system

Abstract

An object of a system according to an embodiment is to effectively prevent fraud when using an ATM.SOLUTION: A system includes an authentication unit, a detection unit, a regulation unit, and a change unit. The authentication unit authenticates a face of a user when operating the ATM. The detection unit detects an abnormal behavior based on the face data authenticated by the authentication unit. The regulation unit regulates the ATM operation when the abnormal behavior is detected by the detection unit. The change unit changes the interface to the interactive interface when the ATM operation is restricted by the restriction unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have had the problem of making it difficult to effectively prevent fraudulent acts when using ATMs.

[0005] The system according to the embodiment aims to effectively prevent fraudulent acts when using ATMs. [Means for solving the problem]

[0006] The system according to the embodiment includes an authentication unit, a detection unit, a restriction unit, and a change unit. The authentication unit authenticates the face of a user when operating an ATM. The detection unit detects abnormal behavior based on face data authenticated by the authentication unit. The restriction unit restricts ATM operation when abnormal behavior is detected by the detection unit. The change unit changes to an interactive interface when ATM operation is restricted by the restriction unit. [Effects of the Invention]

[0007] The system according to the embodiment can effectively prevent fraudulent acts when using ATMs. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) An ATM fraud prevention system according to an embodiment of the present invention authenticates a user's face when operating an ATM, detects any abnormalities in their behavior, restricts the ATM operation, and changes the operation to an interactive mode. The ATM fraud prevention system prevents fraud by authenticating the user's face, detecting any abnormalities in their behavior, restricting the ATM operation, and changing the operation to an interactive mode. For example, in an ATM fraud prevention system, a camera captures the user's face when the user approaches an ATM, and a facial recognition system analyzes the captured image. The ATM fraud prevention system then uses an algorithm to detect patterns, such as the user frequently looking around while operating the ATM, operating abnormally slowly, or suddenly pausing. If the system cannot recognize the user's face, it automatically stops the operation. The ATM fraud prevention system then displays an interactive interface on the ATM screen, allowing the user to proceed with the operation by answering questions. For example, a question such as "Where would you like the transfer to?" is displayed, and the operation proceeds as the user responds. This allows the ATM fraud prevention system to prevent fraud before it occurs, since the user cannot answer interactive questions when a fraudster is instructing the victim to operate the ATM. Furthermore, if the face is unknown, the operation is stopped, thereby preventing fraudulent withdrawals. This allows the ATM fraud prevention system to authenticate the user's face, detect any abnormalities in their behavior, regulate ATM operations, and change them to interactive operations, thereby preventing fraud. For example, if a fraudster is instructing a victim to operate an ATM, the victim will not be able to answer interactive questions, preventing fraud before it occurs. Furthermore, if the face is unknown, the operation is stopped, thereby preventing fraudulent withdrawals.

[0029] An ATM fraud prevention system according to an embodiment includes an authentication unit, a detection unit, a restriction unit, and a change unit. The authentication unit authenticates a user's face when operating an ATM. The authentication unit analyzes the user's face using, for example, a facial recognition algorithm based on deep learning and compares it with registered facial data. For example, when a user approaches an ATM, a camera captures the user's face, and a facial recognition system analyzes it. The detection unit detects abnormal behavior based on the facial data authenticated by the authentication unit. The detection unit detects patterns such as the user frequently looking around while operating the ATM, operating very slowly, or suddenly interrupting the operation. For example, the detection unit analyzes the user's eye movements and operation speed to detect abnormal behavior. The restriction unit restricts ATM operation when the detection unit detects abnormal behavior. For example, the restriction unit stops operation when the user's face cannot be recognized. For example, the restriction unit stops operation when the user's face is obscured by a mask or sunglasses. The change unit changes to an interactive interface when the restriction unit restricts ATM operation. The change unit, for example, displays an interactive interface on the ATM screen, and the user proceeds with the operation by answering questions. For example, a question such as "Where should I transfer the money?" is displayed, and the operation proceeds as the user answers. In this way, the ATM fraud prevention system according to the embodiment can prevent fraud by authenticating the user's face, detecting any abnormality in their behavior, restricting ATM operation, and changing it to an interactive operation. For example, if a fraudster is instructing a victim to operate the ATM, the victim will not be able to answer the interactive questions, and fraud can be prevented before it occurs. Furthermore, if the face is unknown, the operation is stopped, thereby preventing fraudulent withdrawals.

[0030] The authentication unit may use a facial recognition algorithm that uses deep learning. Deep learning includes, but is not limited to, a convolutional neural network (CNN) and a recurrent neural network (RNN). The authentication unit may extract facial features using, for example, a CNN and compare them with registered facial data. The authentication unit may also use an RNN to analyze facial movements and changes in facial expression to improve authentication accuracy. For example, the authentication unit may use deep learning to extract facial features with high accuracy and improve authentication accuracy. This improves the accuracy of facial recognition. Some or all of the above-described processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit may use an AI system that performs facial recognition using a deep learning model.

[0031] The detection unit can detect patterns such as a user frequently looking around while operating an ATM, operating very slowly, or suddenly interrupting an operation. The detection unit, for example, tracks the user's eye movement and detects frequent looking around. For example, the detection unit analyzes eye movement patterns to detect abnormal behavior. The detection unit can also monitor the speed of operation and detect when the operation is very slow. For example, the detection unit measures the average speed of operation and detects abnormal behavior when it falls below a certain threshold. The detection unit can also monitor the continuity of operation to detect interruptions of operation. For example, the detection unit measures the duration of operation interruptions and detects abnormal behavior when the operation is interrupted for more than a certain period of time. This makes it easier to identify abnormal behavior by detecting user behavior patterns. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or without AI. For example, the detection unit can use an AI model that analyzes eye movement and operation speed.

[0032] The regulating unit can stop the operation if the face cannot be recognized. For example, the regulating unit stops the operation if the face is obscured by a mask or sunglasses. For example, the regulating unit stops the operation if part of the face is hidden or if the lighting conditions are poor. The regulating unit can also automatically stop the operation if the facial recognition system cannot recognize the face. For example, the regulating unit stops the operation if the facial recognition system cannot recognize the face within a certain period of time. In this way, by stopping the operation if the face cannot be recognized, it is possible to prevent unauthorized operation. Some or all of the above-mentioned processing in the regulating unit may be performed using, for example, AI, or may be performed without using AI. For example, the regulating unit can use an AI model that stops the operation based on the results of the facial recognition system.

[0033] The change unit can display an interactive interface on the ATM screen and allow the user to proceed with the operation by answering questions. The change unit can, for example, display an interactive interface on the ATM screen and allow the user to proceed with the operation by answering questions. For example, the change unit displays a question such as "Where should I transfer the money?" and the operation proceeds as the user answers. The change unit can also provide various interactive interfaces, such as voice dialogue and text-based question-and-answering. For example, the change unit can analyze a user's voice input using speech recognition technology and provide an interactive interface. The change unit can also use text-based question-and-answering to allow the user to proceed with the operation by entering questions on the screen. In this way, by displaying an interactive interface, the operation can proceed by the user answering questions. Some or all of the above-described processing by the change unit may be performed using, for example, AI, or may be performed without AI. For example, the change unit can use an AI system that provides an interactive interface using speech recognition technology or natural language processing technology.

[0034] The modification unit can stop the operation when the user cannot answer a question or when the answer is inaccurate. For example, the modification unit stops the operation when the user cannot answer a question within a certain time. For example, the modification unit stops the operation when the user does not answer a question within a certain time. The modification unit can also stop the operation when the user's answer is inaccurate. For example, the modification unit stops the operation when the user's answer does not match pre-registered information. This makes it possible to prevent fraud by stopping the operation when the user cannot answer a question or when the answer is inaccurate. Some or all of the above-mentioned processing by the modification unit may be performed using, for example, AI, or may be performed without using AI. For example, the modification unit can use an AI model that analyzes the user's answer and determines its accuracy.

[0035] During facial recognition, the authentication unit can improve authentication accuracy by referring to the user's past authentication history. The authentication unit adjusts authentication accuracy, for example, based on the user's past authentication successes. For example, the authentication unit improves authentication accuracy by referring to past authentication dates and times and authentication results. The authentication unit can also expand the authentication tolerance range based on the user's past authentication failures. For example, the authentication unit analyzes the causes of past authentication failures and adjusts the authentication algorithm. Furthermore, the authentication unit can analyze the user's past authentication history and apply an optimal authentication algorithm. For example, the authentication unit learns the user's facial features based on the past authentication history and improves authentication accuracy. Thus, referring to the past authentication history improves authentication accuracy. Some or all of the above-described processing in the authentication unit may be performed using, for example, AI, or may be performed without AI. For example, the authentication unit can use an AI system that adjusts the authentication algorithm based on the past authentication history.

[0036] The authentication unit can apply different authentication algorithms depending on the user's age and gender during facial recognition. For example, if the user is elderly, the authentication unit widens the tolerance range for facial recognition. For example, the authentication unit adjusts the authentication algorithm taking into account the facial features of elderly people. The authentication unit can also improve the accuracy of facial recognition if the user is young. For example, the authentication unit adjusts the authentication algorithm taking into account the facial features of young people. Furthermore, the authentication unit can select the optimal authentication algorithm depending on the user's gender. For example, the authentication unit adjusts the authentication algorithm taking into account the differences in facial features between men and women. This improves the accuracy of authentication by applying an authentication algorithm depending on the user's age and gender. Some or all of the above-described processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit can use an AI system that applies an authentication algorithm depending on the user's age and gender.

