the caller's call termination history data into a generation AI and cause the generation AI to optimize the termination method.

[0108] The termination unit can improve the termination method by reflecting the caller's feedback. The termination unit improves the termination method by reflecting the caller's feedback. Reflecting the feedback includes, for example, analyzing user ratings and comments. For example, the termination unit improves the termination method based on the caller's feedback. The termination unit can also identify patterns that are likely to be fraudulent from the caller's feedback. Furthermore, the termination unit can customize the termination method by reflecting the caller's feedback. In this way, by reflecting the caller's feedback, the termination method can be improved and a more appropriate termination can be achieved. Some or all of the above-mentioned processing in the termination unit may be performed, for example, using AI or without AI. For example, the termination unit can input the caller's feedback data into a generation AI and have the generation AI execute improvements to the termination method.

[0109] The termination unit can estimate the emotion of the caller and determine the priority of call termination based on the estimated emotion of the caller. The termination unit can estimate the emotion of the caller and determine the priority of call termination based on the estimated emotion of the caller. Methods for determining the priority of call termination include, for example, risk assessment and the emotion of the caller. For example, the termination unit can set a high priority of call termination if the caller is nervous. The termination unit can also end the call with normal priority if the caller is relaxed. Furthermore, the termination unit can immediately end the call if the caller is angry. In this way, by determining the priority of call termination based on the emotion of the caller, the call can be ended with an appropriate priority. Some or all of the above-mentioned processing in the termination unit may be performed using, for example, AI, or may be performed without using AI. For example, the termination unit can input the emotion data of the caller into a generation AI and cause the generation AI to determine the priority of call termination.

[0110] The termination unit can select a termination method taking into account the geographic distribution of the call. The termination unit selects a termination method taking into account the geographic distribution of the call. Methods that take geographic distribution into account include, for example, regional risk assessment and location-based services. For example, the termination unit immediately terminates the call if the caller is in a fraud-prone area. The termination unit can also terminate the call in a normal manner if the caller is in a safe area. Furthermore, the termination unit can identify areas with a high probability of fraud based on the geographic distribution of the caller and adjust the termination method. In this way, the call can be terminated in an appropriate manner by taking into account the geographic distribution of the call. Some or all of the above-described processing in the termination unit may be performed using, for example, AI, or may be performed without using AI. For example, the termination unit can input call geographic distribution data into a generation AI and have the generation AI select a termination method.

[0111] The termination unit can optimize the termination method by referring to literature related to the call. The termination unit can optimize the termination method by referring to literature related to the call. References to related literature include, for example, academic papers and technical reports. For example, the termination unit can refer to literature related to the content of the call and select the optimal termination method. The termination unit can also identify patterns that are likely to be fraudulent from literature related to the content of the call. Furthermore, the termination unit can customize the termination method based on literature related to the content of the call. In this way, the optimal termination method can be selected by referring to literature related to the call. Some or all of the above-mentioned processing in the termination unit can be performed, for example, using AI or without AI. For example, the termination unit can input literature data related to the call into a generation AI and cause the generation AI to optimize the termination method.

[0112] The termination unit can select a termination method taking into account the market value of the call. The termination unit selects a termination method taking into account the market value of the call. Methods that take market value into account include, for example, the importance and economic value of the call content. For example, the termination unit can carefully terminate a call if the call content contains high-value information. The termination unit can also quickly terminate a call if the call content contains low-value information. Furthermore, the termination unit can customize the termination method based on the market value of the call. This makes it possible to terminate a call in an appropriate manner by taking into account the market value of the call. Some or all of the above-mentioned processing in the termination unit may be performed using, for example, AI, or may be performed without using AI. For example, the termination unit can input market value data of the call into a generation AI and have the generation AI select a termination method.

[0113] The recording unit can estimate the emotion of the caller and adjust the start timing of recording based on the estimated emotion of the caller. The recording unit can estimate the emotion of the caller and adjust the start timing of recording based on the estimated emotion of the caller. Methods for adjusting the start timing of recording include, for example, the progress of the call and the emotion of the caller. For example, the recording unit can start recording earlier if the caller is nervous. Alternatively, the recording unit can start recording at a normal timing if the caller is relaxed. Furthermore, the recording unit can start recording immediately if the caller is angry. In this way, by adjusting the start timing of recording based on the emotion of the caller, recording can be started at an appropriate timing. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input emotion data of the caller into a generation AI and have the generation AI adjust the start timing of recording.

