Risk identification method and device, equipment and medium

Abstract

The embodiment of the invention discloses a risk identification method and device, equipment and a medium. The scheme comprises the steps of obtaining multiple frames of to-be-recognized images provided by a terminal; determining the multi-frame image resolution of the multi-frame to-be-identified image; judging whether the resolution of the multi-frame image is matched with a preset resolution or not; the preset resolution at least comprises a first resolution and a second resolution; and if the resolution of the multiple frames of images is not matched with the preset resolution, determining that the multiple frames of images to be identified have risks.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, equipment and medium for risk identification. Background Art

[0002] With the development of computer technology, more and more businesses can be handled through some terminals. For example, in many business fields such as business, finance, and payment, key business steps such as user authentication and operation authorization can be performed based on image or video recognition. For example, face recognition is used to verify whether the user performing the operation is the user himself, or to determine whether the user operation can be performed. Therefore, in order to ensure the security of identity recognition, a method for detecting risks of images to be identified is urgently needed. Summary of the invention

[0003] The embodiments of this specification provide a method, apparatus, device and medium for risk identification to improve the security of identity identification.

[0004] To solve the above technical problems, the embodiments of this specification are implemented as follows: A risk identification method provided in an embodiment of this specification includes: Obtain multiple frames of images to be recognized provided by the terminal; Determine the resolution of multiple frames of images to be recognized; Determine whether the resolution of the multiple frames of images matches a preset resolution; the preset resolution includes at least a first resolution and a second resolution; If the resolution of the multiple frames of images does not match the preset resolution, it is determined that there is a risk in the multiple frames of images to be identified.

[0005] A risk identification method provided in an embodiment of this specification includes: Get image acquisition instructions; Based on the image acquisition instruction, an image is acquired according to a preset resolution; the preset resolution includes at least a first resolution and a second resolution; Send multiple frames of images to be identified to a server; the server is used to execute the above-mentioned risk identification method.

[0006] An embodiment of this specification provides a risk identification device, including: The image acquisition module is used to acquire multiple frames of images to be recognized provided by the terminal.

[0007] The resolution determination module is used to determine the resolution of multiple frames of images to be identified.

[0008] The judgment module is used to judge whether the resolution of the multiple frames of images matches a preset resolution; the preset resolution includes at least a first resolution and a second resolution.

[0009] The risk confirmation module is used to determine that there is a risk in the multiple frames of images to be identified if the resolution of the multiple frames of images does not match the preset resolution.

[0010] An embodiment of this specification provides a risk identification device, including: An instruction acquisition module, used for acquiring image acquisition instructions; An acquisition module, configured to acquire an image according to a preset resolution based on the image acquisition instruction; the preset resolution includes at least a first resolution and a second resolution; The image sending module is used to send multiple frames of images to be identified to a server; the server is used to execute the above-mentioned risk identification method.

[0011] A risk identification device provided in an embodiment of this specification includes: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: Obtain multiple frames of images to be recognized provided by the terminal; Determine the resolution of multiple frames of images to be recognized; Determine whether the resolution of the multiple frames of images matches a preset resolution; the preset resolution includes at least a first resolution and a second resolution; If the resolution of the multiple frames of images does not match the preset resolution, it is determined that there is a risk in the multiple frames of images to be identified.

[0012] A risk identification device provided in an embodiment of this specification includes: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: Get image acquisition instructions; Based on the image acquisition instruction, an image is acquired according to a preset resolution; the preset resolution includes at least a first resolution and a second resolution; Send multiple frames of images to be identified to a server; the server is used to execute the above-mentioned risk identification method.

[0013] An embodiment of the present specification provides a computer-readable medium on which computer-readable instructions are stored. The computer-readable instructions can be executed by a processor to implement a risk identification method.

[0014] An embodiment of this specification can achieve the following beneficial effects: The preset resolution in the embodiment of this specification includes different resolutions. By matching the acquired resolution of multiple frames of images to be identified with the preset resolution, it is possible to determine whether there are risks in the multiple frames of images to be identified, thereby improving the security of identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of this specification 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 recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0016] Figure 1 This is a schematic diagram of an application scenario of a risk identification method in an embodiment of this specification; Figure 2 A flowchart of a risk identification method provided in an embodiment of this specification; Figure 3 A flow chart of a risk identification method provided in an embodiment of this specification; Figure 4 A swim lane diagram of a risk identification method provided in an embodiment of this specification; Figure 5 The embodiments of this specification provide corresponding to Figure 2 A schematic diagram of the structure of a risk identification device; Figure 6 The embodiments of this specification provide corresponding to Figure 3 A schematic diagram of the structure of a risk identification device; Figure 7 A schematic diagram of the structure of a risk identification device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of one or more embodiments of this specification clearer, the technical solutions of one or more embodiments of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of one or more embodiments of this specification.

[0018] To facilitate the understanding of the solution, some terms are explained here: H5 terminal: refers to the online application service accessed through the browser.

[0019] Face recognition: is a biometric technology that verifies personal identity by analyzing facial features.

[0020] Video injection attack: A cyber attack method that deceives face recognition systems by injecting fake video data into the system.

[0021] Resolution: The number of pixels in an image or video in the horizontal and vertical directions.

[0022] Existing recognition methods mainly use static camera images for quality detection, the camera's image acquisition parameters are fixed, or rely on user action verification, etc. The main disadvantages of these solutions include being easily deceived by high-quality pre-recorded videos, and requiring user cooperation, which has a significant impact on user experience.

[0023] Moreover, with the popularization of face recognition technology, H5-end face recognition technology has developed rapidly because it does not require the installation of additional terminal application apps. However, H5-end face recognition is limited by the open capabilities of the browser and is vulnerable to video injection attacks. Attackers can attack the system through pre-recorded face videos. Image recognition-related protection measures are insufficient and cannot effectively respond to such attacks, resulting in security risks.

[0024] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0025] Figure 1 Schematic diagram of an application scenario of a risk identification method in an embodiment of this specification. Figure 1As shown, the solution may include a terminal 1 and a server 2. The terminal 1 may have an image acquisition function, may have an acquisition component such as a camera, or may control an acquisition component such as a camera. The terminal 1 may acquire images or videos, and send the images or videos to the server 2. The server 2 has an image recognition program, which may recognize the acquired images or videos, and may also feed back recognition result information to the terminal 1. In practical applications, if the terminal 1 is not illegally attacked, the images or videos acquired by the server 2 may be images or videos acquired by the camera of the terminal 1 or the lens of the terminal camera. If the terminal 1 is illegally attacked, such as an injection attack, the images acquired by the server 2 may be images or videos injected by the injection attack.