[0037] The authentication unit can improve the accuracy of facial recognition by taking into account changes in the user's facial orientation and facial expression. For example, the authentication unit applies an algorithm that enables authentication even when the user's face is tilted. For example, the authentication unit adjusts the authentication algorithm by taking into account the rotation angle of the face. The authentication unit can also apply an algorithm that enables authentication even when the user's facial expression changes. For example, the authentication unit adjusts the authentication algorithm by taking into account patterns of facial expression change. Furthermore, the authentication unit can detect changes in the user's facial orientation and facial expression in real time and adjust the authentication accuracy. For example, the authentication unit monitors changes in facial orientation and facial expression in real time and adjusts the authentication algorithm. This improves the accuracy of authentication by taking changes in facial orientation and facial expression into account. Some or all of the above-described processing in the authentication unit may be performed using, for example, AI, or may be performed without AI. For example, the authentication unit can use an AI system that adjusts the authentication algorithm by taking changes in facial orientation and facial expression into account.

[0038] The authentication unit can improve the accuracy of authentication by taking into account the user's geographical location information during facial recognition. For example, the authentication unit improves the accuracy of authentication when the user is using an ATM near their home. For example, the authentication unit adjusts the authentication algorithm based on the geographical location information when the user is using an ATM near their home. The authentication unit can also expand the tolerance range of authentication when the user is using an ATM at a travel destination. For example, the authentication unit adjusts the authentication algorithm based on the geographical location information when the user is using an ATM at a travel destination. The authentication unit can also apply an optimal authentication algorithm based on the user's geographical location information. For example, the authentication unit learns the user's facial features based on the geographical location information and improves the accuracy of authentication. As a result, the accuracy of authentication is improved by taking the geographical location information into consideration. Some or all of the above-described processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit can use an AI system that adjusts the authentication algorithm based on the geographical location information.

[0039] During facial recognition, the authentication unit can analyze the user's social media activities and obtain related authentication data. The authentication unit complements the authentication data, for example, based on a facial photo posted by the user on social media. For example, the authentication unit analyzes a facial photo posted on social media to complement the authentication data. The authentication unit can also analyze the user's social media activity history to improve authentication accuracy. For example, the authentication unit analyzes the content of posts and friendships on social media to complement the authentication data. Furthermore, the authentication unit can complement the authentication data by referring to the user's friendships on social media. For example, the authentication unit complements the authentication data based on friendships on social media. In this way, the authentication data is complemented by analyzing social media activities, improving authentication accuracy. Some or all of the above-described processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit can use an AI system that analyzes social media activities and complements authentication data.

[0040] The authentication unit can customize the authentication algorithm by reflecting the user's past feedback during facial recognition. The authentication unit adjusts the authentication algorithm, for example, based on feedback provided by the user in the past. For example, the authentication unit analyzes the past feedback and customizes the authentication algorithm. The authentication unit can also expand the authentication tolerance range based on the user's past feedback. For example, the authentication unit adjusts the authentication algorithm based on the past feedback. Furthermore, the authentication unit can analyze the user's past feedback and apply an optimal authentication algorithm. For example, the authentication unit customizes the authentication algorithm based on the past feedback. In this way, the authentication algorithm is optimized by reflecting the past feedback, and authentication accuracy is improved. Some or all of the above-described processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit can use an AI system that customizes the authentication algorithm based on past feedback.

[0041] When detecting an abnormality in behavior, the detection unit can improve the accuracy of detection by referring to the user's past operation history. The detection unit detects abnormality in behavior, for example, based on the user's past operation history. For example, the detection unit detects an abnormal operation pattern by referring to the date and time of past operations and the content of operations. The detection unit can also detect an abnormal operation pattern from the user's past operation history. For example, the detection unit analyzes the past operation history and identifies an abnormal operation pattern. Furthermore, the detection unit can analyze the user's past operation history and apply an optimal detection algorithm. For example, the detection unit applies an algorithm that detects an abnormal operation pattern based on the past operation history. In this way, by referring to the past operation history, the accuracy of detection is improved. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit may use an AI system that detects an abnormal operation pattern based on the past operation history.

[0042] When detecting incongruent behavior, the detection unit can apply different detection algorithms depending on the age and gender of the user. For example, if the user is elderly, the detection unit relaxes the criteria for detecting incongruent behavior. For example, the detection unit adjusts the detection algorithm taking into account the behavioral patterns of elderly people. Furthermore, if the user is young, the detection unit can tighten the criteria for detecting incongruent behavior. For example, the detection unit adjusts the detection algorithm taking into account the behavioral patterns of young people. Furthermore, the detection unit can select an optimal detection algorithm depending on the gender of the user. For example, the detection unit adjusts the detection algorithm taking into account differences in the behavioral patterns of men and women. In this way, by applying a detection algorithm depending on age and gender, the accuracy of detection is improved. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can use an AI system that applies a detection algorithm depending on age and gender.

[0043] When detecting abnormal behavior, the detection unit can improve the accuracy of detection by taking into account the user's operation speed and operation pattern. The detection unit detects abnormal behavior, for example, when the user's operation speed is abnormally slow. For example, the detection unit measures the average operation speed and detects it as abnormal if it is below a certain threshold. The detection unit can also detect abnormal behavior when the user's operation pattern suddenly changes. For example, the detection unit monitors the consistency of operations and detects sudden changes. Furthermore, the detection unit can analyze the user's operation speed and operation pattern in real time to improve the accuracy of detection. For example, the detection unit monitors the operation speed and operation pattern in real time to detect abnormal behavior. In this way, taking the operation speed and operation pattern into consideration improves the accuracy of detection. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can use an AI system that analyzes the operation speed and operation pattern in real time.

[0044] The detection unit can improve the accuracy of detection when detecting anomalies in behavior by taking into account the user's geographical location information. For example, the detection unit relaxes the criteria for detecting anomalies in behavior when the user uses an ATM near their home. For example, the detection unit adjusts the detection algorithm based on the geographical location information when the user uses an ATM near their home. The detection unit can also tighten the criteria for detecting anomalies in behavior when the user uses an ATM at a travel destination. For example, the detection unit adjusts the detection algorithm based on the geographical location information when the user uses an ATM at a travel destination. The detection unit can also apply an optimal detection algorithm based on the user's geographical location information. For example, the detection unit learns the user's behavioral patterns based on the geographical location information and improves the accuracy of detection. As a result, the accuracy of detection is improved by taking the geographical location information into account. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can use an AI system that adjusts the detection algorithm based on the geographical location information.

[0045] When detecting anomalies in behavior, the detection unit can analyze the user's social media activities and acquire related data. The detection unit detects anomalies in behavior, for example, based on the user's public activity history on social media. For example, the detection unit analyzes the content of social media posts and friendships to detect abnormal behavior. The detection unit can also analyze the user's social media activity history to detect abnormal behavior. For example, the detection unit detects abnormal behavior based on the social media activity history. Furthermore, the detection unit can detect anomalies in behavior with reference to the user's friendships on social media. For example, the detection unit detects abnormal behavior based on the friendships on social media. In this way, by analyzing social media activities, related data can be acquired, and the accuracy of detection can be improved. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit may use an AI system that analyzes social media activities and acquires related data.

[0046] When detecting incongruent behavior, the detection unit can customize the detection algorithm by reflecting the user's past feedback. The detection unit, for example, adjusts the detection algorithm based on feedback provided by the user in the past. For example, the detection unit analyzes the past feedback and customizes the detection algorithm. The detection unit can also relax the criteria for detecting incongruent behavior based on the user's past feedback. For example, the detection unit adjusts the detection algorithm based on the past feedback. The detection unit can also analyze the user's past feedback and apply an optimal detection algorithm. For example, the detection unit customizes the detection algorithm based on the past feedback. In this way, the detection algorithm is optimized by reflecting the past feedback, and detection accuracy is improved. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can use an AI system that customizes the detection algorithm based on past feedback.

[0047] When restricting ATM operations, the regulating unit can improve the accuracy of the restriction by referring to the user's past operation history. The regulating unit adjusts the restriction of ATM operations, for example, based on the user's past operation history. For example, the regulating unit refers to the date and time of past operations and the details of operations to detect abnormal operation patterns and implement the restriction. The regulating unit can also detect abnormal operation patterns from the user's past operation history and implement the restriction. For example, the regulating unit analyzes the past operation history, identifies abnormal operation patterns, and implements the restriction. Furthermore, the regulating unit can analyze the user's past operation history and apply an optimal restriction algorithm. For example, the regulating unit detects abnormal operation patterns based on the past operation history and applies an algorithm for the restriction. As a result, referring to the past operation history improves the accuracy of the restriction. Some or all of the above-described processing in the regulating unit may be performed using, for example, AI, or may be performed without using AI. For example, the regulating unit may use an AI system that detects abnormal operation patterns based on the past operation history and implements the restriction.

[0048] When restricting ATM operation, the regulating unit can apply different restriction algorithms depending on the user's age and gender. For example, if the user is elderly, the regulating unit relaxes the restrictions on ATM operation. For example, the regulating unit adjusts the restriction algorithm taking into account the behavioral patterns of elderly people. The regulating unit can also tighten the restrictions on ATM operation if the user is young. For example, the regulating unit adjusts the restriction algorithm taking into account the behavioral patterns of young people. Furthermore, the regulating unit can select an optimal restriction algorithm depending on the user's gender. For example, the regulating unit adjusts the restriction algorithm taking into account differences in the behavioral patterns of men and women. This improves the accuracy of the restrictions by applying a restriction algorithm depending on the user's age and gender. Some or all of the above-described processing in the regulating unit may be performed using, for example, AI, or may be performed without using AI. For example, the regulating unit may use an AI system that applies a restriction algorithm depending on the user's age and gender.

