System

Abstract

The system according to the embodiment aims to detect a voice of fraud in real time and issue a warning.SOLUTION: A system according to an embodiment includes a collection unit, an analysis unit, a collation unit, and a warning unit. The collection unit collects sound. The analysis unit analyzes the voice collected by the collection unit. The collation unit collates the voice data analyzed by the analysis unit with past fraud data. The warning unit issues a warning when there is a possibility of fraud by the collation unit.SELECTED DRAWING: Figure 1

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 detect fraudulent audio in real time and issue a warning.

[0005] The system according to the embodiment aims to detect fraudulent audio in real time and issue a warning. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a matching unit, and a warning unit. The collection unit collects audio. The analysis unit analyzes the audio collected by the collection unit. The matching unit matches the audio data analyzed by the analysis unit with past fraud data. The warning unit issues a warning when the matching unit detects a possibility of fraud. [Effects of the Invention]

[0007] The system according to the embodiment can detect and warn of fraudulent audio in real time. [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 detection system according to an embodiment of the present invention is a system that collects and analyzes audio, compares it with past fraud data, and issues a warning. The fraud detection system collects and analyzes audio, and compares it with past fraud data to issue a warning if there is a possibility of fraud. For example, the fraud detection system collects telephone conversations and recorded audio. Then, the fraud detection system uses AI to analyze the collected audio and converts the audio data into text. For example, the fraud detection system converts the audio data into text data using speech recognition technology. Then, the fraud detection system compares the analyzed audio data with past fraud data. For example, the fraud detection system identifies conversations containing typical fraudulent phrases and expressions. Then, the fraud detection system issues a warning if there is a possibility of fraud. For example, the fraud detection system issues a warning to a staff member if a conversation with a high probability of fraud is detected. This enables the fraud detection system to detect fraud early and prevent damage before it occurs. This enables the fraud detection system to detect fraud early and prevent damage before it occurs. For example, monitoring conversations at a bank's call center and detecting potentially fraudulent conversations can protect customer assets. It can also protect customer personal information by monitoring conversations at customer service centers and detecting potentially fraudulent conversations.

[0029] A fraud detection system according to an embodiment includes a collection unit, an analysis unit, a matching unit, and a warning unit. The collection unit collects audio. Examples of audio include, but are not limited to, telephone conversations, recorded audio, and real-time audio. The collection unit collects, for example, telephone conversations. The collection unit can also collect recorded audio. The collection unit can also collect real-time audio. For example, the collection unit collects telephone conversations at a customer service center. The analysis unit analyzes the audio collected by the collection unit. The analysis is performed using, for example, but is not limited to, speech recognition technology or natural language processing technology. For example, the analysis unit converts speech data into text data using speech recognition technology. The analysis unit can also analyze speech data using natural language processing technology. The analysis unit can also analyze the speech data and set criteria and conditions for identifying potentially fraudulent conversations. For example, the analysis unit sets criteria and conditions based on the frequency of occurrence of specific keywords or the tone of the conversation. The matching unit compares the speech data analyzed by the analysis unit with past fraud data. The matching is performed based on, for example, a similarity measure or an algorithm used, but is not limited to these examples. For example, the matching unit identifies conversations containing phrases or expressions typical of fraud. The matching unit can also improve the accuracy of the matching by referring to past fraud data. Furthermore, the matching unit can apply matching algorithms to deal with different fraud methods. For example, the matching unit applies matching algorithms that deal with different fraud methods, such as phishing scams and telephone scams. The warning unit issues a warning when the matching unit detects a possibility of fraud. The warning can be in the form of, for example, voice, text, or an alert, but is not limited to these examples. For example, the warning unit issues a warning to a responsible person when a conversation with a high possibility of fraud is detected. The warning unit can also set the timing and method of the warning. Furthermore, the warning unit can estimate the user's emotions and adjust the way the warning is displayed based on the estimated user's emotions. For example, if the user is nervous, the warning unit displays the warning in a calm color scheme.As a result, the fraud detection system according to the embodiment enables early detection of fraud and prevents damage before it occurs.

[0030] The collection unit can collect telephone conversations or recorded voices. For example, the collection unit collects telephone conversations. Telephone conversations include, but are not limited to, landline, mobile phone, VoIP, etc. The collection unit can also collect recorded voices. Recorded voices include, but are not limited to, digital recordings, analog recordings, etc. For example, the collection unit collects telephone conversations at a customer service center. In this way, by collecting telephone conversations and recorded voices, various voice data can be targeted.

[0031] The analysis unit can convert the voice data into text. The analysis unit converts the voice data into text data using, for example, voice recognition technology. Voice recognition technology includes, for example, voice recognition software and transcription software, but is not limited to these examples. The analysis unit can also analyze the voice data using natural language processing technology. For example, the analysis unit converts the voice data into text data and performs analysis based on the text data. By converting the voice data into text, it becomes possible to analyze it as text data.

[0032] The matching unit can identify conversations that include typical phrases or expressions of fraud. For example, the matching unit identifies conversations that include typical phrases or expressions of fraud. Typical phrases or expressions of fraud include, but are not limited to, "Please transfer the money now" and "You have won." The matching unit can also improve the accuracy of matching by referring to past fraud data. For example, the matching unit extracts and matches specific patterns based on past fraud data. This allows the identification of typical phrases or expressions of fraud, thereby enabling the detection of the possibility of fraud with high accuracy.

[0033] The warning unit can issue a warning to a person in charge when a conversation that is highly likely to be fraudulent is detected. For example, the warning unit issues a warning to a person in charge when a conversation that is highly likely to be fraudulent is detected. The person in charge can include, but is not limited to, a customer support person or a security person. The warning unit can also set the timing and method of issuing the warning. For example, the warning unit can issue a warning in real time. The warning unit can also issue a warning as a periodic report. In this way, issuing a warning when a conversation that is highly likely to be fraudulent is detected enables a prompt response.

[0034] The analysis unit can analyze the voice data and set criteria or conditions for identifying potentially fraudulent conversations. For example, the analysis unit can analyze the voice data and set criteria or conditions for identifying potentially fraudulent conversations. Examples of the criteria or conditions include, but are not limited to, the frequency of occurrence of specific keywords and the tone of the conversation. The analysis unit can also analyze the voice data and apply an algorithm for identifying potentially fraudulent conversations. For example, the analysis unit can analyze the voice data and apply a machine learning algorithm for identifying potentially fraudulent conversations. In this way, by setting criteria or conditions, potentially fraudulent conversations can be more accurately identified.

[0035] The warning unit can set the timing and method of issuing a warning when a conversation that may be fraudulent is detected. The warning unit sets, for example, the timing and method of issuing a warning when a conversation that may be fraudulent is detected. Examples of the timing and method include, but are not limited to, real-time warnings and periodic reports. The warning unit can also set the format of the warning. For example, the warning unit issues a warning in the form of voice, text, alert, or the like. In this way, by setting the timing and method of the warning, it is possible to issue a warning at an appropriate time.

[0036] The collection unit can analyze the user's past conversation history and select the optimal collection method when collecting audio. For example, the collection unit can analyze the user's past conversation history and select the optimal collection method when collecting audio. Past conversation history includes, but is not limited to, text logs and audio files. For example, if the user has had many telephone conversations in the past, the collection unit can prioritize collecting telephone conversations. Furthermore, if the user has provided many recorded audio files in the past, the collection unit can also prioritize collecting recorded audio files. Furthermore, the collection unit can concentrate collection on a specific time period from the user's past conversation history. This allows the optimal collection method to be selected by analyzing the user's past conversation history. Some or all of the above-described processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input the past conversation history into a generation AI and have the generation AI select the optimal collection method.