[0026] Next, a risk identification method provided in an embodiment of the specification will be described in detail with reference to the accompanying drawings.

[0027] Figure 2 A schematic diagram of a risk identification method provided in an embodiment of the present specification. From a program perspective, the execution subject of the process can be a program installed on an application server or an application client.

[0028] like Figure 2 As shown, the process may include the following steps.

[0029] Step 202: Acquire multiple frames of images to be recognized provided by the terminal.

[0030] The terminal may be a device terminal capable of performing business processing, such as a mobile phone, a computer, a cash register, a self-service checkout device, a business terminal of a financial institution, etc. The terminal may include a collection component such as a camera, and the terminal may also be associated with a collection component such as a camera, and the terminal may send the collected image. The collection component such as a camera may be located in the terminal, or may be set separately from the terminal, which is not specifically limited here.

[0031] The multiple frames of images to be identified may be multiple frames of images collected within a preset time period, and may include at least two frames of images, or may be 10 frames, 15 frames, etc. The specific number of image frames may be set according to actual business requirements. One frame of image may represent a captured still image.

[0032] The method in the embodiments of this specification can be applied to identity recognition, and the image to be recognized can be an image including biometric features, such as face, iris, fingerprint, palm print and other biometric features.

[0033] In practical applications, multiple frames of images to be identified can represent images collected by the terminal and sent to the server. If the terminal is attacked illegally, multiple frames of images to be identified can also represent images provided by the attacker, which can be called injection attack images or injection attack video streams, which are not images or videos normally collected by the terminal. For example, an attacker can hijack a camera, block the camera's real video stream from being sent to the server, and send a false data stream, that is, an injection attack video stream, to the server as the image to be identified.

[0034] In practical applications, illegal attacks are generally carried out in the form of video injection. In this case, the resolution of the injected attack image or the images of different frames in the injected attack video stream is usually the same.

[0035] Step 204: Determine the image resolutions of the multiple frames of images to be recognized.

[0036] The multi-frame image resolution may represent the resolution of multiple frames of images to be recognized, which may be the resolution of each frame in the multiple frames of images to be recognized, or the resolution of some frames of images, such as the resolution of at least two frames in the multiple frames of images to be recognized, and so on.

[0037] Step 206: Determine whether the resolution of the multiple image frames matches a preset resolution.

[0038] The preset resolution includes at least a first resolution and a second resolution.

[0039] The preset resolution indicates the actual resolution to be used, which can be the resolution used by the image acquisition component of the terminal. Before the terminal acquires an image, the resolution of the image acquisition component such as the camera can be set to the preset resolution, and then the image is acquired. The preset resolution can indicate the resolution actually used by the image acquisition component of the terminal before the server obtains multiple frames of images to be recognized provided by the terminal.

[0040] The preset resolution is a dynamic resolution, and may include at least two different resolutions, a first resolution and a second resolution, and may include a third resolution, a fourth resolution, etc., as long as different resolutions are included.

[0041] The preset resolution may also include several periodic resolutions. A periodic resolution may include at least a first resolution and a second resolution. Assuming that a periodic resolution is resolution A and resolution B, and the preset resolution is 2 periodic resolutions, then the preset resolution may represent the resolution collected in the order of resolution A, resolution B, resolution A, and resolution B.

[0042] It is understandable that the specific content of the preset resolution in the embodiments of this specification is not specifically limited and can be set according to actual needs. For example, for services with higher security, the number of different resolutions included in the preset resolution can be greater, or the resolution change rules can be more complicated.

[0043] Step 208: If the resolution of the multiple frames of images does not match the preset resolution, it is determined that there is a risk in the multiple frames of images to be identified.

[0044] If the resolution of multiple frames of images to be identified does not match the preset resolution, it means that there is a risk in the multiple frames of images to be identified, and they may not be the images actually collected by the image collection component of the terminal, for example, they may be injected attack images.

[0045] In actual applications, if the server is a server that processes business through image recognition, after determining that multiple frames of images to be recognized have risks, the subsequent business processing flow for the images to be recognized can be terminated. For example, in business scenarios such as online banking, e-commerce, and remote office systems, if there is a risk, it can be determined that the user identity authentication has failed and the subsequent identity authentication process can be terminated. For example, the payment process, the financial business processing process, the process of controlling the action of the device, such as terminating the opening of the gate, smart door lock, etc., can also be terminated. The transaction process can also be terminated, etc. Prompt information can also be sent to the terminal to remind the user of the risk, or a reminder message can be sent to remind the user to re-process the business.

[0046] In practical applications, if the resolution of multiple frames of images to be identified matches the preset resolution, it can be determined that there is no risk in the multiple frames of images to be identified, or it can be determined that there is no injection attack risk in the multiple frames of images to be identified, and subsequent business processing can be performed. Corresponding prompt information can also be sent to the terminal.

[0047] It should be understood that the order of some steps in the methods described in one or more embodiments of this specification can be interchanged according to actual needs, or some steps can be omitted or deleted.

[0048] Injection attacks usually use images with fixed resolution as injection attack images. In the embodiments of this specification, the preset resolution includes at least two different resolutions. By matching the resolutions of multiple frames of images to be identified with the dynamic preset resolution, it is possible to determine whether the images to be identified have risks, thereby improving identification security.

[0049] The dynamic resolution mechanism can effectively distinguish real-time facial images from pre-recorded videos at a low cost. The server side can determine whether there is a risk, such as whether there is an injection attack, by performing a simple check without significantly increasing computing and hardware costs.

[0050] On the other hand, in the embodiments of this specification, the user does not need to cooperate in performing additional actions, and can effectively identify high-quality video injection attacks. By using dynamic resolution rather than relying on video content analysis, the reliance on high-performance server resources is also reduced.

[0051] The preset resolution used by the image acquisition application in the embodiment of this specification may be sent by the server to the terminal. Optionally, before obtaining the multiple frames of images to be recognized provided by the terminal in the embodiment of this specification, the following may also be included: Acquire a parameter acquisition request sent by the terminal; the parameter acquisition request is generated by the terminal based on an image acquisition operation; Based on the parameter acquisition request, the preset resolution is sent to the terminal so that the terminal captures images according to the preset resolution.

[0052] In actual applications, the terminal can be equipped with a business processing application, which can be a terminal application APP, a mini program, or an H5 page, etc. The user can trigger the image acquisition function of the terminal, for example, by clicking the start button in the face recognition interface in the H5 face recognition application, or by clicking the confirmation payment control after the cashier or consumer has counted the goods to be settled, etc., which can trigger the image acquisition function of the terminal.