[0049] When restricting ATM operations, the regulating unit can improve the accuracy of the restriction by taking into account the user's operation speed and operation pattern. For example, the regulating unit restricts ATM operations when the user's operation speed is abnormally slow. For example, the regulating unit measures the average operation speed and restricts if it is below a certain threshold. The regulating unit can also restrict ATM operations when the user's operation pattern suddenly changes. For example, the regulating unit monitors the consistency of operations, detects sudden changes, and imposes restrictions. Furthermore, the regulating unit can analyze the user's operation speed and operation pattern in real time to improve the accuracy of the restriction. For example, the regulating unit monitors the operation speed and operation pattern in real time, detects abnormal operations, and imposes restrictions. In this way, the accuracy of the restriction is improved by taking the operation speed and operation pattern into consideration. Some or all of the above-mentioned processing in the regulating unit may be performed using, for example, AI, or may be performed without using AI. For example, the regulating unit can use an AI system that analyzes the operation speed and operation pattern in real time and imposes restrictions.

[0050] When restricting ATM operations, the regulating unit can improve the accuracy of the restriction by taking into account the user's geographical location information. For example, the regulating unit relaxes the restriction on ATM operations when the user uses an ATM near their home. For example, the regulating unit adjusts the restriction algorithm when the user uses an ATM near their home based on the geographical location information. The regulating unit can also tighten the restriction on ATM operations when the user uses an ATM at a travel destination. For example, the regulating unit adjusts the restriction algorithm when the user uses an ATM at a travel destination based on the geographical location information. Furthermore, the regulating unit can apply an optimal restriction algorithm based on the user's geographical location information. For example, the regulating unit learns the user's behavioral patterns based on the geographical location information and improves the accuracy of the restriction. As a result, the accuracy of the restriction is improved by taking the geographical location information into account. Some or all of the above-described processing in the regulating unit may be performed using, for example, AI, or may be performed without using AI. For example, the regulating unit may use an AI system that adjusts the restriction algorithm based on the geographical location information.

[0051] When restricting ATM operations, the regulating unit can analyze the user's social media activities and acquire related data. The regulating unit restricts ATM operations, for example, based on the user's public activity history on social media. For example, the regulating unit analyzes the content of posts and friendships on social media to detect abnormal operation patterns and then performs the restriction. The regulating unit can also analyze the user's social media activity history and detect abnormal operation patterns and then perform the restriction. For example, the regulating unit detects abnormal operation patterns based on the social media activity history and then performs the restriction. Furthermore, the regulating unit can also restrict ATM operations based on the user's social media friendships. For example, the regulating unit detects abnormal operation patterns based on the social media friendships and then performs the restriction. In this way, by analyzing social media activities, related data can be acquired and the accuracy of the restriction can be improved. Some or all of the above-described processing in the regulating unit may be performed using, for example, AI, or may be performed without using AI. For example, the regulating unit may use an AI system that analyzes social media activities and acquires related data.

[0052] When restricting ATM operations, the regulating unit can customize the restriction algorithm by reflecting past user feedback. The regulating unit, for example, adjusts the restriction algorithm based on feedback provided by the user in the past. For example, the regulating unit analyzes the past feedback and customizes the restriction algorithm. The regulating unit can also relax restrictions on ATM operations based on the user's past feedback. For example, the regulating unit adjusts the restriction algorithm based on the past feedback. Furthermore, the regulating unit can analyze the user's past feedback and apply an optimal restriction algorithm. For example, the regulating unit customizes the restriction algorithm based on the past feedback. In this way, the restriction algorithm is optimized by reflecting the past feedback, and the accuracy of the restriction is improved. Some or all of the above-described processing in the regulating unit may be performed using, for example, AI, or may be performed without using AI. For example, the regulating unit can use an AI system that customizes the restriction algorithm based on past feedback.

[0053] When changing to an interactive operation, the change unit can improve the accuracy of the interface by referring to the user's past operation history. The change unit, for example, adjusts the interactive interface based on the user's past operation history. For example, the change unit can suggest optimal questions by referring to past operation dates and times and operation contents. The change unit can also suggest optimal questions based on the user's past operation history. For example, the change unit can analyze the past operation history and provide an optimal interface. The change unit can also analyze the user's past operation history and provide an optimal interface. For example, the change unit adjusts the interactive interface based on the past operation history. As a result, the accuracy of the interface is improved by referring to the past operation history. Some or all of the above-described processing in the change unit may be performed using, for example, AI, or may be performed without using AI. For example, the change unit may use an AI system that adjusts the interface based on the past operation history.

[0054] When changing to an interactive operation, the change unit can apply a different interface depending on the age and gender of the user. For example, if the user is elderly, the change unit provides a simple, highly visible interface. For example, the change unit adjusts the interface taking into account the visual characteristics of elderly people. Furthermore, if the user is young, the change unit can also provide an interface including detailed information. For example, the change unit adjusts the interface taking into account the visual characteristics of young people. Furthermore, the change unit can select an optimal interface depending on the gender of the user. For example, the change unit adjusts the interface taking into account the differences in visual characteristics between men and women. This improves the accuracy of operation by applying an interface depending on the age and gender. Some or all of the above-described processing by the change unit may be performed using, for example, AI, or may be performed without using AI. For example, the change unit may use an AI system that applies an interface depending on the age and gender.

[0055] When changing to an interactive operation, the change unit can improve the accuracy of the interface by taking into account the user's operation speed and operation pattern. For example, the change unit adjusts the interactive interface when the user's operation speed is abnormally slow. For example, the change unit measures the average operation speed and adjusts the interface when it is below a certain threshold. The change unit can also adjust the interactive interface when the user's operation pattern suddenly changes. For example, the change unit monitors the consistency of the operation, detects a sudden change, and adjusts the interface. Furthermore, the change unit can analyze the user's operation speed and operation pattern in real time to improve the accuracy of the interface. For example, the change unit monitors the operation speed and operation pattern in real time and provides an optimal interface. This improves the accuracy of the interface by taking the operation speed and operation pattern into consideration. Some or all of the above-mentioned processing in the change unit may be performed using, for example, AI, or may be performed without using AI. For example, the change unit may use an AI system that analyzes the operation speed and operation pattern in real time and adjusts the interface.

[0056] When changing to an interactive operation, the change unit can improve the accuracy of the interface by taking into account the user's geographical location information. For example, the change unit adjusts the interactive interface when the user is using an ATM near their home. For example, the change unit adjusts the interface when the user is using an ATM near their home based on the geographical location information. The change unit can also adjust the interactive interface when the user is using an ATM at a travel destination. For example, the change unit adjusts the interface when the user is using an ATM at a travel destination based on the geographical location information. Furthermore, the change unit can provide an optimal interface based on the user's geographical location information. For example, the change unit learns the user's behavioral patterns based on the geographical location information and improves the accuracy of the interface. As a result, the accuracy of the interface is improved by taking the geographical location information into account. Some or all of the above-described processing in the change unit may be performed using, for example, AI, or may be performed without using AI. For example, the change unit may use an AI system that adjusts the interface based on the geographical location information.

[0057] When changing to an interactive operation, the change unit can analyze the user's social media activity and acquire related data. The change unit can adjust the interactive interface based on, for example, the user's public activity history on social media. For example, the change unit can analyze the content of posts and friendships on social media to suggest optimal questions. The change unit can also analyze the user's social media activity history to suggest optimal questions. For example, the change unit can provide an optimal interface based on the social media activity history. The change unit can also adjust the interactive interface by referring to the user's friendships on social media. For example, the change unit can suggest optimal questions based on the friendships on social media. In this way, by analyzing social media activity, relevant data can be acquired and the accuracy of the interface can be improved. Some or all of the above-described processing by the change unit can be performed using, for example, AI, or can be performed without using AI. For example, the change unit can use an AI system that analyzes social media activity and acquires relevant data.

[0058] When changing to an interactive operation, the change unit can customize the interface by reflecting the user's past feedback. The change unit, for example, adjusts the interactive interface based on feedback provided by the user in the past. For example, the change unit analyzes the past feedback and suggests optimal questions. The change unit can also suggest optimal questions based on the user's past feedback. For example, the change unit provides an optimal interface based on the past feedback. The change unit can also analyze the user's past feedback and provide an optimal interface. For example, the change unit adjusts the interactive interface based on the past feedback. This optimizes the interface by reflecting the past feedback, and improves the accuracy of operation. Some or all of the above-described processing in the change unit may be performed using, for example, AI, or may be performed without using AI. For example, the change unit may use an AI system that customizes the interface based on past feedback.

[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 authentication unit can also combine fingerprint and iris authentication in addition to facial authentication of the user. For example, when a user approaches an ATM, facial authentication and fingerprint authentication are performed simultaneously, and operation is permitted only if both authentications are successful. Furthermore, adding iris authentication can achieve even higher security. This combines multiple biometric authentications, improving authentication accuracy and security. Some or all of the above-mentioned processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit may use an AI system that combines fingerprint authentication and iris authentication.

[0061] The detection unit can also monitor the user's heart rate and galvanic skin response to detect abnormal behavior. For example, if the user's heart rate suddenly increases while operating an ATM, this is detected as abnormal behavior. The detection unit can also analyze the galvanic skin response to detect signs of stress or tension. Thus, monitoring the heart rate and galvanic skin response enables more accurate abnormality detection. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can use an AI system that monitors the heart rate and galvanic skin response.