[0037] The collection unit may filter the audio data based on the user's current situation or areas of interest when collecting the audio data. For example, the collection unit may filter the audio data based on the user's current situation or areas of interest when collecting the audio data. Examples of the current situation and areas of interest include, but are not limited to, real-time behavioral data and past search history. For example, the collection unit may pause collection if the user is busy in their current situation. The collection unit may also collect only relevant audio data based on the user's areas of interest. The collection unit may also prioritize the audio data to be collected according to the user's current situation. This allows highly relevant audio data to be collected by filtering based on the user's current situation and areas of interest. Some or all of the above-described processing by the collection unit may be performed using, or without, AI. For example, the collection unit may input real-time behavioral data into a generation AI and have the generation AI perform filtering.

[0038] The collection unit can select the optimal collection means depending on the user's input method when collecting voice. For example, the collection unit selects the optimal collection means depending on the user's input method when collecting voice. Input methods include, but are not limited to, voice input, text input, and image input. For example, the collection unit prioritizes voice collection when the user is using voice input. Furthermore, the collection unit can also collect text data when the user is using text input. Furthermore, the collection unit can also collect image data when the user is using image input. This allows voice to be collected efficiently by selecting the optimal collection means depending on the user's input method. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's input method to the generation AI and cause the generation AI to select the optimal collection means.

[0039] The collection unit can prioritize collection of highly relevant voices based on the user's geographical location information when collecting voices. For example, the collection unit prioritizes collection of highly relevant voices based on the user's geographical location information when collecting voices. Geographical location information includes, but is not limited to, GPS data and IP addresses. For example, if the user is in a specific area, the collection unit prioritizes collection of voices related to that area. Furthermore, if the user is traveling, the collection unit can also collect voices related to the user's destination. Furthermore, if the user stays in a specific location for a long time, the collection unit can collect voices related to that location. In this way, by taking the user's geographical location information into consideration, highly relevant voices can be collected preferentially. Some or all of the above-described processing by the collection unit may be performed using, or without, AI. For example, the collection unit can input geographical location information to a generation AI and cause the generation AI to select highly relevant voices.

[0040] The collection unit can analyze the user's social media activity and collect related audio when collecting audio. For example, the collection unit can analyze the user's social media activity and collect related audio when collecting audio. Social media activity includes, but is not limited to, the content of posts and reactions from followers. For example, the collection unit can collect audio related to places where the user checked in on social media. The collection unit can also analyze the content of the user's social media posts and collect related audio. The collection unit can also collect related audio by referring to the activities of the user's friends on social media. In this way, related audio can be efficiently collected by analyzing the user's social media activity. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input social media activity into a generation AI and cause the generation AI to collect related audio.

[0041] The collection unit can customize the collection method by reflecting the user's past feedback when collecting voice. For example, the collection unit customizes the collection method by reflecting the user's past feedback when collecting voice. Past feedback includes, but is not limited to, survey results and customer support records. For example, the collection unit adjusts the collection method based on feedback provided by the user in the past. The collection unit can also prioritize a specific collection method based on the user's past feedback. The collection unit can also select the type of voice to collect by reflecting the user's feedback. In this way, the collection method can be optimized by reflecting the user's past feedback. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input past feedback into a generation AI and cause the generation AI to customize the collection method.

[0042] When analyzing voice data, the analysis unit can prioritize analyzing phrases and expressions that are likely to be fraudulent. For example, the analysis unit prioritizes analyzing voice data containing typical fraud phrases. Typical fraud phrases and expressions include, but are not limited to, "Please transfer the money now" and "You have won." The analysis unit can also prioritize analyzing voice data containing expressions that are likely to be fraudulent. The analysis unit can also prioritize analyzing voice data that shows signs of fraud. This prioritizes analyzing phrases and expressions that are likely to be fraudulent, thereby improving the accuracy of fraud detection. Some or all of the above-mentioned processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input phrases and expressions that are likely to be fraudulent into a generation AI and cause the generation AI to perform prioritized analysis.

[0043] When analyzing voice data, the analysis unit can improve the accuracy of the analysis by referring to the user's past conversation history. For example, when analyzing voice data, the analysis unit can improve the accuracy of the analysis by referring to the user's past conversation history. Past conversation history includes, but is not limited to, text logs and audio files. For example, the analysis unit improves the accuracy of the analysis based on the user's past conversation history. The analysis unit can also extract and analyze specific patterns from the user's past conversation history. The analysis unit can also analyze the user's past conversation history to improve the accuracy of the analysis. By referring to the user's past conversation history, the accuracy of the analysis is improved. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the past conversation history into a generation AI and cause the generation AI to improve the accuracy of the analysis.

[0044] The analysis unit can apply an analysis algorithm to accommodate different languages ​​or dialects when analyzing the speech data. For example, the analysis unit applies an analysis algorithm to accommodate different languages ​​or dialects when analyzing the speech data. Different languages ​​or dialects include, but are not limited to, multilingual speech recognition technology and dialect dictionaries. For example, the analysis unit applies an algorithm to analyze speech data in different languages. The analysis unit can also apply an algorithm to analyze speech data in different dialects. The analysis unit can also apply a multilingual analysis algorithm to improve the accuracy of the analysis. This improves the accuracy of the analysis by accommodating different languages ​​and dialects. Some or all of the above-described 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 speech data in different languages ​​or dialects to a generation AI and cause the generation AI to apply an analysis algorithm.

[0045] When analyzing voice data, the analysis unit can improve the accuracy of the analysis based on the context of the conversation. For example, when analyzing voice data, the analysis unit improves the accuracy of the analysis by taking into account the context of the conversation. The context of the conversation includes, for example, the content of the preceding and following conversations and related topics, but is not limited to these examples. For example, the analysis unit improves the accuracy of the analysis by taking into account the context of the conversation. The analysis unit can also improve the accuracy of the analysis by analyzing the content before and after the conversation. The analysis unit can also analyze specific phrases and expressions based on the context of the conversation. In this way, the accuracy of the analysis is improved by taking the context of the conversation into consideration. 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 context of the conversation into a generation AI and cause the generation AI to improve the accuracy of the analysis.

[0046] When analyzing voice data, the analysis unit can adjust the level of detail of the analysis results according to the user's level of expertise. For example, when analyzing voice data, the analysis unit adjusts the level of detail of the analysis results according to the user's level of expertise. Expertise levels include, but are not limited to, survey results and past behavioral data. For example, the analysis unit adjusts the level of detail of the analysis results according to the user's level of expertise. Furthermore, the analysis unit can provide detailed analysis results if the user has expertise. Furthermore, the analysis unit can provide concise analysis results if the user does not have expertise. By adjusting the level of detail of the analysis results according to the user's level of expertise, appropriate information can be provided. Some or all of the above-described 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 user's level of expertise to the generation AI and cause the generation AI to adjust the level of detail of the analysis results.

[0047] The analysis unit can optimize the analysis algorithm by reflecting the user's past feedback when analyzing the voice data. For example, the analysis unit can optimize the analysis algorithm by reflecting the user's past feedback when analyzing the voice data. Past feedback includes, but is not limited to, survey results and customer support records. For example, the analysis unit optimizes the analysis algorithm based on the user's past feedback. The analysis unit can also prioritize a specific analysis method based on the user's past feedback. The analysis unit can also adjust the analysis algorithm by reflecting the user's feedback. In this way, the analysis algorithm can be optimized by reflecting the user's past feedback. Some or all of the above-described 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 past feedback into a generation AI and cause the generation AI to optimize the analysis algorithm.

[0048] During matching, the matching unit can prioritize matching of typical fraud phrases and expressions. For example, the matching unit prioritizes matching of voice data containing typical fraud phrases. Typical fraud phrases and expressions include, but are not limited to, "Please transfer the money now" and "You have won." The matching unit can also prioritize matching of voice data containing expressions that are likely to be fraudulent. The matching unit can also prioritize matching of voice data that shows signs of fraud. By prioritizing matching of typical fraud phrases and expressions, the accuracy of fraud detection is improved. Some or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input typical fraud phrases and expressions into the generation AI and cause the generation AI to perform prioritized matching.