[0114] The recording unit can adjust the level of detail of the recording based on the importance of the call. The recording unit adjusts the level of detail of the recording based on the importance of the call. Methods for adjusting the level of detail of the recording include, for example, setting the sound quality and the length of the recording time. For example, the recording unit performs detailed recording when the content of the call is important. The recording unit can also perform normal recording when the content of the call is of medium importance. Furthermore, the recording unit can also perform simplified recording when the content of the call is of low importance. In this way, by adjusting the level of detail of the recording based on the importance of the call, it is possible to record with an appropriate level of detail. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input call importance data to a generation AI and have the generation AI adjust the level of detail of the recording.

[0115] The recording unit can apply different recording algorithms depending on the call category. The recording unit applies different recording algorithms depending on the call category. Application of recording algorithms includes, for example, compression algorithms and noise reduction algorithms. For example, in the case of investment fraud, the recording unit can apply a recording algorithm related to investment. In addition, in the case of billing fraud, the recording unit can also apply a recording algorithm related to billing. Furthermore, in the case of solicitation fraud, the recording unit can also apply a recording algorithm related to solicitation. In this way, by applying different recording algorithms depending on the call category, appropriate recording can be performed. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input call category data into a generation AI and have the generation AI apply the recording algorithm.

[0116] The recording unit can improve the accuracy of the recording by referring to the caller's past recording history. The recording unit improves the accuracy of the recording by referring to the caller's past recording history. Reference to the recording history includes, for example, past recording data and recording frequency. For example, the recording unit analyzes the caller's past recording history and selects the optimal recording method. The recording unit can also improve the accuracy of the recording based on the caller's past recording history. Furthermore, the recording unit can also customize the recording method by referring to the caller's past recording history. In this way, the accuracy of the recording can be improved by referring to the caller's past recording history. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input the caller's recording history data into a generation AI and have the generation AI improve the accuracy of the recording.

[0117] The recording unit can estimate the emotion of the caller and adjust the length of the recording based on the estimated emotion of the caller. The recording unit can estimate the emotion of the caller and adjust the length of the recording based on the estimated emotion of the caller. Methods for adjusting the length of the recording include, for example, the progress of the call and the emotion of the caller. For example, the recording unit can shorten the length of the recording if the caller is nervous. The recording unit can also record at a normal length if the caller is relaxed. Furthermore, the recording unit can lengthen the length of the recording if the caller is angry. In this way, by adjusting the length of the recording based on the emotion of the caller, it is possible to record at an appropriate length. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input emotion data of the caller into a generation AI and have the generation AI adjust the length of the recording.

[0118] The recording unit can determine the recording priority based on the time of submission of the call. The recording unit determines the recording priority based on the time of submission of the call. Methods for determining the recording priority include, for example, the importance of the call and the time of submission. For example, the recording unit sets a high recording priority for an emergency call. The recording unit can also record at a normal priority for a normal call. Furthermore, the recording unit can set a low recording priority for a non-urgent call. In this way, by determining the recording priority based on the time of submission of the call, recording can be performed at an appropriate priority. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input call submission time data to a generation AI and have the generation AI determine the recording priority.

[0119] The recording unit can adjust the order of recordings based on the relevance of the calls. The recording unit adjusts the order of recordings based on the relevance of the calls. Methods for adjusting the order of recordings include, for example, evaluating the relevance and determining the importance. For example, if there is a high possibility of investment fraud, the recording unit can give top priority to recordings related to investments. Furthermore, if there is a high possibility of billing fraud, the recording unit can also give top priority to recordings related to billing. Furthermore, if there is a high possibility of solicitation fraud, the recording unit can also give top priority to recordings related to solicitations. In this way, by adjusting the order of recordings based on the relevance of the calls, recordings can be made in an appropriate order. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input call relevance data to a generation AI and have the generation AI adjust the order of recordings.