[0062] The regulating unit can also refer to the user's past transaction history and detect abnormal transaction patterns. For example, if the user attempts to make a large transaction that is not normally performed, the regulating unit will stop the operation. The regulating unit can also stop the operation when the user is using an ATM that the user does not normally use. In this way, by referring to the past transaction history, abnormal transactions can be prevented in advance. Some or all of the above-mentioned processing in the regulating unit may be performed using, for example, AI, or may be performed without using AI. For example, the regulating unit may use an AI system that detects abnormal transactions based on the past transaction history.

[0063] The modification unit can provide an individually customized interactive interface based on the user's operation history. For example, it can prioritize and display operations that the user has frequently performed in the past, thereby improving operation efficiency. It can also analyze the user's operation history and suggest optimal questions. This provides an individually customized interface, thereby improving the accuracy and efficiency of operations. Some or all of the above-described processing in the modification unit may be performed using, for example, AI, or may be performed without using AI. For example, the modification unit can use an AI system that customizes the interface based on the operation history.

[0064] When changing to an interactive operation, the change unit can improve the accuracy of the interface by referring to the user's past operation history. For example, the change unit adjusts the interactive interface based on the user's past operation history. For example, the change unit can suggest optimal questions by referring to the date and time of past operations and the contents of operations. It can also suggest optimal questions from the user's past operation history. In this way, by referring to the past operation history, the accuracy of the interface is improved. Some or all of the above-mentioned processing in the change unit may be performed using, for example, AI, or may be performed without using AI. For example, the change unit can use an AI system that adjusts the interface based on the past operation history.

[0065] When changing to an interactive operation, the change unit can apply a different interface depending on the age and gender of the user. For example, if the user is elderly, a simple, highly visible interface is provided. For example, the change unit adjusts the interface taking into account the visual characteristics of elderly people. Also, if the user is young, an interface including detailed information can be provided. This improves the accuracy of operation by applying an interface depending on age and gender. Some or all of the above-described processing in the change unit may be performed using, for example, AI, or may be performed without using AI. For example, the change unit may use an AI system that applies an interface depending on age and gender.

[0066] The processing flow of the first embodiment will be briefly explained below.

[0067] Step 1: The authentication unit authenticates the user's face when operating the ATM. The authentication unit uses a facial recognition algorithm based on deep learning to analyze the user's face and compare it with registered facial data. For example, when a user approaches the ATM, a camera captures their face, and the facial recognition system analyzes it. Step 2: The detection unit detects abnormal behavior based on the facial data authenticated by the authentication unit. The detection unit detects patterns such as the user frequently looking around while operating the ATM, operating very slowly, or suddenly interrupting the operation. For example, the detection unit analyzes the user's eye movements and operation speed to detect abnormal behavior. Step 3: The restricting unit restricts ATM operation if the detecting unit detects abnormal behavior. The restricting unit stops operation if the face cannot be recognized. For example, operation is stopped if the face is obscured by a mask or sunglasses. Step 4: When ATM operations are restricted by the restricting unit, the modifying unit changes to an interactive interface. The modifying unit displays an interactive interface on the ATM screen, and the user proceeds with the operation by answering questions. For example, a question such as "Where should I transfer the funds?" is displayed, and the operation proceeds as the user answers.

[0068] (Example 2) An ATM fraud prevention system according to an embodiment of the present invention authenticates a user's face when operating an ATM, detects any abnormalities in their behavior, restricts the ATM operation, and changes the operation to an interactive mode. The ATM fraud prevention system prevents fraud by authenticating the user's face, detecting any abnormalities in their behavior, restricting the ATM operation, and changing the operation to an interactive mode. For example, in an ATM fraud prevention system, a camera captures the user's face when the user approaches an ATM, and a facial recognition system analyzes the captured image. The ATM fraud prevention system then uses an algorithm to detect patterns, such as the user frequently looking around while operating the ATM, operating abnormally slowly, or suddenly pausing. If the system cannot recognize the user's face, it automatically stops the operation. The ATM fraud prevention system then displays an interactive interface on the ATM screen, allowing the user to proceed with the operation by answering questions. For example, a question such as "Where would you like the transfer to?" is displayed, and the operation proceeds as the user responds. This allows the ATM fraud prevention system to prevent fraud before it occurs, since the user cannot answer interactive questions when a fraudster is instructing the victim to operate the ATM. Furthermore, if the face is unknown, the operation is stopped, thereby preventing fraudulent withdrawals. This allows the ATM fraud prevention system to authenticate the user's face, detect any abnormalities in their behavior, regulate ATM operations, and change them to interactive operations, thereby preventing fraud. For example, if a fraudster is instructing a victim to operate an ATM, the victim will not be able to answer interactive questions, preventing fraud before it occurs. Furthermore, if the face is unknown, the operation is stopped, thereby preventing fraudulent withdrawals.

[0069] An ATM fraud prevention system according to an embodiment includes an authentication unit, a detection unit, a restriction unit, and a change unit. The authentication unit authenticates a user's face when operating an ATM. The authentication unit analyzes the user's face using, for example, a facial recognition algorithm based on deep learning and compares it with registered facial data. For example, when a user approaches an ATM, a camera captures the user's face, and a facial recognition system analyzes it. The detection unit detects abnormal behavior based on the facial data authenticated by the authentication unit. The detection unit detects patterns such as the user frequently looking around while operating the ATM, operating very slowly, or suddenly interrupting the operation. For example, the detection unit analyzes the user's eye movements and operation speed to detect abnormal behavior. The restriction unit restricts ATM operation when the detection unit detects abnormal behavior. For example, the restriction unit stops operation when the user's face cannot be recognized. For example, the restriction unit stops operation when the user's face is obscured by a mask or sunglasses. The change unit changes to an interactive interface when the restriction unit restricts ATM operation. The change unit, for example, displays an interactive interface on the ATM screen, and the user proceeds with the operation by answering questions. For example, a question such as "Where should I transfer the money?" is displayed, and the operation proceeds as the user answers. In this way, the ATM fraud prevention system according to the embodiment can prevent fraud by authenticating the user's face, detecting any abnormality in their behavior, restricting ATM operation, and changing it to an interactive operation. For example, if a fraudster is instructing a victim to operate the ATM, the victim will not be able to answer the interactive questions, and fraud can be prevented before it occurs. Furthermore, if the face is unknown, the operation is stopped, thereby preventing fraudulent withdrawals.

[0070] The authentication unit may use a facial recognition algorithm that uses deep learning. Deep learning includes, but is not limited to, a convolutional neural network (CNN) and a recurrent neural network (RNN). The authentication unit may extract facial features using, for example, a CNN and compare them with registered facial data. The authentication unit may also use an RNN to analyze facial movements and changes in facial expression to improve authentication accuracy. For example, the authentication unit may use deep learning to extract facial features with high accuracy and improve authentication accuracy. This improves the accuracy of facial recognition. Some or all of the above-described processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit may use an AI system that performs facial recognition using a deep learning model.

[0071] The detection unit can detect patterns such as a user frequently looking around while operating an ATM, operating very slowly, or suddenly interrupting an operation. The detection unit, for example, tracks the user's eye movement and detects frequent looking around. For example, the detection unit analyzes eye movement patterns to detect abnormal behavior. The detection unit can also monitor the speed of operation and detect when the operation is very slow. For example, the detection unit measures the average speed of operation and detects abnormal behavior when it falls below a certain threshold. The detection unit can also monitor the continuity of operation to detect interruptions of operation. For example, the detection unit measures the duration of operation interruptions and detects abnormal behavior when the operation is interrupted for more than a certain period of time. This makes it easier to identify abnormal behavior by detecting user behavior patterns. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or without AI. For example, the detection unit can use an AI model that analyzes eye movement and operation speed.

[0072] The regulating unit can stop the operation if the face cannot be recognized. For example, the regulating unit stops the operation if the face is obscured by a mask or sunglasses. For example, the regulating unit stops the operation if part of the face is hidden or if the lighting conditions are poor. The regulating unit can also automatically stop the operation if the facial recognition system cannot recognize the face. For example, the regulating unit stops the operation if the facial recognition system cannot recognize the face within a certain period of time. In this way, by stopping the operation if the face cannot be recognized, it is possible to prevent unauthorized operation. Some or all of the above-mentioned processing in the regulating unit may be performed using, for example, AI, or may be performed without using AI. For example, the regulating unit can use an AI model that stops the operation based on the results of the facial recognition system.

[0073] The change unit can display an interactive interface on the ATM screen and allow the user to proceed with the operation by answering questions. The change unit can, for example, display an interactive interface on the ATM screen and allow the user to proceed with the operation by answering questions. For example, the change unit displays a question such as "Where should I transfer the money?" and the operation proceeds as the user answers. The change unit can also provide various interactive interfaces, such as voice dialogue and text-based question-and-answering. For example, the change unit can analyze a user's voice input using speech recognition technology and provide an interactive interface. The change unit can also use text-based question-and-answering to allow the user to proceed with the operation by entering questions on the screen. In this way, by displaying an interactive interface, the operation can proceed by the user answering questions. Some or all of the above-described processing by the change unit may be performed using, for example, AI, or may be performed without AI. For example, the change unit can use an AI system that provides an interactive interface using speech recognition technology or natural language processing technology.

[0074] The modification unit can stop the operation when the user cannot answer a question or when the answer is inaccurate. For example, the modification unit stops the operation when the user cannot answer a question within a certain time. For example, the modification unit stops the operation when the user does not answer a question within a certain time. The modification unit can also stop the operation when the user's answer is inaccurate. For example, the modification unit stops the operation when the user's answer does not match pre-registered information. This makes it possible to prevent fraud by stopping the operation when the user cannot answer a question or when the answer is inaccurate. Some or all of the above-mentioned processing by the modification unit may be performed using, for example, AI, or may be performed without using AI. For example, the modification unit can use an AI model that analyzes the user's answer and determines its accuracy.