[0049] During matching, the matching unit can improve the accuracy of matching by referring to past fraud data. The matching unit improves the accuracy of matching, for example, based on past fraud data. Past fraud data includes, for example, a fraud case database and records of past fraud cases, but is not limited to such examples. The matching unit can also extract specific patterns from past fraud data and match them. The matching unit can also analyze past fraud data to improve the accuracy of matching. In this way, by referring to past fraud data, the accuracy of matching is improved. Some or all of the above-mentioned processing in the matching unit may be performed, for example, using AI, or may be performed without using AI. For example, the matching unit can input past fraud data into the generation AI and have the generation AI improve the accuracy of matching.

[0050] The matching unit can apply a matching algorithm to deal with different fraud methods during matching. The matching unit applies, for example, an algorithm to match voice data of different fraud methods. Different fraud methods include, but are not limited to, phishing scams and telephone scams. The matching unit can also analyze patterns of different fraud methods and apply a matching algorithm. The matching unit can also improve the accuracy of matching by applying a matching algorithm that deals with various fraud methods. This improves the accuracy of matching by dealing with different fraud methods. Some or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input voice data of different fraud methods into a generation AI and cause the generation AI to apply a matching algorithm.

[0051] The matching unit can improve the accuracy of matching based on the context of the conversation during matching. The matching unit, for example, improves the accuracy of matching by taking into account the context of the conversation. The context of the conversation includes, for example, the content of the preceding and following conversations and related topics, but is not limited to these examples. For example, the matching unit improves the accuracy of matching by taking into account the context of the conversation. The matching unit can also analyze the content before and after the conversation to improve the accuracy of matching. The matching unit can also match specific phrases or expressions based on the context of the conversation. In this way, the accuracy of matching is improved by taking the context of the conversation into consideration. Some or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input the context of the conversation into the generation AI and cause the generation AI to improve the accuracy of matching.

[0052] During matching, the matching unit can adjust the level of detail of the matching result according to the user's level of expertise. The matching unit adjusts the level of detail of the matching result according to, for example, the user's level of expertise. Examples of levels of expertise include, but are not limited to, survey results and past behavioral data. For example, the matching unit adjusts the level of detail of the matching result according to the user's level of expertise. Furthermore, the matching unit can provide detailed matching results when the user has specialized knowledge. Furthermore, the matching unit can provide concise matching results when the user does not have specialized knowledge. By adjusting the level of detail of the matching result according to the user's level of expertise, appropriate information can be provided. Some or all of the above-described processing in the matching unit may be performed using, or without, AI. For example, the matching unit can input the user's level of expertise to the generation AI and cause the generation AI to adjust the level of detail of the matching result.

[0053] During matching, the matching unit can optimize the matching algorithm by reflecting the user's past feedback. The matching unit optimizes the matching algorithm based on, for example, the user's past feedback. Past feedback includes, for example, survey results and customer support records, but is not limited to these examples. The matching unit can also prioritize a specific matching method based on the user's past feedback. The matching unit can also adjust the matching algorithm by reflecting the user's feedback. In this way, the matching algorithm can be optimized by reflecting the user's past feedback. Some or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input past feedback into the generation AI and cause the generation AI to optimize the matching algorithm.

[0054] When issuing a warning, the warning unit can adjust the level of detail of the warning based on the content of the conversation that is likely to be fraudulent. For example, if a conversation that is likely to be fraudulent is detected, the warning unit displays a detailed warning. The content of the conversation that is likely to be fraudulent includes, but is not limited to, the frequency of occurrence of specific keywords and the tone of the conversation. Furthermore, if a conversation that is likely to be fraudulent is detected, the warning unit can display a brief warning. Furthermore, if a conversation that is likely to be fraudulent is detected, the warning unit can display a warning with appropriate level of detail. This allows for an appropriate warning by adjusting the level of detail of the warning based on the content of the conversation that is likely to be fraudulent. Some or all of the above-described processing in the warning unit may be performed, for example, using AI or without AI. For example, the warning unit can input the content of the conversation that is likely to be fraudulent into a generation AI and cause the generation AI to adjust the level of detail of the warning.

[0055] When issuing a warning, the warning unit can improve the accuracy of the warning by referring to the user's past warning history. The warning unit improves the accuracy of the warning, for example, based on the user's past warning history. The past warning history includes, for example, records of past warnings and the contents of warnings, but is not limited to such examples. The warning unit can also extract a specific pattern from the user's past warning history and issue a warning. The warning unit can also analyze the user's past warning history and improve the accuracy of the warning. In this way, the accuracy of the warning is improved by referring to the user's past warning history. 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 the past warning history into the generation AI and cause the generation AI to improve the accuracy of the warning.

[0056] The warning unit can apply a warning algorithm to deal with different fraud methods when issuing a warning. For example, the warning unit applies an algorithm to warn of audio data of different fraud methods. Different fraud methods include, but are not limited to, phishing scams and telephone scams. The warning unit can also analyze patterns of different fraud methods and apply a warning algorithm. The warning unit can also improve the accuracy of the warning by applying a warning algorithm that deals with various fraud methods. This improves the accuracy of the warning by dealing with different fraud methods. Some or all of the above-mentioned processing in the warning unit can be performed using, for example, AI, or can be performed without using AI. For example, the warning unit can input audio data of different fraud methods to a generation AI and cause the generation AI to apply a warning algorithm.

[0057] The warning unit can improve the accuracy of the warning by taking into account the context of the conversation when issuing a warning. The warning unit, for example, improves the accuracy of the warning by taking into account the context of the conversation. The context of the conversation includes, for example, the content of the preceding and following conversations and related topics, but is not limited to these examples. For example, the warning unit improves the accuracy of the warning by taking into account the context of the conversation. The warning unit can also analyze the content before and after the conversation and improve the accuracy of the warning. The warning unit can also warn about specific phrases or expressions based on the context of the conversation. In this way, the accuracy of the warning is improved by taking the context of the conversation into consideration. 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 context of the conversation into a generation AI and cause the generation AI to improve the accuracy of the warning.

[0058] When issuing a warning, the warning unit can adjust the level of detail of the warning according to the user's level of expertise. The warning unit adjusts the level of detail of the warning according to, for example, the user's level of expertise. Examples of expertise levels include, but are not limited to, survey results and past behavioral data. For example, the warning unit adjusts the level of detail of the warning according to the user's level of expertise. The warning unit can also provide a detailed warning if the user has expertise. The warning unit can also provide a concise warning if the user does not have expertise. By adjusting the level of detail of the warning according to the user's level of expertise, appropriate information can be provided. Some or all of the above-described 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 user's level of expertise to the generation AI and cause the generation AI to adjust the level of detail of the warning.

[0059] The warning unit can optimize the warning algorithm by reflecting the user's past feedback when issuing a warning. The warning unit optimizes the warning algorithm based on, for example, the user's past feedback. Past feedback includes, for example, but is not limited to, survey results and customer support records. The warning unit can also prioritize a specific warning method based on the user's past feedback. The warning unit can also adjust the warning algorithm by reflecting the user's feedback. In this way, the warning algorithm can be optimized by reflecting the user's past feedback. 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 past feedback into a generation AI and cause the generation AI to optimize the warning algorithm.

[0060] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0061] When analyzing voice data, the analysis unit can improve the accuracy of the analysis by taking into account the user's past behavioral patterns. For example, the analysis unit analyzes what types of fraud the user has encountered in the past and performs the analysis based on those patterns. The analysis unit can also refer to the user's past conversation history and perform the analysis by taking into account the frequency of occurrence of specific phrases and expressions. Furthermore, the analysis unit can apply an algorithm to identify conversations that are likely to be fraudulent based on the user's past behavioral patterns. In this way, by taking into account the user's past behavioral patterns, the accuracy of the analysis can be improved, making fraud detection more effective.