[0120] The recording unit can adjust the use of technical terms in the recording according to the caller's level of expertise. The recording unit adjusts the use of technical terms in the recording according to the caller's level of expertise. Methods for adjusting the use of technical terms include, for example, the caller's level of expertise and the difficulty of the terminology. For example, if the caller has technical expertise, the recording unit can record using detailed technical terms. Alternatively, if the caller does not have technical expertise, the recording unit can record using concise terms. Furthermore, the recording unit can customize the technical terms in the recording according to the caller's level of expertise. In this way, by adjusting the use of technical terms in the recording according to the caller's level of expertise, it is possible to record using appropriate terminology. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without AI. For example, the recording unit can input the caller's technical expertise data into a generation AI and have the generation AI adjust the use of technical terms.

[0121] The confirmation unit can estimate the caller's emotions and adjust the confirmation display method based on the estimated caller's emotions. The confirmation unit can estimate the caller's emotions and adjust the confirmation display method based on the estimated caller's emotions. Methods for adjusting the confirmation display method include, for example, text display, voice guidance, and screen display. For example, if the caller is nervous, the confirmation unit can provide a simple, highly visible display method. Furthermore, if the caller is relaxed, the confirmation unit can provide a display method that includes detailed information. Furthermore, if the caller is angry, the confirmation unit can provide a display method that focuses on the main points. In this way, by adjusting the confirmation display method based on the caller's emotions, confirmation can be performed in an appropriate display method. Some or all of the above-mentioned processing in the confirmation unit may be performed using, for example, AI, or without AI. For example, the confirmation unit can input the caller's emotion data into a generation AI and have the generation AI adjust the display method.

[0122] The confirmation unit can adjust the level of detail of the confirmation based on the importance of the call. The confirmation unit adjusts the level of detail of the confirmation based on the importance of the call. Methods for adjusting the level of detail of the confirmation include, for example, the depth of the confirmation content and the amount of displayed information. For example, the confirmation unit performs detailed confirmation when the call content is important. The confirmation unit can also perform normal confirmation when the call content is of medium importance. Furthermore, the confirmation unit can also perform simple confirmation when the call content is of low importance. In this way, by adjusting the level of detail of the confirmation based on the importance of the call, confirmation can be performed with an appropriate level of detail. Some or all of the above-mentioned processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input call importance data to a generation AI and cause the generation AI to adjust the level of detail of the confirmation.

[0123] The verification unit can apply different verification algorithms depending on the call category. The verification unit applies different verification algorithms depending on the call category. Examples of application of verification algorithms include data mining algorithms and machine learning algorithms. For example, in the case of investment fraud, the verification unit applies a verification algorithm related to investment. In addition, in the case of billing fraud, the verification unit can also apply a verification algorithm related to billing. Furthermore, in the case of solicitation fraud, the verification unit can also apply a verification algorithm related to solicitation. In this way, by applying different verification algorithms depending on the call category, appropriate verification can be performed. Some or all of the above-mentioned processing in the verification unit may be performed using, for example, AI, or may be performed without using AI. For example, the verification unit can input call category data into the generation AI and cause the generation AI to apply the verification algorithm.

[0124] The confirmation unit can improve the accuracy of confirmation by referring to the caller's past confirmation history. The confirmation unit improves the accuracy of confirmation by referring to the caller's past confirmation history. Reference to the confirmation history includes, for example, past confirmation data and the frequency of confirmation. For example, the confirmation unit analyzes the caller's past confirmation history and selects the optimal confirmation method. The confirmation unit can also improve the accuracy of confirmation based on the caller's past confirmation history. Furthermore, the confirmation unit can also customize the confirmation method by referring to the caller's past confirmation history. In this way, the accuracy of confirmation can be improved by referring to the caller's past confirmation history. Some or all of the above-mentioned processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input the caller's confirmation history data into the generation AI and cause the generation AI to improve the accuracy of confirmation.

[0125] The confirmation unit can estimate the emotion of the caller and adjust the length of the confirmation based on the estimated emotion of the caller. The confirmation unit estimates the emotion of the caller and adjusts the length of the confirmation based on the estimated emotion of the caller. Methods for adjusting the length of the confirmation include, for example, the progress of the call and the emotion of the caller. For example, the confirmation unit sets the length of the confirmation to be short if the caller is nervous. The confirmation unit can also perform the confirmation at a normal length if the caller is relaxed. Furthermore, the confirmation unit can set the length of the confirmation to be long if the caller is angry. In this way, by adjusting the length of the confirmation based on the emotion of the caller, the confirmation can be performed at an appropriate length. Some or all of the above-mentioned processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input emotion data of the caller into the generation AI and cause the generation AI to adjust the length of the confirmation.

