Transaction verification method and device, computer readable storage medium and electronic equipment

Abstract

The invention discloses a transaction verification method and device, a computer readable storage medium and electronic equipment. Relates to the field of biological recognition, and the method comprises the steps: obtaining a real fingerprint feature of a user under the condition that a transaction request of the user is received, and obtaining a real iris feature of the user; performing identity authentication on the user based on the real fingerprint feature and the real iris feature of the user; under the condition that the identity authentication is passed, real motion information of the user is acquired; and performing transaction security verification on the user based on the real motion information of the user to obtain a transaction verification result. Through the method and the device, the problem of low security of transaction verification caused by performing transaction verification on a user based on a single feature in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the field of biometrics, and more specifically, to a transaction verification method, device, computer-readable storage medium, and electronic device. Background Art

[0002] With the popularization of Internet technology and the rapid development of electronic payment, financial transactions have become more convenient, but the security risks that come with it are also increasing. Problems such as user identity theft and frequent illegal transactions have caused huge economic losses to financial institutions and users. Traditional transaction behavior monitoring methods cannot detect user transaction activities in real time, and it is difficult to identify and prevent abnormal transactions in a timely manner.

[0003] At present, biometric recognition technology based on iris features for identity authentication has made certain progress in identity authentication, but a single biometric feature is easily affected by factors such as environment and age, resulting in a decrease in recognition accuracy, thus affecting the security of transaction verification.

[0004] Currently, no effective solution has been proposed to address the problem that transaction verification based on a single feature in related technologies leads to low security of transaction verification. Summary of the invention

[0005] The main purpose of the present application is to provide a transaction verification method, device, computer-readable storage medium and electronic device to solve the problem in the related art that transaction verification of users is performed based on a single feature, resulting in low security of transaction verification.

[0006] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a transaction verification method is provided, including: upon receiving a transaction request from a user, obtaining the user's real fingerprint features and the user's real iris features; authenticating the user based on the user's real fingerprint features and the real iris features; when the identity authentication is passed, obtaining the user's real motion information; and verifying the transaction security of the user based on the user's real motion information to obtain a transaction verification result.

[0007] Furthermore, the transaction verification method also includes: obtaining a real fingerprint image of the user; preprocessing the real fingerprint image to obtain a preprocessed real fingerprint image, wherein the preprocessing includes at least one of the following: noise removal, contrast enhancement; refining the fingerprint texture in the preprocessed real fingerprint image to obtain a target fingerprint image; identifying fingerprint detail points from the target fingerprint image, and determining the real fingerprint features based on the identified fingerprint detail points, wherein the fingerprint detail points include at least one of the following: ridge ends and ridge bifurcations.

[0008] Furthermore, the transaction verification method also includes: obtaining a facial image of the user; identifying an iris area from the facial image, and performing feature extraction on the iris area to obtain real iris features.

[0009] Furthermore, the transaction verification method also includes: obtaining a portrait activity video of the user in the transaction area, wherein the transaction area is the area where the user initiates the transaction request; processing the portrait activity video based on a frame difference method to obtain a motion projection matrix, wherein the elements in the motion projection matrix represent the cumulative value of the motion intensity of the pixel points in the portrait activity video; and determining the user's real motion information based on the motion projection matrix.

[0010] Furthermore, the transaction verification method also includes: dividing the motion projection matrix by columns to obtain multiple first vectors; dividing the motion projection matrix by rows to obtain multiple second vectors; splicing the multiple first vectors and the multiple second vectors to obtain a motion feature vector, wherein the motion feature vector is used to characterize the user's real motion information.

[0011] Furthermore, the transaction verification method also includes: inputting the motion feature vector into a target classification model, performing classification processing through the target classification model to obtain a classification result, wherein the classification result represents the probability that the transaction of the user corresponding to the motion feature vector is a safe transaction; and determining the transaction verification result based on the classification result.

[0012] Furthermore, the transaction verification method further includes: if the transaction verification result indicates that the transaction security verification has passed, allowing the transaction requested by the transaction request to be executed; if the transaction verification result indicates that the transaction security verification has not passed, prohibiting the execution of the transaction requested by the transaction request.

[0013] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a transaction verification device is provided. The device comprises: a first acquisition module, which is used to obtain the user's real fingerprint feature and the user's real iris feature when receiving the user's transaction request; an authentication module, which is used to authenticate the user based on the user's real fingerprint feature and the real iris feature; a second acquisition module, which is used to obtain the user's real motion information when the identity authentication is passed; and a verification module, which is used to verify the transaction security of the user based on the user's real motion information to obtain a transaction verification result.

[0014] Furthermore, the first acquisition module also includes: a first acquisition submodule, used to acquire the user's real fingerprint image; a first processing submodule, used to preprocess the real fingerprint image to obtain a preprocessed real fingerprint image, wherein the preprocessing includes at least one of the following: noise removal, contrast enhancement; a second processing submodule, used to refine the fingerprint texture in the preprocessed real fingerprint image to obtain a target fingerprint image; a first determination submodule, used to identify fingerprint detail points from the target fingerprint image, and determine the real fingerprint features based on the identified fingerprint detail points, wherein the fingerprint detail points include at least one of the following: ridge ends and ridge bifurcations.

[0015] Furthermore, the first acquisition module also includes: a second acquisition submodule, used to acquire the user's face image; and a recognition submodule, used to recognize the iris area from the face image and perform feature extraction on the iris area to obtain real iris features.

[0016] Furthermore, the second acquisition module also includes: a third acquisition submodule, used to obtain a portrait activity video of a user in a transaction area, wherein the transaction area is an area where the user initiates a transaction request; a third processing submodule, used to process the portrait activity video based on a frame difference method to obtain a motion projection matrix, wherein the elements in the motion projection matrix represent the cumulative value of the motion intensity of the pixel points in the portrait activity video; and a second determination submodule, used to determine the user's real motion information based on the motion projection matrix.