[0062] When matching voice data, the matching unit can adjust the matching criteria based on the user's current situation and environment. For example, the matching unit can tighten the matching criteria when the user is in a public place. The matching unit can also loosen the matching criteria when the user is at home. Furthermore, the matching unit can dynamically adjust the matching criteria when the user is on the move. This allows for more appropriate matching by adjusting the matching criteria according to the user's current situation and environment.

[0063] The warning unit can customize the content of the warning when a conversation that may be fraudulent is detected. For example, the warning unit can display a detailed warning message when a conversation that is highly likely to be fraudulent is detected. The warning unit can also display a concise warning message when a conversation that is low in possibility of fraud is detected. Furthermore, the warning unit can also display a warning message with moderate detail when a conversation that is medium in possibility of fraud is detected. This allows appropriate warnings to be given by customizing the content of the warning depending on the possibility of fraud.

[0064] When collecting audio, the collection unit can customize the collection method by reflecting the user's past feedback. For example, the collection unit can adjust the collection method based on feedback provided by the user in the past. The collection unit can also prioritize a specific collection method based on the user's past feedback. Furthermore, the collection unit can select the type of audio to collect by reflecting the user's feedback. In this way, the collection method can be optimized by reflecting the user's past feedback.

[0065] When analyzing voice data, the analysis unit can adjust the level of detail of the analysis results according to the user's level of expertise. For example, if the user has specialized knowledge, the analysis unit can provide detailed analysis results. Alternatively, if the user does not have specialized knowledge, the analysis unit can provide concise analysis results. Furthermore, the analysis unit can adjust the display method of the analysis results according to the user's level of expertise. This makes it possible to provide appropriate information by adjusting the level of detail of the analysis results according to the user's level of expertise.

[0066] When matching voice data, the matching unit can apply a matching algorithm to deal with different fraud methods. For example, the matching unit applies a matching algorithm that corresponds to different fraud methods, such as phishing fraud and telephone fraud. The matching unit can also analyze the patterns of different fraud methods and apply a matching algorithm. Furthermore, the matching unit can apply a matching algorithm that corresponds to various fraud methods to improve the accuracy of matching. This improves the accuracy of matching by dealing with different fraud methods.

[0067] The processing flow of the first embodiment will be briefly explained below.

[0068] Step 1: The collection unit collects audio. The audio includes, for example, telephone conversations, recorded audio, real-time audio, etc. The collection unit can also collect telephone conversations at a customer service center. Step 2: The analysis unit analyzes the audio collected by the collection unit. The analysis is performed using voice recognition technology and natural language processing technology. For example, the analysis unit converts the audio data into text data using voice recognition technology and analyzes the audio data using natural language processing technology. The analysis unit also sets criteria and conditions for identifying potentially fraudulent conversations based on the frequency of specific keywords and the tone of the conversation. Step 3: The matching unit compares the analyzed voice data with past fraud data. The matching is performed based on a similarity measure and the algorithm used. For example, the matching unit identifies conversations containing typical fraud phrases and expressions and improves the accuracy of the matching by referring to past fraud data. The matching unit also applies matching algorithms that correspond to different fraud methods, such as phishing and telephone fraud. Step 4: The warning unit issues a warning if the matching unit determines there is a possibility of fraud. The warning may be in the form of voice, text, alert, or the like. For example, the warning unit may issue a warning to a person in charge if a conversation that is likely to be fraudulent is detected. The warning unit may also estimate the user's emotions and adjust the way the warning is displayed based on the estimated user's emotions.

[0069] (Example 2) A fraud detection system according to an embodiment of the present invention is a system that collects and analyzes audio, compares it with past fraud data, and issues a warning. The fraud detection system collects and analyzes audio, and compares it with past fraud data to issue a warning if there is a possibility of fraud. For example, the fraud detection system collects telephone conversations and recorded audio. Then, the fraud detection system uses AI to analyze the collected audio and converts the audio data into text. For example, the fraud detection system converts the audio data into text data using speech recognition technology. Then, the fraud detection system compares the analyzed audio data with past fraud data. For example, the fraud detection system identifies conversations containing typical fraudulent phrases and expressions. Then, the fraud detection system issues a warning if there is a possibility of fraud. For example, the fraud detection system issues a warning to a staff member if a conversation with a high probability of fraud is detected. This enables the fraud detection system to detect fraud early and prevent damage before it occurs. This enables the fraud detection system to detect fraud early and prevent damage before it occurs. For example, monitoring conversations at a bank's call center and detecting potentially fraudulent conversations can protect customer assets. It can also protect customer personal information by monitoring conversations at customer service centers and detecting potentially fraudulent conversations.

[0070] A fraud detection system according to an embodiment includes a collection unit, an analysis unit, a matching unit, and a warning unit. The collection unit collects audio. Examples of audio include, but are not limited to, telephone conversations, recorded audio, and real-time audio. The collection unit collects, for example, telephone conversations. The collection unit can also collect recorded audio. The collection unit can also collect real-time audio. For example, the collection unit collects telephone conversations at a customer service center. The analysis unit analyzes the audio collected by the collection unit. The analysis is performed using, for example, but is not limited to, speech recognition technology or natural language processing technology. For example, the analysis unit converts speech data into text data using speech recognition technology. The analysis unit can also analyze speech data using natural language processing technology. The analysis unit can also analyze the speech data and set criteria and conditions for identifying potentially fraudulent conversations. For example, the analysis unit sets criteria and conditions based on the frequency of occurrence of specific keywords or the tone of the conversation. The matching unit compares the speech data analyzed by the analysis unit with past fraud data. The matching is performed based on, for example, a similarity measure or an algorithm used, but is not limited to these examples. For example, the matching unit identifies conversations containing phrases or expressions typical of fraud. The matching unit can also improve the accuracy of the matching by referring to past fraud data. Furthermore, the matching unit can apply matching algorithms to deal with different fraud methods. For example, the matching unit applies matching algorithms that deal with different fraud methods, such as phishing scams and telephone scams. The warning unit issues a warning when the matching unit detects a possibility of fraud. The warning can be in the form of, for example, voice, text, or an alert, but is not limited to these examples. For example, the warning unit issues a warning to a responsible person when a conversation with a high possibility of fraud is detected. The warning unit can also set the timing and method of the warning. Furthermore, the warning unit can estimate the user's emotions and adjust the way the warning is displayed based on the estimated user's emotions. For example, if the user is nervous, the warning unit displays the warning in a calm color scheme.As a result, the fraud detection system according to the embodiment enables early detection of fraud and prevents damage before it occurs.

[0071] The collection unit can collect telephone conversations or recorded voices. For example, the collection unit collects telephone conversations. Telephone conversations include, but are not limited to, landline, mobile phone, VoIP, etc. The collection unit can also collect recorded voices. Recorded voices include, but are not limited to, digital recordings, analog recordings, etc. For example, the collection unit collects telephone conversations at a customer service center. In this way, by collecting telephone conversations and recorded voices, various voice data can be targeted.

[0072] The analysis unit can convert the voice data into text. The analysis unit converts the voice data into text data using, for example, voice recognition technology. Voice recognition technology includes, for example, voice recognition software and transcription software, but is not limited to these examples. The analysis unit can also analyze the voice data using natural language processing technology. For example, the analysis unit converts the voice data into text data and performs analysis based on the text data. By converting the voice data into text, it becomes possible to analyze it as text data.