[0126] The confirmation unit can determine the confirmation priority based on the time of submission of the call. The confirmation unit determines the confirmation priority based on the time of submission of the call. Methods for determining the confirmation priority include, for example, the importance of the call and the time of submission. For example, the confirmation unit sets a high confirmation priority for an emergency call. The confirmation unit can also perform confirmation with a normal priority for a normal call. Furthermore, the confirmation unit can set a low confirmation priority for a non-urgent call. In this way, by determining the confirmation priority based on the time of submission of the call, confirmation can be performed with an appropriate priority. Some or all of the above-mentioned processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input call submission time data into the generation AI and cause the generation AI to determine the confirmation priority.

[0127] The confirmation unit can adjust the order of confirmation based on the relevance of the calls. The confirmation unit adjusts the order of confirmation based on the relevance of the calls. Methods for adjusting the order of confirmation include, for example, evaluating the relevance or determining the importance. For example, if there is a high possibility of investment fraud, the confirmation unit can give top priority to confirmation related to investments. Furthermore, if there is a high possibility of billing fraud, the confirmation unit can also give top priority to confirmation related to billing. Furthermore, if there is a high possibility of solicitation fraud, the confirmation unit can also give top priority to confirmation related to solicitation. In this way, by adjusting the order of confirmation based on the relevance of the calls, confirmation can be performed in an appropriate order. Some or all of the above-mentioned processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input call relevance data to a generation AI and have the generation AI adjust the order of confirmation.

[0128] The verification unit can adjust the use of technical terms for confirmation according to the caller's level of expertise. The verification unit adjusts the use of technical terms for confirmation according to the caller's level of expertise. Methods for adjusting the use of technical terms include, for example, the caller's level of expertise and the difficulty level of terminology. For example, the verification unit can use detailed technical terms for confirmation if the caller has technical knowledge. Alternatively, the verification unit can use concise terms for confirmation if the caller does not have technical knowledge. Furthermore, the verification unit can customize the technical terms for confirmation according to the caller's level of expertise. This allows confirmation to be performed using appropriate terms by adjusting the use of technical terms for confirmation according to the caller's level of expertise. Some or all of the above-described processing in the verification unit may be performed using, for example, AI, or may be performed without AI. For example, the verification unit can input the caller's expertise data into a generation AI and cause the generation AI to adjust the use of technical terms.

[0129] The providing unit can estimate the emotion of the caller and select data to be provided based on the estimated emotion of the caller. The providing unit can estimate the emotion of the caller and select data to be provided based on the estimated emotion of the caller. The selection of data to be provided includes, for example, the importance of the data and the needs of the caller. For example, if the caller is nervous, the providing unit can preferentially provide data that gives a sense of security. Furthermore, if the caller is relaxed, the providing unit can also provide normal data. Furthermore, if the caller is angry, the providing unit can provide data that encourages calmness. In this way, by selecting data to be provided based on the emotion of the caller, appropriate data can be provided. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input emotion data of the caller to a generation AI and cause the generation AI to select data to be provided.

[0130] The providing unit can optimize the providing algorithm by referring to past provided data. The providing unit optimizes the providing algorithm by referring to past provided data. Optimization of the providing algorithm includes, for example, a recommendation algorithm or a data mining algorithm. For example, the providing unit analyzes the effectiveness of data provided in the past and selects an optimal providing algorithm. The providing unit can also identify patterns with a high probability of fraud based on the past provided data. Furthermore, the providing unit can customize the providing algorithm by referring to the past provided data. In this way, by referring to the past provided data, the providing algorithm can be optimized and appropriate data can be provided. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input past provided data into a generation AI and cause the generation AI to optimize the providing algorithm.

[0131] The providing unit can update the provided data by reflecting the caller's feedback. The providing unit updates the provided data by reflecting the caller's feedback. Updating the provided data includes, for example, a method for reflecting the feedback and a frequency for updating the data. For example, the providing unit updates the provided data based on the caller's feedback. The providing unit can also identify patterns that are likely to be fraudulent from the caller's feedback. Furthermore, the providing unit can customize the provided data by reflecting the caller's feedback. In this way, the provided data can be updated and appropriate data can be provided by reflecting the caller's feedback. Some or all of the above-described processing in the providing unit may be performed, for example, using AI or may be performed without using AI. For example, the providing unit can input the caller's feedback data to a generating AI and cause the generating AI to update the provided data.

