System

Abstract

To give an effective warning for reducing the risk of a user being involved in a crime.SOLUTION: A system includes a reception part, an analysis part, a collation part, and a notification part. The reception part receives the input of a user. The analysis part analyzes information received by the reception part. The collation part collates the information analyzed by the analysis part with database of the police. The notification part gives a warning based on the result acquired by the collation part.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional techniques have had the problem that they do not provide sufficient and effective warnings to reduce the risk of users becoming involved in crime.

[0005] The system according to the embodiment aims to provide effective warnings to reduce the risk of users becoming involved in crimes. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a comparison unit, and a notification unit. The reception unit receives a user's input. The analysis unit analyzes the information received by the reception unit. The comparison unit compares the information analyzed by the analysis unit with a police database. The notification unit issues a warning based on the result obtained by the comparison unit. Effect of the Invention

[0007] The system according to the embodiment can effectively warn users to reduce the risk of becoming involved in a crime. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[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 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The special fraud prevention system according to the embodiment of the present invention is a system that prevents special frauds using an ATM with a built-in generation AI. In this system, when a user attempts to transfer a large amount of money, the generation AI asks the user in natural language about the purpose of the transfer and the recipient. The generation AI is linked to police special fraud information and telephone numbers used in crimes, and checks the user's answer in real time. If the user's answer is determined to be a possible special fraud, the generation AI stops the transfer and warns the user. For example, when a user attempts to transfer a large amount of money at an ATM, the generation AI asks questions in natural language such as "What is the purpose of this transfer?" and "Please tell me the recipient's telephone number." When the user answers, the generation AI checks the information against the police database. For example, if the user answers "to lend money to a friend" and enters the recipient's telephone number, the generation AI checks whether the telephone number has been used for special fraud in the past. Next, the generation AI analyzes the user's answer, and if it determines that there is a possibility of a special fraud, it stops the transfer. For example, if the recipient's phone number is registered in the police database, the generation AI will notify the user that "This transfer may be a special fraud. The transfer will be canceled." The generation AI will also warn the user by saying, "Please contact the police." This mechanism can prevent the victim from becoming a victim of special fraud. By receiving an interview and warning from the generation AI, the user can recognize the risk of fraud and cancel the transfer. In addition, by linking with the police database, the latest fraud information can be reflected in real time. For example, if information on a recent fraud case is added to the database, the generation AI can immediately use that information to warn the user. This allows the special fraud prevention system to safely transfer money for users.

[0029] The special fraud prevention system according to the embodiment includes a reception unit, an analysis unit, a collation unit, and a notification unit. The reception unit receives a user's input. The user's input includes, but is not limited to, text input, voice input, image input, and the like. For example, when a user is about to transfer a large amount of money at an ATM, the reception unit has the generation AI ask questions in natural language such as "What is the purpose of this transfer?" or "Please tell me the recipient's phone number." The analysis unit uses the generation AI to analyze the information received by the reception unit. The analysis is performed, for example, by a method such as text analysis, voice analysis, or image analysis, but is not limited to such examples. For example, the generation AI analyzes the user's answer and evaluates the possibility of fraud based on the content. The collation unit compares the information analyzed by the analysis unit with a police database. The collation is performed, for example, based on the type of database and a collation algorithm, but is not limited to such examples. For example, the collation unit compares the phone number entered by the user with a police database and checks whether the phone number has been used for special fraud in the past. The notification unit issues a warning based on the result obtained by the collation unit. The notification is, for example, based on the form and content of the notification, but is not limited to such an example. For example, the notification unit notifies the user that "This transfer may be a special fraud. The transfer will be stopped." The notification unit also issues a warning to the user, such as "Please contact the police." This allows the special fraud prevention system according to the embodiment to safely transfer the user's money. Some or all of the above-mentioned processes in the reception unit, analysis unit, collation unit, and notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit inputs the user's input to the generation AI, the analysis unit compares the information analyzed by the generation AI with the police database, and the notification unit can issue a warning based on the result obtained by the generation AI.

[0030] The reception unit receives user input. Examples of user input include, but are not limited to, text input, voice input, and image input. Specifically, when a user is about to transfer a large amount of money at an ATM, the generation AI asks questions in natural language such as "What is the purpose of this transfer?" and "Please tell me the recipient's phone number." This requires the user to enter their intention and the recipient's information in detail. The reception unit processes these inputs in real time and sends them to the generation AI. The generation AI receives the user's input and understands its contents using natural language processing technology. For example, in the case of text input, the generation AI analyzes the input sentence and grasps the context and intention. In the case of voice input, the voice is converted into text using voice recognition technology, and then text analysis is performed. In the case of image input, image recognition technology is used to extract information in the image and obtain the necessary data. This allows the reception unit to handle a variety of input formats and accurately grasp the user's intention. Furthermore, the reception unit temporarily stores the user's input contents so that the analysis unit and collation unit can access them. This allows the entire system to work smoothly together and respond quickly.

[0031] The analysis unit uses the generation AI to analyze the information received by the reception unit. The analysis is performed by, for example, text analysis, voice analysis, image analysis, etc., but is not limited to such examples. Specifically, the generation AI analyzes the user's answer and evaluates the possibility of fraud based on the content. For example, the generation AI analyzes the text entered by the user and checks whether it contains specific keywords or phrases. This allows early detection of signs of fraud. In the case of voice input, the generation AI analyzes the voice data and infers the user's emotions and intentions from the tone of voice and speaking style. In the case of image input, the generation AI recognizes the text and people in the image and performs analysis based on that information. The analysis unit comprehensively evaluates these analysis results and scores the possibility of fraud. For example, if a certain keyword is included a lot or the tone of the voice is unnatural, it is determined that there is a high possibility of fraud. The analysis unit provides information to the matching unit, which is the next step, based on this score. Furthermore, the analysis unit can perform more accurate analysis by utilizing past data and statistical information. For example, the generation AI that has learned from past fraud cases evolves so that it can respond to new fraud methods. This enables the analysis unit to always provide highly accurate analysis based on the latest information, minimizing the risk of fraud.

[0032] The collation unit compares the information analyzed by the analysis unit with the police database. The collation is performed, for example, based on the type of database and the collation algorithm, but is not limited to such examples. Specifically, the collation unit compares the phone number entered by the user with the police database to check whether the phone number has been used for special fraud in the past. The collation unit accesses the police database and obtains information in real time. For example, a phone number and a transfer account information are entered, and it is checked whether they are related to past fraud cases. The collation algorithm searches data quickly and accurately, and immediately issues a warning if there is matching information. Furthermore, the collation unit evaluates the reliability of the collation result based on the scoring information provided by the analysis unit. For example, if the analysis unit determines that there is a high possibility of fraud, the collation unit can perform a more rigorous check and compare not only the police database but also other related databases. This allows the collation unit to evaluate the risk of fraud from multiple angles and provide more accurate results. Furthermore, the collation unit feeds back the collation result to the analysis unit and the notification unit, strengthening the cooperation of the entire system. This allows the collation unit to quickly and accurately evaluate the risk of fraud and take appropriate measures against the user.

[0033] The notification unit issues a warning based on the result obtained by the collation unit. The notification is, for example, based on the form and content of the notification, but is not limited to such examples. Specifically, the notification unit notifies the user that "This transfer may be a special fraud. The transfer will be stopped." The notification unit also issues a warning to the user, such as "Contact the police." The notification unit sends a notification to the user's device in real time to prompt an immediate response. For example, a warning message is displayed on the ATM screen to instruct the user to stop the transfer. In addition, a notification is sent to the user's smartphone to provide detailed information. The notification unit can flexibly change the form and content of the notification and select the optimal notification method according to the user's situation. For example, it is possible to respond according to the characteristics of the user, such as prioritizing voice notification for the elderly and text notification for the younger generation. Furthermore, the notification unit saves the history of the notification content so that it can be checked later. This allows the user to refer to the past notification content and take the necessary action. The notification unit can collect feedback from users and continuously improve the accuracy and effectiveness of the notification content. For example, the system records how users respond to notifications and optimizes the notification algorithm based on that data, allowing the notification unit to quickly and appropriately alert users and minimize the risk of fraud.

[0034] The special fraud prevention system includes a privacy protection unit that protects the privacy of the user. The privacy protection unit protects the privacy of the user. Privacy protection includes, for example, methods such as anonymization of data and access control, but is not limited to such examples. For example, the privacy protection unit anonymizes the data input by the user to prevent a third party from identifying a specific user. In addition, the privacy protection unit limits the authority to access the user's data and allows access only when necessary. This protects the privacy of the user, allowing the special fraud prevention system to be used with peace of mind. Some or all of the above-mentioned processing in the privacy protection unit may be performed, for example, using AI, or may be performed without using AI. For example, the privacy protection unit can input the user's data to the generation AI and have the generation AI perform the anonymization of the data and the access control.