[0073] The matching unit can identify conversations that include typical phrases or expressions of fraud. For example, the matching unit identifies conversations that include typical phrases or expressions of fraud. Typical phrases or expressions of fraud include, but are not limited to, "Please transfer the money now" and "You have won." The matching unit can also improve the accuracy of matching by referring to past fraud data. For example, the matching unit extracts and matches specific patterns based on past fraud data. This allows the identification of typical phrases or expressions of fraud, thereby enabling the detection of the possibility of fraud with high accuracy.

[0074] The warning unit can issue a warning to a person in charge when a conversation that is highly likely to be fraudulent is detected. For example, the warning unit issues a warning to a person in charge when a conversation that is highly likely to be fraudulent is detected. The person in charge can include, but is not limited to, a customer support person or a security person. The warning unit can also set the timing and method of issuing the warning. For example, the warning unit can issue a warning in real time. The warning unit can also issue a warning as a periodic report. In this way, issuing a warning when a conversation that is highly likely to be fraudulent is detected enables a prompt response.

[0075] The analysis unit can analyze the voice data and set criteria or conditions for identifying potentially fraudulent conversations. For example, the analysis unit can analyze the voice data and set criteria or conditions for identifying potentially fraudulent conversations. Examples of the criteria or conditions include, but are not limited to, the frequency of occurrence of specific keywords and the tone of the conversation. The analysis unit can also analyze the voice data and apply an algorithm for identifying potentially fraudulent conversations. For example, the analysis unit can analyze the voice data and apply a machine learning algorithm for identifying potentially fraudulent conversations. In this way, by setting criteria or conditions, potentially fraudulent conversations can be more accurately identified.

[0076] The warning unit can set the timing and method of issuing a warning when a conversation that may be fraudulent is detected. The warning unit sets, for example, the timing and method of issuing a warning when a conversation that may be fraudulent is detected. Examples of the timing and method include, but are not limited to, real-time warnings and periodic reports. The warning unit can also set the format of the warning. For example, the warning unit issues a warning in the form of voice, text, alert, or the like. In this way, by setting the timing and method of the warning, it is possible to issue a warning at an appropriate time.

[0077] The collection unit can estimate the user's emotion and adjust the timing of audio collection based on the estimated user emotion. The collection unit, for example, estimates the user's emotion and adjusts the timing of audio collection based on the estimated user emotion. Emotion estimation is performed using, for example, technologies such as voice analysis and facial expression recognition, but is not limited to these examples. For example, if the user is nervous, the collection unit delays audio collection until the user relaxes. Also, if the user is relaxed, the collection unit can immediately start audio collection. Also, if the user is excited, the collection unit can pause audio collection until the user calms down. In this way, by adjusting the timing of audio collection according to the user's emotion, audio can be collected at a more appropriate time. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0078] The collection unit can analyze the user's past conversation history and select the optimal collection method when collecting audio. For example, the collection unit can analyze the user's past conversation history and select the optimal collection method when collecting audio. Past conversation history includes, but is not limited to, text logs and audio files. For example, if the user has had many telephone conversations in the past, the collection unit can prioritize collecting telephone conversations. Furthermore, if the user has provided many recorded audio files in the past, the collection unit can also prioritize collecting recorded audio files. Furthermore, the collection unit can concentrate collection on a specific time period from the user's past conversation history. This allows the optimal collection method to be selected by analyzing the user's past conversation history. Some or all of the above-described processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input the past conversation history into a generation AI and have the generation AI select the optimal collection method.

[0079] The collection unit may filter the audio data based on the user's current situation or areas of interest when collecting the audio data. For example, the collection unit may filter the audio data based on the user's current situation or areas of interest when collecting the audio data. Examples of the current situation and areas of interest include, but are not limited to, real-time behavioral data and past search history. For example, the collection unit may pause collection if the user is busy in their current situation. The collection unit may also collect only relevant audio data based on the user's areas of interest. The collection unit may also prioritize the audio data to be collected according to the user's current situation. This allows highly relevant audio data to be collected by filtering based on the user's current situation and areas of interest. Some or all of the above-described processing by the collection unit may be performed using, or without, AI. For example, the collection unit may input real-time behavioral data into a generation AI and have the generation AI perform filtering.

[0080] The collection unit can select the optimal collection means depending on the user's input method when collecting voice. For example, the collection unit selects the optimal collection means depending on the user's input method when collecting voice. Input methods include, but are not limited to, voice input, text input, and image input. For example, the collection unit prioritizes voice collection when the user is using voice input. Furthermore, the collection unit can also collect text data when the user is using text input. Furthermore, the collection unit can also collect image data when the user is using image input. This allows voice to be collected efficiently by selecting the optimal collection means depending on the user's input method. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's input method to the generation AI and cause the generation AI to select the optimal collection means.

[0081] The collection unit can estimate the user's emotions and determine the priority of the audio to be collected based on the estimated user emotions. The collection unit, for example, estimates the user's emotions and determines the priority of the audio to be collected based on the estimated user emotions. Emotion estimation is performed using, for example, technologies such as voice analysis and facial expression recognition, but is not limited to these examples. For example, if the user is nervous, the collection unit can prioritize collecting important audio. Also, if the user is relaxed, the collection unit can collect all audio equally. Also, if the user is excited, the collection unit can pause collection until the user calms down. In this way, by determining the priority of the audio to be collected according to the user's emotions, important audio can be prioritized and collected. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0082] The collection unit can prioritize collection of highly relevant voices based on the user's geographical location information when collecting voices. For example, the collection unit prioritizes collection of highly relevant voices based on the user's geographical location information when collecting voices. Geographical location information includes, but is not limited to, GPS data and IP addresses. For example, if the user is in a specific area, the collection unit prioritizes collection of voices related to that area. Furthermore, if the user is traveling, the collection unit can also collect voices related to the user's destination. Furthermore, if the user stays in a specific location for a long time, the collection unit can collect voices related to that location. In this way, by taking the user's geographical location information into consideration, highly relevant voices can be collected preferentially. Some or all of the above-described processing by the collection unit may be performed using, or without, AI. For example, the collection unit can input geographical location information to a generation AI and cause the generation AI to select highly relevant voices.

[0083] The collection unit can analyze the user's social media activity and collect related audio when collecting audio. For example, the collection unit can analyze the user's social media activity and collect related audio when collecting audio. Social media activity includes, but is not limited to, the content of posts and reactions from followers. For example, the collection unit can collect audio related to places where the user checked in on social media. The collection unit can also analyze the content of the user's social media posts and collect related audio. The collection unit can also collect related audio by referring to the activities of the user's friends on social media. In this way, related audio can be efficiently collected by analyzing the user's social media activity. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input social media activity into a generation AI and cause the generation AI to collect related audio.

[0084] The collection unit can customize the collection method by reflecting the user's past feedback when collecting voice. For example, the collection unit customizes the collection method by reflecting the user's past feedback when collecting voice. Past feedback includes, but is not limited to, survey results and customer support records. For example, the collection unit adjusts the collection method based on feedback provided by the user in the past. The collection unit can also prioritize a specific collection method based on the user's past feedback. The collection unit can also select the type of voice to collect by reflecting the user's feedback. In this way, the collection method can be optimized by reflecting the user's past feedback. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input past feedback into a generation AI and cause the generation AI to customize the collection method.

