Payment information anti-theft method and device, storage medium and computer equipment
The infrared noise floor value is obtained and optimized through the TOF sensor, depth information is constructed and feature information is compared, which solves the problem of unrecognizable malicious devices in the prior art, and achieves stable detection and efficient anti-theft effect in different environments.
Patent Information
- Application Number
- CN202411353632.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-25
- Publication Date
- 2024-12-31
AI Technical Summary
The prior art cannot accurately identify malicious electronic devices hidden inside the device, resulting in theft of payment information of users during transactions, and infrared detection is easily affected by environmental factors, making it difficult to form a unified and reliable detection standard.
The TOF sensor obtains the current noise floor value when the payment application is started, optimizes the infrared emission range, builds the depth information of the detected object, and compares it with the pre-stored password keyboard feature information. If it does not match, stop the transaction process to ensure that it is in different environments Stable detection is provided to reduce false alarms and missed reports.
Effectively detect malicious electronic devices attached to the real keyboard, improve the anti-theft efficiency of user payment information, provide higher level of privacy protection, reduce the risk of payment information being stolen, and is not affected by environmental factors and user observation angles .
Smart Images
Figure CN119228376A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of transaction security technology, and in particular to a payment information theft prevention method, device, storage medium and computer equipment. Background Art
[0002] As mobile payments become increasingly popular, users' transaction payment information is not only a key factor in completing transactions, but also directly related to users' property safety and personal privacy. In order to protect users' payment information from being stolen during transactions, a privacy shield can be installed on the transaction terminal. However, the protection effect of the privacy shield is limited by the viewing angle and distance, and the privacy protection level is relatively low. In particular, malicious devices hidden inside the device that are difficult to detect with the naked eye, such as miniature cameras or fake keyboards, can silently capture users' payment information.
[0003] To address the risks posed by malicious devices, infrared cameras combined with advanced algorithms can be used to detect foreign objects. However, this method requires the resolution and sensitivity of the infrared camera to reach extremely high levels in order to accurately capture tiny foreign objects hidden inside the device. At the same time, infrared detection is easily affected by environmental factors such as temperature, humidity, and light, resulting in frequent false alarms or missed alarms. In addition, due to the different thermal radiation characteristics of different devices, it is difficult to form a unified and reliable detection standard for this technology.
[0004] It can be seen from this that the existing technology is unable to accurately identify malicious electronic devices, which may result in the user's payment information being stolen and misused during transactions. Summary of the invention
[0005] The purpose of this application is to solve at least one of the above-mentioned technical defects, especially the technical defect that the prior art cannot accurately identify malicious electronic devices, thereby causing the user's payment information to be stolen and misused during transactions.
[0006] In a first aspect, the present application provides a payment information theft prevention method, the method comprising:
[0007] When the payment application is started, the current background noise value of the TOF sensor in the current environment is obtained. The TOF sensor is set on the side of the PIN keyboard, and the infrared emission range of the TOF sensor covers the PIN keyboard;
[0008] If the current background noise value does not meet the preset background noise value threshold, the TOF sensor is optimized according to the preset background noise value threshold;
[0009] When the current background noise value meets the preset background noise value threshold, the TOF sensor is triggered to emit multiple infrared rays, so that the TOF sensor constructs the depth information of the detected object according to the flight time of each infrared ray, and the detected object is the object that arrives first after the infrared ray is emitted;
[0010] The depth information of the detected object is compared with the characteristic information of the pre-stored PIN pad. If it is determined that the detected object is not the PIN pad, the transaction process in the payment application is stopped.
[0011] In one embodiment, after the step of obtaining the current background noise value of the TOF sensor in the current environment, the method further includes:
[0012] The current background noise value is preprocessed, and the preprocessed background noise value is analyzed to determine whether the current background noise value meets the preset background noise value threshold.
[0013] In one embodiment, the step of optimizing the TOF sensor according to the preset noise floor threshold includes:
[0014] According to the preset background noise threshold, a deep learning algorithm is used to determine the optimal gain value and optimal compensation value of the TOF sensor, and trigger TOF to perform gain adjustment and compensation correction.