[0035] The special fraud prevention system includes a security unit that takes security measures when linking with the police database. The security unit takes security measures when linking with the police database. The security measures include, but are not limited to, methods such as encryption and authentication processes. For example, the security unit encrypts the user's data to prevent a third party from eavesdropping on the data when the data is transmitted and received. In addition, when accessing the police database, the security unit confirms a legitimate access right through an authentication process. This makes it possible to ensure security when linking with the police database. Some or all of the above-mentioned processing in the security unit may be performed using, for example, AI, or may be performed without using AI. For example, the security unit can cause the generation AI to execute data encryption and authentication processes.

[0036] The special fraud prevention system includes a message generating unit that generates a specific warning message. The message generating unit generates the specific warning message. The warning message includes, but is not limited to, a message template, a generation algorithm, and other methods. For example, the message generating unit generates a specific message such as "This transfer may be a special fraud. The transfer will be stopped" for the user. The message generating unit also generates a warning message such as "Please contact the police" for the user. This makes it possible to provide the user with a specific warning message. A part or all of the above-mentioned processing in the message generating unit may be performed, for example, using AI, or may be performed without using AI. For example, the message generating unit can cause the generation AI to execute the generation of the warning message.

[0037] The reception unit can analyze the user's past input history and select the optimal input reception method. For example, the reception unit automatically displays as candidates the transfer destinations that the user frequently input in the past. The reception unit can also preferentially suggest input methods (such as voice and text) that the user has used in the past. Furthermore, the reception unit can predict and suggest transfer destinations to be used in a specific time period from the user's past input history. This makes it possible to provide the optimal input reception method based on the past input history. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past input history into a generation AI and select the optimal input reception method.

[0038] The reception unit can perform filtering based on the user's current situation and areas of interest when receiving input. For example, when the user is about to transfer a large amount of money, the reception unit preferentially displays a specific question. In addition, when the user is using an ATM during a specific time period, the reception unit can also perform a warning related to that time period. Furthermore, when the user is in a specific area, the reception unit can perform filtering based on fraud information occurring in that area. In this way, more appropriate questions can be provided by performing filtering according to the user's situation and areas of interest. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's current situation and areas of interest into the generation AI and perform filtering.

[0039] The reception unit can preferentially receive highly relevant inputs in consideration of the geographical location information of the user when receiving the input. For example, when the user is in a specific area, the reception unit displays a question based on fraud information occurring in the area. In addition, when the user uses a specific ATM, the reception unit can also display a question based on fraud information that has occurred in the ATM in the past. Furthermore, when the user uses an ATM during a specific time period, the reception unit can also display a question based on fraud information related to that time period. In this way, highly relevant questions can be provided by considering the geographical location information of the user. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the geographical location information of the user to the generation AI and preferentially receive highly relevant inputs.

[0040] The reception unit can analyze the user's social media activity and receive related inputs when receiving inputs. For example, when the user shares specific fraud information on social media, the reception unit displays a question based on the information. In addition, when the user posts information about a specific region on social media, the reception unit can also display a question based on fraud information occurring in the region. Furthermore, when the user posts information about a specific time period on social media, the reception unit can also display a question based on fraud information related to the time period. This makes it possible to provide related questions based on the user's social media activity. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's social media activity to the generation AI and receive related inputs.

[0041] The analysis unit can adjust the level of detail of the analysis based on the importance of the input information during the analysis. For example, in the case of a large amount of transfer, the analysis unit performs a detailed analysis and carefully evaluates the possibility of fraud. In addition, in the case of a low amount of transfer, the analysis unit can perform a simplified analysis and provide the result quickly. Furthermore, in the case of a transfer to a specific transfer destination, the analysis unit can perform a detailed analysis based on the past history of the transfer destination. In this way, by adjusting the level of detail of the analysis according to the importance of the input information, it is possible to provide a prompt and appropriate analysis result. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the importance of the input information to the generation AI and adjust the level of detail of the analysis.

[0042] The analysis unit can apply different analysis algorithms depending on the category of input information during analysis. For example, when the transfer destination is an individual, the analysis unit performs analysis based on fraud information for individuals. Furthermore, when the transfer destination is a company, the analysis unit can also perform analysis based on fraud information for companies. Furthermore, when the transfer destination is a public institution, the analysis unit can also perform analysis based on fraud information for public institutions. This makes it possible to provide more accurate analysis results by applying an analysis algorithm according to the category of input information. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the category of input information to the generation AI and apply different analysis algorithms.

[0043] The analysis unit can determine the priority of the analysis based on the submission time of the input information at the time of analysis. For example, the analysis unit prioritizes the analysis of recent transfer information to reflect the latest fraud information. The analysis unit can also analyze fraud patterns by referring to past transfer information. Furthermore, the analysis unit can also prioritize the analysis of transfer information made in a specific time period to reflect fraud information related to that time period. In this way, by determining the priority of the analysis based on the submission time of the input information, it is possible to provide an analysis result that reflects the latest fraud information. Part or all of the above-mentioned 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 input the submission time of the input information to the generation AI to determine the priority of the analysis.

[0044] The analysis unit can adjust the order of analysis based on the relevance of the input information during analysis. For example, the analysis unit prioritizes analysis of high-value transfer information and carefully evaluates the possibility of fraud. The analysis unit can also prioritize analysis of transfer information for a specific transfer destination and evaluate it based on the past history of the transfer destination. Furthermore, the analysis unit can prioritize analysis of transfer information made in a specific time period and reflect fraud information related to that time period. This makes it possible to provide a prompt and appropriate analysis result by adjusting the order of analysis based on the relevance of the input information. Part or all of the above-mentioned 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 input the relevance of the input information to the generation AI and adjust the order of analysis.

[0045] The matching unit can improve the accuracy of matching by considering the interrelationships of the input information during matching. The matching unit, for example, matches the telephone number of the transfer destination with the purpose of the transfer to evaluate the possibility of fraud. The matching unit can also match the telephone number of the transfer destination with past fraud information to evaluate the possibility of fraud. Furthermore, the matching unit can also match the telephone number of the transfer destination with the user's past transfer history to evaluate the possibility of fraud. This makes it possible to improve the accuracy of matching by considering the interrelationships of the input information. Part or all of the above-mentioned processing in the matching unit may be performed, for example, using AI, or may be performed without using AI. For example, the matching unit can input the interrelationships of the input information to the generation AI to improve the accuracy of matching.

[0046] The matching unit can perform matching by taking into consideration attribute information of the person who submitted the input information. The matching unit can evaluate the possibility of fraud by taking into consideration, for example, the age and gender of the user. The matching unit can also evaluate the possibility of fraud by taking into consideration the user's past transfer history. Furthermore, the matching unit can evaluate the possibility of fraud by taking into consideration the user's current situation (urgency, etc.). This makes it possible to improve the accuracy of matching by taking into consideration the attribute information of the person who submitted the input information. Some or all of the above-mentioned processing in the matching unit may be performed, for example, using AI, or may be performed without using AI. For example, the matching unit can input the attribute information of the person who submitted the input information to the generation AI and perform matching.

[0047] The matching unit can perform matching by taking into consideration the geographical distribution of the input information. For example, when a user is in a specific area, the matching unit performs matching based on fraud information occurring in that area. In addition, when a user uses a specific ATM, the matching unit can also perform matching based on fraud information that has occurred in the past at that ATM. Furthermore, when a user uses an ATM during a specific time period, the matching unit can also perform matching based on fraud information related to that time period. This makes it possible to improve the accuracy of matching by taking into consideration the geographical distribution of the input information. A part or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input the geographical distribution into a generation AI and perform matching.

[0048] The matching unit can improve the accuracy of matching by referring to literature related to the input information during matching. The matching unit can, for example, refer to literature on fraud cases related to the transfer destination telephone number and evaluate the possibility of fraud. The matching unit can also refer to literature on fraud patterns related to the transfer destination telephone number and evaluate the possibility of fraud. Furthermore, the matching unit can also refer to literature on fraud methods related to the transfer destination telephone number and evaluate the possibility of fraud. This makes it possible to improve the accuracy of matching by referring to related literature. Part or all of the above-mentioned processing in the matching unit may be performed, for example, using AI, or may be performed without using AI. For example, the matching unit can input related literature into the generation AI to improve the accuracy of matching.

[0049] The notification unit can optimize the current notification by referring to past notification data at the time of notification. The notification unit selects the optimal notification method based on notifications received by the user in the past, for example. The notification unit can also analyze the reaction of notifications received by the user in the past and determine the optimal notification content. Furthermore, the notification unit can select the optimal notification timing by referring to the timing of notifications received by the user in the past. In this way, the optimal notification method can be provided by referring to the past notification data. A part 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 input past notification data into a generation AI to optimize the current notification.

[0050] The notification unit can apply different notification methods for each category of input information at the time of notification. For example, in the case of a large amount of transfer, the notification unit displays a notification including a detailed warning. In addition, in the case of a low amount of transfer, the notification unit can also display a simplified notification. Furthermore, in the case of a transfer to a specific transfer destination, the notification unit can also display a notification including a warning related to the transfer destination. This makes it possible to provide a more appropriate warning by providing a notification method according to the category of input information. Part 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 input the category of input information to the generation AI and apply different notification methods.