[0085] The analysis unit can estimate the user's emotion and adjust the analysis method of the voice data based on the estimated user emotion. The analysis unit, for example, estimates the user's emotion and adjusts the analysis method of the voice data based on the estimated user emotion. Emotion estimation is performed using, for example, technologies such as voice analysis and facial expression recognition, but is not limited to these examples. For example, the analysis unit can perform a quick analysis when the user is nervous. The analysis unit can also perform a detailed analysis when the user is relaxed. The analysis unit can also pause the analysis when the user is excited until the user calms down. This enables more appropriate analysis by adjusting the analysis method according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0086] When analyzing voice data, the analysis unit can prioritize analyzing phrases and expressions that are likely to be fraudulent. For example, the analysis unit prioritizes analyzing voice data containing typical fraud phrases. Typical fraud phrases and expressions include, but are not limited to, "Please transfer the money now" and "You have won." The analysis unit can also prioritize analyzing voice data containing expressions that are likely to be fraudulent. The analysis unit can also prioritize analyzing voice data that shows signs of fraud. This prioritizes analyzing phrases and expressions that are likely to be fraudulent, thereby improving the accuracy of fraud detection. Some or all of the above-mentioned processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input phrases and expressions that are likely to be fraudulent into a generation AI and cause the generation AI to perform prioritized analysis.

[0087] When analyzing voice data, the analysis unit can improve the accuracy of the analysis by referring to the user's past conversation history. For example, when analyzing voice data, the analysis unit can improve the accuracy of the analysis by referring to the user's past conversation history. Past conversation history includes, but is not limited to, text logs and audio files. For example, the analysis unit improves the accuracy of the analysis based on the user's past conversation history. The analysis unit can also extract and analyze specific patterns from the user's past conversation history. The analysis unit can also analyze the user's past conversation history to improve the accuracy of the analysis. By referring to the user's past conversation history, the accuracy of the analysis is improved. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the past conversation history into a generation AI and cause the generation AI to improve the accuracy of the analysis.

[0088] The analysis unit can apply an analysis algorithm to accommodate different languages ​​or dialects when analyzing the speech data. For example, the analysis unit applies an analysis algorithm to accommodate different languages ​​or dialects when analyzing the speech data. Different languages ​​or dialects include, but are not limited to, multilingual speech recognition technology and dialect dictionaries. For example, the analysis unit applies an algorithm to analyze speech data in different languages. The analysis unit can also apply an algorithm to analyze speech data in different dialects. The analysis unit can also apply a multilingual analysis algorithm to improve the accuracy of the analysis. This improves the accuracy of the analysis by accommodating different languages ​​and dialects. Some or all of the above-described 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 speech data in different languages ​​or dialects to a generation AI and cause the generation AI to apply an analysis algorithm.

[0089] The analysis unit can estimate the user's emotion and adjust the display method of the analysis results based on the estimated user emotion. The analysis unit, for example, estimates the user's emotion and adjusts the display method of the analysis results based on the estimated user emotion. Emotion estimation is performed using, for example, technologies such as voice analysis and facial expression recognition, but is not limited to these examples. For example, if the user is nervous, the analysis unit can provide a simple, highly visible display method. If the user is relaxed, the analysis unit can provide a display method that includes detailed information. If the user is in a hurry, the analysis unit can provide a display method that focuses on the main points. This allows for more appropriate display by adjusting the display method of the analysis results according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0090] When analyzing voice data, the analysis unit can improve the accuracy of the analysis based on the context of the conversation. For example, when analyzing voice data, the analysis unit improves the accuracy of the analysis by taking into account the context of the conversation. The context of the conversation includes, for example, the content of the preceding and following conversations and related topics, but is not limited to these examples. For example, the analysis unit improves the accuracy of the analysis by taking into account the context of the conversation. The analysis unit can also improve the accuracy of the analysis by analyzing the content before and after the conversation. The analysis unit can also analyze specific phrases and expressions based on the context of the conversation. In this way, the accuracy of the analysis is improved by taking the context of the conversation into consideration. 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 context of the conversation into a generation AI and cause the generation AI to improve the accuracy of the analysis.

[0091] When analyzing voice data, the analysis unit can adjust the level of detail of the analysis results according to the user's level of expertise. For example, when analyzing voice data, the analysis unit adjusts the level of detail of the analysis results according to the user's level of expertise. Expertise levels include, but are not limited to, survey results and past behavioral data. For example, the analysis unit adjusts the level of detail of the analysis results according to the user's level of expertise. Furthermore, the analysis unit can provide detailed analysis results if the user has expertise. Furthermore, the analysis unit can provide concise analysis results if the user does not have expertise. By adjusting the level of detail of the analysis results according to the user's level of expertise, appropriate information can be provided. Some or all of the above-described 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 user's level of expertise to the generation AI and cause the generation AI to adjust the level of detail of the analysis results.

[0092] The analysis unit can optimize the analysis algorithm by reflecting the user's past feedback when analyzing the voice data. For example, the analysis unit can optimize the analysis algorithm by reflecting the user's past feedback when analyzing the voice data. Past feedback includes, but is not limited to, survey results and customer support records. For example, the analysis unit optimizes the analysis algorithm based on the user's past feedback. The analysis unit can also prioritize a specific analysis method based on the user's past feedback. The analysis unit can also adjust the analysis algorithm by reflecting the user's feedback. In this way, the analysis algorithm can be optimized by reflecting the user's past feedback. Some or all of the above-described 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 past feedback into a generation AI and cause the generation AI to optimize the analysis algorithm.

[0093] The matching unit can estimate the user's emotion and adjust the matching criteria based on the estimated user's emotion. The matching unit, for example, estimates the user's emotion and adjusts the matching criteria based on the estimated user's emotion. Emotion estimation is performed using, for example, technologies such as voice analysis and facial expression recognition, but is not limited to these examples. For example, the matching unit tightens the matching criteria when the user is nervous. The matching unit can also loosen the matching criteria when the user is relaxed. The matching unit can also pause matching when the user is excited until the user calms down. This enables more appropriate matching by adjusting the matching criteria according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0094] During matching, the matching unit can prioritize matching of typical fraud phrases and expressions. For example, the matching unit prioritizes matching of voice data containing typical fraud phrases. Typical fraud phrases and expressions include, but are not limited to, "Please transfer the money now" and "You have won." The matching unit can also prioritize matching of voice data containing expressions that are likely to be fraudulent. The matching unit can also prioritize matching of voice data that shows signs of fraud. By prioritizing matching of typical fraud phrases and expressions, the accuracy of fraud detection is improved. Some or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input typical fraud phrases and expressions into the generation AI and cause the generation AI to perform prioritized matching.

[0095] During matching, the matching unit can improve the accuracy of matching by referring to past fraud data. The matching unit improves the accuracy of matching, for example, based on past fraud data. Past fraud data includes, for example, a fraud case database and records of past fraud cases, but is not limited to such examples. The matching unit can also extract specific patterns from past fraud data and match them. The matching unit can also analyze past fraud data to improve the accuracy of matching. In this way, by referring to past fraud data, the accuracy of matching is improved. Some or all of the above-mentioned processing in the matching unit may be performed, for example, using AI, or may be performed without using AI. For example, the matching unit can input past fraud data into the generation AI and have the generation AI improve the accuracy of matching.

[0096] The matching unit can apply a matching algorithm to deal with different fraud methods during matching. The matching unit applies, for example, an algorithm to match voice data of different fraud methods. Different fraud methods include, but are not limited to, phishing scams and telephone scams. The matching unit can also analyze patterns of different fraud methods and apply a matching algorithm. The matching unit can also improve the accuracy of matching by applying a matching algorithm that deals with various fraud methods. This improves the accuracy of matching by dealing with different fraud methods. Some or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input voice data of different fraud methods into a generation AI and cause the generation AI to apply a matching algorithm.