[0053] The terminal can generate a parameter acquisition request based on the image acquisition operation to request the server to send a preset resolution. In actual applications, the parameter acquisition request can also be part of the information in the image recognition trigger request generated by the terminal based on the image acquisition operation. The image recognition trigger request can be used to trigger the server to perform the image recognition process. After obtaining the image recognition trigger request, the server can send the preset resolution to the terminal.

[0054] The parameter acquisition request may include a device identifier, a user identifier, a service identifier, etc., so that the server can feed back the determined preset resolution to the device sending the request. If the terminal is equipped with a terminal application, the server may be a server corresponding to the terminal application, and the preset resolution may be sent to the terminal application to control the image acquisition component of the terminal to acquire images according to the preset resolution. It is understandable that in actual applications, the user can authorize the terminal application to use the acquisition component or adjust the parameters of the acquisition component, so that the terminal can automatically adjust the parameters such as the resolution of the acquisition component.

[0055] The server can randomly generate preset resolutions, such as 640×480 and 1920×1080, and can also select a preset resolution from a set storing multiple resolutions, which can include multiple different resolutions, such as 640×480, 800×600, 1024×768, 1280×1024, 1280×720, 1920×1080, 2048×1080, 3840×2160, 7680×4320, 4000×3000, etc.

[0056] In practical applications, the preset resolution can be the full resolution required in the entire acquisition process, or it can be a required partial resolution. For example, if 10 frames of images need to be acquired, the preset resolution can be the resolution of 10 frames, or it can be the resolution of some frames, such as frames 1-3, 5-7, etc. If the preset resolution is the partial resolution required in the acquisition process, the other parts can be acquired at the default resolution of the terminal.

[0057] As another implementation, the terminal may also generate a preset resolution. For example, after obtaining the user's image acquisition operation, the preset resolution may be generated, and the camera and other acquisition components may be controlled to acquire images according to the preset resolution. The terminal may also send the determined preset resolution to the server so that the server can perform image risk identification. In actual applications, the terminal may be equipped with a terminal application, such as the above-mentioned face recognition application. The application may include multiple resolutions. After obtaining the user's image acquisition operation, at least two resolutions may be randomly selected from the multiple resolutions, or at least two resolutions may be randomly generated.

[0058] Considering that the server environment is more secure than that of the terminal, the preset resolution is generated by the server and sent to the terminal to further improve security.

[0059] In actual applications, due to hardware or software differences, different terminals or image acquisition components associated with the terminals may support different resolutions. To ensure the normal progress of the recognition process, the preset resolution may be the resolution supported by the terminal. Optionally, the parameter acquisition request may include the device identification of the terminal; sending the preset resolution to the terminal based on the parameter acquisition request may specifically include: Based on the device identification of the terminal, the preset resolution executable by the terminal is selected from a preset resolution set.

[0060] The server may store the correspondence between different terminals and executable resolutions, and the executable resolution of the terminal may be determined based on the correspondence. The server may also store the correspondence between different terminals and the highest executable resolution, and the executable resolution of the terminal may be a resolution less than or equal to the highest resolution. The server may first determine the highest executable resolution of the terminal, and then determine a preset resolution based on the highest resolution, and each resolution included in the preset resolution is less than or equal to the highest resolution.

[0061] In actual applications, the resolution supported by the terminal can be determined through the product introduction information of the terminal, or the terminal manufacturer or provider can provide resolution-related information. The source of the resolution is not specifically limited here.

[0062] In the embodiment of this specification, the preset resolution is a dynamic resolution including multiple different resolutions. As an implementation mode, the above-mentioned determination of whether the resolution of the multiple frames of images matches the preset resolution may specifically include: It is determined whether the resolutions of the multiple image frames include each of the preset resolutions.

[0063] If the resolution of the multiple image frames does not include each resolution in the preset resolution, it may indicate that the resolution of the multiple image frames does not match the preset resolution.

[0064] Specifically, the resolution of each frame of the image to be identified can be determined by the image attribute information of multiple frames of the image to be identified, and a resolution set including the resolution information of each frame of the image to be identified can be obtained, and then it can be determined whether the resolution set includes each resolution in the preset resolution.

[0065] In actual applications, the resolution set of the resolution information of each frame of the image to be identified may also include other resolutions besides the preset resolution. For example, assuming that 10 frames of images need to be collected, the preset resolution sent by the server to the terminal is the resolution used by the first 3 frames and the last 3 frames, and other frames, such as the middle 4 frames, can use the terminal's default resolution. During the inspection, if the resolution set of the resolution information of each frame of the image to be identified is inclusive of the preset resolution, it can also be determined that the resolution of multiple frames of images matches the preset resolution.

[0066] In order to further improve security, the preset resolution can also be all the resolutions required in the acquisition process. The resolution of each frame of the image to be identified is completely consistent with the preset resolution. It can be determined that the resolution of multiple frames of images matches the preset resolution. If one of the resolutions is inconsistent, it can be determined that the resolution of multiple frames of images does not match the preset resolution. In practical applications, appropriate verification rules can be selected according to business needs, and no specific restrictions are made here.

[0067] In practical applications, multiple frames of images to be identified may be images transmitted in the form of video streams, which may also be called data streams, wherein the resolution of one frame of the image to be identified may be obtained in the order of the video stream, and then it may be determined whether the resolution of the frame of the image to be identified is a resolution in the preset resolution. If the resolution of the frame is not a resolution in the preset resolution, it may be determined that the resolution of multiple frames of images does not match the preset resolution, and there is a risk, and there is no need to determine the subsequent frames. If the resolution of the frame is a resolution in the preset resolution, the resolution of the next frame of the image to be identified may be obtained, and it may be determined whether the resolution of the next frame is a resolution in the preset resolution, and so on, to determine whether the resolution of multiple frames of the image to be identified matches the preset resolution.

[0068] The resolutions of each frame or part of the frames in the multiple frames of images to be identified can also be matched synchronously. If the resolution of a frame does not match the preset resolution or the number of frames in the multiple frames of images to be identified that do not match the preset resolution is greater than or equal to the preset number of frames, or the mismatch probability is greater than or equal to a preset threshold, it can be determined that there is a risk.

[0069] In the embodiments of this specification, the preset resolution may also specifically indicate the resolution corresponding to each frame or part of the frames, and the preset resolution may include frame number information so that the terminal can capture the image of the frame number using the corresponding resolution according to the frame number. For example, the preset resolution may include the resolution used to capture each frame or a specified frame image. In the embodiments of this specification, the preset resolution may include a variety of different resolutions, and one or more of the resolutions may be verified during verification, or one or more frames of images may be verified.

