system

Abstract

The system according to the embodiment aims to automatically detect fraudulent phone calls and prevent damage before it occurs. [Solution] A system according to an embodiment includes a voice recognition unit, an analysis unit, and a notification unit. The voice recognition unit converts telephone voice into text data. The analysis unit analyzes the text data converted by the voice recognition unit and determines whether it matches a fraud template. If the analysis unit determines that the call is fraud, the notification unit sends a notification to family members or the police.

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] With conventional technology, there was a problem that telephone fraud methods were becoming more sophisticated, making it difficult to prevent damage before it occurred.

[0005] The system according to the embodiment aims to automatically detect fraudulent phone calls and prevent damage before it occurs. [Means for solving the problem]

[0006] The system according to the embodiment includes a voice recognition unit, an analysis unit, and a notification unit. The voice recognition unit converts telephone voice into text data. The analysis unit analyzes the text data converted by the voice recognition unit and determines whether it matches a fraud template. The notification unit sends a notification to family members or the police if the analysis unit determines that the call is fraud. [Effects of the Invention]

[0007] The system according to the embodiment can automatically detect fraudulent phone calls and prevent damage before it occurs. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A fraud prevention system according to an embodiment of the present invention determines whether a phone call is fraudulent and, if so, notifies family members or the police. This fraud prevention system uses speech recognition technology to convert phone speech into text data. A generation AI analyzes the text data and determines whether it matches a fraud template. If a fraud is determined, the system automatically sends a notification to family members and the police. For example, if an elderly person receives a phone call and the content of the call is "a request for money from someone claiming to be their son," the generation AI matches the call to a fraud template and immediately notifies family members and the police. This allows elderly people to take measures before they fall victim to fraud. By combining speech recognition technology and generation AI, this system can quickly and accurately identify fraudulent methods and prevent damage. Furthermore, the notification function allows family members and the police to respond quickly, ensuring the safety of the elderly. This allows the fraud prevention system to quickly and accurately identify fraudulent methods and prevent damage.

[0029] The fraud prevention system according to the embodiment includes a speech recognition unit, an analysis unit, and a notification unit. The speech recognition unit converts telephone speech into text data. For example, the speech recognition unit uses noise reduction technology to make the speech clearer and improve speech recognition accuracy. The speech recognition unit can also use speech enhancement technology to enhance the speech and convert it into text data. For example, the speech recognition unit can use filtering technology to remove background noise and make the speech clearer. The speech recognition unit can also use echo cancellation technology to remove echo and enhance the speech. The analysis unit uses a generation AI to analyze the text data converted by the speech recognition unit and determine whether it matches a fraud template. The generation AI can, for example, analyze the text data using a deep learning model and determine whether it matches a fraud template. The analysis unit can also use past fraud cases as training data to make highly accurate determinations. For example, the analysis unit stores past fraud cases in a database, and the generation AI learns from them to accurately determine whether it matches a fraud template. The notification unit sends a notification to family members and the police if the analysis unit determines that a fraud has occurred. The notification unit can send notifications by means of, for example, email or SMS. The notification unit can also automatically summarize the content of the notification and convey it concisely. For example, the notification unit can briefly summarize the content of the fraud and notify family members or the police. The notification unit can also automatically update the contact information for the notified family members and the police. For example, the notification unit automatically updates the contact information for family members or the police if there is a change in the contact information for the family members or the police. This allows the fraud prevention system to quickly and accurately determine the fraud method and prevent damage before it occurs. The voice recognition unit, analysis unit, and notification unit work in conjunction with each other to form a system that prevents fraud before it occurs. For example, the analysis unit receives text data converted by the voice recognition unit, and if the analysis unit determines that it is fraud, the notification unit sends a notification. This allows the fraud prevention system to quickly and accurately determine the fraud method and prevent damage before it occurs.

[0030] The speech recognition unit can convert speech into text data using noise reduction or speech enhancement technology. The speech recognition unit can, for example, use filtering technology to remove background noise and make speech clearer. For example, the speech recognition unit can use a bandpass filter to remove low-frequency noise. The speech recognition unit can also use echo cancellation technology to remove echo and enhance speech. For example, the speech recognition unit can use an echo cancellation algorithm to remove echo in real time. The speech recognition unit can also use speech amplification technology to enhance speech and convert it into text data. For example, the speech recognition unit can use a speech amplification algorithm to increase the volume of the speech. This improves the accuracy of speech recognition by using noise reduction or speech enhancement technology. Some or all of the above-mentioned processing in the speech recognition unit can be performed using, for example, AI, or can be performed without AI. For example, the speech recognition unit can have a generation AI perform noise reduction or speech enhancement processing.

[0031] The analysis unit can use the generation AI to analyze the text data and determine whether it matches a fraud template. The analysis unit can, for example, use a deep learning model to analyze the text data and determine whether it matches a fraud template. For example, the analysis unit allows the generation AI to receive text data as input and output whether it matches a fraud template. The analysis unit can also use past fraud cases as training data to make highly accurate determinations. For example, the analysis unit stores past fraud cases in a database, and the generation AI learns from these to determine with high accuracy whether it matches a fraud template. In this way, the use of the generation AI improves the accuracy of determining whether it matches a fraud template. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input text data to the generation AI and have the generation AI determine whether it matches a fraud template.

[0032] The notification unit can send a notification to family members or the police by email or SMS if it determines that a fraud has occurred. For example, the notification unit can send an email if it determines that a fraud has occurred. For example, the notification unit can send an email using the SMTP protocol. The notification unit can also send an SMS if it determines that a fraud has occurred. For example, the notification unit can send an SMS using an SMS gateway. This makes it possible to quickly send a notification to family members or the police if a fraud has been determined, thereby preventing damage from occurring. Some or all of the above-mentioned processing in the notification unit can be performed using AI, or can be performed without using AI. For example, the notification unit can input the notification content into the generation AI and have the generation AI send the notification.

[0033] The analysis unit uses past fraud cases as training data to make highly accurate judgments. For example, the analysis unit stores past fraud cases in a database, and the generation AI learns from them to make highly accurate judgments about whether a fraud case matches a fraud template. For example, the analysis unit stores past fraud cases in a database, and the generation AI learns from them to make highly accurate judgments about whether a fraud case matches a fraud template. The analysis unit can also periodically update past fraud cases to be able to respond to the latest fraud methods. For example, the analysis unit periodically collects the latest fraud cases and updates the database. In this way, by using past fraud cases as training data, the accuracy of fraud judgments is improved. 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 past fraud cases into the generation AI and have the generation AI determine whether a fraud case matches a fraud template.