[0017] Furthermore, the second determination submodule also includes: a first slicing unit, used to slice the motion projection matrix by column to obtain multiple first vectors; a second slicing unit, used to slice the motion projection matrix by row to obtain multiple second vectors; a splicing unit, used to splice the multiple first vectors and the multiple second vectors to obtain a motion feature vector, wherein the motion feature vector is used to characterize the user's real motion information.

[0018] Furthermore, the verification module also includes: a classification submodule, which is used to input the motion feature vector into a target classification model, perform classification processing through the target classification model, and obtain a classification result, wherein the classification result represents the probability that the transaction of the user corresponding to the motion feature vector is a safe transaction; a third determination submodule, which is used to determine the transaction verification result based on the classification result.

[0019] Furthermore, the transaction verification device also includes: a first execution module, which is used to allow the execution of the transaction requested by the transaction request when the transaction verification result indicates that the transaction security verification has passed; and a second execution module, which is used to prohibit the execution of the transaction requested by the transaction request when the transaction verification result indicates that the transaction security verification has not passed.

[0020] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer-readable storage medium is provided, and the computer-readable storage medium includes a stored executable program, wherein when the executable program runs, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned transaction verification method.

[0021] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an electronic device is provided, the electronic device comprising a memory storing an executable program; and a processor for running the program, wherein the above-mentioned transaction verification method is executed when the program is running.

[0022] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer program product is provided, comprising computer instructions, which implement the steps of the above-mentioned transaction verification method when executed by a processor.

[0023] In the embodiments of the present application, a method of transaction security verification is adopted based on the user's fingerprint features, iris features and motion information as identity authentication information. By performing the first-level identity authentication based on fingerprint features and iris features, the uniqueness of the verification data is guaranteed, and the risk of data forgery is effectively avoided. By performing the second-level identity authentication based on the user's motion information, the deficiency of static biometric verification is compensated, and the combination of static verification and dynamic verification methods is realized, thereby improving the system's ability to judge transaction behavior. By combining motion information with biometrics for identity authentication, the security of transaction verification is improved, the risk of user identity forgery or theft is reduced, and the user's transaction security is thereby improved.

[0024] It can be seen that the solution provided in the present application achieves the purpose of conducting transaction security verification based on the user's fingerprint features, iris features and motion information as identity authentication information, thereby achieving the technical effect of improving the security of transaction verification, and further solving the problem of low security of transaction verification caused by conducting transaction verification on users based on a single feature in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0026] Figure 1 is a hardware structure block diagram of a computer terminal provided according to an embodiment of the present application;

[0027] Figure 2 is a schematic diagram of a transaction verification method provided according to an embodiment of the present application;

[0028] Figure 3 is a flow chart of a transaction verification method provided according to an embodiment of the present application;

[0029] Figure 4 is a schematic diagram of a transaction verification device provided according to an embodiment of the present application;

[0030] Figure 5 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present application.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] It should be noted that the collected information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with relevant laws, regulations and standards, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation entrances are provided for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions to provide users with corresponding operation entrances for users to choose to agree or refuse the results of automated decision-making; if the user chooses to refuse, the expert decision-making process will be entered.

[0034] Example 1

[0035] According to an embodiment of the present application, an embodiment of a transaction verification method is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0036] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal (or mobile device) for implementing a transaction verification method. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0037] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0038] The memory 104 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the transaction verification method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the above-mentioned transaction verification method is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0039] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0040] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0041] Under the above operating environment, this application provides Figure 2 Transaction verification method shown. Figure 2 It is a schematic diagram of a transaction verification method provided according to an embodiment of the present application.

[0042] Step S201, upon receiving a transaction request from a user, obtaining the user's real fingerprint feature and the user's real iris feature.

[0043] Optionally, electronic devices, application systems, servers and other devices may be used as the execution subject of the present application. In this embodiment, the transaction verification system is used as the execution subject to execute the above-mentioned transaction verification method.

[0044] Optionally, the user's transaction request can be initiated in a variety of scenarios, such as ATM machines of various offline financial institutions.

[0045] Optionally, when the user initiates a transaction request, the transaction verification system activates the ATM camera to obtain the user's facial image and activates the fingerprint collection device to obtain the user's real fingerprint image to ensure the reliability of the user's identity information.

[0046] Optionally, the user's real fingerprint feature is determined based on preprocessing the real fingerprint image and identifying fingerprint minutiae, wherein the preprocessing may select noise removal or contrast enhancement technology, and the fingerprint minutiae may include ridge ends or ridge bifurcations. The user's real iris feature is obtained by identifying the iris area based on the face image and extracting features from the iris area.

[0047] Step S202: authenticating the user based on the user's real fingerprint features and real iris features.

[0048] In some embodiments, after extracting the user's real fingerprint features and real iris features, the transaction verification system concatenates the fingerprint and iris features through a feature fusion algorithm, merges them into a single feature, and generates a multimodal feature vector. The feature fusion algorithm removes redundant information from the fingerprint and iris features, retains the most distinguishing features, and enhances the performance of the identity authentication model.

[0049] Optionally, after feature fusion, a preset identity recognition model (such as a support vector machine or a deep neural network) is used to perform identity authentication based on the user's multimodal feature vector to obtain an authentication result. The identity authentication of the identity recognition model is achieved by comparing the input multimodal feature vector with the feature vector of the data in the data storage area (such as a database, a cloud server), and the data storage area stores the reference fingerprint feature and reference iris feature corresponding to the user. The identity authentication system can input the user's multimodal feature vector and the user's corresponding reference multimodal feature vector (composed of reference fingerprint features and reference iris features) into the identity recognition model to obtain an authentication result. The authentication result indicates whether the user's identity authentication is passed.