[0051] The notification unit can determine the priority of the notification based on the submission time of the input information at the time of notification. The notification unit, for example, prioritizes the notification of recent transfer information to reflect the latest fraud information. The notification unit can also notify fraud patterns by referring to past transfer information. Furthermore, the notification unit can also prioritize the notification of transfer information made in a specific time period to reflect fraud information related to that time period. In this way, by determining the priority of the notification based on the submission time of the input information, it is possible to provide a notification that reflects the latest fraud information. Part 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 input the submission time of the input information to the generation AI to determine the priority of the notification.

[0052] At the time of notification, the notification unit can provide notification by referring to market data related to the input information. The notification unit, for example, refers to market data related to the transfer destination telephone number and provides notification of the possibility of fraud. The notification unit can also provide notification of the possibility of fraud by referring to market trends related to the transfer destination telephone number. Furthermore, the notification unit can also provide notification of the possibility of fraud by referring to market analysis related to the transfer destination telephone number. In this way, it is possible to provide notification of the possibility of fraud by referring to the related market data. Part 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 input the related market data into the generation AI and provide notification.

[0053] The privacy protection unit can select the optimal protection method by referring to past privacy protection data during privacy protection. The privacy protection unit, for example, proposes the optimal protection method based on the privacy protection settings selected by the user in the past. The privacy protection unit can also select the optimal protection method based on cases of privacy infringement suffered by the user in the past. Furthermore, the privacy protection unit can analyze the user's past privacy protection history and propose the optimal protection method. In this way, the optimal protection method can be provided by referring to the past privacy protection data. A part or all of the above-mentioned processing in the privacy protection unit may be performed, for example, using AI or may be performed without using AI. For example, the privacy protection unit can input past privacy protection data into a generation AI to select the optimal protection method.

[0054] The privacy protection unit can select the optimal protection method in consideration of the geographical location information of the user during privacy protection. For example, when the user is in a specific area, the privacy protection unit selects the optimal protection method based on the privacy protection regulations of the area. In addition, when the user uses a specific ATM, the privacy protection unit can also select the optimal protection method based on the privacy protection settings of the ATM. Furthermore, when the user uses the ATM during a specific time period, the privacy protection unit can also select a privacy protection method related to that time period. In this way, it is possible to provide an optimal privacy protection method by considering the geographical location information of the user. Part or all of the above-mentioned processing in the privacy protection unit may be performed, for example, using AI, or may be performed without using AI. For example, the privacy protection unit can input geographical location information to the generation AI and select the optimal protection method.

[0055] The security unit can select the optimal countermeasure by referring to past security data when taking security measures. For example, the security unit proposes the optimal countermeasure based on security measures selected by the user in the past. The security unit can also select the optimal countermeasure based on cases of security infringement suffered by the user in the past. Furthermore, the security unit can analyze the history of the user's past security measures and propose the optimal countermeasure. In this way, the optimal security countermeasure can be provided by referring to the past security data. A part or all of the above-mentioned processing in the security unit may be performed, for example, using AI, or may be performed without using AI. For example, the security unit can input past security data into a generating AI and select the optimal countermeasure.

[0056] The security unit can select the optimal security measure in consideration of the geographical location information of the user. For example, when the user is in a specific area, the security unit selects the optimal measure based on the security regulations of the area. In addition, when the user uses a specific ATM, the security unit can also select the optimal measure based on the security settings of the ATM. Furthermore, when the user uses the ATM during a specific time period, the security unit can also select security measures related to that time period. In this way, the optimal security measure can be provided by considering the geographical location information of the user. Part or all of the above-mentioned processing in the security unit may be performed, for example, using AI, or may be performed without using AI. For example, the security unit can input geographical location information to a generation AI and select the optimal measure.

[0057] The message generating unit can generate an optimal message by referring to past message data when generating a message. The message generating unit generates an optimal message based on, for example, messages received by the user in the past. The message generating unit can also analyze the reaction to the message received by the user in the past and determine the optimal message content. Furthermore, the message generating unit can select the optimal message timing by referring to the timing of the message received by the user in the past. In this way, the optimal message can be provided by referring to the past message data. A part or all of the above-mentioned processing in the message generating unit may be performed, for example, using AI or may be performed without using AI. For example, the message generating unit can input past message data into a generation AI to generate an optimal message.

[0058] The message generating unit can generate an optimal message in consideration of the geographical location information of the user when generating a message. For example, when the user is in a specific area, the message generating unit generates an optimal message based on fraud information for that area. In addition, when the user uses a specific ATM, the message generating unit can also generate an optimal message based on fraud information for that ATM. Furthermore, when the user uses an ATM during a specific time period, the message generating unit can also generate an optimal message based on fraud information related to that time period. This makes it possible to provide an optimal message by considering the geographical location information of the user. A part or all of the above-mentioned processing in the message generating unit may be performed, for example, using AI, or may be performed without using AI. For example, the message generating unit can input geographical location information into the generating AI to generate an optimal message.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The analysis unit can analyze the user's past transfer history and evaluate the possibility of fraud. For example, if the user has made multiple transfers to the same transfer destination in the past, it evaluates whether the transfer destination is likely to be fraudulent. The analysis unit can also detect similar patterns based on the user's history of being a victim of fraud in the past. Furthermore, the analysis unit can analyze the user's past transfer amounts and frequencies and detect abnormal patterns. This makes it possible to provide more accurate analysis results by evaluating the possibility of fraud based on the user's past transfer history. Some or all of the above-mentioned 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 input the user's past transfer history into the generation AI and evaluate the possibility of fraud.

[0061] The privacy protection unit can store the user's data in a distributed network to enhance security. For example, the user's data is distributed and stored in multiple servers so as not to be concentrated in one place. The privacy protection unit can also store the user's data using blockchain technology to prevent tampering. Furthermore, the privacy protection unit can encrypt and store the user's data so that it cannot be accessed by a third party. This makes it possible to enhance security and protect privacy by storing the user's data in a distributed network. Some or all of the above-mentioned processing in the privacy protection unit may be performed, for example, using AI or may be performed without using AI. For example, the privacy protection unit can input the user's data into a generation AI and store it in a distributed network.

[0062] The security unit can learn the user's behavioral patterns and detect abnormal behavior. For example, if the user uses an ATM during a time period when the user does not normally use the ATM, the security unit can determine the behavior as abnormal and issue a warning. In addition, if the user uses an ATM in an area where the user does not normally use the ATM, the security unit can also determine the behavior as abnormal and issue a warning. Furthermore, if the user attempts to transfer an amount that is not normally used, the security unit can also determine the behavior as abnormal and issue a warning. In this way, security can be strengthened by learning the user's behavioral patterns and detecting abnormal behavior. Part or all of the above-mentioned processing in the security unit may be performed, for example, using AI, or may be performed without using AI. For example, the security unit can input the user's behavioral patterns into the generation AI and detect abnormal behavior.

[0063] The message generation unit can analyze the user's past message history and generate an optimal message. For example, the optimal message content is determined based on the user's reaction to the message received in the past. The message generation unit can also select the optimal message timing by referring to the timing of the message received in the past by the user. Furthermore, the message generation unit can also select the optimal message format based on the format of the message received in the past by the user. This makes it possible to provide an optimal message based on the past message history. A part or all of the above-mentioned processing in the message generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the message generation unit can input the past message history into a generation AI and generate an optimal message.

[0064] The process flow of the first embodiment will be briefly described below.

[0065] Step 1: The reception unit accepts user input. User input includes, for example, text input, voice input, image input, and the like. For example, when a user tries to transfer a large amount at an ATM, the generation AI asks questions in natural language such as "What is the purpose of this transfer?" or "Please tell me the recipient's phone number." Step 2: The analysis unit uses the generation AI to analyze the information received by the reception unit. The analysis is performed by methods such as text analysis, voice analysis, and image analysis. For example, the generation AI analyzes the user's response and evaluates the possibility of fraud based on the content. Step 3: The matching unit matches the information analyzed by the analysis unit with the police database. Matching is performed, for example, based on the type of database and matching algorithm. For example, the matching unit matches the phone number entered by the user with the police database to check whether the phone number has been used for special fraud in the past. Step 4: The notification unit issues a warning based on the results obtained by the collation unit. The notification is issued based on, for example, the form and content of the notification. For example, the notification unit may notify the user, "This transfer may be a specialized fraud. The transfer will be canceled." It may also warn the user, "Please contact the police."

[0066] (Example 2) The special fraud prevention system according to the embodiment of the present invention is a system that prevents special frauds using an ATM with a built-in generation AI. In this system, when a user attempts to transfer a large amount of money, the generation AI asks the user in natural language about the purpose of the transfer and the recipient. The generation AI is linked to police special fraud information and telephone numbers used in crimes, and checks the user's answer in real time. If the user's answer is determined to be a possible special fraud, the generation AI stops the transfer and warns the user. For example, when a user attempts to transfer a large amount of money at an ATM, the generation AI asks questions in natural language such as "What is the purpose of this transfer?" and "Please tell me the recipient's telephone number." When the user answers, the generation AI checks the information against the police database. For example, if the user answers "to lend money to a friend" and enters the recipient's telephone number, the generation AI checks whether the telephone number has been used for special fraud in the past. Next, the generation AI analyzes the user's answer, and if it determines that there is a possibility of a special fraud, it stops the transfer. For example, if the recipient's phone number is registered in the police database, the generation AI will notify the user that "This transfer may be a special fraud. The transfer will be canceled." The generation AI will also warn the user by saying, "Please contact the police." This mechanism can prevent the victim from becoming a victim of special fraud. By receiving an interview and warning from the generation AI, the user can recognize the risk of fraud and cancel the transfer. In addition, by linking with the police database, the latest fraud information can be reflected in real time. For example, if information on a recent fraud case is added to the database, the generation AI can immediately use that information to warn the user. This allows the special fraud prevention system to safely transfer money for users.