[0132] The providing unit can select the data to be provided taking into account the caller's current situation. The providing unit selects the data to be provided taking into account the caller's current situation. Methods for considering the current situation include, for example, the progress of the call and the caller's environment. For example, the providing unit provides concise data when the caller is on the move. The providing unit can also provide detailed data when the caller is at home. Furthermore, the providing unit can select optimal data to be provided based on the caller's current situation. This makes it possible to provide appropriate data by taking into account the caller's current situation. Some or all of the above-described processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input the caller's current situation data into the generating AI and cause the generating AI to select the data to be provided.

[0133] The providing unit can estimate the emotion of the caller and adjust the frequency of data provision based on the estimated emotion of the caller. The providing unit can estimate the emotion of the caller and adjust the frequency of data provision based on the estimated emotion of the caller. Methods for adjusting the frequency of data provision include, for example, the needs of the caller and the importance of the data. For example, the providing unit can set the frequency of data provision higher if the caller is nervous. The providing unit can also provide data at a normal frequency if the caller is relaxed. Furthermore, the providing unit can set the frequency of data provision lower if the caller is angry. In this way, by adjusting the frequency of data provision based on the emotion of the caller, data can be provided at an appropriate frequency. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the emotion data of the caller to a generation AI and cause the generation AI to adjust the frequency of data provision.

[0134] The providing unit can weight the provided data based on the submission time of the call. The providing unit weights the provided data based on the submission time of the call. Methods for weighting the provided data include, for example, the submission time and the importance of the data. For example, the providing unit sets a high weighting for the provided data in the case of an emergency call. The providing unit can also provide data with a normal weighting in the case of a normal call. Furthermore, the providing unit can set a low weighting for the provided data in the case of a non-urgent call. In this way, by weighting the provided data based on the submission time of the call, data can be provided with an appropriate weighting. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input call submission time data to a generation AI and cause the generation AI to weight the provided data.

[0135] The providing unit can integrate information from different data sources to enrich the provided data. The providing unit integrates information from different data sources to enrich the provided data. Integration of different data sources includes, for example, external databases and internal databases. For example, the providing unit integrates information from different data sources to enrich the provided data. The providing unit can also identify patterns with a high likelihood of fraud based on information from different data sources. Furthermore, the providing unit can customize the provided data by referring to information from different data sources. In this way, the provided data can be enriched and appropriate data can be provided by integrating information from different data sources. Some or all of the above-described processing in the providing unit may be performed, for example, using AI or without AI. For example, the providing unit can input information from different data sources to a generation AI and cause the generation AI to integrate the information.