[0015] In one embodiment, the step of comparing the depth information of the detected object with the pre-stored characteristic information of the password keyboard includes:
[0016] Determine the attribute of each first information in the depth information of the detected object, and determine the attribute of each second information in the pre-stored characteristic information of the PIN pad;
[0017] A one-to-one correspondence is established between the depth information of the detected object and the information of the same attribute in the pre-stored characteristic information of the password keyboard, and the first information and the second information with the established correspondence are compared one-to-one.
[0018] In one embodiment, the method further comprises:
[0019] If it is determined that the detected object is not a password keyboard, an early warning signal is issued.
[0020] In one embodiment, the method further comprises:
[0021] If the detected object is determined to be a password keyboard, the TOF sensor is used to verify the user's hand movements;
[0022] When it is determined that the user's hand movement is an abnormal key gesture, the transaction process of the payment application is stopped and a key error prompt message is generated.
[0023] In one embodiment, the step of verifying the user's hand movement by using a TOF sensor includes:
[0024] Trigger the TOF sensor to continuously emit multiple infrared rays, so that the TOF sensor can continuously construct the depth information of the password keyboard and the user's hand;
[0025] Determine the background model corresponding to the password keyboard, and identify the user's hand movements based on the difference in depth information of the password keyboard and the user's hand relative to the background model;
[0026] The user's hand movement is compared with the pre-stored normal key gesture to verify whether the user's hand movement is a normal key gesture.
[0027] In a second aspect, the present application provides a payment information anti-theft device, the device comprising:
[0028] A noise floor value acquisition module is used to acquire the current noise floor value of the TOF sensor in the current environment when the payment application is started. The TOF sensor is arranged on the side of the PIN keyboard, and the infrared emission range of the TOF sensor covers the PIN keyboard.
[0029] A sensor optimization module, used to optimize the TOF sensor according to the preset noise floor value threshold if the current noise floor value does not meet the preset noise floor value threshold;
[0030] A depth information building module is used to trigger the TOF sensor to emit multiple infrared rays when the current background noise value meets the preset background noise value threshold, so that the TOF sensor builds the depth information of the detected object according to the flight time of each infrared ray, and the detected object is the object that arrives first after the infrared ray is emitted;
[0031] The information comparison module is used to compare the depth information of the detected object with the characteristic information of the pre-stored PIN pad. If it is determined that the detected object is not the PIN pad, the transaction process in the payment application is stopped.
[0032] In a third aspect, the present application provides a storage medium: the storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the payment information anti-theft method in any of the above embodiments.
[0033] In a fourth aspect, the present application provides a computer device, comprising: one or more processors, and a memory;
[0034] The memory stores computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the steps of the payment information anti-theft method in any of the above embodiments are performed.
[0035] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:
[0036] In the payment information anti-theft method, device, storage medium and computer equipment provided by the present application, since the side position of the password keyboard is very limited, the encryption circuit is generally not placed. The TOF sensor is set on the side of the password keyboard without causing signal interference, and the side placement makes it difficult for dust to fall and gather, thereby avoiding the TOF sensor's transceiver function from being affected. The infrared emission range of the TOF sensor covers the password keyboard, so that the environment around the password keyboard can be fully monitored, hidden malicious electronic devices can be effectively detected, and the user's payment information can be prevented from being maliciously stolen when input, thereby improving the security of the transaction. The current background noise value of the TOF sensor is obtained, and when the current background noise value does not meet the preset background noise value threshold, the TOF sensor is optimized so that the current background noise value meets the preset background noise value threshold to ensure that the TOF sensor can work stably in different light and humidity environments, and the TOF sensor is not limited to the temperature of the object itself, therefore, adjusting the background noise value can reduce the impact of environmental factors and reduce false alarms and missed alarms. By comparing the depth information of the detected object with the characteristic information of the PIN pad, the false alarm rate can be reduced, and when it is confirmed that the detected object is not a PIN pad, the transaction process of the payment application is automatically stopped, which improves the efficiency of preventing theft of user payment information. In this way, malicious electronic devices attached to real keyboards can be effectively detected without relying on the user's observation angle and being affected by environmental factors, providing a higher level of privacy protection and reducing the risk of payment information being stolen. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0038] Figure 1 A schematic diagram of a payment information anti-theft method provided in an embodiment of the present application;
[0039] Figure 2 A schematic diagram of the installation of a TOF sensor provided in an embodiment of the present application;
[0040] Figure 3 A schematic diagram of the structure of a payment information anti-theft device provided in an embodiment of the present application;
[0041] Figure 4 A schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0042] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0043] The present application provides a payment information theft prevention method. The following embodiments are described by taking the method applied to a computer device as an example. It can be understood that the computer device can be any device with data processing functions, including but not limited to a single server, a server cluster, a personal laptop computer, a desktop computer, etc. Figure 1 As shown, the method includes:
[0044] S101: When the payment application is started, a current background noise value of the TOF sensor in the current environment is obtained, the TOF sensor is arranged on the side of the PIN keyboard, and the infrared emission range of the TOF sensor covers the PIN keyboard.