[0067] The special fraud prevention system according to the embodiment includes a reception unit, an analysis unit, a collation unit, and a notification unit. The reception unit receives a user's input. The user's input includes, but is not limited to, text input, voice input, image input, and the like. For example, when a user is about to transfer a large amount of money at an ATM, the reception unit has the generation AI ask questions in natural language such as "What is the purpose of this transfer?" or "Please tell me the recipient's phone number." The analysis unit uses the generation AI to analyze the information received by the reception unit. The analysis is performed, for example, by a method such as text analysis, voice analysis, or image analysis, but is not limited to such examples. For example, the generation AI analyzes the user's answer and evaluates the possibility of fraud based on the content. The collation unit compares the information analyzed by the analysis unit with a police database. The collation is performed, for example, based on the type of database and a collation algorithm, but is not limited to such examples. For example, the collation unit compares the phone number entered by the user with a police database and checks whether the phone number has been used for special fraud in the past. The notification unit issues a warning based on the result obtained by the collation unit. The notification is, for example, based on the form and content of the notification, but is not limited to such an example. For example, the notification unit notifies the user that "This transfer may be a special fraud. The transfer will be stopped." The notification unit also issues a warning to the user, such as "Please contact the police." This allows the special fraud prevention system according to the embodiment to safely transfer the user's money. Some or all of the above-mentioned processes in the reception unit, analysis unit, collation unit, and notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit inputs the user's input to the generation AI, the analysis unit compares the information analyzed by the generation AI with the police database, and the notification unit can issue a warning based on the result obtained by the generation AI.

[0068] The reception unit receives user input. Examples of user input include, but are not limited to, text input, voice input, and image input. Specifically, when a user is about to transfer a large amount of money at an ATM, the generation AI asks questions in natural language such as "What is the purpose of this transfer?" and "Please tell me the recipient's phone number." This requires the user to enter their intention and the recipient's information in detail. The reception unit processes these inputs in real time and sends them to the generation AI. The generation AI receives the user's input and understands its contents using natural language processing technology. For example, in the case of text input, the generation AI analyzes the input sentence and grasps the context and intention. In the case of voice input, the voice is converted into text using voice recognition technology, and then text analysis is performed. In the case of image input, image recognition technology is used to extract information in the image and obtain the necessary data. This allows the reception unit to handle a variety of input formats and accurately grasp the user's intention. Furthermore, the reception unit temporarily stores the user's input contents so that the analysis unit and collation unit can access them. This allows the entire system to work smoothly together and respond quickly.

[0069] The analysis unit uses the generation AI to analyze the information received by the reception unit. The analysis is performed by, for example, text analysis, voice analysis, image analysis, etc., but is not limited to such examples. Specifically, the generation AI analyzes the user's answer and evaluates the possibility of fraud based on the content. For example, the generation AI analyzes the text entered by the user and checks whether it contains specific keywords or phrases. This allows early detection of signs of fraud. In the case of voice input, the generation AI analyzes the voice data and infers the user's emotions and intentions from the tone of voice and speaking style. In the case of image input, the generation AI recognizes the text and people in the image and performs analysis based on that information. The analysis unit comprehensively evaluates these analysis results and scores the possibility of fraud. For example, if a certain keyword is included a lot or the tone of the voice is unnatural, it is determined that there is a high possibility of fraud. The analysis unit provides information to the matching unit, which is the next step, based on this score. Furthermore, the analysis unit can perform more accurate analysis by utilizing past data and statistical information. For example, the generation AI that has learned from past fraud cases evolves so that it can respond to new fraud methods. This enables the analysis unit to always provide highly accurate analysis based on the latest information, minimizing the risk of fraud.

[0070] The collation unit compares the information analyzed by the analysis unit with the police database. The collation is performed, for example, based on the type of database and the collation algorithm, but is not limited to such examples. Specifically, the collation unit compares the phone number entered by the user with the police database to check whether the phone number has been used for special fraud in the past. The collation unit accesses the police database and obtains information in real time. For example, a phone number and a transfer account information are entered, and it is checked whether they are related to past fraud cases. The collation algorithm searches data quickly and accurately, and immediately issues a warning if there is matching information. Furthermore, the collation unit evaluates the reliability of the collation result based on the scoring information provided by the analysis unit. For example, if the analysis unit determines that there is a high possibility of fraud, the collation unit can perform a more rigorous check and compare not only the police database but also other related databases. This allows the collation unit to evaluate the risk of fraud from multiple angles and provide more accurate results. Furthermore, the collation unit feeds back the collation result to the analysis unit and the notification unit, strengthening the cooperation of the entire system. This allows the collation unit to quickly and accurately evaluate the risk of fraud and take appropriate measures against the user.

[0071] The notification unit issues a warning based on the result obtained by the collation unit. The notification is, for example, based on the form and content of the notification, but is not limited to such examples. Specifically, the notification unit notifies the user that "This transfer may be a special fraud. The transfer will be stopped." The notification unit also issues a warning to the user, such as "Contact the police." The notification unit sends a notification to the user's device in real time to prompt an immediate response. For example, a warning message is displayed on the ATM screen to instruct the user to stop the transfer. In addition, a notification is sent to the user's smartphone to provide detailed information. The notification unit can flexibly change the form and content of the notification and select the optimal notification method according to the user's situation. For example, it is possible to respond according to the characteristics of the user, such as prioritizing voice notification for the elderly and text notification for the younger generation. Furthermore, the notification unit saves the history of the notification content so that it can be checked later. This allows the user to refer to the past notification content and take the necessary action. The notification unit can collect feedback from users and continuously improve the accuracy and effectiveness of the notification content. For example, the system records how users respond to notifications and optimizes the notification algorithm based on that data, allowing the notification unit to quickly and appropriately alert users and minimize the risk of fraud.

[0072] The special fraud prevention system includes a privacy protection unit that protects the privacy of the user. The privacy protection unit protects the privacy of the user. Privacy protection includes, for example, methods such as anonymization of data and access control, but is not limited to such examples. For example, the privacy protection unit anonymizes the data input by the user to prevent a third party from identifying a specific user. In addition, the privacy protection unit limits the authority to access the user's data and allows access only when necessary. This protects the privacy of the user, allowing the special fraud prevention system to be used with peace of mind. Some or all of the above-mentioned processing in the privacy protection unit may be performed, for example, using AI, or may be performed without using AI. For example, the privacy protection unit can input the user's data to the generation AI and have the generation AI perform the anonymization of the data and the access control.

[0073] The special fraud prevention system includes a security unit that takes security measures when linking with the police database. The security unit takes security measures when linking with the police database. The security measures include, but are not limited to, methods such as encryption and authentication processes. For example, the security unit encrypts the user's data to prevent a third party from eavesdropping on the data when the data is transmitted and received. In addition, when accessing the police database, the security unit confirms a legitimate access right through an authentication process. This makes it possible to ensure security when linking with the police database. Some or all of the above-mentioned processing in the security unit may be performed using, for example, AI, or may be performed without using AI. For example, the security unit can cause the generation AI to execute data encryption and authentication processes.

[0074] The special fraud prevention system includes a message generating unit that generates a specific warning message. The message generating unit generates the specific warning message. The warning message includes, but is not limited to, a message template, a generation algorithm, and other methods. For example, the message generating unit generates a specific message such as "This transfer may be a special fraud. The transfer will be stopped" for the user. The message generating unit also generates a warning message such as "Please contact the police" for the user. This makes it possible to provide the user with a specific warning message. A part or all of the above-mentioned processing in the message generating unit may be performed, for example, using AI, or may be performed without using AI. For example, the message generating unit can cause the generation AI to execute the generation of the warning message.

[0075] The reception unit can estimate the user's emotion and adjust the input reception method based on the estimated user's emotion. For example, when the user is nervous, the reception unit provides a simple and intuitive interface and minimizes the input procedure. In addition, when the user is relaxed, the reception unit can provide detailed input options and suggest a customizable input method. Furthermore, when the user is in a hurry, the reception unit can prioritize voice input and enable the user to complete the input quickly. This allows for more appropriate response by adjusting the input reception method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion to the generation AI and adjust the input reception method based on the emotion.

[0076] The reception unit can analyze the user's past input history and select the optimal input reception method. For example, the reception unit automatically displays as candidates the transfer destinations that the user frequently input in the past. The reception unit can also preferentially suggest input methods (such as voice and text) that the user has used in the past. Furthermore, the reception unit can predict and suggest transfer destinations to be used in a specific time period from the user's past input history. This makes it possible to provide the optimal input reception method based on the past input history. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past input history into a generation AI and select the optimal input reception method.