[0050] In some embodiments, the transaction verification system may also compare the user's real fingerprint feature with the user's reference fingerprint feature according to a preset fingerprint feature comparison rule to obtain a first comparison result, and compare the user's real iris feature with the user's reference iris feature according to a preset iris feature comparison rule to obtain a second comparison result, thereby determining the identity authentication result according to the first comparison result and the second comparison result. For example, if the first comparison result indicates that the fingerprint feature similarity is greater than a threshold, and the second comparison result indicates that the iris feature similarity is greater than a threshold, it is determined that the identity authentication is passed, and if the first comparison result indicates that the fingerprint feature is less than or equal to the threshold, or if the second comparison result indicates that the iris feature similarity is less than the threshold, it is determined that the identity authentication is not passed.

[0051] Step S203, when the identity authentication is passed, obtaining the user's real movement information.

[0052] In some embodiments, if the identity authentication based on fingerprint and iris features is passed, the camera can be used to record the user's portrait activity video during the transaction, and the behavioral features can be extracted, and the motion projection matrix can be generated based on the frame difference method to determine the user's real motion information.

[0053] Step S204: Perform transaction security verification on the user based on the user's real movement information to obtain a transaction verification result.

[0054] In some embodiments, the user's actual motion information may be a motion feature vector of the user.

[0055] Optionally, the motion feature vector may be input into a target classification model to classify the user's behavior to determine whether the transaction behavior is a legal operation, that is, to perform transaction security verification and obtain a transaction verification result.

[0056] Optionally, the legality judgment may be based on the stability or consistency of the user's movements to identify abnormal behaviors, where the abnormal behaviors may be fast movements or camera occlusions.

[0057] In some embodiments, when the identity authentication result obtained in step S202 indicates that the identity authentication has not passed, it is determined that the transaction verification result indicates that the transaction security verification has not passed.

[0058] In the embodiments of the present application, a method of transaction security verification is adopted based on the user's fingerprint features, iris features and motion information as identity authentication information. By performing the first-level identity authentication based on fingerprint features and iris features, the uniqueness of the verification data is guaranteed, and the risk of data forgery is effectively avoided. By performing the second-level identity authentication based on the user's motion information, the deficiency of static biometric verification is compensated, and the combination of static verification and dynamic verification methods is realized, thereby improving the system's ability to judge transaction behavior. By combining motion information with biometrics for identity authentication, the security of transaction verification is improved, the risk of user identity forgery or theft is reduced, and the user's transaction security is thereby improved.

[0059] It can be seen that the solution provided in the present application achieves the purpose of conducting transaction security verification based on the user's fingerprint features, iris features and motion information as identity authentication information, thereby achieving the technical effect of improving the security of transaction verification, and further solving the problem of low security of transaction verification caused by conducting transaction verification on users based on a single feature in related technologies.

[0060] In an optional embodiment, in the process of obtaining the user's real fingerprint features, the transaction verification system can obtain the user's real fingerprint image; preprocess the real fingerprint image to obtain a preprocessed real fingerprint image, wherein the preprocessing includes at least one of the following: noise removal, contrast enhancement; refine the fingerprint texture in the preprocessed real fingerprint image to obtain a target fingerprint image; identify fingerprint detail points from the target fingerprint image, and determine the real fingerprint features based on the identified fingerprint detail points, wherein the fingerprint detail points include at least one of the following: ridge ends and ridge bifurcations.

[0061] Optionally, the transaction verification system obtains the user's real fingerprint features including the following process:

[0062] 1. Obtain fingerprint information: The transaction verification system collects the user's fingerprint image (i.e., the real fingerprint image) in real time through the fingerprint sensor and records the fingerprint data at the current moment.

[0063] 2. Fingerprint image preprocessing: You can choose at least one of the following two operations for preprocessing: use Gabor filter to remove environmental noise in the image, and use adaptive histogram equalization algorithm to improve the contrast of the fingerprint image. The specific process of noise removal and contrast enhancement is as follows:

[0064] (1) Noise removal: First, initialize a filter (i.e., Gabor filter) obtained by multiplying a Gaussian function and a complex sine wave, and adjust the filter parameters (such as wavelength, direction, or bandwidth) to adapt to the image characteristics and noise type. Then, convolve the Gabor filter with the image, and use its frequency and direction selectivity to enhance the image features and suppress noise. The convolution operation calculates a weighted sum for each local area of ​​the image to achieve noise suppression and feature retention. Finally, check whether the image in the image is effectively removed. If necessary, adjust the parameters of the Gabor filter to optimize the denoising effect.

[0065] (2) Contrast enhancement:

[0066] a. The fingerprint image processed in the previous step is further divided into multiple context areas. These areas are relatively small and can capture local detail changes. Then, a histogram is calculated for each context area, and the number of pixels with different gray levels in the area is counted to understand the grayscale distribution of the area. The mapping function is calculated based on the histogram to adjust the grayscale distribution in the area.

[0067] b. Each pixel in the image is weighted averaged according to the mapping function of its context area and the four adjacent context areas to obtain the new grayscale value of the pixel. The weight is calculated based on the proximity of the pixel to the center of its adjacent area.

[0068] c. Apply the mapping function to update the gray value of each pixel to improve the contrast of the image. In the histogram, a certain number of pixels are evenly divided for each gray level, and the pixels are divided based on the average value of all pixels in each gray level.

[0069] Through the above process, the contrast of the fingerprint image is effectively improved, and the detailed features of the fingerprint are more obvious.

[0070] 3. Fingerprint image segmentation: The fingerprint image is segmented into the foreground fingerprint area and the background area using the adaptive Otsu segmentation technique. The Otsu method automatically determines the optimal threshold value through the information of the image histogram, thereby separating the fingerprint ridge from the background. To improve the accuracy of segmentation, the adaptive Otsu segmentation technique of this method is based on the Otsu method, and the modulus value of the background pixel is subtracted from the standard deviation of the object pixel to determine the optimal threshold value, so as to reduce noise interference and improve segmentation quality.