[0070] As an implementation manner, the preset resolution in the embodiments of this specification may also include a first frame number corresponding to the first resolution. Wherein, the above-mentioned determination of the resolution of multiple frames of images to be identified may specifically include: determining a third resolution of the image to be identified corresponding to the first frame number in the multiple frames of images to be identified.

[0071] Correspondingly, the above-mentioned determination of whether the resolution of the multiple frames of images matches the preset resolution specifically includes: determining whether the third resolution is the same as the first resolution. If the third resolution is not the same as the first resolution, it indicates that the resolution of the multiple frames of images does not match the preset resolution.

[0072] In the process of biometric recognition, if a video stream is used as the input source, each frame of the image will have a unique identifier, usually called a frame number or frame ID. The frame number is usually an integer that increases in sequence in the video stream. For example, the first frame may be number 0 or 1, the next frame may be number 1 or 2, and so on.

[0073] In the embodiment of this specification, the preset resolution may include a corresponding frame number, and the first frame number may represent the frame number of the image that needs to be acquired with the first resolution during the image acquisition process. The first sequence number may include one sequence number or multiple sequence numbers.

[0074] For example, suppose that 6 frames of images need to be collected, and the frame numbers are 1 to 6. If the first resolution corresponds to the sequence number 1, it means that the first frame needs to be collected using the first resolution; if the first resolution corresponds to the sequence numbers 1 and 3, it means that the first frame and the third frame need to be collected using the first resolution.

[0075] The third resolution is the resolution of the image to be identified whose frame number is the first frame number among the multiple frames of images to be identified acquired by the server. Wherein, whether the resolution of the multiple frames of images matches the preset resolution can be determined by determining whether the third resolution is the same as the first resolution.

[0076] If the first frame number is a plurality of frame numbers, such as frame numbers 1 and 3, as an example, the third resolution may be the resolution of a frame to be identified whose frame number is any frame number in the first frame number among the plurality of frames to be identified, such as the resolution of the first frame or the third frame to be identified among the plurality of frames to be identified. The above determination of whether the third resolution is the same as the first resolution may be the determination of whether the resolution of a frame to be identified having any frame number is the same as the first resolution.

[0077] As another example, the third resolution may be the resolution of each frame to be identified in the multiple frames of images to be identified whose frame numbers are the frame numbers in the first frame number, such as the resolution of the first frame and the third frame to be identified in the multiple frames of images to be identified, which may be multiple identical or different resolutions. The above-mentioned determination of whether the third resolution is the same as the first resolution may be to determine whether the resolution of each frame to be identified in the multiple frames of images to be identified whose frame numbers are the frame numbers in the first frame number is the same as the first resolution. For example, determine whether the resolution of the first frame and the third frame in the multiple frames of images to be identified is the first resolution. If the resolution of one frame in the resolution of each frame to be identified in the multiple frames of images to be identified whose frame numbers are the frame numbers in the first frame number is different from the preset resolution, or the different proportion is greater than or equal to the preset threshold, it may indicate that the third resolution is different from the first resolution, and the resolution of the multiple frames of images does not match the preset resolution. Similarly, if the resolutions of the frames of images to be identified whose frame numbers are in the first frame number in the multiple frames of images to be identified are different from the preset resolution, or the difference ratio is less than the preset threshold, it can be said that the third resolution is the same as the first resolution, and the resolutions of the multiple frames of images match the preset resolution.

[0078] The preset resolution of the embodiment of this specification may also include a second frame number corresponding to the second resolution; in order to further improve the accuracy of risk identification, the second resolution in the preset resolution may also be used for judgment. Optionally, the method also includes: Determining a fourth resolution of the image to be identified corresponding to the second frame sequence number among the multiple frames of images to be identified; It is determined whether the fourth resolution is the same as the second resolution.

[0079] If the fourth resolution is the same as the second resolution, it means that the resolution of the multi-frame images does not match the preset resolution.

[0080] The second frame sequence number may represent the frame sequence number of the image that needs to be captured with the second resolution. The second sequence number may include one sequence number or multiple sequence numbers.

[0081] The fourth resolution is the resolution of the image to be identified whose frame number is the second frame number among the multiple frames of images to be identified acquired by the server, and can be multiple identical or different resolutions. In the embodiment of this specification, whether the resolution of the multiple frames of images matches the preset resolution can be determined by determining whether the fourth resolution is the same as the second resolution. The specific determination process can be similar to the above-mentioned process of determining whether the third resolution is the same as the first resolution, and will not be repeated here.

[0082] In practical applications, the above process steps of determining whether the third resolution is the same as the first resolution and determining whether the fourth resolution is the same as the second resolution can be performed simultaneously or in a preset order, which is not specifically limited here.

[0083] As an implementation, if the third resolution is the same as the first resolution and the fourth resolution is the same as the second resolution, it can indicate that the resolution of multiple frames of images matches the preset resolution, and it can also be determined that there is no risk in the multiple frames of images to be identified.

[0084] It is understandable that the descriptions such as "first" and "second" used in the embodiments of this specification are only used to distinguish different description objects and do not represent other relationships. For example, the first resolution and the second resolution mentioned above represent different resolutions, and do not represent resolutions that have a sequence or size relationship; for example, the first frame number and the second frame number mentioned above represent frame numbers corresponding to different resolutions, and do not represent the frame number of the first frame image or the frame number of the second frame image in the video stream.

[0085] In actual applications, if the third resolution is different from the first resolution, it may indicate that the resolution of multiple frames of images does not match the preset resolution, and it may be determined that there is a risk, and the process may be terminated without performing subsequent business processing steps.

[0086] To improve recognition accuracy, if the third resolution is the same as the first resolution, further determination may be performed. Optionally, the determination of whether the fourth resolution is the same as the second resolution specifically includes: If the third resolution is the same as the first resolution, it is determined whether the fourth resolution is the same as the second resolution. If the third resolution is the same as the first resolution and the fourth resolution is the same as the second resolution, it can be indicated that the resolution of the multi-frame image matches the preset resolution, there is no risk, and the subsequent processing flow can be performed.

[0087] In practical applications, after determining that the third resolution is the same as the first resolution, the fourth resolution of the image to be identified corresponding to the second frame number in the multiple frames of images to be identified can be determined, and then it can be determined whether the fourth resolution is the same as the second resolution.

[0088] It is understandable that in actual application, it is also possible to first determine whether the fourth resolution is the same as the second resolution, and if the fourth resolution is the same as the second resolution, then determine whether the third resolution is the same as the first resolution. The specific process is not repeated here.