[0136] The providing unit can optimize the provided data by referring to the caller's past behavioral history. The providing unit optimizes the provided data by referring to the caller's past behavioral history. Reference to the behavioral history includes, for example, past behavioral patterns and frequency of behavior. For example, the providing unit analyzes the caller's past behavioral history and selects optimal provided data. The providing unit can also identify patterns that are likely to be fraudulent based on the caller's past behavioral history. Furthermore, the providing unit can customize the provided data by referring to the caller's past behavioral history. In this way, by referring to the caller's past behavioral history, the provided data can be optimized and appropriate data can be provided. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the caller's behavioral history data into a generation AI and cause the generation AI to optimize the provided data. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned analysis unit, warning unit, termination unit, recording unit, confirmation unit, and providing unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart device 14 and analyzes the content of the call. The warning unit is realized by the output device 40 of the smart device 14 and issues a warning. The termination unit is realized by the control unit 46A of the smart device 14 and ends the call. The recording unit is realized by the storage 50 of the smart device 14 and records the content of the call. The confirmation unit is realized by the display 40A of the smart device 14 and confirms the recorded content of the call. The providing unit is realized by the database 24 of the data processing device 12 and provides a database for AI learning. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned analysis unit, warning unit, termination unit, recording unit, confirmation unit, and providing unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart glasses 214 and analyzes the content of the call. The warning unit is realized by the speaker 240 of the smart glasses 214 and issues a warning. The termination unit is realized by the control unit 46A of the smart glasses 214 and ends the call. The recording unit is realized by the storage 50 of the smart glasses 214 and records the content of the call. The confirmation unit is realized by the display of the smart glasses 214 and confirms the recorded content of the call. The providing unit is realized by the database 24 of the data processing device 12 and provides a database for AI learning. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, warning unit, termination unit, recording unit, confirmation unit, and providing unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the headset type terminal 314 and analyzes the content of the call. The warning unit is realized by the speaker 240 of the headset type terminal 314 and issues a warning. The termination unit is realized by the control unit 46A of the headset type terminal 314 and ends the call. The recording unit is realized by the storage 50 of the headset type terminal 314 and records the content of the call. The confirmation unit is realized by the display 343 of the headset type terminal 314 and confirms the recorded content of the call. The providing unit is realized by the database 24 of the data processing device 12 and provides a database for AI learning. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, warning unit, termination unit, recording unit, confirmation unit, and provision unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the robot 414 and analyzes the content of the call. The warning unit is realized by the speaker 240 of the robot 414 and issues a warning. The termination unit is realized by the control unit 46A of the robot 414 and ends the call. The recording unit is realized by the storage 50 of the robot 414 and records the content of the call. The confirmation unit is realized by the display of the robot 414 and confirms the recorded content of the call. The provision unit is realized by the database 24 of the data processing device 12 and provides a database for the AI ​​to learn from.

[0137] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0138] The analysis unit can also analyze the tone and speed of the caller's voice to assess the possibility of fraud. For example, if the caller's tone of voice suddenly changes, it can be determined that there is a high possibility of fraud. Also, if the caller's speaking speed is abnormally fast, it can be determined that there is a high possibility of fraud. Furthermore, if the caller's tone and speed of voice are not constant, it can be determined that there is a high possibility of fraud. In this way, the possibility of fraud can be assessed by analyzing the caller's tone and speed of voice.

[0139] The recording unit can estimate the emotion of the caller and adjust the timing to start recording based on the estimated emotion of the caller. For example, if the caller is nervous, recording can start earlier. If the caller is relaxed, recording can start at a normal timing. Furthermore, if the caller is angry, recording can start immediately. In this way, by adjusting the timing to start recording based on the emotion of the caller, recording can start at an appropriate time.

[0140] The verification unit can improve the accuracy of verification by referring to the caller's past verification history. For example, it can analyze past verification data and the frequency of verification to select the optimal verification method. It can also improve the accuracy of verification based on the caller's past verification history. Furthermore, it can also customize the verification method by referring to the caller's past verification history. In this way, it is possible to improve the accuracy of verification by referring to the caller's past verification history.

[0141] The providing unit can estimate the emotion of the caller and select data to be provided based on the estimated emotion of the caller. For example, if the caller is nervous, data that gives a sense of security can be provided preferentially. If the caller is relaxed, normal data can be provided. Furthermore, if the caller is angry, data that encourages calmness can be provided. In this way, by selecting data to be provided based on the emotion of the caller, appropriate data can be provided.

[0142] The warning unit can estimate the emotion of the caller and adjust the way the warning is expressed based on the estimated emotion of the caller. For example, if the caller is nervous, the warning can be issued in a gentle manner. If the caller is relaxed, the warning can be issued in a normal manner. Furthermore, if the caller is angry, the warning can be issued in a strong manner. In this way, by adjusting the way the warning is expressed based on the emotion of the caller, a more effective warning can be issued.

[0143] The analysis unit can analyze background sounds during a call and identify factors that increase the likelihood of fraud. For example, from the background sounds heard during a call, it can identify environmental sounds that are likely to be fraudulent (e.g., sounds like those in a call center). It can also identify environmental sounds that are unlikely to be fraudulent (e.g., household sounds) from the background sounds heard during a call. Furthermore, it can detect specific sounds (e.g., other people's voices) from the background sounds heard during a call and evaluate the likelihood of fraud. In this way, by analyzing the background sounds of a call, it is possible to identify factors that increase the likelihood of fraud.