[0077] The reception unit can perform filtering based on the user's current situation and areas of interest when receiving input. For example, when the user is about to transfer a large amount of money, the reception unit preferentially displays a specific question. In addition, when the user is using an ATM during a specific time period, the reception unit can also perform a warning related to that time period. Furthermore, when the user is in a specific area, the reception unit can perform filtering based on fraud information occurring in that area. In this way, more appropriate questions can be provided by performing filtering according to the user's situation and areas of interest. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's current situation and areas of interest into the generation AI and perform filtering.

[0078] The reception unit can estimate the user's emotion and determine the priority of input based on the estimated user's emotion. For example, when the user is nervous, the reception unit can display important questions first to allow the user to respond quickly. In addition, when the user is relaxed, the reception unit can display detailed questions in sequence to allow the user to respond carefully. Furthermore, when the user is in a hurry, the reception unit can display the most important questions preferentially to allow the user to complete the input quickly. This allows for a quick and appropriate response by determining the priority of input according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion to the generation AI to determine the priority of input.

[0079] The reception unit can preferentially receive highly relevant inputs in consideration of the geographical location information of the user when receiving the input. For example, when the user is in a specific area, the reception unit displays a question based on fraud information occurring in the area. In addition, when the user uses a specific ATM, the reception unit can also display a question based on fraud information that has occurred in the ATM in the past. Furthermore, when the user uses an ATM during a specific time period, the reception unit can also display a question based on fraud information related to that time period. In this way, highly relevant questions can be provided by considering the geographical location information of the user. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the geographical location information of the user to the generation AI and preferentially receive highly relevant inputs.

[0080] The reception unit can analyze the user's social media activity and receive related inputs when receiving inputs. For example, when the user shares specific fraud information on social media, the reception unit displays a question based on the information. In addition, when the user posts information about a specific region on social media, the reception unit can also display a question based on fraud information occurring in the region. Furthermore, when the user posts information about a specific time period on social media, the reception unit can also display a question based on fraud information related to the time period. This makes it possible to provide related questions based on the user's social media activity. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's social media activity to the generation AI and receive related inputs.

[0081] The analysis unit can estimate the user's emotion and adjust the expression method of the analysis based on the estimated user's emotion. For example, when the user is nervous, the analysis unit displays a simple and intuitive analysis result. In addition, when the user is relaxed, the analysis unit can also display a detailed analysis result. Furthermore, when the user is in a hurry, the analysis unit can also display an analysis result that covers the main points. This makes it possible to provide a more appropriate analysis result by adjusting the expression method of the analysis according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion to the generation AI and adjust the expression method of the analysis.

[0082] The analysis unit can adjust the level of detail of the analysis based on the importance of the input information during the analysis. For example, in the case of a large amount of transfer, the analysis unit performs a detailed analysis and carefully evaluates the possibility of fraud. In addition, in the case of a low amount of transfer, the analysis unit can perform a simplified analysis and provide the result quickly. Furthermore, in the case of a transfer to a specific transfer destination, the analysis unit can perform a detailed analysis based on the past history of the transfer destination. In this way, by adjusting the level of detail of the analysis according to the importance of the input information, it is possible to provide a prompt and appropriate analysis result. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the importance of the input information to the generation AI and adjust the level of detail of the analysis.

[0083] The analysis unit can apply different analysis algorithms depending on the category of input information during analysis. For example, when the transfer destination is an individual, the analysis unit performs analysis based on fraud information for individuals. Furthermore, when the transfer destination is a company, the analysis unit can also perform analysis based on fraud information for companies. Furthermore, when the transfer destination is a public institution, the analysis unit can also perform analysis based on fraud information for public institutions. This makes it possible to provide more accurate analysis results by applying an analysis algorithm according to the category of input information. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the category of input information to the generation AI and apply different analysis algorithms.

[0084] The analysis unit can estimate the user's emotion and adjust the length of the analysis based on the estimated user's emotion. For example, when the user is in a hurry, the analysis unit provides a short and to the point analysis result. In addition, when the user is relaxed, the analysis unit can also provide a detailed analysis result. Furthermore, when the user is excited, the analysis unit can also provide an analysis result with a visually stimulating effect. This allows for a quick and appropriate analysis result to be provided by adjusting the length of the analysis according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion into the generation AI and adjust the length of the analysis.

[0085] The analysis unit can determine the priority of the analysis based on the submission time of the input information at the time of analysis. For example, the analysis unit prioritizes the analysis of recent transfer information to reflect the latest fraud information. The analysis unit can also analyze fraud patterns by referring to past transfer information. Furthermore, the analysis unit can also prioritize the analysis of transfer information made in a specific time period to reflect fraud information related to that time period. In this way, by determining the priority of the analysis based on the submission time of the input information, it is possible to provide an analysis result that reflects the latest fraud information. Part or all of the above-mentioned 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 input the submission time of the input information to the generation AI to determine the priority of the analysis.

[0086] The analysis unit can adjust the order of analysis based on the relevance of the input information during analysis. For example, the analysis unit prioritizes analysis of high-value transfer information and carefully evaluates the possibility of fraud. The analysis unit can also prioritize analysis of transfer information for a specific transfer destination and evaluate it based on the past history of the transfer destination. Furthermore, the analysis unit can prioritize analysis of transfer information made in a specific time period and reflect fraud information related to that time period. This makes it possible to provide a prompt and appropriate analysis result by adjusting the order of analysis based on the relevance of the input information. Part or all of the above-mentioned 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 input the relevance of the input information to the generation AI and adjust the order of analysis.

[0087] The matching unit can estimate the user's emotions and adjust the matching criteria based on the estimated user's emotions. For example, when the user is nervous, the matching unit performs matching with strict criteria and carefully evaluates the possibility of fraud. Also, when the user is relaxed, the matching unit can perform matching with flexible criteria and provide detailed information. Furthermore, when the user is in a hurry, the matching unit can perform matching quickly and provide information with the main points. In this way, by adjusting the matching criteria according to the user's emotions, it is possible to provide a quick and appropriate matching result. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the matching unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the matching unit can input the user's emotions into the generation AI and adjust the matching criteria.

[0088] The matching unit can improve the accuracy of matching by considering the interrelationships of the input information during matching. The matching unit, for example, matches the telephone number of the transfer destination with the purpose of the transfer to evaluate the possibility of fraud. The matching unit can also match the telephone number of the transfer destination with past fraud information to evaluate the possibility of fraud. Furthermore, the matching unit can also match the telephone number of the transfer destination with the user's past transfer history to evaluate the possibility of fraud. This makes it possible to improve the accuracy of matching by considering the interrelationships of the input information. Part or all of the above-mentioned processing in the matching unit may be performed, for example, using AI, or may be performed without using AI. For example, the matching unit can input the interrelationships of the input information to the generation AI to improve the accuracy of matching.

[0089] The matching unit can perform matching by taking into consideration attribute information of the person who submitted the input information. The matching unit can evaluate the possibility of fraud by taking into consideration, for example, the age and gender of the user. The matching unit can also evaluate the possibility of fraud by taking into consideration the user's past transfer history. Furthermore, the matching unit can evaluate the possibility of fraud by taking into consideration the user's current situation (urgency, etc.). This makes it possible to improve the accuracy of matching by taking into consideration the attribute information of the person who submitted the input information. Some or all of the above-mentioned processing in the matching unit may be performed, for example, using AI, or may be performed without using AI. For example, the matching unit can input the attribute information of the person who submitted the input information to the generation AI and perform matching.

[0090] The collation unit can estimate the user's emotion and adjust the order of displaying the collation results based on the estimated user's emotion. For example, when the user is nervous, the collation unit can display important results first to allow the user to respond quickly. In addition, when the user is relaxed, the collation unit can display detailed results sequentially to allow the user to respond carefully. Furthermore, when the user is in a hurry, the collation unit can display the most important results preferentially to allow the user to respond quickly. This allows for a quick and appropriate response by adjusting the order of displaying the collation results according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collation unit can input the user's emotion into the generation AI and adjust the order of displaying the collation results.

[0091] The matching unit can perform matching by taking into consideration the geographical distribution of the input information. For example, when a user is in a specific area, the matching unit performs matching based on fraud information occurring in that area. In addition, when a user uses a specific ATM, the matching unit can also perform matching based on fraud information that has occurred in the past at that ATM. Furthermore, when a user uses an ATM during a specific time period, the matching unit can also perform matching based on fraud information related to that time period. This makes it possible to improve the accuracy of matching by taking into consideration the geographical distribution of the input information. A part or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input the geographical distribution into a generation AI and perform matching.

[0092] The matching unit can improve the accuracy of matching by referring to literature related to the input information during matching. The matching unit can, for example, refer to literature on fraud cases related to the transfer destination telephone number and evaluate the possibility of fraud. The matching unit can also refer to literature on fraud patterns related to the transfer destination telephone number and evaluate the possibility of fraud. Furthermore, the matching unit can also refer to literature on fraud methods related to the transfer destination telephone number and evaluate the possibility of fraud. This makes it possible to improve the accuracy of matching by referring to related literature. Part or all of the above-mentioned processing in the matching unit may be performed, for example, using AI, or may be performed without using AI. For example, the matching unit can input related literature into the generation AI to improve the accuracy of matching.