[0089] In practical applications, the judgment can be made according to the order of each image in the video stream in the multiple frames of images to be identified. For example, if the first frame number is less than the second frame number, it can be judged whether the third resolution is the same as the first resolution; and then it can be judged whether the fourth resolution is the same as the second resolution. If the second frame number is less than the first frame number, it can be judged whether the fourth resolution is the same as the second resolution first, and then it can be judged whether the third resolution is the same as the first resolution. In practical applications, the preset resolution can be a resolution sequence set according to the preset resolution rule, which can represent a series of resolutions required for capturing images. Continuing with the above example, assuming that 6 frames of images need to be captured, the preset resolution can be a resolution sequence arranged in the order of first resolution, second resolution, first resolution, second resolution, second resolution, and second resolution, which is used to represent the resolution of each frame of image that needs to be captured. In practical applications, the preset resolution can also represent the image resolution of at least some continuous frames in the image to be captured. For example, if 10 frames of images need to be captured, the preset resolution can be the resolution that should be used for the 3rd to 8th frames of images.

[0090] In practical applications, the corresponding resolution can also be set by the acquisition time or duration. As an implementation method, the preset resolution can also include the first time information corresponding to the first resolution and the second time information corresponding to the second resolution. The first time information indicates the time information when the image acquisition component acquires the image according to the first resolution, and the second time information indicates the time information when the image acquisition component acquires the image according to the second resolution. The time information can be time period information indicating a period of time. For example, if it is necessary to acquire an image of 5 seconds, the first 2 seconds use the first resolution, and the second 3 seconds use the second resolution. After the server obtains the image to be identified, it can also determine the acquisition time of each frame of the image according to the identification information indicating the time information such as the timestamp contained in the image. The above-mentioned determination of whether the resolution of multiple frames of images matches the preset resolution can specifically include: determining whether the resolution of any frame of the image whose acquisition time is the first time information is the first resolution, and determining whether the resolution of any frame of the image whose acquisition time is the first time information is the second resolution. If the resolution of any frame of the image whose acquisition time is the first time information is the first resolution, and the resolution of any frame of the image whose acquisition time is the first time information is the second resolution, it can be determined that there is no risk in the image to be identified. If the resolution of any frame image collected at the first time information is not the first resolution, or the resolution of any frame image collected at the first time information is not the second resolution, it can be determined that the image to be identified has risks.

[0091] In practical applications, the preset resolution may also include the correspondence between each preset resolution and the corresponding preset acquisition time, for example, it may include the correspondence between the first resolution and the first time information, and it may also include the correspondence between the second resolution and the second time information. After the server obtains multiple frames of images to be identified, it can determine the correspondence between the resolution and the acquisition time of each frame of the image to be identified. The above judgment of whether the resolution of multiple frames of images matches the preset resolution may specifically include: judging whether the correspondence between the resolution and the acquisition time of each frame of the image to be identified is consistent with the correspondence between each preset resolution and the corresponding preset acquisition time in the preset resolution. If they are inconsistent, it can be indicated that the resolution of multiple frames of images does not match the preset resolution, and it can be determined that there is a risk in the multiple frames of images to be identified. If they are consistent, it can be indicated that the resolution of multiple frames of images matches the preset resolution, and it can be determined that there is no risk in the multiple frames of images to be identified.

[0092] Among them, as an implementation method, judging whether the correspondence between the resolution and the acquisition time of each frame of the image to be identified is consistent with the correspondence between each preset resolution and the corresponding preset acquisition time in the preset resolution, specifically may include: determining the acquisition time and image resolution of each frame of the image to be identified, and obtaining the correspondence between the acquisition time and the image resolution of each frame of the image to be identified; sorting the correspondence between each frame of the image to be identified according to the order of each frame of the image to be identified, and obtaining the sorted correspondence; the preset resolution contains the correspondence between each preset acquisition time and the corresponding preset resolution, and calculating the similarity between the sorted correspondence and the correspondence contained in the preset resolution; if the similarity is greater than or equal to the preset threshold, it can be indicated that the resolution of the multiple frames of images matches the preset resolution; if the similarity is less than the preset threshold, it can be indicated that the resolution of the multiple frames of images does not match the preset resolution. As an implementation method, the preset resolution can be a preset resolution sequence obtained by arranging multiple different resolutions according to a preset frame order; the above-mentioned determination of the resolution of multiple frames of the image to be identified specifically includes: arranging the resolutions of the multiple frames of the image to be identified according to the order of the multiple frames of the image to be identified, and obtaining a resolution sequence; The determining whether the resolution of the multiple frames of images matches the preset resolution specifically includes: Determining whether the resolution sequence is consistent with the preset resolution sequence; If the resolution of the multiple frames of images does not match the preset resolution, specifically includes: If the resolution sequence is inconsistent with the preset resolution sequence.

[0093] The resolution sequence may include the resolution of each frame of the multiple frames of images to be identified, and the multiple frames of images to be identified may be arranged in the order of the multiple frames of images to be identified. The order of the multiple frames of images to be identified may be the order of the multiple frames of images to be identified in the video stream, and may be ordered according to the time when they are collected or acquired. The resolution sequence may include at least a first resolution and a second resolution.

[0094] The preset resolution sequence may be a plurality of resolutions arranged in a certain order, and specifically may be a plurality of different resolutions arranged in the frame order of image acquisition. For example, the resolution of the first frame to be acquired is a1, the resolution of the second frame to be acquired is a2, the resolution of the third frame to be acquired is a3, the resolution of the fourth frame to be acquired is a4, and the resolution of the fifth frame to be acquired is a5, so the preset resolution sequence is a1 a2 a3 a4 a5.

[0095] In actual applications, the first resolution in the resolution sequence can be obtained in sequence to determine whether the first resolution is the same as the first resolution in the preset resolution sequence. If they are different, it can be determined that the resolution sequence is inconsistent with the preset resolution sequence, which can indicate that the resolution of multiple frames of images does not match the preset resolution. If they are the same, it is determined whether the second resolution in the resolution sequence is the same as the second resolution in the preset resolution sequence, and so on, to determine whether the resolution sequence is consistent with the preset resolution sequence.

[0096] In practical applications, a computer model can also be used to determine whether the resolution sequence is consistent with the preset resolution sequence. For example, a similarity calculation model calculates the similarity between the resolution sequence and the preset resolution sequence. If the similarity is greater than or equal to a preset threshold, it can be indicated that the resolution sequence is consistent with the preset resolution sequence. If the similarity is less than the preset threshold, it can be indicated that the resolution sequence is inconsistent with the preset resolution sequence.