[0034] The speech recognition unit, analysis unit, and notification unit may work in cooperation with each other to form a system that prevents fraud. The speech recognition unit, analysis unit, and notification unit may work in cooperation with each other, for example, using a data sharing method or a communication protocol. For example, the analysis unit receives text data converted by the speech recognition unit, and if the analysis unit determines that a fraud has occurred, the notification unit sends a notification. The speech recognition unit, analysis unit, and notification unit may also share data in real time and respond quickly. For example, the analysis unit immediately receives text data converted by the speech recognition unit in real time, and if the analysis unit determines that a fraud has occurred, the notification unit immediately sends a notification. This allows each unit to work in cooperation with each other to prevent fraud. Some or all of the above-described processing in the speech recognition unit, analysis unit, and notification unit may be performed using, for example, AI, or may be performed without AI. For example, the speech recognition unit, analysis unit, and notification unit may work in cooperation with each other using a generation AI.

[0035] The speech recognition unit can be added with a function to emphasize specific keywords during speech recognition. The speech recognition unit, for example, emphasizes keywords related to fraud during recognition. For example, the speech recognition unit can emphasize keywords such as "money," "transfer," and "son" during recognition. The speech recognition unit can also emphasize specific keywords set by the user during recognition. For example, the speech recognition unit improves the accuracy of fraud detection by emphasizing keywords set by the user during recognition. The speech recognition unit can also emphasize keywords extracted from past fraud cases during recognition. For example, the speech recognition unit improves the accuracy of fraud detection by emphasizing keywords extracted from past fraud cases during recognition. As a result, emphasizing specific keywords during recognition improves the accuracy of fraud detection. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can cause the generation AI to emphasize specific keywords during recognition.

[0036] The speech recognition unit can add a multilingual recognition function to support multiple languages ​​during speech recognition. The speech recognition unit, for example, performs speech recognition in both Japanese and English and converts the speech into text data. For example, the speech recognition unit can simultaneously recognize Japanese and English speech and convert the speech into text data. The speech recognition unit can also perform speech recognition based on a language set by a user. For example, the speech recognition unit can perform speech recognition based on a language set by a user and convert the speech into text data. Furthermore, the speech recognition unit can perform speech recognition that supports multiple languages ​​in preparation for cases where fraudulent methods are used in multiple languages. For example, the speech recognition unit can perform speech recognition that supports multiple languages ​​in preparation for cases where fraudulent methods are used in multiple languages ​​and convert the speech into text data. By supporting multiple languages, it is possible to respond to cases where fraudulent methods are used in multiple languages. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can have a generation AI recognize multiple languages.

[0037] The speech recognition unit may add a function to analyze background sounds and remove specific environmental sounds during speech recognition. The speech recognition unit may remove, for example, background television sounds to improve speech recognition accuracy. For example, the speech recognition unit may remove background television sounds using filtering technology. The speech recognition unit may also remove background traffic sounds to improve speech recognition accuracy. For example, the speech recognition unit may remove background traffic sounds using noise canceling technology. The speech recognition unit may also remove background people's voices to improve speech recognition accuracy. For example, the speech recognition unit may remove background people's voices using voice separation technology. This removes background sounds, thereby improving speech recognition accuracy. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without AI. For example, the speech recognition unit may have a generation AI analyze background sounds and remove specific environmental sounds.

[0038] The voice recognition unit may be added with a function for learning the characteristics of a user's voice and individually optimizing the voice recognition. The voice recognition unit may, for example, learn the tone and pitch of the user's voice to improve the accuracy of the voice recognition. For example, the voice recognition unit may learn the tone and pitch of the user's voice to improve the accuracy of the voice recognition. The voice recognition unit may also learn the user's speaking habits to improve the accuracy of the voice recognition. For example, the voice recognition unit may learn the user's speaking habits to improve the accuracy of the voice recognition. Furthermore, the voice recognition unit may also learn the speed of the user's voice to improve the accuracy of the voice recognition. For example, the voice recognition unit may learn the speed of the user's voice to improve the accuracy of the voice recognition. As a result, the accuracy of the voice recognition is improved by learning the characteristics of the user's voice. Some or all of the above-described processing in the voice recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice recognition unit may have a generation AI learn the characteristics of the user's voice to optimize the accuracy of the voice recognition.

[0039] The analysis unit can add a function to update the learning data in real time during analysis, taking into account the evolution of fraudulent methods. The analysis unit updates the learning data in real time, for example, when a new fraudulent method is reported. For example, the analysis unit can update the learning data in real time when a new fraudulent method is reported. The analysis unit can also periodically collect the latest fraud cases and update the learning data. For example, the analysis unit can periodically collect the latest fraud cases and update the learning data. Furthermore, the analysis unit can also update the learning data in real time based on reports from users. For example, the analysis unit can update the learning data in real time based on reports from users. In this way, by updating the learning data in real time, it is possible to respond to the latest fraudulent methods. 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 data on new fraudulent methods into the generation AI and update the learning data in real time.

[0040] During analysis, the analysis unit can classify fraudulent methods and apply different analysis algorithms to each category. The analysis unit can apply different analysis algorithms to each category, such as financial fraud, bank transfer fraud, and fictitious billing fraud. For example, the analysis unit can apply a specific algorithm to financial fraud and a different algorithm to bank transfer fraud. The analysis unit can also apply an appropriate analysis algorithm to each category, taking into account the evolution of fraudulent methods. For example, the analysis unit can apply an appropriate analysis algorithm to each category, taking into account the evolution of fraudulent methods. Furthermore, the analysis unit can apply an optimal analysis algorithm to each category based on past fraud cases. For example, the analysis unit can apply an optimal analysis algorithm to each category based on past fraud cases. This improves analysis accuracy by classifying fraudulent methods and applying an appropriate analysis algorithm to each category. 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 have a generation AI classify fraudulent methods and apply a different analysis algorithm to each category.