[0097] The matching unit can estimate the user's emotion and adjust the display method of the matching result based on the estimated user emotion. The matching unit, for example, estimates the user's emotion and adjusts the display method of the matching result based on the estimated user emotion. Emotion estimation is performed using, for example, technologies such as voice analysis and facial expression recognition, but is not limited to these examples. For example, if the user is nervous, the matching unit can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the matching unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the matching unit can provide a display method that focuses on the main points. This allows for more appropriate display by adjusting the display method of the matching result according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0098] The matching unit can improve the accuracy of matching based on the context of the conversation during matching. The matching unit, for example, improves the accuracy of matching by taking into account the context of the conversation. The context of the conversation includes, for example, the content of the preceding and following conversations and related topics, but is not limited to these examples. For example, the matching unit improves the accuracy of matching by taking into account the context of the conversation. The matching unit can also analyze the content before and after the conversation to improve the accuracy of matching. The matching unit can also match specific phrases or expressions based on the context of the conversation. In this way, the accuracy of matching is improved by taking the context of the conversation into consideration. Some or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input the context of the conversation into the generation AI and cause the generation AI to improve the accuracy of matching.

[0099] During matching, the matching unit can adjust the level of detail of the matching result according to the user's level of expertise. The matching unit adjusts the level of detail of the matching result according to, for example, the user's level of expertise. Examples of levels of expertise include, but are not limited to, survey results and past behavioral data. For example, the matching unit adjusts the level of detail of the matching result according to the user's level of expertise. Furthermore, the matching unit can provide detailed matching results when the user has specialized knowledge. Furthermore, the matching unit can provide concise matching results when the user does not have specialized knowledge. By adjusting the level of detail of the matching result according to the user's level of expertise, appropriate information can be provided. Some or all of the above-described processing in the matching unit may be performed using, or without, AI. For example, the matching unit can input the user's level of expertise to the generation AI and cause the generation AI to adjust the level of detail of the matching result.

[0100] During matching, the matching unit can optimize the matching algorithm by reflecting the user's past feedback. The matching unit optimizes the matching algorithm based on, for example, the user's past feedback. Past feedback includes, for example, survey results and customer support records, but is not limited to these examples. The matching unit can also prioritize a specific matching method based on the user's past feedback. The matching unit can also adjust the matching algorithm by reflecting the user's feedback. In this way, the matching algorithm can be optimized by reflecting the user's past feedback. Some or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input past feedback into the generation AI and cause the generation AI to optimize the matching algorithm.

[0101] The warning unit can estimate the user's emotion and adjust the display method of the warning based on the estimated user's emotion. The warning unit, for example, estimates the user's emotion and adjusts the display method of the warning based on the estimated user's emotion. Emotion estimation is performed using, for example, technologies such as voice analysis and facial expression recognition, but is not limited to these examples. For example, if the user is nervous, the warning unit can display the warning in subdued colors. Also, if the user is relaxed, the warning unit can display the warning in bright colors. Also, if the user is in a hurry, the warning unit can display a concise and highly visible warning. This allows for more appropriate warnings by adjusting the display method of the warning according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0102] When issuing a warning, the warning unit can adjust the level of detail of the warning based on the content of the conversation that is likely to be fraudulent. For example, if a conversation that is likely to be fraudulent is detected, the warning unit displays a detailed warning. The content of the conversation that is likely to be fraudulent includes, but is not limited to, the frequency of occurrence of specific keywords and the tone of the conversation. Furthermore, if a conversation that is likely to be fraudulent is detected, the warning unit can display a brief warning. Furthermore, if a conversation that is likely to be fraudulent is detected, the warning unit can display a warning with appropriate level of detail. This allows for an appropriate warning by adjusting the level of detail of the warning based on the content of the conversation that is likely to be fraudulent. Some or all of the above-described processing in the warning unit may be performed, for example, using AI or without AI. For example, the warning unit can input the content of the conversation that is likely to be fraudulent into a generation AI and cause the generation AI to adjust the level of detail of the warning.

[0103] When issuing a warning, the warning unit can improve the accuracy of the warning by referring to the user's past warning history. The warning unit improves the accuracy of the warning, for example, based on the user's past warning history. The past warning history includes, for example, records of past warnings and the contents of warnings, but is not limited to such examples. The warning unit can also extract a specific pattern from the user's past warning history and issue a warning. The warning unit can also analyze the user's past warning history and improve the accuracy of the warning. In this way, the accuracy of the warning is improved by referring to the user's past warning history. 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 the past warning history into the generation AI and cause the generation AI to improve the accuracy of the warning.

[0104] The warning unit can apply a warning algorithm to deal with different fraud methods when issuing a warning. For example, the warning unit applies an algorithm to warn of audio data of different fraud methods. Different fraud methods include, but are not limited to, phishing scams and telephone scams. The warning unit can also analyze patterns of different fraud methods and apply a warning algorithm. The warning unit can also improve the accuracy of the warning by applying a warning algorithm that deals with various fraud methods. This improves the accuracy of the warning by dealing with different fraud methods. Some or all of the above-mentioned processing in the warning unit can be performed using, for example, AI, or can be performed without using AI. For example, the warning unit can input audio data of different fraud methods to a generation AI and cause the generation AI to apply a warning algorithm.

[0105] The warning unit can estimate the user's emotions and determine the priority of warnings based on the estimated user emotions. The warning unit can, for example, estimate the user's emotions and determine the priority of warnings based on the estimated user emotions. Emotion estimation can be performed using, for example, technologies such as voice analysis and facial expression recognition, but is not limited to these examples. For example, if the user is nervous, the warning unit can prioritize displaying important warnings. Also, if the user is relaxed, the warning unit can equally display all warnings. Also, if the user is excited, the warning unit can pause warnings until the user calms down. In this way, by determining the priority of warnings according to the user's emotions, important warnings can be prioritized and displayed. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0106] The warning unit can improve the accuracy of the warning by taking into account the context of the conversation when issuing a warning. The warning unit, for example, improves the accuracy of the warning by taking into account the context of the conversation. The context of the conversation includes, for example, the content of the preceding and following conversations and related topics, but is not limited to these examples. For example, the warning unit improves the accuracy of the warning by taking into account the context of the conversation. The warning unit can also analyze the content before and after the conversation and improve the accuracy of the warning. The warning unit can also warn about specific phrases or expressions based on the context of the conversation. In this way, the accuracy of the warning is improved by taking the context of the conversation into consideration. 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 context of the conversation into a generation AI and cause the generation AI to improve the accuracy of the warning.

[0107] When issuing a warning, the warning unit can adjust the level of detail of the warning according to the user's level of expertise. The warning unit adjusts the level of detail of the warning according to, for example, the user's level of expertise. Examples of expertise levels include, but are not limited to, survey results and past behavioral data. For example, the warning unit adjusts the level of detail of the warning according to the user's level of expertise. The warning unit can also provide a detailed warning if the user has expertise. The warning unit can also provide a concise warning if the user does not have expertise. By adjusting the level of detail of the warning according to the user's level of expertise, appropriate information can be provided. Some or all of the above-described 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 user's level of expertise to the generation AI and cause the generation AI to adjust the level of detail of the warning.

[0108] The warning unit can optimize the warning algorithm by reflecting the user's past feedback when issuing a warning. The warning unit optimizes the warning algorithm based on, for example, the user's past feedback. Past feedback includes, for example, but is not limited to, survey results and customer support records. The warning unit can also prioritize a specific warning method based on the user's past feedback. The warning unit can also adjust the warning algorithm by reflecting the user's feedback. In this way, the warning algorithm can be optimized by reflecting the user's past feedback. 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 past feedback into a generation AI and cause the generation AI to optimize the warning algorithm. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, matching unit, and warning unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects voice using the microphone 38B of the smart device 14 and transmits the collected voice data to the data processing device 12 by the control unit 46A. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, converts the voice data into text data and analyzes it using natural language processing technology. The matching unit, realized, for example, by the specific processing unit 290 of the data processing device 12, matches the analyzed voice data with past fraud data. The warning unit can issue a warning using, for example, the output device 40 of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, matching unit, and warning unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects voice using the microphone 238 of the smart glasses 214 and transmits the collected voice data to the data processing device 12 by the control unit 46A. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, converts the voice data into text data and analyzes it using natural language processing technology. The matching unit, realized, for example, by the specific processing unit 290 of the data processing device 12, matches the analyzed voice data with past fraud data. The warning unit can issue a warning using, for example, the speaker 240 of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned collection unit, analysis unit, matching unit, and warning unit is realized, for example, in at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit collects voice using the microphone 238 of the headset-type terminal 314 and transmits the collected voice data to the data processing device 12 by the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, converts the voice data into text data, and analyzes it using natural language processing technology. The matching unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and matches the analyzed voice data with past fraud data. The warning unit can issue a warning using, for example, the speaker 240 of the headset-type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, analysis unit, matching unit, and warning unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects voice using the microphone 238 of the robot 414 and transmits the collected voice data to the data processing device 12 by the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, converts the voice data into text data, and analyzes it using natural language processing technology. The matching unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and matches the analyzed voice data with past fraud data. The warning unit can issue a warning using, for example, the speaker 240 of the robot 414.