[0093] The notification unit can estimate the user's emotion and adjust the notification display method based on the estimated user's emotion. For example, when the user is nervous, the notification unit displays a simple and highly visible notification. In addition, when the user is relaxed, the notification unit can also display a notification including detailed information. Furthermore, when the user is in a hurry, the notification unit can also display a notification that covers the main points. This allows for a quick and appropriate response by adjusting the notification display method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the notification unit can input the user's emotion into the generation AI and adjust the notification display method.

[0094] The notification unit can optimize the current notification by referring to past notification data at the time of notification. The notification unit selects the optimal notification method based on notifications received by the user in the past, for example. The notification unit can also analyze the reaction of notifications received by the user in the past and determine the optimal notification content. Furthermore, the notification unit can select the optimal notification timing by referring to the timing of notifications received by the user in the past. In this way, the optimal notification method can be provided by referring to the past notification data. A part 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 input past notification data into a generation AI to optimize the current notification.

[0095] The notification unit can apply different notification methods for each category of input information at the time of notification. For example, in the case of a large amount of transfer, the notification unit displays a notification including a detailed warning. In addition, in the case of a low amount of transfer, the notification unit can also display a simplified notification. Furthermore, in the case of a transfer to a specific transfer destination, the notification unit can also display a notification including a warning related to the transfer destination. This makes it possible to provide a more appropriate warning by providing a notification method according to the category of input information. Part 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 input the category of input information to the generation AI and apply different notification methods.

[0096] The notification unit can estimate the user's emotion and adjust the importance of the notification based on the estimated user's emotion. For example, when the user is nervous, the notification unit displays important notifications first to enable a quick response. In addition, when the user is relaxed, the notification unit can display detailed notifications in sequence to enable a careful response. Furthermore, when the user is in a hurry, the notification unit can display the most important notifications preferentially to enable a quick response. This allows a quick and appropriate response by adjusting the importance of the notification according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the notification unit can input the user's emotion to the generation AI and adjust the importance of the notification.

[0097] The notification unit can determine the priority of the notification based on the submission time of the input information at the time of notification. The notification unit, for example, prioritizes the notification of recent transfer information to reflect the latest fraud information. The notification unit can also notify fraud patterns by referring to past transfer information. Furthermore, the notification unit can also prioritize the notification of transfer information made in a specific time period to reflect fraud information related to that time period. In this way, by determining the priority of the notification based on the submission time of the input information, it is possible to provide a notification that reflects the latest fraud information. Part 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 input the submission time of the input information to the generation AI to determine the priority of the notification.

[0098] At the time of notification, the notification unit can provide notification by referring to market data related to the input information. The notification unit, for example, refers to market data related to the transfer destination telephone number and provides notification of the possibility of fraud. The notification unit can also provide notification of the possibility of fraud by referring to market trends related to the transfer destination telephone number. Furthermore, the notification unit can also provide notification of the possibility of fraud by referring to market analysis related to the transfer destination telephone number. In this way, it is possible to provide notification of the possibility of fraud by referring to the related market data. Part 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 input the related market data into the generation AI and provide notification.

[0099] The privacy protection unit can estimate the user's emotion and adjust the privacy protection method based on the estimated user's emotion. For example, when the user is nervous, the privacy protection unit increases the level of privacy protection to provide a sense of security. In addition, the privacy protection unit can also provide a flexible privacy protection method when the user is relaxed. Furthermore, when the user is in a hurry, the privacy protection unit can quickly set privacy protection. This makes it possible to provide a sense of security by adjusting the privacy protection method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the privacy protection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the privacy protection unit can input the user's emotion into the generation AI and adjust the privacy protection method.

[0100] The privacy protection unit can select the optimal protection method by referring to past privacy protection data during privacy protection. The privacy protection unit, for example, proposes the optimal protection method based on the privacy protection settings selected by the user in the past. The privacy protection unit can also select the optimal protection method based on cases of privacy infringement suffered by the user in the past. Furthermore, the privacy protection unit can analyze the user's past privacy protection history and propose the optimal protection method. In this way, the optimal protection method can be provided by referring to the past privacy protection data. A part or all of the above-mentioned processing in the privacy protection unit may be performed, for example, using AI or may be performed without using AI. For example, the privacy protection unit can input past privacy protection data into a generation AI to select the optimal protection method.

[0101] The privacy protection unit can estimate the user's emotions and determine the priority of privacy protection based on the estimated user's emotions. For example, when the user is nervous, the privacy protection unit first sets important privacy protection to provide a sense of security. In addition, when the user is relaxed, the privacy protection unit can sequentially set detailed privacy protection. Furthermore, when the user is in a hurry, the privacy protection unit can prioritize the most important privacy protection. This enables a quick and appropriate response by determining the priority of privacy protection according to the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the privacy protection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the privacy protection unit can input the user's emotions into the generation AI and determine the priority of privacy protection.

[0102] The privacy protection unit can select the optimal protection method in consideration of the geographical location information of the user during privacy protection. For example, when the user is in a specific area, the privacy protection unit selects the optimal protection method based on the privacy protection regulations of the area. In addition, when the user uses a specific ATM, the privacy protection unit can also select the optimal protection method based on the privacy protection settings of the ATM. Furthermore, when the user uses the ATM during a specific time period, the privacy protection unit can also select a privacy protection method related to that time period. In this way, it is possible to provide an optimal privacy protection method by considering the geographical location information of the user. Part or all of the above-mentioned processing in the privacy protection unit may be performed, for example, using AI, or may be performed without using AI. For example, the privacy protection unit can input geographical location information to the generation AI and select the optimal protection method.

[0103] The security unit can estimate the user's emotion and adjust the security measures based on the estimated user's emotion. For example, when the user is nervous, the security unit strengthens the security measures to provide a sense of security. The security unit can also provide flexible security measures when the user is relaxed. Furthermore, the security unit can also quickly implement security measures when the user is in a hurry. This makes it possible to provide a sense of security by adjusting security measures according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the security unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the security unit can input the user's emotion into the generation AI and adjust the security measures.

[0104] The security unit can select the optimal countermeasure by referring to past security data when taking security measures. For example, the security unit proposes the optimal countermeasure based on security measures selected by the user in the past. The security unit can also select the optimal countermeasure based on cases of security infringement suffered by the user in the past. Furthermore, the security unit can analyze the history of the user's past security measures and propose the optimal countermeasure. In this way, the optimal security countermeasure can be provided by referring to the past security data. A part or all of the above-mentioned processing in the security unit may be performed, for example, using AI, or may be performed without using AI. For example, the security unit can input past security data into a generating AI and select the optimal countermeasure.

[0105] The security unit can estimate the user's emotions and determine the priority of security measures based on the estimated user's emotions. For example, when the user is nervous, the security unit takes important security measures first to provide a sense of security. In addition, when the user is relaxed, the security unit can take detailed security measures sequentially. Furthermore, when the user is in a hurry, the security unit can take the most important security measures first. This enables a quick and appropriate response by determining the priority of security measures according to the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the security unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the security unit can input the user's emotions into the generation AI and determine the priority of security measures.

[0106] The security unit can select the optimal security measure in consideration of the geographical location information of the user. For example, when the user is in a specific area, the security unit selects the optimal measure based on the security regulations of the area. In addition, when the user uses a specific ATM, the security unit can also select the optimal measure based on the security settings of the ATM. Furthermore, when the user uses the ATM during a specific time period, the security unit can also select security measures related to that time period. In this way, the optimal security measure can be provided by considering the geographical location information of the user. Part or all of the above-mentioned processing in the security unit may be performed, for example, using AI, or may be performed without using AI. For example, the security unit can input geographical location information to a generation AI and select the optimal measure.

[0107] The message generating unit can estimate the user's emotion and adjust the message generation method based on the estimated user's emotion. For example, when the user is nervous, the message generating unit generates a simple and highly visible message. In addition, when the user is relaxed, the message generating unit can also generate a message including detailed information. Furthermore, when the user is in a hurry, the message generating unit can also generate a message that focuses on the main points. This allows for a quick and appropriate response by adjusting the message generation method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the message generating unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the message generating unit can input the user's emotion into the generation AI and adjust the message generation method.

[0108] The message generating unit can generate an optimal message by referring to past message data when generating a message. The message generating unit generates an optimal message based on, for example, messages received by the user in the past. The message generating unit can also analyze the reaction to the message received by the user in the past and determine the optimal message content. Furthermore, the message generating unit can select the optimal message timing by referring to the timing of the message received by the user in the past. In this way, the optimal message can be provided by referring to the past message data. A part or all of the above-mentioned processing in the message generating unit may be performed, for example, using AI or may be performed without using AI. For example, the message generating unit can input past message data into a generation AI to generate an optimal message.