[0041] During analysis, the analysis unit can improve the accuracy of the analysis by referring to not only past fraud cases but also the latest news and reports. The analysis unit, for example, refers to the latest news articles to improve the accuracy of the analysis. For example, the analysis unit can store the latest news articles in a database and refer to them during analysis. The analysis unit can also refer to the latest fraud reports to improve the accuracy of the analysis. For example, the analysis unit can store the latest fraud reports in a database and refer to them during analysis. Furthermore, the analysis unit can improve the accuracy of the analysis by combining past fraud cases with the latest information. For example, the analysis unit can improve the accuracy of the analysis by combining past fraud cases with the latest news articles and reports. In this way, by referring to the latest information, the accuracy of the analysis is improved. Some or all of the above-described processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can have the generation AI refer to the latest news articles and reports to improve the accuracy of the analysis.

[0042] During analysis, the analysis unit can apply a region-specific analysis algorithm, taking into account that fraud methods differ from region to region. The analysis unit, for example, analyzes the characteristics of fraud methods for each region and applies an appropriate analysis algorithm. For example, the analysis unit can analyze the characteristics of fraud methods for each region and apply an appropriate analysis algorithm. The analysis unit can also apply an optimal analysis algorithm based on fraud cases for each region. For example, the analysis unit can apply an optimal analysis algorithm based on fraud cases for each region. Furthermore, the analysis unit can also apply an appropriate analysis algorithm, taking into account the evolution of fraud methods for each region. For example, the analysis unit can apply an appropriate analysis algorithm, taking into account the evolution of fraud methods for each region. This improves analysis accuracy by responding to fraud methods for each region. 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 data on fraud methods for each region into the generation AI and apply an analysis algorithm for each region.

[0043] The notification unit can add a function to automatically summarize and concisely communicate the notification content at the time of notification. The notification unit, for example, briefly summarizes the details of the fraud and notifies family members or the police. For example, the notification unit can use a generation AI to briefly summarize the details of the fraud and notify family members or the police. The notification unit can also briefly summarize the notification content and communicate it quickly. For example, the notification unit can use a generation AI to briefly summarize the notification content and communicate it quickly. Furthermore, the notification unit can also briefly explain the method of fraud and notify family members or the police. For example, the notification unit can use a generation AI to briefly explain the method of fraud and notify family members or the police. This allows information to be shared quickly by concisely communicating the notification content. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can have a generation AI summarize the notification content and communicate it concisely.

[0044] The notification unit may add a function to automatically update the contact information of the notified family member or police when a notification is sent. The notification unit may automatically update the contact information of the notified family member or police, for example, if the contact information of the notified family member or police changes. For example, the notification unit may manage the contact information of the notified family member or police using a database and automatically update the contact information if there is a change. The notification unit may also automatically update the contact information if a user adds a new contact. For example, the notification unit may automatically update the database if a user adds a new contact. Furthermore, the notification unit may periodically check the contact information and update it to the latest information. For example, the notification unit may periodically check the contact information and update it to the latest information. By automatically updating the contact information, notifications can always be sent with the latest information. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit may cause the generation AI to update the contact information.

[0045] The notification unit can add a function to send notification content via multiple media when sending a notification. The notification unit, for example, sends a notification by both email and SMS. For example, the notification unit can send a notification by both email and SMS. The notification unit can also send a notification by app notification and email. For example, the notification unit can send a notification by app notification and email. The notification unit can also send a notification by SMS and app notification. For example, the notification unit can send a notification by SMS and app notification. This allows information to be transmitted reliably by sending notifications via multiple media. Some or all of the above-described processing in the notification unit may be performed using AI, or may be performed without using AI. For example, the notification unit can cause the generation AI to send the notification content via multiple media.

[0046] The notification unit can add a function to send the notification content as a voice message when notifying. The notification unit, for example, sends the notification content to a family member as a voice message. For example, the notification unit can use a generation AI to send the notification content to a family member as a voice message. The notification unit can also send the notification content to the police as a voice message. For example, the notification unit can use a generation AI to send the notification content to the police as a voice message. The notification unit can also send the notification content to a user as a voice message. For example, the notification unit can use a generation AI to send the notification content to a user as a voice message. By sending a notification as a voice message, information can be conveyed even when visual confirmation is difficult. Some or all of the above-mentioned processing in the notification unit may be performed, for example, using AI or may be performed without using AI. For example, the notification unit can cause the generation AI to send the notification content as a voice message.

[0047] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0048] The analysis unit can add a function to update the learning data in real time during analysis, taking into account the evolution of fraud methods. For example, when a new fraud method is reported, the learning data can be updated in real time. The analysis unit can also periodically collect the latest fraud cases and update the learning data. Furthermore, the analysis unit can also update the learning data in real time based on reports from users. In this way, by updating the learning data in real time, it is possible to respond to the latest fraud methods. 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 data on new fraud methods into the generation AI and update the learning data in real time.

[0049] The speech recognition unit can add a function to emphasize specific keywords during speech recognition. For example, it can emphasize keywords related to fraud during recognition. The speech recognition unit can also emphasize specific keywords set by the user during recognition. Furthermore, the speech recognition unit can also emphasize keywords extracted from past fraud cases during recognition. By emphasizing specific keywords during recognition, the accuracy of fraud detection is improved. Some or all of the above-mentioned processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can cause the generation AI to emphasize specific keywords during recognition.

[0050] During analysis, the analysis unit can classify fraudulent methods and apply different analysis algorithms to each category. For example, different analysis algorithms can be applied to categories such as financial fraud, bank transfer fraud, and fictitious billing fraud. The analysis unit can also apply an appropriate analysis algorithm to each category, taking into account the evolution of fraudulent methods. Furthermore, the analysis unit can apply the optimal analysis algorithm to each category based on past fraud cases. This improves analysis accuracy by classifying fraudulent methods and applying an appropriate analysis algorithm to each category. 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 have a generation AI classify fraudulent methods and apply a different analysis algorithm to each category.

[0051] The notification unit can add a function to automatically summarize and concisely communicate the notification content at the time of notification. For example, the content of the fraud can be concisely summarized and notified to family members or the police. The notification unit can also summarize the notification content in a short form and communicate it quickly. Furthermore, the notification unit can also briefly explain the method of fraud and notify family members or the police. This allows information to be shared quickly by concisely communicating the notification content. Some or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can have a generation AI summarize the notification content and communicate it concisely.