[0071] 4. Fingerprint texture refinement: First, the segmented grayscale fingerprint image is converted into a binary image. This step divides the pixels in the grayscale image into two categories: ridges (foreground) and bones (background) by setting a threshold. Then, the fingerprint image is refined to reduce the thickness of the fingerprint ridges to a single pixel width. This process reduces the thickness of the lines as much as possible while maintaining the continuity of the ridges by eliminating redundant and unnecessary pixels in the image. Finally, the refined fingerprint image with clearer fingerprint ridges is used as the target fingerprint image.

[0072] 5. Minutiae extraction: Based on the crossover number algorithm, the fingerprint minutiae (i.e., ridge end and ridge bifurcation) is extracted by scanning the neighborhood of each ridge pixel, and then the real fingerprint features are obtained. Among them, the crossover number is half of the sum of the differences between adjacent pixel pairs in the input image. The crossover number corresponding to the ridge end is 1, and the crossover number corresponding to the ridge bifurcation point is 3. After the fingerprint minutiae points are identified, the number, position and other information of each fingerprint minutiae point can be determined as the real fingerprint features.

[0073] It should be noted that by preprocessing the real fingerprint image based on noise removal and contrast enhancement, the influence of the external environment (such as light, finger surface state) on fingerprint image acquisition is effectively reduced. The core structural features of the fingerprint are obtained based on texture refinement and detail point extraction, ensuring the uniqueness of the extracted fingerprint data. Through multiple preprocessing and refinement analysis of fingerprint images, the system improves the accuracy of extracting real fingerprint features, thereby improving the accuracy of identity authentication results, and further improving the credibility of transaction verification results.

[0074] In an optional embodiment, in the process of obtaining the user's real iris features, the transaction verification system may obtain the user's facial image; identify the iris area from the facial image, and perform feature extraction on the iris area to obtain the real iris features.

[0075] Optionally, the transaction verification system obtains the user's real iris features including the following process:

[0076] 1. Obtain facial images: The transaction verification system can activate the ATM's dedicated camera equipment to capture the user's real-time facial image to ensure the authenticity and uniqueness of the image.

[0077] 2. Segmentation of iris region: First, preprocess the image, including denoising and contrast enhancement. Then, based on the Kernelized Snake Contour Model (KSCM), the iris region is segmented by dynamically adjusting the boundary curve. The specific process is as follows:

[0078] (1) Initialize the boundary curve: Set the initial curve, which is usually a circle or ellipse close to the shape of the iris.

[0079] (2) Contour movement: According to the gradient information of the iris area, the curve boundary is adjusted so that it gradually converges to the iris boundary.

[0080] (3) The contour stops moving: When the boundary curve reaches the clear edge of the iris area, the curve adjustment stops and the segmentation of the iris area is completed.

[0081] 3. Iris feature extraction: After the iris region segmentation is completed, the iris features are extracted, including the analysis of geometric and structural features. The process is as follows:

[0082] (1) Geometric feature extraction: This process extracts important pupil-centered and iris-centered features.

[0083] a. Centered on the pupil: Use the pupil's 8' angle for center positioning, calculate the pupil's diameter, and evaluate its smoothness based on the pupil's curvature to ensure detection accuracy.

[0084] b. With the iris as the center: calculate the roundness feature of the iris, extract the maximum and minimum values ​​of the iris diameter in different directions (such as horizontal, vertical, diagonal: 0°, 45°, 90°, 135°, etc.), and calculate their ratio to quantify the asymmetry of the iris.

[0085] (2) Structural feature extraction: Analyze iris texture features, such as ridge structure and dot patches, and extract parameters such as texture distribution direction and density to generate a unique iris texture template.

[0086] Optionally, the features extracted from the geometric features and the features extracted from the structural features are determined as true iris features.

[0087] It should be noted that the transaction verification system effectively avoids the errors and inefficiencies of manual operation by capturing facial images and automatically extracting the iris area. By accurately extracting features from the iris area, the system's recognition efficiency and accuracy are improved, thereby improving the security of the system's transaction verification.

[0088] In an optional embodiment, in the process of obtaining the user's real motion information, the transaction verification system can obtain a portrait activity video of the user in a transaction area, wherein the transaction area is the area where the user initiates a transaction request; the portrait activity video is processed based on a frame difference method to obtain a motion projection matrix, wherein the elements in the motion projection matrix represent the cumulative values ​​of the motion intensity of the pixel points in the portrait activity video; and the user's real motion information is determined based on the motion projection matrix.

[0089] Optionally, if the identity authentication based on fingerprint and iris features is passed, the transaction verification system can activate the dedicated camera device of the ATM machine to capture the video of human activities in the area where the user initiates the transaction request for subsequent motion information extraction and analysis.

[0090] In some embodiments, if the user's fingerprint and iris authentication have been passed, the ATM's camera device is activated to record the user's activity video in real time, recording the user's body movements. Abnormal activities (such as snatching or attacking) are usually accompanied by rapid or violent body movements, while normal activities (such as key input or reading the screen) are manifested as gentle movements.

[0091] Optionally, the frame difference method identifies the motion area in the portrait activity video by calculating the pixel difference between two consecutive image frames. The motion projection matrix is ​​a two-dimensional matrix of temporal and spatial motion information extracted from consecutive frame videos. The elements in the matrix represent the cumulative value of the motion intensity of the pixel points in the portrait activity video. It can be judged whether the user is moving based on the change of pixel values.

[0092] Optionally, when capturing the user's body motion difference based on the frame difference method and obtaining the motion projection matrix, the following steps can be performed:

[0093] 1. RGB to Grayscale: Convert each image frame in the video from the RGB color space to a grayscale image to reduce the amount of data and focus on the brightness changes of the image. For example, a color image frame converted to a grayscale image only contains the intensity information of the pixel, which is convenient for the subsequent calculation of the difference value.