[0075] The authentication unit can estimate the user's emotions and adjust the accuracy of facial recognition based on the estimated user emotions. The authentication unit, for example, analyzes the user's facial expressions to estimate emotions. For example, the authentication unit can analyze the user's facial expressions using facial recognition technology to estimate emotions such as tension, relaxation, and impatience. The authentication unit can also analyze the user's voice using voice analysis technology to estimate emotions. For example, the authentication unit can analyze the tone and speed of the voice to estimate emotions. The authentication unit can also adjust the accuracy of facial recognition based on the estimated emotions. For example, if the user is nervous, the tolerance range for facial recognition can be widened for authentication. Also, if the user is relaxed, the accuracy of facial recognition can be increased for authentication. In this way, adjusting the accuracy of facial recognition based on the user's emotions improves the accuracy of authentication. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit may use an AI system that estimates emotions using facial expression recognition technology or voice analysis technology and adjusts the accuracy of face authentication.

[0076] During facial recognition, the authentication unit can improve authentication accuracy by referring to the user's past authentication history. The authentication unit adjusts authentication accuracy, for example, based on the user's past authentication successes. For example, the authentication unit improves authentication accuracy by referring to past authentication dates and times and authentication results. The authentication unit can also expand the authentication tolerance range based on the user's past authentication failures. For example, the authentication unit analyzes the causes of past authentication failures and adjusts the authentication algorithm. Furthermore, the authentication unit can analyze the user's past authentication history and apply an optimal authentication algorithm. For example, the authentication unit learns the user's facial features based on the past authentication history and improves authentication accuracy. Thus, referring to the past authentication history improves authentication accuracy. Some or all of the above-described processing in the authentication unit may be performed using, for example, AI, or may be performed without AI. For example, the authentication unit can use an AI system that adjusts the authentication algorithm based on the past authentication history.

[0077] The authentication unit can apply different authentication algorithms depending on the user's age and gender during facial recognition. For example, if the user is elderly, the authentication unit widens the tolerance range for facial recognition. For example, the authentication unit adjusts the authentication algorithm taking into account the facial features of elderly people. The authentication unit can also improve the accuracy of facial recognition if the user is young. For example, the authentication unit adjusts the authentication algorithm taking into account the facial features of young people. Furthermore, the authentication unit can select the optimal authentication algorithm depending on the user's gender. For example, the authentication unit adjusts the authentication algorithm taking into account the differences in facial features between men and women. This improves the accuracy of authentication by applying an authentication algorithm depending on the user's age and gender. Some or all of the above-described processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit can use an AI system that applies an authentication algorithm depending on the user's age and gender.

[0078] The authentication unit can improve the accuracy of facial recognition by taking into account changes in the user's facial orientation and facial expression. For example, the authentication unit applies an algorithm that enables authentication even when the user's face is tilted. For example, the authentication unit adjusts the authentication algorithm by taking into account the rotation angle of the face. The authentication unit can also apply an algorithm that enables authentication even when the user's facial expression changes. For example, the authentication unit adjusts the authentication algorithm by taking into account patterns of facial expression change. Furthermore, the authentication unit can detect changes in the user's facial orientation and facial expression in real time and adjust the authentication accuracy. For example, the authentication unit monitors changes in facial orientation and facial expression in real time and adjusts the authentication algorithm. This improves the accuracy of authentication by taking changes in facial orientation and facial expression into account. Some or all of the above-described processing in the authentication unit may be performed using, for example, AI, or may be performed without AI. For example, the authentication unit can use an AI system that adjusts the authentication algorithm by taking changes in facial orientation and facial expression into account.

[0079] The authentication unit can estimate the user's emotions and determine the authentication priority based on the estimated user's emotions. The authentication unit, for example, analyzes the user's facial expression to estimate the emotions. For example, the authentication unit can analyze the user's facial expression using facial expression recognition technology to estimate emotions such as tension, relaxation, and impatience. The authentication unit can also analyze the user's voice using voice analysis technology to estimate the emotions. For example, the authentication unit can analyze the tone and speed of the voice to estimate the emotions. The authentication unit can also determine the authentication priority based on the estimated emotions. For example, if the user is nervous, the authentication priority can be set high. Also, if the user is relaxed, the authentication priority can be set low. This improves authentication efficiency by determining the authentication priority based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit may use an AI system that uses facial expression recognition technology or voice analysis technology to estimate emotions and determine authentication priorities.

[0080] The authentication unit can improve the accuracy of authentication by taking into account the user's geographical location information during facial recognition. For example, the authentication unit improves the accuracy of authentication when the user is using an ATM near their home. For example, the authentication unit adjusts the authentication algorithm based on the geographical location information when the user is using an ATM near their home. The authentication unit can also expand the tolerance range of authentication when the user is using an ATM at a travel destination. For example, the authentication unit adjusts the authentication algorithm based on the geographical location information when the user is using an ATM at a travel destination. The authentication unit can also apply an optimal authentication algorithm based on the user's geographical location information. For example, the authentication unit learns the user's facial features based on the geographical location information and improves the accuracy of authentication. As a result, the accuracy of authentication is improved by taking the geographical location information into consideration. Some or all of the above-described processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit can use an AI system that adjusts the authentication algorithm based on the geographical location information.

[0081] During facial recognition, the authentication unit can analyze the user's social media activities and obtain related authentication data. The authentication unit complements the authentication data, for example, based on a facial photo posted by the user on social media. For example, the authentication unit analyzes a facial photo posted on social media to complement the authentication data. The authentication unit can also analyze the user's social media activity history to improve authentication accuracy. For example, the authentication unit analyzes the content of posts and friendships on social media to complement the authentication data. Furthermore, the authentication unit can complement the authentication data by referring to the user's friendships on social media. For example, the authentication unit complements the authentication data based on friendships on social media. In this way, the authentication data is complemented by analyzing social media activities, improving authentication accuracy. Some or all of the above-described processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit can use an AI system that analyzes social media activities and complements authentication data.

[0082] The authentication unit can customize the authentication algorithm by reflecting the user's past feedback during facial recognition. The authentication unit adjusts the authentication algorithm, for example, based on feedback provided by the user in the past. For example, the authentication unit analyzes the past feedback and customizes the authentication algorithm. The authentication unit can also expand the authentication tolerance range based on the user's past feedback. For example, the authentication unit adjusts the authentication algorithm based on the past feedback. Furthermore, the authentication unit can analyze the user's past feedback and apply an optimal authentication algorithm. For example, the authentication unit customizes the authentication algorithm based on the past feedback. In this way, the authentication algorithm is optimized by reflecting the past feedback, and authentication accuracy is improved. Some or all of the above-described processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit can use an AI system that customizes the authentication algorithm based on past feedback.

[0083] The detection unit can estimate the user's emotion and adjust the criteria for detecting incongruent behavior based on the estimated user emotion. The detection unit, for example, analyzes the user's facial expression to estimate the emotion. For example, the detection unit can analyze the user's facial expression using facial expression recognition technology to estimate emotions such as tension, relaxation, and impatience. The detection unit can also analyze the user's voice using voice analysis technology to estimate the emotion. For example, the detection unit can analyze the tone and speed of the voice to estimate the emotion. The detection unit can also adjust the criteria for detecting incongruent behavior based on the estimated emotion. For example, if the user is nervous, the criteria for detecting incongruent behavior can be relaxed. Also, if the user is relaxed, the criteria for detecting incongruent behavior can be tightened. This improves the accuracy of detection by adjusting the criteria for detecting incongruent behavior based on the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit may use an AI system that estimates emotions using facial expression recognition technology or voice analysis technology and adjusts the criteria for detecting incongruent behavior.

[0084] When detecting an abnormality in behavior, the detection unit can improve the accuracy of detection by referring to the user's past operation history. The detection unit detects abnormality in behavior, for example, based on the user's past operation history. For example, the detection unit detects an abnormal operation pattern by referring to the date and time of past operations and the content of operations. The detection unit can also detect an abnormal operation pattern from the user's past operation history. For example, the detection unit analyzes the past operation history and identifies an abnormal operation pattern. Furthermore, the detection unit can analyze the user's past operation history and apply an optimal detection algorithm. For example, the detection unit applies an algorithm that detects an abnormal operation pattern based on the past operation history. In this way, by referring to the past operation history, the accuracy of detection is improved. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit may use an AI system that detects an abnormal operation pattern based on the past operation history.

[0085] When detecting incongruent behavior, the detection unit can apply different detection algorithms depending on the age and gender of the user. For example, if the user is elderly, the detection unit relaxes the criteria for detecting incongruent behavior. For example, the detection unit adjusts the detection algorithm taking into account the behavioral patterns of elderly people. Furthermore, if the user is young, the detection unit can tighten the criteria for detecting incongruent behavior. For example, the detection unit adjusts the detection algorithm taking into account the behavioral patterns of young people. Furthermore, the detection unit can select an optimal detection algorithm depending on the gender of the user. For example, the detection unit adjusts the detection algorithm taking into account differences in the behavioral patterns of men and women. In this way, by applying a detection algorithm depending on age and gender, the accuracy of detection is improved. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can use an AI system that applies a detection algorithm depending on age and gender.