[0052] During analysis, the analysis unit can improve the accuracy of the analysis by referring to not only past fraud cases but also the latest news and reports. For example, the analysis accuracy can be improved by referring to the latest news articles. The analysis unit can also improve the accuracy of the analysis by referring to the latest fraud reports. Furthermore, the analysis unit can improve the accuracy of the analysis by combining past fraud cases with the latest information. In this way, by referring to the latest information, the accuracy of the analysis is improved. 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 have the generation AI refer to the latest news articles and reports to improve the accuracy of the analysis.

[0053] The processing flow of the first embodiment will be briefly explained below.

[0054] Step 1: The speech recognition unit converts the phone call into text data. The speech recognition unit uses noise reduction and voice enhancement technologies to make the voice clearer and improve the accuracy of speech recognition. For example, filtering technology is used to remove background noise, and echo cancellation technology is used to remove echoes. Step 2: The analysis unit analyzes the text data converted by the speech recognition unit and determines whether it matches a fraud template. The analysis unit analyzes the text data using generative AI and deep learning models, and uses past fraud cases as training data to make highly accurate judgments. Step 3: If the analysis unit determines that the information is fraudulent, the notification unit sends a notification to family members or the police. The notification unit sends notifications by email, SMS, or other means, automatically summarizing the content of the notification and conveying it concisely. It can also automatically update the contact information of the notification recipient.

[0055] (Example 2) A fraud prevention system according to an embodiment of the present invention determines whether a phone call is fraudulent and, if so, notifies family members or the police. This fraud prevention system uses speech recognition technology to convert phone speech into text data. A generation AI analyzes the text data and determines whether it matches a fraud template. If a fraud is determined, the system automatically sends a notification to family members and the police. For example, if an elderly person receives a phone call and the content of the call is "a request for money from someone claiming to be their son," the generation AI matches the call to a fraud template and immediately notifies family members and the police. This allows elderly people to take measures before they fall victim to fraud. By combining speech recognition technology and generation AI, this system can quickly and accurately identify fraudulent methods and prevent damage. Furthermore, the notification function allows family members and the police to respond quickly, ensuring the safety of the elderly. This allows the fraud prevention system to quickly and accurately identify fraudulent methods and prevent damage.

[0056] The fraud prevention system according to the embodiment includes a speech recognition unit, an analysis unit, and a notification unit. The speech recognition unit converts telephone speech into text data. For example, the speech recognition unit uses noise reduction technology to make the speech clearer and improve speech recognition accuracy. The speech recognition unit can also use speech enhancement technology to enhance the speech and convert it into text data. For example, the speech recognition unit can use filtering technology to remove background noise and make the speech clearer. The speech recognition unit can also use echo cancellation technology to remove echo and enhance the speech. The analysis unit uses a generation AI to analyze the text data converted by the speech recognition unit and determine whether it matches a fraud template. The generation AI can, for example, analyze the text data using a deep learning model and determine whether it matches a fraud template. The analysis unit can also use past fraud cases as training data to make highly accurate determinations. For example, the analysis unit stores past fraud cases in a database, and the generation AI learns from them to accurately determine whether it matches a fraud template. The notification unit sends a notification to family members and the police if the analysis unit determines that a fraud has occurred. The notification unit can send notifications by means of, for example, email or SMS. The notification unit can also automatically summarize the content of the notification and convey it concisely. For example, the notification unit can briefly summarize the content of the fraud and notify family members or the police. The notification unit can also automatically update the contact information for the notified family members and the police. For example, the notification unit automatically updates the contact information for family members or the police if there is a change in the contact information for the family members or the police. This allows the fraud prevention system to quickly and accurately determine the fraud method and prevent damage before it occurs. The voice recognition unit, analysis unit, and notification unit work in conjunction with each other to form a system that prevents fraud before it occurs. For example, the analysis unit receives text data converted by the voice recognition unit, and if the analysis unit determines that it is fraud, the notification unit sends a notification. This allows the fraud prevention system to quickly and accurately determine the fraud method and prevent damage before it occurs.

[0057] The speech recognition unit can convert speech into text data using noise reduction or speech enhancement technology. The speech recognition unit can, for example, use filtering technology to remove background noise and make speech clearer. For example, the speech recognition unit can use a bandpass filter to remove low-frequency noise. The speech recognition unit can also use echo cancellation technology to remove echo and enhance speech. For example, the speech recognition unit can use an echo cancellation algorithm to remove echo in real time. The speech recognition unit can also use speech amplification technology to enhance speech and convert it into text data. For example, the speech recognition unit can use a speech amplification algorithm to increase the volume of the speech. This improves the accuracy of speech recognition by using noise reduction or speech enhancement technology. Some or all of the above-mentioned processing in the speech recognition unit can be performed using, for example, AI, or can be performed without AI. For example, the speech recognition unit can have a generation AI perform noise reduction or speech enhancement processing.

[0058] The analysis unit can use the generation AI to analyze the text data and determine whether it matches a fraud template. The analysis unit can, for example, use a deep learning model to analyze the text data and determine whether it matches a fraud template. For example, the analysis unit allows the generation AI to receive text data as input and output whether it matches a fraud template. The analysis unit can also use past fraud cases as training data to make highly accurate determinations. For example, the analysis unit stores past fraud cases in a database, and the generation AI learns from these to determine with high accuracy whether it matches a fraud template. In this way, the use of the generation AI improves the accuracy of determining whether it matches a fraud template. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input text data to the generation AI and have the generation AI determine whether it matches a fraud template.

[0059] The notification unit can send a notification to family members or the police by email or SMS if it determines that a fraud has occurred. For example, the notification unit can send an email if it determines that a fraud has occurred. For example, the notification unit can send an email using the SMTP protocol. The notification unit can also send an SMS if it determines that a fraud has occurred. For example, the notification unit can send an SMS using an SMS gateway. This makes it possible to quickly send a notification to family members or the police if a fraud has been determined, thereby preventing damage from occurring. Some or all of the above-mentioned processing in the notification unit can be performed using AI, or can be performed without using AI. For example, the notification unit can input the notification content into the generation AI and have the generation AI send the notification.