[0045] Among them, payment applications refer to software applications used to process payment transactions, such as mobile payment, online banking applications, etc., which allow users to transfer money, pay bills, view transaction records, etc. A TOF sensor (Time-of-Flight Sensor) is a sensor used to measure the distance between an object and a sensor. It calculates the distance by emitting infrared or laser pulses and measuring the time it takes for these pulses to be reflected back. In signal processing, the background noise refers to the level of background noise generated inside a system or device when there is no useful signal. In the current environment, the background noise value of a TOF sensor refers to the level of noise signal received by the sensor when there are no external objects reflecting its infrared rays. A password keyboard is a special input device designed to securely enter passwords.
[0046] In this step, after the payment application is started, the TOF sensor is initialized to ensure that it is in working state and ready to receive data. Specifically, a command is sent to the TOF sensor, requiring it to only monitor the ambient noise without activating infrared emission, and read and record the ambient noise value returned by the TOF sensor.
[0047] It can be understood that understanding the background noise value of the TOF sensor in the current environment helps to eliminate or compensate for this part of the noise during use to ensure that these detection processes are not interfered by environmental noise, thereby improving the accuracy and reliability of the detection.
[0048] It should be noted that placing the TOF sensor on the side of the PIN pad can prevent it from directly blocking the user's line of sight or interfering with the user's input operation, so that the user will not feel uncomfortable or encounter any physical obstacles when using the PIN pad. The side setting also helps to improve security. For example, when an object, such as a fraud tool or another hand, is detected approaching the PIN pad without authorization, the TOF sensor can immediately trigger an alarm or take other security measures.
[0049] The infrared emission range of the TOF sensor covers the area of the PIN pad, which means that no matter where the user enters the password on the PIN pad, or where the malicious electronic device is attached to the PIN pad, the TOF sensor can receive the infrared reflection signal from that position. At the same time, through comprehensive coverage, the TOF sensor can more accurately measure the distance between the user's finger and abnormal objects, effectively identify gestures and prevent fraud. Figure 2 shown.
[0050] S102: If the current noise floor value does not meet the preset noise floor value threshold, the TOF sensor is optimized according to the preset noise floor value threshold.
[0051] In this step, the detected current background noise value is compared with the preset background noise value threshold. If the current background noise value does not meet the preset threshold, that is, exceeds or falls below the threshold value, it means that the TOF sensor is affected by environmental noise such as light and humidity. Relevant instructions can be sent to the TOF sensor to trigger automatic optimization of the TOF sensor, or the TOF sensor can be optimized through algorithms on computer equipment software. For example, adjust the sensitivity of the sensor to reduce or increase the detection capability of weak signals; adjust the gain setting to amplify or attenuate the received signal strength; apply more complex filtering algorithms to filter out noise signals and improve the signal-to-noise ratio; correct the calibration parameters of the sensor to ensure the accuracy of the measurement results; and adjust the exposure time to meet the recognition accuracy.
[0052] It can be understood that the background noise value is one of the important factors affecting the measurement accuracy of the TOF sensor. By ensuring that the background noise value is within the preset threshold range, the impact of noise on the measurement results can be minimized, thereby improving the accuracy and reliability of the measurement. In payment scenarios, any tiny error may affect security. By ensuring the measurement accuracy and reliability of the TOF sensor, fraud and other security threats can be better prevented.
[0053] Furthermore, strong light or weak light contains light of different wavelengths, which will interfere with the specific wavelength of light that the TOF sensor can identify, causing the current noise floor value to exceed the preset noise floor value threshold. Based on this, the TOF sensor is optimized according to the actual situation to ensure that the current noise floor value meets the preset noise floor value threshold, so that the TOF sensor can operate stably in both strong light and weak light.