[0086] When detecting abnormal behavior, the detection unit can improve the accuracy of detection by taking into account the user's operation speed and operation pattern. The detection unit detects abnormal behavior, for example, when the user's operation speed is abnormally slow. For example, the detection unit measures the average operation speed and detects it as abnormal if it is below a certain threshold. The detection unit can also detect abnormal behavior when the user's operation pattern suddenly changes. For example, the detection unit monitors the consistency of operations and detects sudden changes. Furthermore, the detection unit can analyze the user's operation speed and operation pattern in real time to improve the accuracy of detection. For example, the detection unit monitors the operation speed and operation pattern in real time to detect abnormal behavior. In this way, taking the operation speed and operation pattern into consideration improves the accuracy of detection. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can use an AI system that analyzes the operation speed and operation pattern in real time.

[0087] The detection unit can estimate the user's emotion and determine a priority for detecting incongruent behavior based on the estimated user's emotion. The detection unit, for example, analyzes the user's facial expression to estimate the emotion. For example, the detection unit can analyze the user's facial expression using facial expression recognition technology to estimate emotions such as tension, relaxation, and impatience. The detection unit can also analyze the user's voice using voice analysis technology to estimate the emotion. For example, the detection unit can analyze the tone and speed of the voice to estimate the emotion. The detection unit can also determine a priority for detecting incongruent behavior based on the estimated emotion. For example, if the user is nervous, the priority for detecting incongruent behavior can be set high. Also, if the user is relaxed, the priority for detecting incongruent behavior can be set low. This improves detection efficiency by determining the priority for detecting incongruent behavior based on the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit may use an AI system that estimates emotions using facial expression recognition technology or voice analysis technology and determines priorities for detecting incongruent behavior.

[0088] The detection unit can improve the accuracy of detection when detecting anomalies in behavior by taking into account the user's geographical location information. For example, the detection unit relaxes the criteria for detecting anomalies in behavior when the user uses an ATM near their home. For example, the detection unit adjusts the detection algorithm based on the geographical location information when the user uses an ATM near their home. The detection unit can also tighten the criteria for detecting anomalies in behavior when the user uses an ATM at a travel destination. For example, the detection unit adjusts the detection algorithm based on the geographical location information when the user uses an ATM at a travel destination. The detection unit can also apply an optimal detection algorithm based on the user's geographical location information. For example, the detection unit learns the user's behavioral patterns based on the geographical location information and improves the accuracy of detection. As a result, the accuracy of detection is improved by taking the geographical location information into account. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can use an AI system that adjusts the detection algorithm based on the geographical location information.

[0089] When detecting anomalies in behavior, the detection unit can analyze the user's social media activities and acquire related data. The detection unit detects anomalies in behavior, for example, based on the user's public activity history on social media. For example, the detection unit analyzes the content of social media posts and friendships to detect abnormal behavior. The detection unit can also analyze the user's social media activity history to detect abnormal behavior. For example, the detection unit detects abnormal behavior based on the social media activity history. Furthermore, the detection unit can detect anomalies in behavior with reference to the user's friendships on social media. For example, the detection unit detects abnormal behavior based on the friendships on social media. In this way, by analyzing social media activities, related data can be acquired, and the accuracy of detection can be improved. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit may use an AI system that analyzes social media activities and acquires related data.

[0090] When detecting incongruent behavior, the detection unit can customize the detection algorithm by reflecting the user's past feedback. The detection unit, for example, adjusts the detection algorithm based on feedback provided by the user in the past. For example, the detection unit analyzes the past feedback and customizes the detection algorithm. The detection unit can also relax the criteria for detecting incongruent behavior based on the user's past feedback. For example, the detection unit adjusts the detection algorithm based on the past feedback. The detection unit can also analyze the user's past feedback and apply an optimal detection algorithm. For example, the detection unit customizes the detection algorithm based on the past feedback. In this way, the detection algorithm is optimized by reflecting the past feedback, and detection accuracy is improved. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can use an AI system that customizes the detection algorithm based on past feedback.

[0091] The regulating unit can estimate the user's emotion and adjust the ATM operation restriction method based on the estimated user's emotion. The regulating unit, for example, analyzes the user's facial expression to estimate the emotion. For example, the regulating unit may analyze the user's facial expression using facial expression recognition technology to estimate emotions such as tension, relaxation, and impatience. The regulating unit can also analyze the user's voice using voice analysis technology to estimate the emotion. For example, the regulating unit may analyze the tone and speed of the voice to estimate the emotion. The regulating unit can then adjust the ATM operation restriction method based on the estimated emotion. For example, if the user is nervous, the ATM operation restriction can be relaxed. Alternatively, if the user is relaxed, the ATM operation restriction can be tightened. This improves the accuracy of the restriction by adjusting the ATM operation restriction method based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the regulating unit may be performed using, for example, AI, or may be performed without using AI. For example, the regulating unit may use an AI system that uses facial expression recognition technology or voice analysis technology to estimate emotions and adjust the method of regulating ATM operation.

[0092] When restricting ATM operations, the regulating unit can improve the accuracy of the restriction by referring to the user's past operation history. The regulating unit adjusts the restriction of ATM operations, for example, based on the user's past operation history. For example, the regulating unit refers to the date and time of past operations and the details of operations to detect abnormal operation patterns and implement the restriction. The regulating unit can also detect abnormal operation patterns from the user's past operation history and implement the restriction. For example, the regulating unit analyzes the past operation history, identifies abnormal operation patterns, and implements the restriction. Furthermore, the regulating unit can analyze the user's past operation history and apply an optimal restriction algorithm. For example, the regulating unit detects abnormal operation patterns based on the past operation history and applies an algorithm for the restriction. As a result, referring to the past operation history improves the accuracy of the restriction. Some or all of the above-described processing in the regulating unit may be performed using, for example, AI, or may be performed without using AI. For example, the regulating unit may use an AI system that detects abnormal operation patterns based on the past operation history and implements the restriction.

[0093] When restricting ATM operation, the regulating unit can apply different restriction algorithms depending on the user's age and gender. For example, if the user is elderly, the regulating unit relaxes the restrictions on ATM operation. For example, the regulating unit adjusts the restriction algorithm taking into account the behavioral patterns of elderly people. The regulating unit can also tighten the restrictions on ATM operation if the user is young. For example, the regulating unit adjusts the restriction algorithm taking into account the behavioral patterns of young people. Furthermore, the regulating unit can select an optimal restriction algorithm depending on the user's gender. For example, the regulating unit adjusts the restriction algorithm taking into account differences in the behavioral patterns of men and women. This improves the accuracy of the restrictions by applying a restriction algorithm depending on the user's age and gender. Some or all of the above-described processing in the regulating unit may be performed using, for example, AI, or may be performed without using AI. For example, the regulating unit may use an AI system that applies a restriction algorithm depending on the user's age and gender.

[0094] When restricting ATM operations, the regulating unit can improve the accuracy of the restriction by taking into account the user's operation speed and operation pattern. For example, the regulating unit restricts ATM operations when the user's operation speed is abnormally slow. For example, the regulating unit measures the average operation speed and restricts if it is below a certain threshold. The regulating unit can also restrict ATM operations when the user's operation pattern suddenly changes. For example, the regulating unit monitors the consistency of operations, detects sudden changes, and imposes restrictions. Furthermore, the regulating unit can analyze the user's operation speed and operation pattern in real time to improve the accuracy of the restriction. For example, the regulating unit monitors the operation speed and operation pattern in real time, detects abnormal operations, and imposes restrictions. In this way, the accuracy of the restriction is improved by taking the operation speed and operation pattern into consideration. Some or all of the above-mentioned processing in the regulating unit may be performed using, for example, AI, or may be performed without using AI. For example, the regulating unit can use an AI system that analyzes the operation speed and operation pattern in real time and imposes restrictions.

[0095] The regulating unit can estimate the user's emotion and determine the priority of ATM operation restriction based on the estimated emotion. The regulating unit, for example, analyzes the user's facial expression to estimate the emotion. For example, the regulating unit may use facial expression recognition technology to analyze the user's facial expression and estimate emotions such as tension, relaxation, and impatience. The regulating unit can also use voice analysis technology to analyze the user's voice and estimate the emotion. For example, the regulating unit may analyze the tone and speed of the voice to estimate the emotion. The regulating unit then determines the priority of ATM operation restriction based on the estimated emotion. For example, if the user is nervous, the regulating unit can set the priority of ATM operation restriction high. Also, if the user is relaxed, the regulating unit can set the priority of ATM operation restriction low. This improves the efficiency of the restriction by determining the priority of ATM operation restriction based on the user's emotion. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing by the regulating unit may be performed using, for example, AI, or may be performed without using AI. For example, the regulating unit may use an AI system that uses facial expression recognition technology or voice analysis technology to estimate emotions and determine the priority of regulating ATM operations.

[0096] When restricting ATM operations, the regulating unit can improve the accuracy of the restriction by taking into account the user's geographical location information. For example, the regulating unit relaxes the restriction on ATM operations when the user uses an ATM near their home. For example, the regulating unit adjusts the restriction algorithm when the user uses an ATM near their home based on the geographical location information. The regulating unit can also tighten the restriction on ATM operations when the user uses an ATM at a travel destination. For example, the regulating unit adjusts the restriction algorithm when the user uses an ATM at a travel destination based on the geographical location information. Furthermore, the regulating unit can apply an optimal restriction algorithm based on the user's geographical location information. For example, the regulating unit learns the user's behavioral patterns based on the geographical location information and improves the accuracy of the restriction. As a result, the accuracy of the restriction is improved by taking the geographical location information into account. Some or all of the above-described processing in the regulating unit may be performed using, for example, AI, or may be performed without using AI. For example, the regulating unit may use an AI system that adjusts the restriction algorithm based on the geographical location information.