[0060] The analysis unit uses past fraud cases as training data to make highly accurate judgments. For example, the analysis unit stores past fraud cases in a database, and the generation AI learns from them to make highly accurate judgments about whether a fraud case matches a fraud template. For example, the analysis unit stores past fraud cases in a database, and the generation AI learns from them to make highly accurate judgments about whether a fraud case matches a fraud template. The analysis unit can also periodically update past fraud cases to be able to respond to the latest fraud methods. For example, the analysis unit periodically collects the latest fraud cases and updates the database. In this way, by using past fraud cases as training data, the accuracy of fraud judgments is improved. 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 past fraud cases into the generation AI and have the generation AI determine whether a fraud case matches a fraud template.

[0061] The speech recognition unit, analysis unit, and notification unit may work in cooperation with each other to form a system that prevents fraud. The speech recognition unit, analysis unit, and notification unit may work in cooperation with each other, for example, using a data sharing method or a communication protocol. For example, the analysis unit receives text data converted by the speech recognition unit, and if the analysis unit determines that a fraud has occurred, the notification unit sends a notification. The speech recognition unit, analysis unit, and notification unit may also share data in real time and respond quickly. For example, the analysis unit immediately receives text data converted by the speech recognition unit in real time, and if the analysis unit determines that a fraud has occurred, the notification unit immediately sends a notification. This allows each unit to work in cooperation with each other to prevent fraud. Some or all of the above-described processing in the speech recognition unit, analysis unit, and notification unit may be performed using, for example, AI, or may be performed without AI. For example, the speech recognition unit, analysis unit, and notification unit may work in cooperation with each other using a generation AI.

[0062] The voice recognition unit can estimate the user's emotion and adjust the accuracy of voice recognition based on the estimated user's emotion. The voice recognition unit can estimate the user's emotion using, for example, voice analysis technology. For example, the voice recognition unit can analyze the tone and pitch of the voice to estimate the user's emotion. The voice recognition unit can also estimate the user's emotion using facial expression recognition technology. For example, the voice recognition unit can analyze the user's facial expression captured by a camera to estimate the emotion. Furthermore, the voice recognition unit adjusts the accuracy of voice recognition based on the estimated user's emotion. For example, if the user is nervous, the voice recognition sensitivity can be increased to convert the voice into text data more accurately. Alternatively, if the user is relaxed, the voice can be converted into text data with normal voice recognition accuracy. Furthermore, if the user is excited, the voice recognition filtering can be strengthened to remove noise and convert the voice into text data. This allows for more accurate voice recognition by adjusting the accuracy of voice recognition according to the user's emotion. Some or all of the above-mentioned processing in the voice recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can have the generation AI estimate the user's emotions and adjust the accuracy of speech recognition based on the results.

[0063] The speech recognition unit can be added with a function to emphasize specific keywords during speech recognition. The speech recognition unit, for example, emphasizes keywords related to fraud during recognition. For example, the speech recognition unit can emphasize keywords such as "money," "transfer," and "son" during recognition. The speech recognition unit can also emphasize specific keywords set by the user during recognition. For example, the speech recognition unit improves the accuracy of fraud detection by emphasizing keywords set by the user during recognition. The speech recognition unit can also emphasize keywords extracted from past fraud cases during recognition. For example, the speech recognition unit improves the accuracy of fraud detection by emphasizing keywords extracted from past fraud cases during recognition. As a result, emphasizing specific keywords during recognition improves the accuracy of fraud detection. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can cause the generation AI to emphasize specific keywords during recognition.

[0064] The speech recognition unit can add a multilingual recognition function to support multiple languages ​​during speech recognition. The speech recognition unit, for example, performs speech recognition in both Japanese and English and converts the speech into text data. For example, the speech recognition unit can simultaneously recognize Japanese and English speech and convert the speech into text data. The speech recognition unit can also perform speech recognition based on a language set by a user. For example, the speech recognition unit can perform speech recognition based on a language set by a user and convert the speech into text data. Furthermore, the speech recognition unit can perform speech recognition that supports multiple languages ​​in preparation for cases where fraudulent methods are used in multiple languages. For example, the speech recognition unit can perform speech recognition that supports multiple languages ​​in preparation for cases where fraudulent methods are used in multiple languages ​​and convert the speech into text data. By supporting multiple languages, it is possible to respond to cases where fraudulent methods are used in multiple languages. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can have a generation AI recognize multiple languages.

[0065] The voice recognition unit can estimate the user's emotion and adjust voice recognition filtering based on the estimated user's emotion. The voice recognition unit can estimate the user's emotion using, for example, voice analysis technology. For example, the voice recognition unit can analyze the tone and pitch of the voice to estimate the user's emotion. The voice recognition unit can also estimate the user's emotion using facial expression recognition technology. For example, the voice recognition unit can analyze the user's facial expression captured by a camera to estimate the emotion. The voice recognition unit can also adjust voice recognition filtering based on the estimated user's emotion. For example, if the user is nervous, noise filtering can be strengthened to improve voice recognition accuracy. If the user is relaxed, voice recognition can be performed with normal filtering settings. Furthermore, if the user is excited, filtering to remove background sounds can be strengthened to improve voice recognition accuracy. This improves voice recognition accuracy by adjusting filtering according to the user's emotion. Some or all of the above-mentioned processing in the voice recognition unit may be performed using, for example, AI, or without AI. For example, the voice recognition unit can have a generation AI estimate the user's emotion and adjust filtering based on the result.

[0066] The speech recognition unit may add a function to analyze background sounds and remove specific environmental sounds during speech recognition. The speech recognition unit may remove, for example, background television sounds to improve speech recognition accuracy. For example, the speech recognition unit may remove background television sounds using filtering technology. The speech recognition unit may also remove background traffic sounds to improve speech recognition accuracy. For example, the speech recognition unit may remove background traffic sounds using noise canceling technology. The speech recognition unit may also remove background people's voices to improve speech recognition accuracy. For example, the speech recognition unit may remove background people's voices using voice separation technology. This removes background sounds, thereby improving speech recognition accuracy. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without AI. For example, the speech recognition unit may have a generation AI analyze background sounds and remove specific environmental sounds.