[0109] The message generating unit can estimate the user's emotion and determine the priority of messages based on the estimated user's emotion. For example, when the user is nervous, the message generating unit can display important messages first to enable a quick response. In addition, when the user is relaxed, the message generating unit can display detailed messages sequentially to enable a polite response. Furthermore, when the user is in a hurry, the message generating unit can display the most important messages preferentially to enable a quick response. This enables a quick and appropriate response by determining the priority of messages according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the message generating unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the message generating unit can input the user's emotion into the generation AI to determine the priority of messages.

[0110] The message generating unit can generate an optimal message in consideration of the geographical location information of the user when generating a message. For example, when the user is in a specific area, the message generating unit generates an optimal message based on fraud information for that area. In addition, when the user uses a specific ATM, the message generating unit can also generate an optimal message based on fraud information for that ATM. Furthermore, when the user uses an ATM during a specific time period, the message generating unit can also generate an optimal message based on fraud information related to that time period. This makes it possible to provide an optimal message by considering the geographical location information of the user. A part or all of the above-mentioned processing in the message generating unit may be performed, for example, using AI, or may be performed without using AI. For example, the message generating unit can input geographical location information into the generating AI to generate an optimal message.

[0111] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0112] The analysis unit can analyze the user's past transfer history and evaluate the possibility of fraud. For example, if the user has made multiple transfers to the same transfer destination in the past, it evaluates whether the transfer destination is likely to be fraudulent. The analysis unit can also detect similar patterns based on the user's history of being a victim of fraud in the past. Furthermore, the analysis unit can analyze the user's past transfer amounts and frequencies and detect abnormal patterns. This makes it possible to provide more accurate analysis results by evaluating the possibility of fraud based on the user's past transfer history. Some or all of the above-mentioned 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 input the user's past transfer history into the generation AI and evaluate the possibility of fraud.

[0113] The privacy protection unit can store the user's data in a distributed network to enhance security. For example, the user's data is distributed and stored in multiple servers so as not to be concentrated in one place. The privacy protection unit can also store the user's data using blockchain technology to prevent tampering. Furthermore, the privacy protection unit can encrypt and store the user's data so that it cannot be accessed by a third party. This makes it possible to enhance security and protect privacy by storing the user's data in a distributed network. Some or all of the above-mentioned processing in the privacy protection unit may be performed, for example, using AI or may be performed without using AI. For example, the privacy protection unit can input the user's data into a generation AI and store it in a distributed network.

[0114] The security unit can learn the user's behavioral patterns and detect abnormal behavior. For example, if the user uses an ATM during a time period when the user does not normally use the ATM, the security unit can determine the behavior as abnormal and issue a warning. In addition, if the user uses an ATM in an area where the user does not normally use the ATM, the security unit can also determine the behavior as abnormal and issue a warning. Furthermore, if the user attempts to transfer an amount that is not normally used, the security unit can also determine the behavior as abnormal and issue a warning. In this way, security can be strengthened by learning the user's behavioral patterns and detecting abnormal behavior. Part or all of the above-mentioned processing in the security unit may be performed, for example, using AI, or may be performed without using AI. For example, the security unit can input the user's behavioral patterns into the generation AI and detect abnormal behavior.

[0115] The message generation unit can analyze the user's past message history and generate an optimal message. For example, the optimal message content is determined based on the user's reaction to the message received in the past. The message generation unit can also select the optimal message timing by referring to the timing of the message received in the past by the user. Furthermore, the message generation unit can also select the optimal message format based on the format of the message received in the past by the user. This makes it possible to provide an optimal message based on the past message history. A part or all of the above-mentioned processing in the message generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the message generation unit can input the past message history into a generation AI and generate an optimal message.

[0116] The reception unit can estimate the user's emotion and adjust the input reception method based on the estimated user's emotion. For example, if the user is nervous, a simple and intuitive interface is provided to minimize the input procedure. In addition, if the user is relaxed, the reception unit can provide detailed input options and suggest a customizable input method. Furthermore, if the user is in a hurry, the reception unit can prioritize voice input and enable the user to complete the input quickly. This allows for more appropriate response by adjusting the input reception method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion to the generation AI and adjust the input reception method based on the emotion.

[0117] The analysis unit can estimate the user's emotion and adjust the expression method of the analysis based on the estimated user's emotion. For example, if the user is nervous, a simple and intuitive analysis result is displayed. In addition, the analysis unit can also display a detailed analysis result when the user is relaxed. Furthermore, if the user is in a hurry, the analysis unit can also display an analysis result that focuses on the main points. This makes it possible to provide a more appropriate analysis result by adjusting the expression method of the analysis according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion into the generation AI and adjust the expression method of the analysis.

[0118] The matching unit can estimate the user's emotions and adjust the matching criteria based on the estimated user's emotions. For example, if the user is nervous, matching is performed with strict criteria to carefully evaluate the possibility of fraud. Also, if the user is relaxed, the matching unit can perform matching with flexible criteria to provide detailed information. Furthermore, if the user is in a hurry, the matching unit can perform matching quickly to provide information with the main points. This allows the matching criteria to be adjusted according to the user's emotions, thereby providing a quick and appropriate matching result. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the matching unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the matching unit can input the user's emotions into the generation AI and adjust the matching criteria.

[0119] The notification unit can estimate the user's emotion and adjust the notification display method based on the estimated user's emotion. For example, if the user is nervous, a simple and highly visible notification is displayed. In addition, if the user is relaxed, the notification unit can also display a notification including detailed information. Furthermore, if the user is in a hurry, the notification unit can also display a notification that covers the main points. This allows for a quick and appropriate response by adjusting the notification display method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the notification unit can input the user's emotion into the generation AI and adjust the notification display method.

[0120] The privacy protection unit can estimate the user's emotion and adjust the privacy protection method based on the estimated user's emotion. For example, when the user is nervous, the level of privacy protection is increased to provide a sense of security. The privacy protection unit can also provide a flexible privacy protection method when the user is relaxed. Furthermore, when the user is in a hurry, the privacy protection unit can quickly set privacy protection. This makes it possible to provide a sense of security by adjusting the privacy protection method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the privacy protection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the privacy protection unit can input the user's emotion into the generation AI and adjust the privacy protection method.

[0121] The security unit can estimate the user's emotions and adjust security measures based on the estimated user's emotions. For example, when the user is nervous, the security measures are strengthened to provide a sense of security. The security unit can also provide flexible security measures when the user is relaxed. Furthermore, the security unit can also quickly implement security measures when the user is in a hurry. This makes it possible to provide a sense of security by adjusting security measures according to the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the security unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the security unit can input the user's emotions into the generation AI and adjust the security measures.

[0122] The process flow of the second embodiment will be briefly described below.

[0123] Step 1: The reception unit accepts user input. User input includes, for example, text input, voice input, image input, and the like. For example, when a user tries to transfer a large amount at an ATM, the generation AI asks questions in natural language such as "What is the purpose of this transfer?" or "Please tell me the recipient's phone number." Step 2: The analysis unit uses the generation AI to analyze the information received by the reception unit. The analysis is performed by methods such as text analysis, voice analysis, and image analysis. For example, the generation AI analyzes the user's response and evaluates the possibility of fraud based on the content. Step 3: The matching unit matches the information analyzed by the analysis unit with the police database. Matching is performed, for example, based on the type of database and matching algorithm. For example, the matching unit matches the phone number entered by the user with the police database to check whether the phone number has been used for special fraud in the past. Step 4: The notification unit issues a warning based on the results obtained by the collation unit. The notification is issued based on, for example, the form and content of the notification. For example, the notification unit may notify the user, "This transfer may be a specialized fraud. The transfer will be canceled." It may also warn the user, "Please contact the police."

[0124] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0125] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0126] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0127] Each of the multiple elements including the above-mentioned reception unit, analysis unit, collation unit, notification unit, privacy protection unit, security unit, and message generation unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the reception device 38 of the smart device 14 and receives a user's input. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the user's input. The collation unit is realized by the specific processing unit 290 of the data processing device 12 and compares the analyzed information with the police database. The notification unit is realized by the output device 40 of the smart device 14 and issues a warning to the user. The privacy protection unit is realized by the specific processing unit 290 of the data processing device 12 and protects the user's privacy. The security unit is realized by the specific processing unit 290 of the data processing device 12 and takes security measures when linking with the police database. The message generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a specific warning message. The correspondence between each part and the device or control part is not limited to the above-mentioned example, and various modifications are possible.

[0128] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0129] 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.

[0130] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0131] 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.

[0132] 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 the voice according to instructions from the processor 46.

[0133] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0134] 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 performed in a secure state.

[0135] Fig. 4 shows an example of 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.

[0136] 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.

[0137] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0138] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0139] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0140] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0141] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0142] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0143] Each of the multiple elements including the above-mentioned reception unit, analysis unit, collation unit, notification unit, privacy protection unit, security unit, and message generation unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the smart glasses 214 and receives a user's input. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the user's input. The collation unit is realized by the specific processing unit 290 of the data processing device 12 and compares the analyzed information with a police database. The notification unit is realized by the speaker 240 of the smart glasses 214 and issues a warning to the user. The privacy protection unit is realized by the specific processing unit 290 of the data processing device 12 and protects the user's privacy. The security unit is realized by the specific processing unit 290 of the data processing device 12 and takes security measures when linking with the police database. The message generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a specific warning message. The correspondence between each part and the device or control part is not limited to the above-mentioned example, and various modifications are possible.