[0097] When restricting ATM operations, the regulating unit can analyze the user's social media activities and acquire related data. The regulating unit restricts ATM operations, for example, based on the user's public activity history on social media. For example, the regulating unit analyzes the content of posts and friendships on social media to detect abnormal operation patterns and then performs the restriction. The regulating unit can also analyze the user's social media activity history and detect abnormal operation patterns and then perform the restriction. For example, the regulating unit detects abnormal operation patterns based on the social media activity history and then performs the restriction. Furthermore, the regulating unit can also restrict ATM operations based on the user's social media friendships. For example, the regulating unit detects abnormal operation patterns based on the social media friendships and then performs the restriction. In this way, by analyzing social media activities, related data can be acquired and the accuracy of the restriction can be improved. Some or all of the above-described processing in the regulating unit may be performed using, for example, AI, or may be performed without using AI. For example, the regulating unit may use an AI system that analyzes social media activities and acquires related data.

[0098] When restricting ATM operations, the regulating unit can customize the restriction algorithm by reflecting past user feedback. The regulating unit, for example, adjusts the restriction algorithm based on feedback provided by the user in the past. For example, the regulating unit analyzes the past feedback and customizes the restriction algorithm. The regulating unit can also relax restrictions on ATM operations based on the user's past feedback. For example, the regulating unit adjusts the restriction algorithm based on the past feedback. Furthermore, the regulating unit can analyze the user's past feedback and apply an optimal restriction algorithm. For example, the regulating unit customizes the restriction algorithm based on the past feedback. In this way, the restriction algorithm is optimized by reflecting the past feedback, and the accuracy of the restriction is improved. Some or all of the above-described processing in the regulating unit may be performed using, for example, AI, or may be performed without using AI. For example, the regulating unit can use an AI system that customizes the restriction algorithm based on past feedback.

[0099] The modification unit can estimate the user's emotion and adjust the interactive operation interface based on the estimated user emotion. The modification unit, for example, analyzes the user's facial expression to estimate the emotion. For example, the modification unit can analyze the user's facial expression using facial expression recognition technology to estimate emotions such as tension, relaxation, and impatience. The modification unit can also analyze the user's voice using voice analysis technology to estimate the emotion. For example, the modification unit can analyze the tone and speed of the voice to estimate the emotion. The modification unit can also adjust the interactive operation interface based on the estimated emotion. For example, if the user is nervous, a simple, highly visible interface can be provided. Also, if the user is relaxed, an interface including detailed information can be provided. This improves the accuracy of operation by adjusting the interface based on the user's emotion. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the modification unit may be performed using, for example, AI, or may be performed without using AI. For example, the modification unit may use an AI system that estimates emotions using facial expression recognition technology or voice analysis technology and adjusts the interactive operation interface.

[0100] When changing to an interactive operation, the change unit can improve the accuracy of the interface by referring to the user's past operation history. The change unit, for example, adjusts the interactive interface based on the user's past operation history. For example, the change unit can suggest optimal questions by referring to past operation dates and times and operation contents. The change unit can also suggest optimal questions based on the user's past operation history. For example, the change unit can analyze the past operation history and provide an optimal interface. The change unit can also analyze the user's past operation history and provide an optimal interface. For example, the change unit adjusts the interactive interface based on the past operation history. As a result, the accuracy of the interface is improved by referring to the past operation history. Some or all of the above-described processing in the change unit may be performed using, for example, AI, or may be performed without using AI. For example, the change unit may use an AI system that adjusts the interface based on the past operation history.

[0101] When changing to an interactive operation, the change unit can apply a different interface depending on the age and gender of the user. For example, if the user is elderly, the change unit provides a simple, highly visible interface. For example, the change unit adjusts the interface taking into account the visual characteristics of elderly people. Furthermore, if the user is young, the change unit can also provide an interface including detailed information. For example, the change unit adjusts the interface taking into account the visual characteristics of young people. Furthermore, the change unit can select an optimal interface depending on the gender of the user. For example, the change unit adjusts the interface taking into account the differences in visual characteristics between men and women. This improves the accuracy of operation by applying an interface depending on the age and gender. Some or all of the above-described processing by the change unit may be performed using, for example, AI, or may be performed without using AI. For example, the change unit may use an AI system that applies an interface depending on the age and gender.

[0102] When changing to an interactive operation, the change unit can improve the accuracy of the interface by taking into account the user's operation speed and operation pattern. For example, the change unit adjusts the interactive interface when the user's operation speed is abnormally slow. For example, the change unit measures the average operation speed and adjusts the interface when it is below a certain threshold. The change unit can also adjust the interactive interface when the user's operation pattern suddenly changes. For example, the change unit monitors the consistency of the operation, detects a sudden change, and adjusts the interface. Furthermore, the change unit can analyze the user's operation speed and operation pattern in real time to improve the accuracy of the interface. For example, the change unit monitors the operation speed and operation pattern in real time and provides an optimal interface. This improves the accuracy of the interface by taking the operation speed and operation pattern into consideration. Some or all of the above-mentioned processing in the change unit may be performed using, for example, AI, or may be performed without using AI. For example, the change unit may use an AI system that analyzes the operation speed and operation pattern in real time and adjusts the interface.

[0103] The modification unit can estimate the user's emotion and determine the priority of interactive operations based on the estimated user's emotion. The modification unit, for example, analyzes the user's facial expression to estimate the emotion. For example, the modification unit can analyze the user's facial expression using facial expression recognition technology to estimate emotions such as tension, relaxation, and impatience. The modification unit can also analyze the user's voice using voice analysis technology to estimate the emotion. For example, the modification unit can analyze the tone and speed of the voice to estimate the emotion. The modification unit can also determine the priority of interactive operations based on the estimated emotion. For example, if the user is nervous, the priority of interactive operations can be set high. Also, if the user is relaxed, the priority of interactive operations can be set low. This improves the efficiency of operations by determining the priority of interactive operations based on the user's emotion. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the modification unit may be performed using, for example, AI, or may be performed without using AI. For example, the modification unit may use an AI system that estimates emotions using facial expression recognition technology or voice analysis technology and determines the priority of interactive operations.

[0104] When changing to an interactive operation, the change unit can improve the accuracy of the interface by taking into account the user's geographical location information. For example, the change unit adjusts the interactive interface when the user is using an ATM near their home. For example, the change unit adjusts the interface when the user is using an ATM near their home based on the geographical location information. The change unit can also adjust the interactive interface when the user is using an ATM at a travel destination. For example, the change unit adjusts the interface when the user is using an ATM at a travel destination based on the geographical location information. Furthermore, the change unit can provide an optimal interface based on the user's geographical location information. For example, the change unit learns the user's behavioral patterns based on the geographical location information and improves the accuracy of the interface. As a result, the accuracy of the interface is improved by taking the geographical location information into account. Some or all of the above-described processing in the change unit may be performed using, for example, AI, or may be performed without using AI. For example, the change unit may use an AI system that adjusts the interface based on the geographical location information.

[0105] When changing to an interactive operation, the change unit can analyze the user's social media activity and acquire related data. The change unit can adjust the interactive interface based on, for example, the user's public activity history on social media. For example, the change unit can analyze the content of posts and friendships on social media to suggest optimal questions. The change unit can also analyze the user's social media activity history to suggest optimal questions. For example, the change unit can provide an optimal interface based on the social media activity history. The change unit can also adjust the interactive interface by referring to the user's friendships on social media. For example, the change unit can suggest optimal questions based on the friendships on social media. In this way, by analyzing social media activity, relevant data can be acquired and the accuracy of the interface can be improved. Some or all of the above-described processing by the change unit can be performed using, for example, AI, or can be performed without using AI. For example, the change unit can use an AI system that analyzes social media activity and acquires relevant data.

[0106] When changing to an interactive operation, the change unit can customize the interface by reflecting the user's past feedback. The change unit, for example, adjusts the interactive interface based on feedback provided by the user in the past. For example, the change unit analyzes the past feedback and suggests optimal questions. The change unit can also suggest optimal questions based on the user's past feedback. For example, the change unit provides an optimal interface based on the past feedback. The change unit can also analyze the user's past feedback and provide an optimal interface. For example, the change unit adjusts the interactive interface based on the past feedback. This optimizes the interface by reflecting the past feedback, and improves the accuracy of operation. Some or all of the above-described processing in the change unit may be performed using, for example, AI, or may be performed without using AI. For example, the change unit may use an AI system that customizes the interface based on past feedback. === Hard Collateral 1-1 === Each of the multiple elements including the authentication unit, detection unit, regulation unit, and change unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the authentication unit captures the user's face using the camera 42 of the smart device 14, and the specific processing unit 290 of the data processing device 12 executes a face recognition algorithm. For example, the detection unit analyzes the user's behavior using the specific processing unit 290 of the data processing device 12 and detects an abnormal pattern. For example, the regulation unit stops the operation when the specific processing unit 290 of the data processing device 12 detects an abnormality. For example, the change unit displays an interactive interface on the display 40A of the smart device 14, and the user proceeds with the operation by answering questions. === Hard Collateral 1-2 === Each of the multiple elements including the above-described authentication unit, detection unit, regulation unit, and change unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the authentication unit captures the user's face using the camera 42 of the smart glasses 214 and executes a face recognition algorithm by the specific processing unit 290 of the data processing device 12. For example, the detection unit analyzes the user's behavior by the specific processing unit 290 of the data processing device 12 and detects an abnormal pattern. For example, the regulation unit stops the operation when the specific processing unit 290 of the data processing device 12 detects an abnormality. For example, the change unit displays an interactive interface on the display of the smart glasses 214 and allows the user to proceed with the operation by answering questions. === Hard Collateral 1-3 === Each of the multiple elements including the above-described authentication unit, detection unit, regulation unit, and change unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the authentication unit captures the user's face using the camera 42 of the headset type terminal 314, and the specific processing unit 290 of the data processing device 12 executes a face recognition algorithm. For example, the detection unit analyzes the user's behavior using the specific processing unit 290 of the data processing device 12 and detects an abnormal pattern. For example, the regulation unit stops the operation when the specific processing unit 290 of the data processing device 12 detects an abnormality. For example, the change unit displays an interactive interface on the display 343 of the headset type terminal 314, and the operation proceeds by the user answering questions. === Hard Collateral 1-4 === Each of the multiple elements including the authentication unit, detection unit, regulation unit, and change unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the authentication unit captures the user's face using the camera 42 of the robot 414, and the specific processing unit 290 of the data processing device 12 executes a face recognition algorithm. For example, the detection unit analyzes the user's behavior using the specific processing unit 290 of the data processing device 12 and detects an abnormal pattern. For example, the regulation unit stops the operation when the specific processing unit 290 of the data processing device 12 detects an abnormality. For example, the change unit displays an interactive interface on the display of the robot 414, and the user proceeds with the operation by answering questions.