[0067] The voice recognition unit may be added with a function for learning the characteristics of a user's voice and individually optimizing the voice recognition. The voice recognition unit may, for example, learn the tone and pitch of the user's voice to improve the accuracy of the voice recognition. For example, the voice recognition unit may learn the tone and pitch of the user's voice to improve the accuracy of the voice recognition. The voice recognition unit may also learn the user's speaking habits to improve the accuracy of the voice recognition. For example, the voice recognition unit may learn the user's speaking habits to improve the accuracy of the voice recognition. Furthermore, the voice recognition unit may also learn the speed of the user's voice to improve the accuracy of the voice recognition. For example, the voice recognition unit may learn the speed of the user's voice to improve the accuracy of the voice recognition. As a result, the accuracy of the voice recognition is improved by learning the characteristics of the user's voice. Some or all of the above-described processing in the voice recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice recognition unit may have a generation AI learn the characteristics of the user's voice to optimize the accuracy of the voice recognition.

[0068] The analysis unit can estimate the user's emotions and adjust the analysis priority based on the estimated user's emotions. The analysis unit can estimate the user's emotions using, for example, voice analysis technology. For example, the analysis unit can analyze the tone and pitch of the voice to estimate the user's emotions. The analysis unit can also estimate the user's emotions using facial expression recognition technology. For example, the analysis unit can analyze the user's facial expressions captured by a camera to estimate the user's emotions. The analysis unit can also adjust the analysis priority based on the estimated user's emotions. For example, if the user is nervous, the analysis priority can be increased and results can be provided quickly. If the user is relaxed, the analysis can be performed with normal priority. If the user is excited, the analysis priority can be increased and results can be provided quickly. In this way, adjusting the analysis priority according to the user's emotions allows results to be provided quickly. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can have a generation AI estimate the user's emotions and adjust the analysis priority based on the results.

[0069] The analysis unit can add a function to update the learning data in real time during analysis, taking into account the evolution of fraudulent methods. The analysis unit updates the learning data in real time, for example, when a new fraudulent method is reported. For example, the analysis unit can update the learning data in real time when a new fraudulent method is reported. The analysis unit can also periodically collect the latest fraud cases and update the learning data. For example, the analysis unit can periodically collect the latest fraud cases and update the learning data. Furthermore, the analysis unit can also update the learning data in real time based on reports from users. For example, the analysis unit can update the learning data in real time based on reports from users. In this way, by updating the learning data in real time, it is possible to respond to the latest fraudulent methods. 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 data on new fraudulent methods into the generation AI and update the learning data in real time.

[0070] During analysis, the analysis unit can classify fraudulent methods and apply different analysis algorithms to each category. The analysis unit can apply different analysis algorithms to each category, such as financial fraud, bank transfer fraud, and fictitious billing fraud. For example, the analysis unit can apply a specific algorithm to financial fraud and a different algorithm to bank transfer fraud. The analysis unit can also apply an appropriate analysis algorithm to each category, taking into account the evolution of fraudulent methods. For example, the analysis unit can apply an appropriate analysis algorithm to each category, taking into account the evolution of fraudulent methods. Furthermore, the analysis unit can apply an optimal analysis algorithm to each category based on past fraud cases. For example, the analysis unit can apply an optimal analysis algorithm to each category based on past fraud cases. This improves analysis accuracy by classifying fraudulent methods and applying an appropriate analysis algorithm to each category. 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 have a generation AI classify fraudulent methods and apply a different analysis algorithm to each category.

[0071] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user's emotions. The analysis unit can estimate the user's emotions using, for example, voice analysis technology. For example, the analysis unit can analyze the tone and pitch of the voice to estimate the user's emotions. The analysis unit can also estimate the user's emotions using facial expression recognition technology. For example, the analysis unit can analyze the user's facial expressions captured by a camera to estimate the user's emotions. The analysis unit can also adjust the display method of the analysis results based on the estimated user's emotions. For example, if the user is nervous, a simple, highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. Furthermore, if the user is excited, a visually stimulating display method can be provided. This improves visibility by adjusting the display method of the analysis results according to the user's emotions. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can have a generation AI estimate the user's emotions and adjust the display method of the analysis results based on the result.

[0072] During analysis, the analysis unit can improve the accuracy of the analysis by referring to not only past fraud cases but also the latest news and reports. The analysis unit, for example, refers to the latest news articles to improve the accuracy of the analysis. For example, the analysis unit can store the latest news articles in a database and refer to them during analysis. The analysis unit can also refer to the latest fraud reports to improve the accuracy of the analysis. For example, the analysis unit can store the latest fraud reports in a database and refer to them during analysis. Furthermore, the analysis unit can improve the accuracy of the analysis by combining past fraud cases with the latest information. For example, the analysis unit can improve the accuracy of the analysis by combining past fraud cases with the latest news articles and reports. In this way, by referring to the latest information, the accuracy of the analysis is improved. Some or all of the above-described processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can have the generation AI refer to the latest news articles and reports to improve the accuracy of the analysis.

[0073] During analysis, the analysis unit can apply a region-specific analysis algorithm, taking into account that fraud methods differ from region to region. The analysis unit, for example, analyzes the characteristics of fraud methods for each region and applies an appropriate analysis algorithm. For example, the analysis unit can analyze the characteristics of fraud methods for each region and apply an appropriate analysis algorithm. The analysis unit can also apply an optimal analysis algorithm based on fraud cases for each region. For example, the analysis unit can apply an optimal analysis algorithm based on fraud cases for each region. Furthermore, the analysis unit can also apply an appropriate analysis algorithm, taking into account the evolution of fraud methods for each region. For example, the analysis unit can apply an appropriate analysis algorithm, taking into account the evolution of fraud methods for each region. This improves analysis accuracy by responding to fraud methods for each region. 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 data on fraud methods for each region into the generation AI and apply an analysis algorithm for each region.

[0074] The notification unit can estimate the user's emotion and adjust the urgency of the notification based on the estimated user's emotion. The notification unit can estimate the user's emotion using, for example, voice analysis technology. For example, the notification unit can analyze the tone and pitch of the voice to estimate the user's emotion. The notification unit can also estimate the user's emotion using facial expression recognition technology. For example, the notification unit can analyze the user's facial expression captured by a camera to estimate the emotion. The notification unit can also adjust the urgency of the notification based on the estimated user's emotion. For example, if the user is nervous, the urgency of the notification can be increased and the notification can be quickly sent to family members or the police. If the user is relaxed, the notification can be sent with a normal urgency. If the user is excited, the urgency of the notification can be increased and the notification can be quickly sent to family members or the police. This allows for a prompt response by adjusting the urgency of the notification according to the user's emotion. Some or all of the above-described processing in the notification unit can be performed using, for example, AI, or without AI. For example, the notification unit can have a generation AI estimate the user's emotion and adjust the urgency of the notification based on the result.