[0094] 2. Frame difference calculation: Calculate the pixel difference between two consecutive image frames. If the pixel difference is large, it means that there is obvious movement in the corresponding transaction area, such as the user quickly moves his arm to enter the password.

[0095] 3. Information accumulation: Since the difference between a single set of continuous frames may not accurately reflect the overall trend of the user's body movement, the motion intensities corresponding to the differences between multiple sets of continuous frames can be summed and accumulated to obtain a motion projection matrix, in which each element of the matrix represents the cumulative motion intensity of a certain pixel in the portrait activity video. For example, for each set of continuous frames, when the pixel difference value is greater than a preset value, the motion intensity corresponding to the pixel in the single set of continuous frames is determined to be 1 to represent the user's movement, otherwise, the motion intensity corresponding to the pixel in the single set of continuous frames is determined to be 0 to represent the user's non-movement; in some embodiments, the pixel difference value corresponding to the pixel in the set of continuous frames can also be directly determined as the motion intensity corresponding to the pixel in the single set of continuous frames.

[0096] Optionally, the motion projection matrix obtained from the motion intensity accumulation value can determine the user's real motion information, such as the motion intensity accumulation value corresponding to the state where the user's body is almost still is close to 0, and the motion intensity accumulation value corresponding to the state where the user's body is in continuous motion is higher. If there are multiple areas with higher values ​​in the motion projection matrix (such as violent whole body shaking), it may indicate that the user has abnormal activities, such as robbery or attack behavior.

[0097] It should be noted that by acquiring user activity videos in the transaction area and generating a motion projection matrix based on the frame difference method, dynamic capture and security analysis of user motion behavior are achieved, and both computational efficiency and accuracy are improved. By determining the user's motion information based on the motion projection matrix, the frequency, amplitude, and duration of the user's movements are accurately described, reflecting the user's true state in the transaction scenario, providing effective data for the second-layer identity authentication, and thereby improving the security of the system's transaction verification.

[0098] In an optional embodiment, in the process of determining the user's real motion information based on the motion projection matrix, the transaction verification system can divide the motion projection matrix by columns to obtain multiple first vectors; divide the motion projection matrix by rows to obtain multiple second vectors; and concatenate the multiple first vectors and the multiple second vectors to obtain a motion feature vector, wherein the motion feature vector is used to characterize the user's real motion information.

[0099] Optionally, determining the user's real motion information based on the motion projection matrix is ​​to vertically and horizontally segment the motion projection matrix through a strip method to generate a feature vector to represent the user's overall motion information, which is convenient for subsequent classification processing and abnormal behavior detection. To facilitate feature extraction in the vertical and horizontal directions, the motion projection matrix can be copied into two copies, the first copy is used for vertical strip segmentation (i.e., segmentation by column), and the second copy is used for horizontal strip segmentation (i.e., segmentation by row).

[0100] Optionally, when the motion projection matrix is ​​vertically and horizontally segmented based on the strip method, the first copy is evenly divided into multiple vertical strips of equal size in the vertical direction to obtain multiple first vectors, each vertical strip corresponds to the cumulative motion intensity of a column range in the matrix, and the number of columns covered by each vertical strip determines the precision of its feature extraction. The second copy is evenly divided into multiple horizontal strips of equal size in the horizontal direction to obtain multiple second vectors, each horizontal strip corresponds to the cumulative motion intensity of a row range in the matrix. Among them, the vertical strips and horizontal strips can represent the global motion amount, such as the movement of the foot is equivalent to the movement of the upper body of the human body because their center of gravity movement is equivalent.

[0101] In some embodiments, assuming that the motion projection matrix size is 100×100, it is copied into two copies, the first matrix copy is divided into 10 vertical strips, each with a width of 10 elements, representing the motion intensity distribution from left to right; the second matrix copy is divided into 10 horizontal strips, each with a height of 10 elements, representing the motion intensity distribution from top to bottom.

[0102] Optionally, when the plurality of first vectors and the plurality of second vectors are spliced, the motion intensity values ​​represented by all vertical strips and horizontal strips are flattened into one-dimensional vectors, and then the vertical strip and horizontal strip vectors are connected to obtain a complete motion feature vector, which is used to represent the user's real motion information. For example, if a user performs a small hand movement (such as entering a password) and a large body movement (such as a robbery attempt) in front of an ATM machine, the global motion amount of the two will be significantly different, which is reflected in the intensity value of the strip.

[0103] Optionally, the motion projection matrix is ​​divided into vertical strips and horizontal strips, and the corresponding motion feature vectors are extracted, which can effectively enhance the adaptability of the motion features to the relative position change of the camera. For example, if a certain motion is detected in the vertical strips of one motion projection matrix, and similar motion also exists in the corresponding vertical strips of another matrix, even if the motion distribution in their horizontal strips is different, the same type of motion can be judged through the information of the vertical strips. Therefore, even if the distance or position between the user and the camera changes, the motion features of the vertical strips can still be guaranteed to be consistent.

[0104] It should be noted that by dividing the motion projection matrix by rows and columns to generate motion feature vectors, the processing and analysis process of multi-dimensional motion information is simplified. By representing the user's dynamic behavior based on vectors, the calculation complexity is reduced while retaining the key features of the motion data, thereby improving the accuracy and efficiency of the system in transaction security verification.

[0105] In an optional embodiment, in the process of verifying the transaction security of the user based on the user's real motion information to obtain the transaction verification result, the transaction verification system can input the motion feature vector into the target classification model, perform classification processing through the target classification model, and obtain the classification result, wherein the classification result represents the probability that the transaction of the user corresponding to the motion feature vector is a safe transaction; and the transaction verification result is determined based on the classification result.

[0106] Optionally, the target classification model can be a target random forest classification model, which can be obtained by training an initial random forest classification model based on a sample motion feature vector (the same as the acquisition process of the above motion feature vector). The target classification model includes multiple decision trees, and each decision tree independently determines the user's transaction category and probability.