[0107] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0108] The authentication unit can also combine fingerprint and iris authentication in addition to facial authentication of the user. For example, when a user approaches an ATM, facial authentication and fingerprint authentication are performed simultaneously, and operation is permitted only if both authentications are successful. Furthermore, adding iris authentication can achieve even higher security. This combines multiple biometric authentications, improving authentication accuracy and security. Some or all of the above-mentioned processing in the authentication unit may be performed using, for example, AI, or may be performed without using AI. For example, the authentication unit may use an AI system that combines fingerprint authentication and iris authentication.

[0109] The detection unit can also monitor the user's heart rate and galvanic skin response to detect abnormal behavior. For example, if the user's heart rate suddenly increases while operating an ATM, this is detected as abnormal behavior. The detection unit can also analyze the galvanic skin response to detect signs of stress or tension. Thus, monitoring the heart rate and galvanic skin response enables more accurate abnormality detection. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can use an AI system that monitors the heart rate and galvanic skin response.

[0110] The regulating unit can also refer to the user's past transaction history and detect abnormal transaction patterns. For example, if the user attempts to make a large transaction that is not normally performed, the regulating unit will stop the operation. The regulating unit can also stop the operation when the user is using an ATM that the user does not normally use. In this way, by referring to the past transaction history, abnormal transactions can be prevented in advance. Some or all of the above-mentioned processing in the regulating unit may be performed using, for example, AI, or may be performed without using AI. For example, the regulating unit may use an AI system that detects abnormal transactions based on the past transaction history.

[0111] The modification unit can provide an individually customized interactive interface based on the user's operation history. For example, it can prioritize and display operations that the user has frequently performed in the past, thereby improving operation efficiency. It can also analyze the user's operation history and suggest optimal questions. This provides an individually customized interface, thereby improving the accuracy and efficiency of operations. Some or all of the above-described processing in the modification unit may be performed using, for example, AI, or may be performed without using AI. For example, the modification unit can use an AI system that customizes the interface based on the operation history.

[0112] The authentication unit can estimate the user's emotions and adjust the difficulty of authentication based on the estimated emotions. For example, if the user is nervous, the authentication tolerance can be widened to make authentication easier. Also, if the user is relaxed, the authentication accuracy can be increased. This adjusts the authentication difficulty according to the user's emotions, improving authentication accuracy and usability. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the authentication unit can be performed using AI, or without AI. For example, the authentication unit can use an AI system that estimates emotions using facial expression recognition technology or voice analysis technology and adjusts the difficulty of authentication.

[0113] The detection unit can estimate the user's emotions and adjust the criteria for detecting abnormal behavior based on the estimated emotions. For example, if the user is nervous, the criteria for detecting abnormal behavior can be relaxed. Also, if the user is relaxed, the criteria for detecting abnormal behavior can be tightened. This improves detection accuracy by adjusting the criteria for detecting abnormal behavior based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the detection unit can be performed using, for example, AI, or without AI. For example, the detection unit can use an AI system that estimates emotions using facial expression recognition technology or voice analysis technology and adjusts the criteria for detecting abnormal behavior.

[0114] The regulating unit can estimate the user's emotions and adjust the method of regulating ATM operation based on the estimated emotions. For example, if the user is nervous, the restriction on ATM operation can be relaxed. On the other hand, if the user is relaxed, the restriction on ATM operation can be tightened. This improves the accuracy of the regulation by adjusting the method of regulating ATM operation based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the regulating unit can be performed using AI, for example, or without AI. For example, the regulating unit can use an AI system that estimates emotions using facial expression recognition technology or voice analysis technology and adjusts the method of regulating ATM operation.

[0115] The modification unit can estimate the user's emotions and adjust the interactive operation interface based on the estimated emotions. For example, if the user is nervous, a simple, highly visible interface can be provided. Alternatively, if the user is relaxed, an interface containing detailed information can be provided. By adjusting the interface based on the user's emotions, the accuracy of the operation can be improved. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the modification unit can be performed using, for example, AI, or without AI. For example, the modification unit can use an AI system that estimates emotions using facial expression recognition technology or voice analysis technology and adjusts the interactive operation interface.

[0116] When changing to an interactive operation, the change unit can improve the accuracy of the interface by referring to the user's past operation history. For example, the change unit adjusts the interactive interface based on the user's past operation history. For example, the change unit can suggest optimal questions by referring to the date and time of past operations and the contents of operations. It can also suggest optimal questions from the user's past operation history. In this way, by referring to the past operation history, the accuracy of the interface is improved. Some or all of the above-mentioned processing in the change unit may be performed using, for example, AI, or may be performed without using AI. For example, the change unit can use an AI system that adjusts the interface based on the past operation history.

[0117] When changing to an interactive operation, the change unit can apply a different interface depending on the age and gender of the user. For example, if the user is elderly, a simple, highly visible interface is provided. For example, the change unit adjusts the interface taking into account the visual characteristics of elderly people. Also, if the user is young, an interface including detailed information can be provided. This improves the accuracy of operation by applying an interface depending on age and gender. Some or all of the above-described processing in the change unit may be performed using, for example, AI, or may be performed without using AI. For example, the change unit may use an AI system that applies an interface depending on age and gender.

[0118] The processing flow of the second embodiment will be briefly explained below.

[0119] Step 1: The authentication unit authenticates the user's face when operating the ATM. The authentication unit uses a facial recognition algorithm based on deep learning to analyze the user's face and compare it with registered facial data. For example, when a user approaches the ATM, a camera captures their face, and the facial recognition system analyzes it. Step 2: The detection unit detects abnormal behavior based on the facial data authenticated by the authentication unit. The detection unit detects patterns such as the user frequently looking around while operating the ATM, operating very slowly, or suddenly interrupting the operation. For example, the detection unit analyzes the user's eye movements and operation speed to detect abnormal behavior. Step 3: The restricting unit restricts ATM operation if the detecting unit detects abnormal behavior. The restricting unit stops operation if the face cannot be recognized. For example, operation is stopped if the face is obscured by a mask or sunglasses. Step 4: When ATM operations are restricted by the restricting unit, the modifying unit changes to an interactive interface. The modifying unit displays an interactive interface on the ATM screen, and the user proceeds with the operation by answering questions. For example, a question such as "Where should I transfer the funds?" is displayed, and the operation proceeds as the user answers.

[0120] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0121] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0122] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0123] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0124] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0125] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0126] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0127] 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.

[0128] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0129] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0130] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0131] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0132] 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.

[0133] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0134] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0135] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0136] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0137] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0138] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0139] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0140] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0141] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0142] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0143] 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.

[0144] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0145] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0146] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0147] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0148] 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.

[0149] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0150] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0151] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0152] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0153] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0154] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0155] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0156] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0157] 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.

[0158] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0159] 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.

[0160] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0161] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0162] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0163] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0164] 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.

[0165] 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.

[0166] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0167] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0168] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0169] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0170] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0171] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0172] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0173] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0174] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0175] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0176] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0177] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0178] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0179] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0180] 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.

[0181] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0182] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0183] 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.

[0184] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0185] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0186] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0187] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0188] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0189] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0190] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0191] [Explanation of symbols]

[0192] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an authentication unit that authenticates the user's face when operating the ATM; a detection unit that detects abnormal behavior based on face data authenticated by the authentication unit; a regulation unit that regulates ATM operations when abnormal behavior is detected by the detection unit; a change unit that changes the interface to an interactive interface when the ATM operation is restricted by the restriction unit. A system characterized by:

2. The authentication unit Uses deep learning facial recognition algorithms 2. The system of claim 1.

3. The detection unit Detect patterns such as users frequently looking around while operating the ATM, operating very slowly, or suddenly stopping operations 2. The system of claim 1.

4. The restriction portion is Stop operation if face is not recognized 2. The system of claim 1.

5. The change unit An interactive interface is displayed on the ATM screen, and the user can proceed with the operation by answering questions.

2. The system of claim 1.

6. The change unit Stop the interaction if the user cannot answer the question or answers it incorrectly 2. The system of claim 1.

7. The authentication unit Estimate the user's emotions and adjust the accuracy of facial recognition based on the estimated user emotions.

2. The system of claim 1.

8. The authentication unit During facial recognition, the accuracy of authentication is improved by referencing the user's past authentication history.

2. The system of claim 1.

Images