[0075] The notification unit can add a function to automatically summarize and concisely communicate the notification content at the time of notification. The notification unit, for example, briefly summarizes the details of the fraud and notifies family members or the police. For example, the notification unit can use a generation AI to briefly summarize the details of the fraud and notify family members or the police. The notification unit can also briefly summarize the notification content and communicate it quickly. For example, the notification unit can use a generation AI to briefly summarize the notification content and communicate it quickly. Furthermore, the notification unit can also briefly explain the method of fraud and notify family members or the police. For example, the notification unit can use a generation AI to briefly explain the method of fraud and notify family members or the police. This allows information to be shared quickly by concisely communicating the notification content. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can have a generation AI summarize the notification content and communicate it concisely.

[0076] The notification unit may add a function to automatically update the contact information of the notified family member or police when a notification is sent. The notification unit may automatically update the contact information of the notified family member or police, for example, if the contact information of the notified family member or police changes. For example, the notification unit may manage the contact information of the notified family member or police using a database and automatically update the contact information if there is a change. The notification unit may also automatically update the contact information if a user adds a new contact. For example, the notification unit may automatically update the database if a user adds a new contact. Furthermore, the notification unit may periodically check the contact information and update it to the latest information. For example, the notification unit may periodically check the contact information and update it to the latest information. By automatically updating the contact information, notifications can always be sent with the latest information. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit may cause the generation AI to update the contact information.

[0077] The notification unit can estimate the user's emotion and select a notification method based on the estimated user's emotion. The notification unit can estimate the user's emotion using, for example, voice analysis technology. For example, the notification unit can analyze the tone and pitch of the voice to estimate the user's emotion. The notification unit can also estimate the user's emotion using facial expression recognition technology. For example, the notification unit can analyze the user's facial expression captured by a camera to estimate the emotion. The notification unit can also select a notification method based on the estimated user's emotion. For example, if the user is nervous, the notification unit can select a method for sending a notification quickly. If the user is relaxed, the notification unit can select a normal notification method. If the user is excited, the notification unit can select a method for sending a notification quickly. This allows for a quick response by selecting the optimal notification method according to the user's emotion. Some or all of the above-mentioned processing in the notification unit can be performed using, for example, AI, or without AI. For example, the notification unit can have a generation AI estimate the user's emotion and select a notification method based on the result.

[0078] The notification unit can add a function to send notification content via multiple media when sending a notification. The notification unit, for example, sends a notification by both email and SMS. For example, the notification unit can send a notification by both email and SMS. The notification unit can also send a notification by app notification and email. For example, the notification unit can send a notification by app notification and email. The notification unit can also send a notification by SMS and app notification. For example, the notification unit can send a notification by SMS and app notification. This allows information to be transmitted reliably by sending notifications via multiple media. Some or all of the above-described processing in the notification unit may be performed using AI, or may be performed without using AI. For example, the notification unit can cause the generation AI to send the notification content via multiple media.

[0079] The notification unit can add a function to send the notification content as a voice message when notifying. The notification unit, for example, sends the notification content to a family member as a voice message. For example, the notification unit can use a generation AI to send the notification content to a family member as a voice message. The notification unit can also send the notification content to the police as a voice message. For example, the notification unit can use a generation AI to send the notification content to the police as a voice message. The notification unit can also send the notification content to a user as a voice message. For example, the notification unit can use a generation AI to send the notification content to a user as a voice message. By sending a notification as a voice message, information can be conveyed even when visual confirmation is difficult. Some or all of the above-mentioned processing in the notification unit may be performed, for example, using AI or may be performed without using AI. For example, the notification unit can cause the generation AI to send the notification content as a voice message. === Hard Collateral 1-1 === Each of the multiple elements, including the voice recognition unit, analysis unit, and notification unit, described above, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the voice recognition unit is implemented by the processor 46 of the smart device 14 and converts telephone voice into text data. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the text data using a generation AI to determine whether it matches a fraud template. The notification unit is implemented, for example, by the control unit 46A of the smart device 14 and sends a notification to family members or the police if a fraud is determined. === Hard Collateral 1-2 === Each of the multiple elements, including the voice recognition unit, analysis unit, and notification unit, described above, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the voice recognition unit is implemented by the processor 46 of the smart glasses 214 and converts telephone voice into text data. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the text data using a generation AI to determine whether it matches a fraud template. The notification unit is implemented, for example, by the control unit 46A of the smart glasses 214 and sends a notification to family members or the police if a fraud is determined. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned voice recognition unit, analysis unit, and notification unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the voice recognition unit is realized by the processor 46 of the headset type terminal 314 and converts telephone voice into text data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the text data using a generation AI to determine whether it matches a fraud template. The notification unit is realized, for example, by the control unit 46A of the headset type terminal 314 and sends a notification to family members or the police if a fraud is determined. === Hard Collateral 1-4 === Each of the multiple elements, including the voice recognition unit, analysis unit, and notification unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the voice recognition unit is realized by the processor 46 of the robot 414 and converts telephone voice into text data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the text data using a generation AI to determine whether it matches a fraud template. The notification unit is realized, for example, by the control unit 46A of the robot 414 and sends a notification to family members or the police if a fraud is determined.

[0080] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0081] The analysis unit can estimate the user's emotions and adjust the analysis priority based on the estimated user emotions. For example, if the user is nervous, the analysis priority can be increased and results can be provided quickly. If the user is relaxed, the analysis can be performed at normal priority. Furthermore, if the user is excited, the analysis priority can be increased and results can be provided quickly. In this way, by adjusting the analysis priority according to the user's emotions, results can be provided quickly. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can have a generation AI estimate the user's emotions and adjust the analysis priority based on the results.

[0082] The notification unit can estimate the user's emotions and adjust the urgency of the notification based on the estimated user's emotions. For example, if the user is nervous, the urgency of the notification can be increased and the notification can be quickly sent to family members or the police. Alternatively, if the user is relaxed, the notification can be sent with a normal urgency. Furthermore, if the user is excited, the urgency of the notification can be increased and the notification can be quickly sent to family members or the police. This allows for a prompt response by adjusting the urgency of the notification according to the user's emotions. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can have a generation AI estimate the user's emotions and adjust the urgency of the notification based on the result.