[0097] Based on the same idea, the embodiments of this specification also provide a solution with the terminal as the execution subject. Figure 3 Flow chart of a risk identification method provided in the embodiments of this specification. Figure 3 As shown, the scheme may include the following steps: Step 302: Obtain image acquisition instructions.

[0098] Step 304: Based on the image acquisition instruction, an image is acquired at a preset resolution.

[0099] The preset resolution includes at least a first resolution and a second resolution.

[0100] Step 306: Send multiple frames of images to be recognized to the server.

[0101] Wherein, the server is used to execute the above-mentioned risk identification method.

[0102] The image acquisition instruction may be generated based on a preset operation performed by a user to start the image acquisition function. For example, when a financial institution handles business, a financial service staff or a user handling business performs an operation to start face recognition in a business terminal; another example is a cashier performing a checkout operation at a cash register in a shopping mall or a consumer performing a checkout operation at a self-service checkout terminal. The specific operation form is not specifically limited here, as long as it can trigger the image acquisition instruction.

[0103] The preset resolution is the resolution that the terminal or an image acquisition component associated with the terminal actually uses or should use to acquire images. The first resolution and the second resolution included in the preset resolution can be different resolutions, for example, 640*480 and 1920*1080. In practical applications, the preset resolution can also include more than two different resolutions, and the specific number and value of resolutions can be set according to actual needs, and are not specifically limited here.

[0104] The image acquisition process may include starting the image acquisition component, verifying whether the terminal has the authority to use the image acquisition component, etc. By executing the image acquisition process, the image acquisition component in the terminal or associated with the terminal, such as a camera, can acquire images. The terminal or the image acquisition component can also send the acquired image to the server so that the server can recognize the image.

[0105] In actual applications, if the terminal is not attacked by injection, the terminal can send the image actually collected by the camera to the server, which can also be understood as sending the image of the collection object within the collection range of the camera to the server. If the terminal is attacked by injection, the camera can also collect images, but the image sent to the server is the image injected by the injection attack.

[0106] Usually, the image acquisition terminal can call the camera to capture the image or video of the target object, such as the face image or video. The camera sends the acquired face image, for example, in the form of a data stream, to the image acquisition terminal. The image acquisition terminal can send the image to the server, for example, it can receive the face image data stream through the face acquisition SDK and send it to the server, and call the relevant algorithm to extract the face image for business detection, such as for face liveness recognition or face comparison. However, in actual production scenarios, attackers may use the above-mentioned camera to send data streams to implement injection attacks. Attackers can hijack the process of the camera sending data streams to the terminal's face acquisition SDK, block the camera's real data stream, and send a false data stream, also called an injected data stream, to the terminal face acquisition SDK, so that the image obtained by the server is an injected image. In this way, attackers can use the false images or videos they have obtained in advance to achieve their illegal purposes, such as illegally obtaining user data or operation permissions, through various business verification processes using face recognition.

[0107] The multiple frames of images to be identified sent to the server may be multiple frames of images actually used by the terminal, or may be attack images injected by an illegal user. The server may execute the process of the above-mentioned risk identification method to determine whether the multiple frames of images to be identified have risks and whether they are injected attack images. The specific execution process of the server may be described in the above-mentioned embodiment, which will not be repeated here.

[0108] Optionally, the method in the embodiments of this specification may further include: Send parameter acquisition request to the server; The preset resolution sent by the server is obtained.

[0109] The parameter acquisition request may be generated after the terminal obtains the image acquisition instruction, and is used to obtain the preset resolution sent by the server. The preset resolution may be a plurality of resolutions randomly determined by the server, and may include at least a first resolution and a second resolution. The server may also randomly select a plurality of resolutions available to the terminal as the preset resolution based on information such as the model of the terminal.

[0110] After the terminal obtains the preset resolution, it can set the parameters of the camera to the preset resolution, and control the camera to capture images according to the preset resolution. In practical applications, a program for controlling the resolution of the camera can be set in the terminal. After the terminal obtains the resolution, the camera resolution can be adjusted through the preset program so that the camera captures images according to the preset resolution. Optionally, the preset resolution includes a first frame number corresponding to the first resolution and a second frame number corresponding to the second resolution; the above-mentioned image capture process according to the preset resolution may specifically include: The camera is controlled to capture the image of the first frame number according to the first resolution, and to capture the image of the second frame number according to the second resolution.

[0111] Among them, the first frame number and the second frame number can represent the frame numbers of the image to be captured. For example, assuming that 10 frames of images need to be captured, the preset resolution indicates that the 1st to 4th frames are captured at a resolution of 640*480, and the 5th to 10th frames are captured at a resolution of 1920*1080. The terminal can control the camera to capture the 1st to 4th frames at a resolution of 640*480, and capture the 5th to 10th frames at a resolution of 1920*1080.

[0112] In practical applications, the corresponding resolution may also be determined based on time. As an implementation, the preset resolution may include a correspondence between each preset resolution and the corresponding preset acquisition time. For example, the preset resolution may also include first time information corresponding to the first resolution and second time information corresponding to the second resolution. The first terminal may control the acquisition component to use the corresponding preset resolution within the preset time. The above-mentioned execution of the image acquisition process according to the preset resolution may specifically include: controlling the camera to acquire images using the first resolution within the time period represented by the first time information, and to acquire images using the second resolution within the time period represented by the second time information.

[0113] For example, assuming that you need to capture 5 seconds of images, the preset resolution means that the first 2 seconds use the first resolution and the next 3 seconds use the second resolution. The terminal can control the camera to capture images with the first resolution in the 1st and 2nd seconds, and the second resolution in the 3rd to 5th seconds.

[0114] It is understandable that the terminal can capture images at a preset resolution. If the terminal is attacked by injection, the image sent by the terminal to the server is most likely not the image captured by the terminal itself, but the image injected with the attack. The multiple frames of images to be identified sent above may be images captured by the terminal itself, or images injected with the attack.

[0115] In actual applications, the preset resolution can also be randomly generated by the terminal, and the terminal can also send the determined preset resolution to the server so that the server can identify risks. For example, after obtaining the image acquisition instruction, the terminal can locally determine or generate multiple resolutions as the preset resolution, and set the camera's resolution parameter to the preset resolution. The camera performs image acquisition according to the preset resolution, and can also send the preset resolution to the server.

[0116] In this embodiment, the server can execute the risk identification steps in the above embodiments. The same or similar parts in each embodiment can also refer to each other and will not be repeated here.