[0054] S103: When the current background noise value meets the preset background noise value threshold, trigger the TOF sensor to emit multiple infrared rays, so that the TOF sensor constructs depth information of the detected object according to the flight time of each infrared ray, and the detected object is the object that arrives first after the infrared ray is emitted.
[0055] Depth information refers to the distance information between the object and the sensor calculated and obtained by measuring the time required for the light signal to be emitted from the sensor and reflected by the object and then returned to the sensor. The distance information constitutes the depth map of the object in three-dimensional space, that is, the depth information. The detection object refers to the object that first reaches and reflects back to the sensor after the infrared light is emitted, and is the target measured by the TOF sensor.
[0056] In this step, under the condition that the current background noise value meets the background noise value threshold, the TOF sensor is controlled to emit multiple infrared rays, which are emitted at different angles or patterns to cover a wider detection area or improve the accuracy of the measurement. For each infrared ray emitted, the TOF sensor measures the flight time required from emission to reflection from the detected object and then returning to the sensor. The flight time data of all infrared rays are collected and used to construct the depth information of the detected object, that is, the flight time is converted into the distance between the object and the sensor, and the three-dimensional shape or position of the object is constructed.
[0057] It can be understood that by emitting multiple infrared rays and measuring their flight time, more data points about the detected object can be obtained, thereby more accurately constructing the depth information of the object. At the same time, in a complex environment, there may be multiple objects or interference sources. By emitting multiple infrared rays and processing these data in different ways, it is possible to better distinguish between the detected object and background noise, and improve the robustness of the measurement.
[0058] S104: Compare the depth information of the detected object with the pre-stored characteristic information of the PIN pad. If it is determined that the detected object is not the PIN pad, stop the transaction process in the payment application.
[0059] Among them, the characteristic information refers to the distance, shape outline, surface texture, size, material characteristics, temperature information, movement status, etc. of the password keyboard.
[0060] In this step, the depth information of the detected object is compared with the pre-stored characteristic information of the PIN pad to accurately determine whether the detected object matches the characteristics of the PIN pad. If the comparison result shows that the detected object is not the PIN pad, the transaction process in the payment application will be stopped. If the comparison is successful, the transaction process will continue.
[0061] It is understandable that fraudsters may attempt to use forged or unauthorized password input devices to steal user information or conduct illegal transactions. By comparing the depth information to verify the authenticity of the password input device, malicious or forged devices can be prevented from being used for payment transactions, thereby protecting the user's financial security and privacy information.
[0062] Furthermore, when the current background noise value meets the preset background noise value threshold, foreign object detection will be performed immediately, and the TOF sensor is not affected by the temperature, shape and material of the detected object itself. Therefore, if the user starts to enter the password or performs other operations during the detection, causing the password keyboard to be blocked by hands or other objects, it can quickly detect and determine the presence of foreign objects, making the payment application unable to conduct transactions normally.
[0063] In the above embodiment, since the side position of the password keyboard is very limited, the encryption circuit is generally not placed. The TOF sensor is arranged on the side of the password keyboard without causing signal interference, and the side placement makes it difficult for dust to fall and gather, thereby avoiding the TOF sensor's transceiver function from being affected. The infrared emission range of the TOF sensor covers the password keyboard, so that the environment around the password keyboard can be fully monitored, and hidden malicious electronic devices can be effectively detected to prevent the user's payment information from being maliciously stolen when input, thereby improving the security of the transaction. The current background noise value of the TOF sensor is obtained, and when the current background noise value does not meet the preset background noise value threshold, the TOF sensor is optimized so that the current background noise value meets the preset background noise value threshold to ensure that the TOF sensor can work stably in different environments, and the TOF sensor is not limited to the temperature of the detected object itself, therefore, adjusting the background noise value can reduce the influence of environmental factors and reduce the situation of false alarms and missed alarms. By comparing the depth information of the detected object with the characteristic information of the password keyboard, the false alarm rate can be reduced, and when it is confirmed that the detected object is not the password keyboard, the transaction process of the payment application is automatically stopped, thereby improving the efficiency of preventing theft of user payment information. In this way, malicious electronic devices attached to a real keyboard can be effectively detected without relying on the user's observation angle and being affected by environmental factors, providing a higher level of privacy protection and reducing the risk of payment information being stolen.