[0107] Optionally, during the classification processing based on the target classification model, the transaction verification system first inputs the extracted motion feature vector into the target classification model, where the motion feature vector represents the user's actual motion information, such as body movement amplitude, direction, frequency, and movement of body parts (hands, feet), etc. Each decision tree is then used to determine the transaction category and probability, and the judgment results of each decision tree are weighted averaged to obtain the probability that the user transaction corresponding to the input motion feature vector is a safe transaction, i.e., the classification result, and finally the transaction verification result is determined based on the classification result and a preset security threshold.

[0108] Optionally, the preset security threshold represents the lower limit of the probability that the user transaction is a safe transaction. If the classification result is greater than or equal to the threshold, it is a safe transaction. If the classification result is less than the threshold, it is an unsafe transaction.

[0109] In some embodiments, it is assumed that the target classification model includes three decision trees, and the extracted motion feature vectors (such as [0.3, 0.7, 1.2, ...]) are input into the target classification model. The transaction types and probabilities predicted by the three decision trees are respectively: decision tree 1 (weight 0.5): category "safe", probability 0.9; decision tree 2 (weight 0.3): category "safe", probability 0.8; decision tree 3 (weight 0.2): category "unsafe", probability 0.8. Then the judgment results of all decision trees are weighted averaged, and the processing result (the probability that the transaction is a safe transaction) is 0.73. Comparing it with the security threshold of 0.65, it can be seen that the processing result is greater than the preset threshold, and the transaction verification result of this transaction is safe.

[0110] It should be noted that by processing the motion feature vector based on the target classification model and judging the security of the user's transaction behavior through probabilistic output, it is possible to obtain accurate results based on accurate data, thereby improving the applicability of the system in various scenarios and thereby improving the security of the system's transaction verification.

[0111] In an optional embodiment, after obtaining the transaction verification result, the transaction verification system may allow execution of the transaction requested by the transaction request if the transaction verification result indicates that the transaction security verification has passed; and prohibit execution of the transaction requested by the transaction request if the transaction verification result indicates that the transaction security verification has failed.

[0112] Optionally, after the transaction verification system completes the user's identity authentication, motion feature extraction and classification processing, if the transaction verification result obtained indicates that the user's transaction is a "safe transaction", the transaction request is approved and the system allows the execution of specific operations of the transaction, such as completing fund transfer, withdrawal, payment and other requests; if the transaction verification result obtained indicates that the user's transaction is an "unsafe transaction" (when there is abnormal behavior or identity authentication fails), the transaction request is rejected and the system terminates the transaction operation.

[0113] It should be noted that executing corresponding operations according to clear transaction verification results ensures the connection between transaction verification and actual operations, as well as the authenticity of the system's transaction verification results, thereby improving the security of the system's transaction verification.

[0114] In an optional embodiment, Figure 3 is a flowchart of a transaction verification method provided according to an embodiment of the present application. Figure 3 An optional transaction verification method of the embodiment of the present application is described. Figure 3As shown, when conducting transaction verification, the transaction verification system first obtains the user's fingerprint and face image through the fingerprint collection device and the dedicated camera device on the ATM machine, and processes the fingerprint and face image to extract features. For the fingerprint image, the fingerprint image preprocessing, fingerprint texture refinement and minutiae extraction operations are performed respectively to obtain the real fingerprint feature, wherein the preprocessing operation can use noise removal or contrast enhancement, and the fingerprint minutiae can include the end of the ridge and the bifurcation of the ridge; for the face image, the iris area recognition, iris area segmentation and iris information extraction operations are performed respectively to obtain the real iris feature. Then the first level of identity verification is performed, combining the real fingerprint feature and the real iris feature with the reference fingerprint feature and reference iris feature preset by the user to verify whether the user's identity is passed. If not, the system prohibits the transaction. If passed, the second level of identity verification is performed. When performing the second level of identity verification, the user's real motion information (portrait activity video) is first obtained, and the difference between the motions is captured therefrom to generate a motion projection matrix, and then the information in the motion projection matrix is ​​extracted to generate a motion feature vector, wherein the motion projection matrix is ​​generated based on the frame difference method, and the motion feature vector is generated based on the strip method. Finally, the motion feature vector is classified through a target classification model (e.g., a target random forest model) to detect user behavior to determine whether the transaction is legal. If the result indicates that it is illegal, the identity authentication fails and the system prohibits the transaction. If the result indicates that it is legal, the transaction is allowed.

[0115] In the embodiments of the present application, a method of transaction security verification is adopted based on the user's fingerprint features, iris features and motion information as identity authentication information. By performing the first-level identity authentication based on fingerprint features and iris features, the uniqueness of the verification data is guaranteed, and the risk of data forgery is effectively avoided. By performing the second-level identity authentication based on the user's motion information, the deficiency of static biometric verification is compensated, and the combination of static verification and dynamic verification methods is realized, thereby improving the system's ability to judge transaction behavior. By combining motion information with biometrics for identity authentication, the security of transaction verification is improved, the risk of user identity forgery or theft is reduced, and the user's transaction security is thereby improved.

[0116] It can be seen that the solution provided in the present application achieves the purpose of conducting transaction security verification based on the user's fingerprint features, iris features and motion information as identity authentication information, thereby achieving the technical effect of improving the security of transaction verification, and further solving the problem of low security of transaction verification caused by conducting transaction verification on users based on a single feature in related technologies.

[0117] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0118] Example 2

[0119] The embodiment of the present application also provides a transaction verification device. It should be noted that the transaction verification device of the embodiment of the present application can be used to execute the transaction verification method provided by the embodiment of the present application. The transaction verification device provided by the embodiment of the present application is introduced below.