[0117] In order to more clearly illustrate the risk identification method provided in the embodiments of this specification, Figure 4 This is a swim lane diagram of a risk identification method provided in the embodiments of this specification. Figure 4 As shown, the scheme may include an image acquisition phase, a recognition phase, and a result display phase, and may specifically include the following steps: Step 402: The terminal obtains an image acquisition instruction.

[0118] The image acquisition instruction may indicate an instruction to start an image acquisition process, for example, it may indicate the start of face recognition.

[0119] Step 404: The terminal sends a parameter acquisition request to the server.

[0120] Step 406: The server determines the preset resolution and sends it to the terminal.

[0121] For example, the server randomly generates and returns two resolutions of 640*480 and 1920*1080. The server may also store the preset resolution and the corresponding relationship between the preset resolution and the terminal for subsequent use.

[0122] Step 408: The terminal executes an image acquisition process based on a preset resolution.

[0123] After the terminal obtains the preset resolution sent by the server, the camera resolution can be adjusted to the preset resolution, and images can be captured according to the preset resolution.

[0124] Continuing with the above example, the camera resolution can be adjusted to 640*480, and face photos can be collected at this resolution, where one or more frames of photos can be collected at this resolution. Then the camera resolution can be adjusted to 1920*1080, and face photos can be collected at this resolution, where one or more frames of photos can also be collected.

[0125] Step 410: Send multiple frames of images to be recognized to a server.

[0126] The multiple frames of images to be identified may be images actually collected by the terminal, or other images provided by illegal users through illegal means such as video injection. Illegal attacks are generally in the form of video injection, in which case the resolution is the same.

[0127] Step 412: The server obtains multiple frames of images to be recognized.

[0128] Step 414: Determine the image resolutions of the multiple frames of images to be recognized.

[0129] Step 416: Determine whether the resolution of the multiple frames of images matches the preset resolution.

[0130] For example, it can be determined whether the resolutions of multiple frames of images are 640*480 and 1920*1080.

[0131] If the resolution of the multiple frames of images does not match the preset image resolution, step 418 may be executed: determining that the multiple frames of images to be identified have risks.

[0132] If the resolution of the multiple frames of images matches the preset image resolution, step 420 can be performed: determining that the multiple frames of images to be identified do not have risks. In practical applications, if it is determined that the multiple frames of images to be identified have risks, the server can terminate the identification process and can also generate identification result information indicating the existence of risks and send it to the terminal.

[0133] The server may also execute step 422 after obtaining the judgment result: generating recognition result information.

[0134] Among them, if it is determined that there is no risk in the multiple frames of images to be identified, the server can continue the subsequent identification process, such as the face matching process, etc. After the entire process is completed, it can also generate identification result information indicating that there is no risk and send it to the terminal. If an identification problem occurs during the execution of the subsequent identification process, such as the acquired face image does not match the pre-stored user image, identification result information indicating that there is a risk or identification failure can also be generated and sent to the terminal. The specific content and form of the identification result information are not specifically limited here.

[0135] The terminal may obtain the recognition result information fed back by the server and execute step 424: displaying the recognition result.

[0136] Based on the same idea, the embodiments of this specification also provide a device corresponding to the above method. Figure 5 The embodiments of this specification provide corresponding to Figure 2 A schematic diagram of the structure of a risk identification device. Figure 5 As shown, the device may include: The image acquisition module 502 is used to acquire multiple frames of to-be-recognized images provided by the terminal.

[0137] The resolution determination module 504 is used to determine the resolution of multiple frames of images to be recognized.

[0138] The judgment module 506 is used to judge whether the resolution of the multiple frames of images matches a preset resolution; the preset resolution includes at least a first resolution and a second resolution.

[0139] The risk confirmation module 508 is used to determine that there is a risk in the multiple frames of images to be identified if the resolution of the multiple frames of images does not match the preset resolution.

[0140] based on Figure 5 The present specification also provides some specific implementation schemes of the method, which are described below.

[0141] Optionally, the device may further include a resolution sending module, configured to: Acquire a parameter acquisition request sent by the terminal; the parameter acquisition request is generated by the terminal based on an image acquisition operation; Based on the parameter acquisition request, the preset resolution is sent to the terminal so that the terminal captures images according to the preset resolution.

[0142] Optionally, the resolution sending module can be specifically used for: Based on the device identification of the terminal, a preset resolution that can be executed by the terminal is selected from a preset resolution set.

[0143] Optionally, the above-mentioned judgment module may be specifically used for: It is determined whether the resolutions of the multiple image frames include each of the preset resolutions.

[0144] Optionally, the preset resolution also includes a first frame number corresponding to the first resolution.

[0145] The above-mentioned resolution determination module can be specifically used to: determine the third resolution of the image to be identified corresponding to the first frame sequence number in the multiple frames of images to be identified.

[0146] The above-mentioned determination module can be specifically used to determine whether the third resolution is the same as the first resolution.

[0147] If the third resolution is different from the first resolution, it means that the resolution of the multi-frame images does not match the preset resolution.

[0148] Optionally, the preset resolution also includes a second frame number corresponding to the second resolution. The resolution determination module may also be used to determine a fourth resolution of the image to be identified corresponding to the second frame number in the plurality of frames of images to be identified.

[0149] The above-mentioned determination module may also be specifically used to determine whether the fourth resolution is the same as the second resolution.

[0150] If the fourth resolution is different from the second resolution, it means that the resolution of the multi-frame images does not match the preset resolution.

[0151] Optionally, the above-mentioned resolution determination module can be specifically used to: if the third resolution is the same as the first resolution, determine whether the fourth resolution is the same as the second resolution.

[0152] Optionally, the preset resolution is a preset resolution sequence obtained by arranging multiple different resolutions according to a preset frame order; the above-mentioned resolution determination module can be specifically used to: arrange the various resolutions of the multiple frames of images to be identified according to the order of the multiple frames of images to be identified, so as to obtain a resolution sequence.

[0153] The above-mentioned judgment module may also be specifically used to: judge whether the resolution sequence is consistent with a preset resolution sequence.

[0154] Optionally, the image to be identified is an image including biometric features; the biometric features include at least one of face, iris, fingerprint, and palm print.

[0155] Figure 6 The embodiments of this specification provide corresponding to Figure 3 A schematic diagram of the structure of a risk identification device. Figure 6 As shown, the device may include: The instruction acquisition module 602 is used to acquire image acquisition instructions.

[0156] The acquisition module 604 is used to acquire an image according to a preset resolution based on the image acquisition instruction; the preset resolution includes at least a first resolution and a second resolution.