[0064] In one embodiment, after the step of obtaining the current background noise value of the TOF sensor in the current environment, the following steps are included:
[0065] The current background noise value is preprocessed, and the preprocessed background noise value is analyzed to determine whether the current background noise value meets the preset background noise value threshold.
[0066] Specifically, preprocessing refers to a series of processing steps performed on raw data before data analysis, aiming to improve data quality, reduce noise interference, extract useful information, etc. In this embodiment, preprocessing may include operations such as filtering, denoising, and normalization. For example, a digital filter is applied to smooth the background noise value data to reduce random noise and interference; a more complex denoising algorithm is used to further remove noise and improve data quality; and the background noise value data is scaled to a specific range for subsequent analysis and comparison.
[0067] Analyze the preprocessed data to extract useful information or draw conclusions. When analyzing the current noise floor value, you may compare it with a preset threshold or check whether it shows an abnormal pattern. Based on the analysis results, determine whether the current noise floor value meets the preset noise floor value threshold.
[0068] In this embodiment, the preprocessing step helps to reduce noise interference and improve the accuracy and reliability of the noise floor value data. By performing a detailed analysis on the preprocessed data, it is possible to more accurately determine whether the current noise floor value meets the preset threshold requirement, thereby avoiding misjudgment or missed judgment.
[0069] In one embodiment, the step of optimizing the TOF sensor according to the preset noise floor threshold includes:
[0070] According to the preset background noise threshold, a deep learning algorithm is used to determine the optimal gain value and optimal compensation value of the TOF sensor, and trigger TOF to perform gain adjustment and compensation correction.
[0071] Among them, in signal processing, gain refers to the degree of signal amplification. In TOF sensors, the gain value is used to adjust the signal strength received by the sensor to ensure that the signal can maintain an appropriate level in subsequent processing. The compensation value is used to correct the value of the error or deviation generated during the measurement process. In TOF sensors, the compensation value may include ambient light compensation, temperature compensation, etc. to improve the accuracy of the measurement results.
[0072] Specifically, a deep learning algorithm is used to train a model to predict the optimal gain and compensation values of the TOF sensor with a preset noise floor threshold as the optimization target. The trained model is deployed to receive data from the TOF sensor in real time, and the model is used to predict the optimal gain and compensation values. Based on the optimal gain and compensation values predicted by the model, instructions are sent to the TOF sensor through a control interface or wireless communication to perform gain adjustment and compensation correction.
[0073] In this embodiment, due to the influence of various environmental factors such as ambient light and temperature, the measurement results of the TOF sensor may produce errors. By presetting the noise floor threshold and deep learning algorithm to optimize the gain value and compensation value of the sensor, the influence of environmental factors can be effectively reduced and the accuracy and reliability of the measurement results can be improved. At the same time, the deep learning algorithm can learn the sensor data characteristics under different environmental conditions, so that the TOF sensor can maintain high measurement accuracy and stability in different environments.
[0074] In one embodiment, the step of comparing the depth information of the detected object with the pre-stored characteristic information of the PIN pad includes:
[0075] Determine the attribute of each first information in the depth information of the detected object, and determine the attribute of each second information in the pre-stored characteristic information of the PIN pad;
[0076] A one-to-one correspondence is established between the depth information of the detected object and the information of the same attribute in the pre-stored characteristic information of the password keyboard, and the first information and the second information with the established correspondence are compared one-to-one.
[0077] The first information refers to each data point or data block in the depth information of the detected object, such as a pixel, voxel, etc. The attributes of the first information are used to describe the characteristics of the data point or data block, such as the position coordinates, color, reflectivity, etc. Similar to the attributes of the first information, each data point or data block in the pre-stored characteristic information of the PIN pad also has its own attributes, which are used to describe the characteristics of the PIN pad, such as the position, size, shape, etc. of the key.