[0120] According to an embodiment of the present application, a device for implementing the above transaction verification method is also provided, such as Figure 4 As shown, the device comprises:

[0121] The first acquisition module 401 is used to acquire the real fingerprint feature of the user and the real iris feature of the user when receiving a transaction request from the user;

[0122] Authentication module 402, used to authenticate the user based on the user's real fingerprint features and real iris features;

[0123] The second acquisition module 403 is used to acquire the user's real movement information when the identity authentication is passed;

[0124] The verification module 404 is used to verify the transaction security of the user based on the user's real movement information to obtain a transaction verification result.

[0125] It should be noted that the above-mentioned first acquisition module 401, authentication module 402, second acquisition module 403 and verification module 404 correspond to steps S201 to S204 in Example 1, and the instances and application scenarios implemented by the four modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned Example 1.

[0126] In the embodiments of the present application, a method of transaction security verification is adopted based on the user's fingerprint features, iris features and motion information as identity authentication information. By performing the first-level identity authentication based on fingerprint features and iris features, the uniqueness of the verification data is guaranteed, and the risk of data forgery is effectively avoided. By performing the second-level identity authentication based on the user's motion information, the deficiency of static biometric verification is compensated, and the combination of static verification and dynamic verification methods is realized, thereby improving the system's ability to judge transaction behavior. By combining motion information with biometrics for identity authentication, the security of transaction verification is improved, the risk of user identity forgery or theft is reduced, and the user's transaction security is thereby improved.

[0127] It can be seen that the solution provided in the present application achieves the purpose of conducting transaction security verification based on the user's fingerprint features, iris features and motion information as identity authentication information, thereby achieving the technical effect of improving the security of transaction verification, and further solving the problem of low security of transaction verification caused by conducting transaction verification on users based on a single feature in related technologies.

[0128] Optionally, in the transaction verification device provided in the embodiment of the present application, the first acquisition module also includes: a first acquisition submodule, used to acquire the user's real fingerprint image; a first processing submodule, used to preprocess the real fingerprint image to obtain a preprocessed real fingerprint image, wherein the preprocessing includes at least one of the following: noise removal, contrast enhancement; a second processing submodule, used to refine the fingerprint texture in the preprocessed real fingerprint image to obtain a target fingerprint image; a first determination submodule, used to identify fingerprint detail points from the target fingerprint image, and determine the real fingerprint features based on the identified fingerprint detail points, wherein the fingerprint detail points include at least one of the following: ridge ends and ridge bifurcations.

[0129] Optionally, in the transaction verification device provided in the embodiment of the present application, the first acquisition module also includes: a second acquisition submodule, used to acquire the user's facial image; and an identification submodule, used to identify the iris area from the facial image and perform feature extraction on the iris area to obtain real iris features.

[0130] Optionally, in the transaction verification device provided in the embodiment of the present application, the second acquisition module also includes: a third acquisition sub-module, used to obtain a portrait activity video of the user in the transaction area, wherein the transaction area is the area where the user initiates a transaction request; a third processing sub-module, used to process the portrait activity video based on a frame difference method to obtain a motion projection matrix, wherein the elements in the motion projection matrix represent the cumulative value of the motion intensity of the pixel points in the portrait activity video; and a second determination sub-module, used to determine the user's real motion information based on the motion projection matrix.

[0131] Optionally, in the transaction verification device provided in the embodiment of the present application, the second determination submodule also includes: a first slicing unit, used to slice the motion projection matrix by column to obtain multiple first vectors; a second slicing unit, used to slice the motion projection matrix by row to obtain multiple second vectors; a splicing unit, used to splice the multiple first vectors and the multiple second vectors to obtain a motion feature vector, wherein the motion feature vector is used to characterize the user's real motion information.

[0132] Optionally, in the transaction verification device provided in the embodiment of the present application, the verification module also includes: a classification submodule, used to input the motion feature vector into a target classification model, perform classification processing through the target classification model, and obtain a classification result, wherein the classification result represents the probability that the transaction of the user corresponding to the motion feature vector is a safe transaction; a third determination submodule, used to determine the transaction verification result based on the classification result.

[0133] Optionally, in the transaction verification device provided in the embodiment of the present application, the transaction verification device also includes: a first execution module, used to allow the execution of the transaction requested by the transaction request when the transaction verification result indicates that the transaction security verification has passed; and a second execution module, used to prohibit the execution of the transaction requested by the transaction request when the transaction verification result indicates that the transaction security verification has not passed.

[0134] It should be noted that the first acquisition module 401, the authentication module 402, the second acquisition module 403 and the verification module 404 correspond to steps S201 to S204 in Example 1, and the four modules and the corresponding steps implement the same examples and application scenarios, but are not limited to the contents disclosed in the above-mentioned Example 1. It should be noted that the above-mentioned modules or units may be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n), and the above-mentioned modules may also be part of the device and may be run in the computer terminal 10 provided in Example 1.

[0135] Example 3

[0136] An embodiment of the present application may provide an electronic device, Figure 5 is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 5 As shown, the electronic device may include: one or more ( Figure 5 (only one is shown) processor 1002, memory 1004, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0137] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0138] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: upon receiving a transaction request from the user, obtain the user's real fingerprint features and the user's real iris features; authenticate the user based on the user's real fingerprint features and real iris features; if the identity authentication is successful, obtain the user's real motion information; and verify the transaction security of the user based on the user's real motion information to obtain a transaction verification result.

[0139] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain the user's real fingerprint image; preprocess the real fingerprint image to obtain a preprocessed real fingerprint image, wherein the preprocessing includes at least one of the following: noise removal, contrast enhancement; refine the fingerprint texture in the preprocessed real fingerprint image to obtain a target fingerprint image; identify fingerprint detail points from the target fingerprint image, and determine the real fingerprint features based on the identified fingerprint detail points, wherein the fingerprint detail points include at least one of the following: ridge end and ridge bifurcation.

[0140] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: obtaining the user's facial image; identifying the iris area from the facial image, and extracting features from the iris area to obtain real iris features.