[0083] The speech recognition unit can estimate the user's emotions and adjust the accuracy of speech recognition based on the estimated user's emotions. For example, if the user is nervous, the sensitivity of speech recognition can be increased to convert speech into text data more accurately. Alternatively, if the user is relaxed, speech can be converted into text data with normal speech recognition accuracy. Furthermore, if the user is excited, speech recognition filtering can be strengthened to remove noise and convert speech into text data. This allows for more accurate speech recognition by adjusting the accuracy of speech recognition according to the user's emotions. Some or all of the above-described processing in the speech recognition unit may be performed using, or without, AI. For example, the speech recognition unit can have a generation AI estimate the user's emotions and adjust the accuracy of speech recognition based on the results.

[0084] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, a simple, highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. Furthermore, if the user is excited, a visually stimulating display method can be provided. This improves visibility by adjusting the display method of the analysis results according to the user's emotions. 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 have a generation AI estimate the user's emotions and adjust the display method of the analysis results based on the result.

[0085] The notification unit can estimate the user's emotions and select a notification method based on the estimated user's emotions. For example, if the user is nervous, a method for sending a notification quickly can be selected. If the user is relaxed, a normal notification method can be selected. Furthermore, if the user is excited, a method for sending a notification quickly can be selected. This allows for a quick response by selecting the optimal notification method according to the user's emotions. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can have a generation AI estimate the user's emotions and select a notification method based on the result.

[0086] The analysis unit can add a function to update the learning data in real time during analysis, taking into account the evolution of fraud methods. For example, when a new fraud method is reported, the learning data can be updated in real time. The analysis unit can also periodically collect the latest fraud cases and update the learning data. Furthermore, the analysis unit can also update the learning data in real time based on reports from users. In this way, by updating the learning data in real time, it is possible to respond to the latest fraud methods. 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 data on new fraud methods into the generation AI and update the learning data in real time.

[0087] The speech recognition unit can add a function to emphasize specific keywords during speech recognition. For example, it can emphasize keywords related to fraud during recognition. The speech recognition unit can also emphasize specific keywords set by the user during recognition. Furthermore, the speech recognition unit can also emphasize keywords extracted from past fraud cases during recognition. By emphasizing specific keywords during recognition, the accuracy of fraud detection is improved. Some or all of the above-mentioned processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can cause the generation AI to emphasize specific keywords during recognition.

[0088] During analysis, the analysis unit can classify fraudulent methods and apply different analysis algorithms to each category. For example, different analysis algorithms can be applied to categories such as financial fraud, bank transfer fraud, and fictitious billing fraud. The analysis unit can also apply an appropriate analysis algorithm to each category, taking into account the evolution of fraudulent methods. Furthermore, the analysis unit can apply the optimal analysis algorithm to each category based on past fraud cases. This improves analysis accuracy by classifying fraudulent methods and applying an appropriate analysis algorithm to each category. 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 have a generation AI classify fraudulent methods and apply a different analysis algorithm to each category.

[0089] The notification unit can add a function to automatically summarize and concisely communicate the notification content at the time of notification. For example, the content of the fraud can be concisely summarized and notified to family members or the police. The notification unit can also summarize the notification content in a short form and communicate it quickly. Furthermore, the notification unit can also briefly explain the method of fraud and notify family members or the police. This allows information to be shared quickly by concisely communicating the notification content. Some or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can have a generation AI summarize the notification content and communicate it concisely.

[0090] During analysis, the analysis unit can improve the accuracy of the analysis by referring to not only past fraud cases but also the latest news and reports. For example, the analysis accuracy can be improved by referring to the latest news articles. The analysis unit can also improve the accuracy of the analysis by referring to the latest fraud reports. Furthermore, the analysis unit can improve the accuracy of the analysis by combining past fraud cases with the latest information. In this way, by referring to the latest information, the accuracy of the analysis is improved. 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 have the generation AI refer to the latest news articles and reports to improve the accuracy of the analysis.

[0091] The processing flow of the second embodiment will be briefly explained below.

[0092] Step 1: The speech recognition unit converts the phone call into text data. The speech recognition unit uses noise reduction and voice enhancement technologies to make the voice clearer and improve the accuracy of speech recognition. For example, filtering technology is used to remove background noise, and echo cancellation technology is used to remove echoes. Step 2: The analysis unit analyzes the text data converted by the speech recognition unit and determines whether it matches a fraud template. The analysis unit analyzes the text data using generative AI and deep learning models, and uses past fraud cases as training data to make highly accurate judgments. Step 3: If the analysis unit determines that the information is fraudulent, the notification unit sends a notification to family members or the police. The notification unit sends notifications by email, SMS, or other means, automatically summarizing the content of the notification and conveying it concisely. It can also automatically update the contact information of the notification recipient.

[0093] 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.

[0094] 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 the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0095] 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.

[0096] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0097] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0098] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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).

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0111] 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.

[0112] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0113] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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).

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0127] 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.

[0128] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0129] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0130] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0144] 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.

[0145] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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).

[0150] 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.

[0151] 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."

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] [Explanation of symbols]

[0165] 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 speech recognition unit that converts telephone voice into text data; an analysis unit that analyzes the text data converted by the speech recognition unit and determines whether it matches a fraud template; a notification unit that sends a notification to a family member or the police if the analysis unit determines that the fraud has occurred. A system characterized by:

2. The voice recognition unit Converting speech to text using noise reduction or speech enhancement technology The system of claim 1 .

3. The analysis unit Generative AI is used to analyze text data and determine whether it matches a fraud template. The system of claim 1 .

4. The notification unit If a fraud is detected, a notification will be sent to your family or the police via email or SMS. The system of claim 1 .

5. The analysis unit Uses past fraud cases as learning data to make highly accurate judgments The system of claim 1 .

6. The speech recognition unit, the analysis unit, and the notification unit They work together to form a system that prevents fraud damage before it happens. The system of claim 1 .

7. The voice recognition unit Estimate the user's emotions and adjust the accuracy of speech recognition based on the estimated user emotions. The system of claim 1 .

8. The voice recognition unit Add a function to emphasize specific keywords when recognizing voice. The system of claim 1 .

Images