[0078] Specifically, algorithms such as image processing or point cloud processing can be used to extract the attributes of each first information, such as position coordinates, from the depth information. At the same time, the attributes of each second information are extracted from the pre-stored feature information of the password keyboard. According to the similarity of the attributes, such as position, shape, etc., a feature matching algorithm or template matching technology is used to establish a one-to-one correspondence between the depth information of the detected object and the information of the same or similar attributes in the feature information of the password keyboard. The first information and the second information with which the correspondence has been established are compared one by one, and the difference between the two can be calculated, and it can be judged whether the difference is within an acceptable range based on a preset threshold.
[0079] In this embodiment, by comparing the depth information, the real password keyboard can be more accurately identified, reducing the risk of being deceived or forged, thereby improving overall security. It can be understood that the depth information comparison does not rely on specific visual features, so it can cope with complex environments such as lighting changes and background interference, and improve the adaptability and robustness of the system.
[0080] In one embodiment, the method further comprises:
[0081] If it is determined that the detected object is not a password keyboard, an early warning signal is issued.
[0082] Specifically, once it is determined that the detected object is not a password keyboard, the early warning mechanism is immediately triggered, including but not limited to sending email or text message notifications to relevant personnel, displaying warning information on the user interface, recording logs for subsequent analysis, activating sound or visual alarms, etc.
[0083] In this embodiment, timely issuing of warning signals can quickly respond to potential security risks and prevent unauthorized access or data leakage.
[0084] In one embodiment, the method further comprises:
[0085] If the detected object is determined to be a password keyboard, the TOF sensor is used to verify the user's hand movements;
[0086] When it is determined that the user's hand movement is an abnormal key gesture, the transaction process of the payment application is stopped and a key error prompt message is generated.
[0087] Specifically, after determining that the detected object is a PIN pad, the TOF sensor continues to capture the user's hand movements and uses algorithms such as dynamic gesture recognition to verify whether the user's hand movements conform to normal operating specifications. If the user's hand movements are determined to be abnormal key gestures, the computer device will immediately stop the current transaction process of the payment application and generate and display a key error prompt message to the user, informing him that there is an abnormality in his operation.
[0088] In this embodiment, criminals may try to bypass security verification by simulating or forging user gestures, or steal money through abnormal key gestures. Therefore, by monitoring and verifying user hand movements, potential fraud can be discovered and prevented in a timely manner. At the same time, payment failures caused by misoperation can be reduced, thereby improving the smoothness and success rate of the payment process.
[0089] In one embodiment, the step of verifying the user's hand movement by using a TOF sensor includes:
[0090] Trigger the TOF sensor to continuously emit multiple infrared rays, so that the TOF sensor can continuously construct the depth information of the password keyboard and the user's hand;
[0091] Determine the background model corresponding to the password keyboard, and identify the user's hand movements based on the difference in depth information of the password keyboard and the user's hand relative to the background model;
[0092] The user's hand movement is compared with the pre-stored normal key gesture to verify whether the user's hand movement is a normal key gesture.
[0093] The background model is a pre-established three-dimensional model or data set representing the password keyboard, which is used to compare with real-time data to identify changes or differences.
[0094] Specifically, the TOF sensor is triggered to emit infrared rays and is set to continuous working mode. The TOF sensor continuously emits infrared rays to illuminate the PIN pad and the user's hands. The TOF sensor receives infrared rays reflected from the PIN pad and the user's hands, and calculates and generates depth information such as depth images or point cloud data of the PIN pad and the user's hands based on the time difference of the infrared rays going back and forth.
[0095] Load the pre-established PIN pad background model, which contains the depth information of the PIN pad when there is no hand contact. Compare the real-time constructed depth information with the background model, and identify the user's hand position, shape, movement trajectory and other action information by analyzing the difference. Compare the identified user hand movements with the pre-stored normal key gestures, and use pattern matching, machine learning algorithms and other methods to evaluate the similarity and compliance of the movements. If the movement is consistent with the normal key gesture, the verification is passed; otherwise, it is considered an abnormal gesture.
[0096] In this embodiment, by real-time monitoring and verification of the user's hand movements, illegal access and fraud can be effectively prevented, thereby improving the security of payment and identity authentication.