[0141] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: obtain a portrait activity video of the user in the transaction area, wherein the transaction area is the area where the user initiates a transaction request; process the portrait activity video based on the frame difference method to obtain a motion projection matrix, wherein the elements in the motion projection matrix represent the cumulative value of the motion intensity of the pixel points in the portrait activity video; and determine the user's real motion information based on the motion projection matrix.

[0142] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: divide the motion projection matrix by columns to obtain multiple first vectors; divide the motion projection matrix by rows to obtain multiple second vectors; splice the multiple first vectors and the multiple second vectors to obtain a motion feature vector, wherein the motion feature vector is used to characterize the user's real motion information.

[0143] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: input the motion feature vector into the target classification model, perform classification processing through the target classification model, and obtain a classification result, wherein the classification result represents the probability that the transaction of the user corresponding to the motion feature vector is a safe transaction; determine the transaction verification result based on the classification result.

[0144] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: after obtaining the transaction verification result, if the transaction verification result indicates that the transaction security verification has passed, allow the transaction requested by the transaction request to be executed; if the transaction verification result indicates that the transaction security verification has not passed, prohibit the execution of the transaction requested by the transaction request.

[0145] In the embodiments of the present application, a method of transaction security verification is adopted based on the user's fingerprint features, iris features and motion information as identity authentication information. By performing the first-level identity authentication based on fingerprint features and iris features, the uniqueness of the verification data is guaranteed, and the risk of data forgery is effectively avoided. By performing the second-level identity authentication based on the user's motion information, the deficiency of static biometric verification is compensated, and the combination of static verification and dynamic verification methods is realized, thereby improving the system's ability to judge transaction behavior. By combining motion information with biometrics for identity authentication, the security of transaction verification is improved, the risk of user identity forgery or theft is reduced, and the user's transaction security is thereby improved.

[0146] It can be seen that the solution provided in the present application achieves the purpose of conducting transaction security verification based on the user's fingerprint features, iris features and motion information as identity authentication information, thereby achieving the technical effect of improving the security of transaction verification, and further solving the problem of low security of transaction verification caused by conducting transaction verification on users based on a single feature in related technologies.

[0147] It can be understood by those skilled in the art that Figure 5 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 5The structure of the electronic device is not limited. Figure 5 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 5 Different configurations are shown.

[0148] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0149] Example 4

[0150] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the transaction verification method provided in the first embodiment.

[0151] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0152] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing the steps of the transaction verification method.

[0153] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0154] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0155] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0156] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0157] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0158] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0159] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A transaction verification method, characterized in that: include: Upon receiving a transaction request from a user, obtaining a real fingerprint feature of the user and obtaining a real iris feature of the user; Authenticating the user based on the user's real fingerprint features and real iris features; When the identity authentication is passed, obtaining the real movement information of the user; Transaction security verification is performed on the user based on the real movement information of the user to obtain a transaction verification result.

2. The method according to claim 1, characterized in that Acquiring the real fingerprint feature of the user, including: Acquire a real fingerprint image of the user; Preprocessing the real fingerprint image to obtain a preprocessed real fingerprint image, wherein the preprocessing includes at least one of the following: noise removal and contrast enhancement; Performing a thinning process on the fingerprint texture in the preprocessed real fingerprint image to obtain a target fingerprint image; Fingerprint minutiae points are identified from the target fingerprint image, and the real fingerprint features are determined based on the identified fingerprint minutiae points, wherein the fingerprint minutiae points include at least one of the following: a ridge end and a ridge bifurcation.

3. The method according to claim 1, characterized in that: Acquiring the real iris features of the user, including: Acquire a facial image of the user; An iris region is identified from the face image, and features are extracted from the iris region to obtain the real iris features.

4. The method according to claim 1, characterized in that: Acquiring the real movement information of the user, including: Acquire a portrait activity video of the user in a transaction area, wherein the transaction area is an area where the user initiates the transaction request; Processing the portrait activity video based on a frame difference method to obtain a motion projection matrix, wherein the elements in the motion projection matrix represent the cumulative values ​​of motion intensity of pixel points in the portrait activity video; The actual motion information of the user is determined based on the motion projection matrix.

5. The method according to claim 4, characterized in that Determining the real motion information of the user based on the motion projection matrix includes: Divide the motion projection matrix by columns to obtain a plurality of first vectors; Dividing the motion projection matrix by row to obtain a plurality of second vectors; The multiple first vectors and the multiple second vectors are concatenated to obtain a motion feature vector, wherein the motion feature vector is used to represent the real motion information of the user.

6. The method according to claim 5, characterized in that Performing transaction security verification on the user based on the real movement information of the user to obtain a transaction verification result, including: Inputting the motion feature vector into a target classification model, performing classification processing through the target classification model, and obtaining a classification result, wherein the classification result represents the probability that the transaction of the user corresponding to the motion feature vector is a safe transaction; The transaction verification result is determined based on the classification result.

7. The method according to claim 1, characterized in that After obtaining the transaction verification result, the method further includes: If the transaction verification result indicates that the transaction security verification has passed, allowing the transaction requested by the transaction request to be executed; When the transaction verification result indicates that the transaction security verification has not been passed, the transaction requested by the transaction request is prohibited from being executed.

8. A transaction verification device, characterized in that: include: A first acquisition module, configured to acquire the real fingerprint feature of the user and the real iris feature of the user upon receiving a transaction request from the user; An authentication module, used to authenticate the user based on the real fingerprint feature and the real iris feature of the user; A second acquisition module, used for acquiring the real movement information of the user when the identity authentication is passed; The verification module is used to verify the transaction security of the user based on the real movement information of the user to obtain a transaction verification result.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the computer-readable storage medium is located is controlled to execute the transaction verification method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: A memory storing an executable program; A processor, configured to run the program, wherein the program, when running, executes the transaction verification method described in any one of claims 1 to 7.

11. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the transaction verification method described in any one of claims 1 to 7 are implemented.

Images