[0109] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0110] When analyzing voice data, the analysis unit can improve the accuracy of the analysis by taking into account the user's past behavioral patterns. For example, the analysis unit analyzes what types of fraud the user has encountered in the past and performs the analysis based on those patterns. The analysis unit can also refer to the user's past conversation history and perform the analysis by taking into account the frequency of occurrence of specific phrases and expressions. Furthermore, the analysis unit can apply an algorithm to identify conversations that are likely to be fraudulent based on the user's past behavioral patterns. In this way, by taking into account the user's past behavioral patterns, the accuracy of the analysis can be improved, making fraud detection more effective.

[0111] When matching voice data, the matching unit can adjust the matching criteria based on the user's current situation and environment. For example, the matching unit can tighten the matching criteria when the user is in a public place. The matching unit can also loosen the matching criteria when the user is at home. Furthermore, the matching unit can dynamically adjust the matching criteria when the user is on the move. This allows for more appropriate matching by adjusting the matching criteria according to the user's current situation and environment.

[0112] The warning unit can customize the content of the warning when a conversation that may be fraudulent is detected. For example, the warning unit can display a detailed warning message when a conversation that is highly likely to be fraudulent is detected. The warning unit can also display a concise warning message when a conversation that is low in possibility of fraud is detected. Furthermore, the warning unit can also display a warning message with moderate detail when a conversation that is medium in possibility of fraud is detected. This allows appropriate warnings to be given by customizing the content of the warning depending on the possibility of fraud.

[0113] The collection unit can adjust the collection method based on the user's current emotional state when collecting audio. For example, the collection unit can pause collection when the user is nervous. The collection unit can also resume collection when the user is relaxed. Furthermore, the collection unit can delay collection when the user is excited. In this way, by adjusting the collection method according to the user's emotional state, audio can be collected at a more appropriate time.

[0114] When analyzing voice data, the analysis unit can determine the analysis priority based on the user's emotional state. For example, if the user is nervous, the analysis unit will prioritize analyzing important voice data. Also, if the user is relaxed, the analysis unit can analyze all voice data equally. Furthermore, if the user is excited, the analysis unit can pause analysis until the user calms down. In this way, by determining the analysis priority according to the user's emotional state, important voice data can be analyzed preferentially.

[0115] When matching voice data, the matching unit can adjust the matching accuracy based on the user's emotional state. For example, if the user is nervous, the matching unit can increase the matching accuracy. Also, if the user is relaxed, the matching unit can relax the matching accuracy. Furthermore, if the user is excited, the matching unit can pause matching until the user calms down. In this way, adjusting the matching accuracy according to the user's emotional state enables more appropriate matching.

[0116] When a potentially fraudulent conversation is detected, the warning unit can adjust the warning display method based on the user's emotional state. For example, if the user is nervous, the warning unit can display the warning in subdued colors. If the user is relaxed, the warning unit can also display the warning in bright colors. Furthermore, if the user is in a hurry, the warning unit can display a concise and highly visible warning. This allows for more appropriate warnings by adjusting the warning display method according to the user's emotional state.

[0117] When collecting audio, the collection unit can customize the collection method by reflecting the user's past feedback. For example, the collection unit can adjust the collection method based on feedback provided by the user in the past. The collection unit can also prioritize a specific collection method based on the user's past feedback. Furthermore, the collection unit can select the type of audio to collect by reflecting the user's feedback. In this way, the collection method can be optimized by reflecting the user's past feedback.

[0118] When analyzing voice data, the analysis unit can adjust the level of detail of the analysis results according to the user's level of expertise. For example, if the user has specialized knowledge, the analysis unit can provide detailed analysis results. Alternatively, if the user does not have specialized knowledge, the analysis unit can provide concise analysis results. Furthermore, the analysis unit can adjust the display method of the analysis results according to the user's level of expertise. This makes it possible to provide appropriate information by adjusting the level of detail of the analysis results according to the user's level of expertise.

[0119] When matching voice data, the matching unit can apply a matching algorithm to deal with different fraud methods. For example, the matching unit applies a matching algorithm that corresponds to different fraud methods, such as phishing fraud and telephone fraud. The matching unit can also analyze the patterns of different fraud methods and apply a matching algorithm. Furthermore, the matching unit can apply a matching algorithm that corresponds to various fraud methods to improve the accuracy of matching. This improves the accuracy of matching by dealing with different fraud methods.

[0120] The processing flow of the second embodiment will be briefly explained below.

[0121] Step 1: The collection unit collects audio. The audio includes, for example, telephone conversations, recorded audio, real-time audio, etc. The collection unit can also collect telephone conversations at a customer service center. Step 2: The analysis unit analyzes the audio collected by the collection unit. The analysis is performed using voice recognition technology and natural language processing technology. For example, the analysis unit converts the audio data into text data using voice recognition technology and analyzes the audio data using natural language processing technology. The analysis unit also sets criteria and conditions for identifying potentially fraudulent conversations based on the frequency of specific keywords and the tone of the conversation. Step 3: The matching unit compares the analyzed voice data with past fraud data. The matching is performed based on a similarity measure and the algorithm used. For example, the matching unit identifies conversations containing typical fraud phrases and expressions and improves the accuracy of the matching by referring to past fraud data. The matching unit also applies matching algorithms that correspond to different fraud methods, such as phishing and telephone fraud. Step 4: The warning unit issues a warning if the matching unit determines there is a possibility of fraud. The warning may be in the form of voice, text, alert, or the like. For example, the warning unit may issue a warning to a person in charge if a conversation that is likely to be fraudulent is detected. The warning unit may also estimate the user's emotions and adjust the way the warning is displayed based on the estimated user's emotions.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0126] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0127] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0142] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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).

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0158] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0159] 7, a 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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).

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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).

[0179] 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.

[0180] 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."

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] [Explanation of symbols]

[0194] 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. a collection unit that collects audio; an analysis unit that analyzes the voice collected by the collection unit; a matching unit that matches the voice data analyzed by the analysis unit with past fraud data; a warning unit that issues a warning when the checking unit determines that there is a possibility of fraud; A system characterized by:

2. The collecting unit Collect telephone conversations or audio recordings 2. The system of claim 1.

3. The analysis unit Converting audio data to text 2. The system of claim 1.

4. The collation unit Identify conversations that contain typical scam phrases or phrases 2. The system of claim 1.

5. The warning unit Alert agents when potentially fraudulent conversations are detected 2. The system of claim 1.

6. The analysis unit Analyze voice data and set criteria or conditions to identify potentially fraudulent conversations 2. The system of claim 1.

7. The warning unit Configure when and how you want to be alerted when potentially fraudulent conversations are detected 2. The system of claim 1.

8. The collecting unit Estimate the user's emotions and adjust the timing of voice collection based on the estimated user emotions.

2. The system of claim 1.

Images