[0097] The following describes the payment information anti-theft device provided in the embodiment of the present application. The payment information anti-theft device described below and the payment information anti-theft method described above can be referred to each other. Figure 3 As shown, the present application provides a payment information anti-theft device, the device comprising:
[0098] The noise floor value acquisition module 201 is used to acquire the current noise floor value of the TOF sensor in the current environment when the payment application is started. The TOF sensor is arranged on the side of the PIN keyboard, and the infrared emission range of the TOF sensor covers the PIN keyboard;
[0099] The sensor optimization module 202 is used to optimize the TOF sensor according to the preset noise floor value threshold if the current noise floor value does not meet the preset noise floor value threshold;
[0100] The depth information building module 203 is used to trigger the TOF sensor to emit multiple infrared rays when the current background noise value meets the preset background noise value threshold, so that the TOF sensor builds the depth information of the detected object according to the flight time of each infrared ray, and the detected object is the object that arrives first after the infrared ray is emitted;
[0101] The information comparison module 204 is used to compare the depth information of the detected object with the pre-stored characteristic information of the PIN pad, and if it is determined that the detected object is not the PIN pad, the transaction process in the payment application is stopped.
[0102] In one embodiment, after the noise floor value acquisition module 201, it includes:
[0103] The noise floor value processing module is used to pre-process the current noise floor value and analyze the pre-processed noise floor value to determine whether the current noise floor value meets a preset noise floor value threshold.
[0104] In one embodiment, the sensor optimization module 202 includes:
[0105] The sensor optimization unit is used to determine the optimal gain value and optimal compensation value of the TOF sensor based on a preset background noise threshold using a deep learning algorithm, and trigger TOF to perform gain adjustment and compensation correction.
[0106] In one embodiment, the information comparison module 204 includes:
[0107] An information attribute determination unit, used to determine the attribute of each first information in the depth information of the detected object, and to determine the attribute of each second information in the pre-stored characteristic information of the password keyboard;
[0108] The information comparison unit is used to establish a one-to-one correspondence between the depth information of the detected object and the information of the same attribute in the pre-stored characteristic information of the password keyboard, and to compare the first information and the second information with which the correspondence has been established one-to-one.
[0109] In one embodiment, the apparatus further comprises:
[0110] The warning signal issuing module is used to issue a warning signal if it is determined that the detected object is not a password keyboard.
[0111] In one embodiment, the apparatus further comprises:
[0112] The motion verification module is used to verify the user's hand motion through the TOF sensor if the detected object is determined to be a password keyboard;
[0113] The prompt information generation module is used to stop the transaction process of the payment application and generate a key error prompt information when it is determined that the user's hand movement is an abnormal key gesture.
[0114] In one embodiment, the action verification module includes:
[0115] An infrared emitting unit, used to trigger the TOF sensor to continuously emit multiple infrared rays, so that the TOF sensor can continuously construct the depth information of the password keyboard and the user's hand;
[0116] The motion recognition unit is used to determine the background model corresponding to the password keyboard and recognize the user's hand motion according to the difference between the depth information of the password keyboard and the user's hand and the background model;
[0117] The gesture comparison unit is used to compare the user's hand movement with the pre-stored normal key gesture to verify whether the user's hand movement is a normal key gesture.
[0118] In one embodiment, the present application also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the payment information anti-theft method as described in any of the above embodiments.
[0119] In one embodiment, the present application also provides a computer device having computer-readable instructions stored therein. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the payment information anti-theft method as described in any one of the above embodiments.
[0120] Indicatively, Figure 4 As shown, Figure 4 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. The computer device 300 may be provided as a server. Figure 4 , the computer device 300 includes a processing component 302, which further includes one or more processors, and a memory resource represented by a memory 301, for storing instructions executable by the processing component 302, such as an application. The application stored in the memory 301 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 302 is configured to execute instructions to perform the payment information anti-theft method of any of the above embodiments.
[0121] The computer device 300 may further include a power supply component 303 configured to perform power management of the computer device 300, a wired or wireless network interface 304 configured to connect the computer device 300 to a network, and an input / output (I / O) interface 305. The computer device 300 may operate based on an operating system stored in the memory 301, such as Windows Server TM, Mac OS X TM, Unix TM, Linux TM, Free BSD TM, or the like.
[0122] Those skilled in the art will understand that Figure 4The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0123] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the term "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not clearly listed, or also includes elements inherent to such process, method, article or equipment. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or equipment including the elements. Herein, "one", "one", "said", "the" and "it" may also include plural forms, unless the context clearly indicates another way. A plurality refers to at least two cases, such as 2, 3, 5 or 8, etc. "And / or" includes any and all combinations of the relevant listed items.