[0144] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0145] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0146] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0147] 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.

[0148] 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 the voice according to instructions from the processor 46.

[0149] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0150] 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 performed in a secure state.

[0151] 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.

[0152] 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.

[0153] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0154] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific 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.

[0155] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0156] 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 a voice indicating a user input for 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.

[0157] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0158] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0159] Each of the multiple elements including the above-mentioned reception unit, analysis unit, comparison unit, notification unit, privacy protection unit, security unit, and message generation unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the headset type terminal 314 and receives a user's input. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the user's input. The comparison unit is realized by the specific processing unit 290 of the data processing device 12 and compares the analyzed information with the police database. The notification unit is realized by the speaker 240 of the headset type terminal 314 and issues a warning to the user. The privacy protection unit is realized by the specific processing unit 290 of the data processing device 12 and protects the user's privacy. The security unit is realized by the specific processing unit 290 of the data processing device 12 and takes security measures when linking with the police database. The message generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a specific warning message. The correspondence between each part and the device or control part is not limited to the above-mentioned example, and various modifications are possible.

[0160] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0161] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0162] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0163] 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.

[0164] 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 the voice according to instructions from the processor 46.

[0165] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0166] 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 performed in a secure state.

[0167] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0168] 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.

[0169] 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.

[0170] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0171] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 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.

[0172] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0173] 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 a voice indicating a user input for 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.

[0174] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0175] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information 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.

[0176] Each of the multiple elements including the above-mentioned reception unit, analysis unit, collation unit, notification unit, privacy protection unit, security unit, and message generation unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the robot 414 and receives a user's input. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the user's input. The collation unit is realized by the specific processing unit 290 of the data processing device 12 and compares the analyzed information with the police database. The notification unit is realized by the speaker 240 of the robot 414 and issues a warning to the user. The privacy protection unit is realized by the specific processing unit 290 of the data processing device 12 and protects the user's privacy. The security unit is realized by the specific processing unit 290 of the data processing device 12 and takes security measures when linking with the police database. The message generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a specific warning message. The correspondence between each part and the device or control part is not limited to the above-mentioned example, and various modifications are possible.

[0177] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0178] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0179] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0180] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0181] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0182] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0183] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0184] 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.

[0185] 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 Universal Serial Bus (USB) 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.

[0186] In addition, 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 upon request from the data processing device 12.

[0187] 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.

[0188] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0189] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0190] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0191] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0192] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0193] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0194] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0195] (Appendix 1) A reception unit that receives input from a user; an analysis unit that analyzes the information received by the reception unit; a comparison unit that compares the information analyzed by the analysis unit with a police database; A notification unit that issues a warning based on the result obtained by the collation unit. A system characterized by: (Appendix 2) Equipped with a privacy protection section that protects user privacy 2. The system of claim 1, (Appendix 3) Equipping the department with a security department to take security measures when linking with police databases 2. The system of claim 1, (Appendix 4) Equipped with a message generating unit that generates specific attention-calling messages 2. The system of claim 1, (Appendix 5) The reception unit is Estimate the user's emotions and adjust the input reception method based on the estimated user's emotions. 2. The system of claim 1, (Appendix 6) The reception unit is Analyze the user's past input history and select the appropriate input reception method 2. The system of claim 1, (Appendix 7) The reception unit is As input is received, it is filtered based on the user's current situation and interests. 2. The system of claim 1, (Appendix 8) The reception unit is Estimate the user's emotions and prioritize inputs based on the estimated user emotions. 2. The system of claim 1, (Appendix 9) The reception unit is When accepting input, the system takes into account the user's geographic location information and prioritizes relevant input. 2. The system of claim 1, (Appendix 10) The reception unit is When receiving input, analyze the user's social media activity and receive relevant input 2. The system of claim 1, (Appendix 11) The analysis unit is Infer user emotions and adjust the presentation of analytics based on the inferred user emotions 2. The system of claim 1, (Appendix 12) The analysis unit is During analysis, adjust the level of detail of the analysis based on the importance of the input information 2. The system of claim 1, (Appendix 13) The analysis unit is During parsing, different parsing algorithms are applied depending on the category of input information 2. The system of claim 1, (Appendix 14) The analysis unit is Infer user sentiment and adjust the length of the analysis based on the inferred user sentiment 2. The system of claim 1, (Appendix 15) The analysis unit is During analysis, prioritize analysis based on when input information was submitted 2. The system of claim 1, (Appendix 16) The analysis unit is During parsing, adjust the order of parsing based on the relevance of the input information 2. The system of claim 1, (Appendix 17) The collation unit is Inferring a user's sentiment and adjusting matching criteria based on the inferred user's sentiment 2. The system of claim 1, (Appendix 18) The collation unit is When matching, the accuracy of matching is improved by taking into account the correlation between input information. 2. The system of claim 1, (Appendix 19) The collation unit is When matching, the attribute information of the person submitting the input information is taken into consideration. 2. The system of claim 1, (Appendix 20) The collation unit is Inferring user sentiment and adjusting the order in which matching results are displayed based on the estimated user sentiment 2. The system of claim 1, (Appendix 21) The collation unit is When matching, the geographical distribution of the input information is taken into account. 2. The system of claim 1, (Appendix 22) The collation unit is When matching, the accuracy of the match is improved by referring to related literature of the input information. 2. The system of claim 1, (Appendix 23) The notification unit is Infer user emotions and adjust notification display based on the inferred user emotions 2. The system of claim 1, (Appendix 24) The notification unit is During notifications, look at past notification data to adjust current notifications appropriately 2. The system of claim 1, (Appendix 25) The notification unit is When notifying, apply different notification methods to different categories of input information 2. The system of claim 1, (Appendix 26) The notification unit is Infer user emotions and adjust notification importance based on the estimated user emotions 2. The system of claim 1, (Appendix 27) The notification unit is When notifications are sent, they will be prioritized based on when the input information was submitted 2. The system of claim 1, (Appendix 28) The notification unit is When sending a notification, the relevant market data of the input information is referenced. 2. The system of claim 1, (Appendix 29) The privacy protection unit includes: Inferring user emotions and adjusting privacy protection methods based on the estimated user emotions 2. The system of claim 1, (Appendix 30) The privacy protection unit includes: When protecting privacy, select an appropriate protection method by referring to past privacy protection data. 2. The system of claim 1, (Appendix 31) The privacy protection unit includes: Estimating user emotions and determining privacy protection priorities based on the estimated user emotions 2. The system of claim 1, (Appendix 32) The privacy protection unit includes: When protecting privacy, select an appropriate protection method taking into account the user's geographic location information 2. The system of claim 1, (Appendix 33) The security unit includes: Inferring user emotions and adjusting security measures based on the inferred user emotions 2. The system of claim 1, (Appendix 34) The security unit includes: When implementing security measures, select appropriate measures by referring to past security data. 2. The system of claim 1, (Appendix 35) The security unit includes: Inferring user emotions and prioritizing security measures based on the inferred user emotions 2. The system of claim 1, (Appendix 36) The security unit includes: When implementing security measures, select appropriate measures taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 37) The message generation unit Inferring user emotions and adjusting message generation methods based on the estimated user emotions 2. The system of claim 1, (Appendix 38) The message generation unit When generating a message, the most appropriate message is generated by referencing past message data. 2. The system of claim 1, (Appendix 39) The message generation unit Infer user sentiment and prioritize messages based on the inferred sentiment 2. The system of claim 1, (Appendix 40) The message generation unit When generating messages, the most appropriate message is generated taking into account the user's geographic location information. 2. The system of claim 1, [Explanation of symbols]

[0196] 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 reception unit that receives input from a user; an analysis unit that analyzes the information received by the reception unit; a comparison unit that compares the information analyzed by the analysis unit with a police database; A notification unit that issues a warning based on the result obtained by the collation unit. A system characterized by:

2. Equipped with a privacy protection section that protects user privacy 2. The system of claim 1 .

3. Equipping the department with a security department to take security measures when linking with police databases 2. The system of claim 1 .

4. Equipped with a message generating unit that generates specific attention-calling messages 2. The system of claim 1 .

5. The reception unit is Estimate the user's emotions and adjust the input reception method based on the estimated user's emotions.

2. The system of claim 1 .

6. The reception unit is Analyze the user's past input history and select the appropriate input reception method 2. The system of claim 1 .

7. The reception unit is As input is received, it is filtered based on the user's current situation and interests.

2. The system of claim 1 .

8. The reception unit is Estimate the user's emotions and prioritize inputs based on the estimated user emotions.

2. The system of claim 1 .

9. The reception unit is When accepting input, the system takes into account the user's geographic location information and prioritizes relevant input.

2. The system of claim 1 .

10. The reception unit is When receiving input, analyze the user's social media activity and receive relevant input 2. The system of claim 1 .

11. The analysis unit is Infer user emotions and adjust the presentation of analytics based on the inferred user emotions 2. The system of claim 1 .

Images