[0144] The termination unit can estimate the emotion of the caller and adjust the timing of the call end based on the estimated emotion of the caller. For example, if the caller is nervous, the call can be ended early. If the caller is relaxed, the call can be ended at a normal timing. Furthermore, if the caller is angry, the call can be ended immediately. In this way, by adjusting the timing of the call end based on the emotion of the caller, the call can be ended at an appropriate timing.

[0145] The providing unit can integrate information from different data sources to enrich the provided data. For example, the providing unit can integrate information from external databases and internal databases to enrich the provided data. Furthermore, the providing unit can identify patterns that are likely to be fraudulent based on information from different data sources. Furthermore, the providing unit can refer to information from different data sources to customize the provided data. In this way, the provided data can be enriched by integrating information from different data sources, and appropriate data can be provided.

[0146] The analysis unit can perform analysis taking into account the time of the call and the caller's past call history. For example, if a call is made late at night, it can determine that there is a high possibility of fraud and improve the accuracy of the analysis. It can also analyze the caller's past call history to identify patterns that are likely to be fraudulent. Furthermore, it can identify times when fraud is more likely (e.g., daytime on weekdays) based on the time of the call and adjust the accuracy of the analysis. In this way, by taking into account the time of the call and the caller's past call history, it is possible to more accurately evaluate the possibility of fraud.

[0147] The warning unit can adjust the order of warnings based on the relevance of the call. For example, if there is a high possibility of investment fraud, a warning about investments can be issued with the highest priority. Also, if there is a high possibility of billing fraud, a warning about billing can be issued with the highest priority. Furthermore, if there is a high possibility of solicitation fraud, a warning about solicitation can be issued with the highest priority. In this way, by adjusting the order of warnings based on the relevance of the call, warnings can be issued in an appropriate order.

[0148] The processing flow of the second embodiment will be briefly explained below.

[0149] Step 1: The analysis unit analyzes the call content. The analysis unit uses voice recognition technology to convert the call content into text data and analyzes it using natural language processing technology. The analysis unit also uses machine learning algorithms to analyze keywords and phrases in the call content and assess the risk of fraud. Step 2: The warning unit issues a warning if a fraud risk is detected based on the call content analyzed by the analysis unit. The warning unit can issue a warning by voice warning, text message, screen display, etc. If the fraud risk is high, a strong warning can be issued. Step 3: The Termination Unit terminates the call if a warning is issued by the Warning Unit. The Termination Unit can automatically disconnect the call or prompt the caller to end the call. If there is a high risk of fraud, the call can be terminated immediately.

[0150] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0151] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0152] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0153] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0154] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0155] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0156] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0157] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0158] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0159] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0160] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0161] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0162] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0163] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0164] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0165] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0166] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0167] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0168] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0169] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0170] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0171] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0172] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0173] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0174] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0175] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0176] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0177] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0178] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0179] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0180] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0181] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0182] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0183] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0184] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0185] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0186] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0187] 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.

[0188] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0189] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0190] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0191] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0192] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0193] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0194] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0195] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0196] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0197] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0198] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0199] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0200] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0201] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0202] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0203] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0204] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0205] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0206] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0207] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0208] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0209] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0210] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0211] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0212] 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.

[0213] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0214] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0215] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0216] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0217] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0218] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0219] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0220] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0221] [Explanation of symbols]

[0222] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an analysis unit that analyzes the contents of the call; a warning unit that issues a warning when a fraud risk is detected based on the call content analyzed by the analysis unit; a termination unit that terminates the call when a warning is issued by the warning unit. A system characterized by:

2. Equipped with a recording unit that records the contents of calls 2. The system of claim 1.

3. Equipped with a confirmation section for checking the recorded conversation contents 2. The system of claim 1.

4. Equipped with a provision unit that provides a database for AI to learn from 2. The system of claim 1.

5. The analysis unit Analyzing call content using natural language processing technology 2. The system of claim 1.

6. The warning unit Detect keywords or phrases that are at high risk of fraud 2. The system of claim 1.

7. The end portion is Automatically end calls when there is a high risk of fraud 2. The system of claim 1.

8. The analysis unit Estimate the caller's emotions and adjust the accuracy of the analysis based on the estimated emotions of the caller 2. The system of claim 1.

9. The analysis unit Analyze background noise on calls to identify factors that increase the likelihood of fraud 2. The system of claim 1.

Images