[0124] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can refer to each other.
[0125] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A payment information theft prevention method, characterized in that: The method comprises: When the payment application is started, the current background noise value of the TOF sensor in the current environment is obtained, the TOF sensor is arranged on the side of the PIN keyboard, and the infrared emission range of the TOF sensor covers the PIN keyboard; If the current background noise value does not meet the preset background noise value threshold, optimizing the TOF sensor according to the preset background noise value threshold; When the current background noise value meets the preset background noise value threshold, the TOF sensor is triggered to emit multiple infrared rays, so that the TOF sensor constructs depth information of the detected object according to the flight time of each infrared ray, and the detected object is the object that arrives first after the infrared ray is emitted; The depth information of the detected object is compared with the pre-stored characteristic information of the PIN keyboard. If it is determined that the detected object is not the PIN keyboard, the transaction process in the payment application is stopped.
2. The payment information anti-theft method according to claim 1, characterized in that: After the step of obtaining the current background noise value of the TOF sensor in the current environment, the method further includes: The current background noise value is preprocessed, and the preprocessed background noise value is analyzed to determine whether the current background noise value meets the preset background noise value threshold.
3. The payment information anti-theft method according to claim 1, characterized in that: The step of optimizing the TOF sensor according to the preset noise floor threshold includes: According to the preset background noise threshold, a deep learning algorithm is used to determine the optimal gain value and the optimal compensation value of the TOF sensor, and the TOF is triggered to perform gain adjustment and compensation correction.
4. The payment information anti-theft method according to claim 1, characterized in that: The step of comparing the depth information of the detected object with the pre-stored characteristic information of the password keyboard comprises: Determine the attribute of each first information in the depth information of the detected object, and determine the attribute of each second information in the pre-stored characteristic information of the PIN keyboard; A one-to-one correspondence is established between the depth information of the detected object and the information of the same attribute in the pre-stored characteristic information of the password keyboard, and the first information and the second information with the established correspondence are compared one-to-one.
5. The payment information anti-theft method according to claim 1, characterized in that: The method further comprises: If it is determined that the detected object is not the password keyboard, an early warning signal is issued.
6. The payment information anti-theft method according to any one of claims 1 to 5, characterized in that: The method further comprises: If it is determined that the detected object is the password keyboard, verifying the user's hand movement through the TOF sensor; When it is determined that the user's hand movement is an abnormal key gesture, the transaction process of the payment application is stopped and a key error prompt message is generated.
7. The payment information anti-theft method according to claim 6, characterized in that: The step of verifying the user's hand movement by the TOF sensor includes: Triggering the TOF sensor to continuously emit a plurality of infrared rays, so that the TOF sensor continuously constructs depth information of the password keyboard and the user's hand; Determine a background model corresponding to the PIN keyboard, and identify the movement of the user's hand according to the difference between the depth information of the PIN keyboard and the user's hand and the background model; The user's hand movement is compared with a pre-stored normal key gesture to verify whether the user's hand movement is a normal key gesture.
8. A payment information theft prevention device, characterized in that: The device comprises: A noise floor value acquisition module, used to acquire the current noise floor value of the TOF sensor in the current environment when the payment application is started, wherein the TOF sensor is arranged on the side of the PIN keyboard, and the infrared emission range of the TOF sensor covers the PIN keyboard; A sensor optimization module, configured to optimize the TOF sensor according to the preset noise floor value threshold if the current noise floor value does not meet the preset noise floor value threshold; A depth information building module, used to trigger the TOF sensor to emit multiple infrared rays when the current background noise value meets the preset background noise value threshold, so that the TOF sensor builds the depth information of the detected object according to the flight time of each infrared ray, and the detected object is the object that reaches first after the infrared ray is emitted; The information comparison module is used to compare the depth information of the detected object with the pre-stored characteristic information of the PIN keyboard, and if it is determined that the detected object is not the PIN keyboard, stop the transaction process in the payment application.
9. A storage medium, characterized in that: The storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the payment information anti-theft method as described in any one of claims 1 to 7.
10. A computer device, characterized in that: include: one or more processors, and memory; The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the payment information anti-theft method according to any one of claims 1 to 7 are performed.