[0157] The image sending module 606 is used to send multiple frames of images to be identified to a server; the server is used to execute the above-mentioned risk identification method.

[0158] Optionally, the device may further include a resolution acquisition module, configured to: Sending a parameter acquisition request to the server; The preset resolution sent by the server is obtained.

[0159] Optionally, the preset resolution includes a first frame number corresponding to the first resolution and a second frame number corresponding to the second resolution; and the image acquisition process performed according to the preset resolution may specifically include: The camera is controlled to capture the image of the first frame number according to the first resolution, and to capture the image of the second frame number according to the second resolution.

[0160] Figure 7 This is a schematic diagram of the structure of a risk identification device provided in an embodiment of this specification. Figure 7 As shown, the device 700 may include: at least one processor 710; and, A memory 730 communicatively connected to the at least one processor; Among them, corresponding to Figure 2The risk identification method shown in the figure, the memory 730 stores instructions 720 that can be executed by the at least one processor 710, and the instructions are executed by the at least one processor 710 to enable the at least one processor 710 to: Obtain multiple frames of images to be recognized provided by the terminal; Determine the resolution of multiple frames of images to be recognized; Determine whether the resolution of the multiple frames of images matches a preset resolution; the preset resolution includes at least a first resolution and a second resolution; If the resolution of the multiple frames of images does not match the preset resolution, it is determined that there is a risk in the multiple frames of images to be identified.

[0161] Among them, corresponding to Figure 3 The risk identification method shown in the figure, the memory 730 stores instructions 720 that can be executed by the at least one processor 710, and the instructions are executed by the at least one processor 710 to enable the at least one processor 710 to: Get image acquisition instructions; Based on the image acquisition instruction, an image is acquired according to a preset resolution; the preset resolution includes at least a first resolution and a second resolution; Send multiple frames of images to be identified to a server; the server is used to execute the above-mentioned risk identification method.

[0162] Based on the same idea, the embodiment of this specification also provides a computer-readable medium corresponding to the above method. The computer-readable medium stores computer-readable instructions, and the computer-readable instructions can be executed by a processor to implement the above risk identification method.

[0163] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. Figure 7 As for the device shown, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0164] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards in the relevant regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0165] In the 1990s, it was very clear whether the improvement of a technology was hardware improvement (for example, improvement of the circuit structure of diodes, transistors, switches, etc.) or software improvement (improvement of the method flow). However, with the development of technology, many improvements of the method flow today can be regarded as direct improvements of the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented with hardware entity modules. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask chip manufacturers to design and make dedicated integrated circuit chips. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0166] The controller may be implemented in any suitable manner, for example, the controller may take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (e.g., software or firmware) executable by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, and the memory controller may also be implemented as part of the control logic of the memory. It is also known to those skilled in the art that, in addition to implementing the controller in a purely computer-readable program code manner, the controller may be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, such a controller may be considered as a hardware component, and the devices for implementing various functions included therein may also be considered as structures within the hardware component. Or even, the devices for implementing various functions may be considered as both software modules for implementing the method and structures within the hardware component.

[0167] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0168] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0169] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0170] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0171] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0172] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0173] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0174] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0175] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined in this article, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0176] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0177] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0178] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0179] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for risk identification, comprising: Obtain multiple frames of images to be recognized provided by the terminal; Determine the image resolution of multiple frames of the multiple frames of images to be recognized; Determining whether the resolution of the multiple image frames matches a preset resolution; The preset resolution includes at least a first resolution and a second resolution; If the resolution of the multiple frames of images does not match the preset resolution, it is determined that there is a risk in the multiple frames of images to be identified.

2. The method according to claim 1, before acquiring the multiple frames of images to be identified provided by the terminal, further comprising: Obtaining a parameter acquisition request sent by the terminal; The parameter acquisition request is generated by the terminal based on an image acquisition operation; Based on the parameter acquisition request, the preset resolution is sent to the terminal so that the terminal captures images according to the preset resolution.

3. The method according to claim 2, wherein the parameter acquisition request includes a device identifier of the terminal; and sending the preset resolution to the terminal based on the parameter acquisition request specifically comprises: Based on the device identification of the terminal, the preset resolution executable by the terminal is selected from a preset resolution set.

4. According to the method of claim 1, the determining whether the resolution of the multiple frames of images matches the preset resolution specifically comprises: It is determined whether the resolutions of the multiple image frames include each of the preset resolutions.

5. According to the method of claim 1, the preset resolution also includes a first frame number corresponding to the first resolution; and determining the resolution of multiple frames of the multiple frames of images to be identified specifically includes: Determine a third resolution of the image to be identified corresponding to the first frame sequence number among the multiple frames of images to be identified; The determining whether the resolution of the multiple frames of images matches the preset resolution specifically includes: Determining whether the third resolution is the same as the first resolution; If the third resolution is different from the first resolution, it means that the resolution of the multi-frame images does not match the preset resolution.

6. The method according to claim 5, wherein the preset resolution further includes a second frame sequence number corresponding to the second resolution; The method further comprises: Determining a fourth resolution of the image to be identified corresponding to the second frame sequence number among the multiple frames of images to be identified; Determining whether the fourth resolution is the same as the second resolution; If the fourth resolution is different from the second resolution, it means that the resolution of the multi-frame images does not match the preset resolution.

7. The method according to claim 6, wherein determining whether the fourth resolution is the same as the second resolution comprises: If the third resolution is the same as the first resolution, it is determined whether the fourth resolution is the same as the second resolution.

8. The method according to claim 1, wherein the preset resolution is a preset resolution sequence obtained by arranging a plurality of different resolutions in a preset frame order; Determining the resolution of multiple frames of images to be recognized specifically includes: Arranging the resolutions of the multiple frames of images to be recognized according to the order of the multiple frames of images to be recognized to obtain a resolution sequence; The determining whether the resolution of the multiple frames of images matches the preset resolution specifically includes: Determine whether the resolution sequence is consistent with the preset resolution sequence.

9. The method according to any one of claims 1 to 8, wherein the image to be identified is an image including biometric features; the biometric features include at least one of face, iris, fingerprint, and palm print.

10. A method for risk identification, comprising: Get image acquisition instructions; Based on the image acquisition instruction, acquire an image according to a preset resolution; The preset resolution includes at least a first resolution and a second resolution; Send multiple frames of images to be recognized to the server; The server is used to execute the method according to claim 1.

11. The method according to claim 10, further comprising: Sending a parameter acquisition request to the server; The preset resolution sent by the server is obtained.

12. The solution according to claim 11, wherein the preset resolution includes a first frame number corresponding to the first resolution and a second frame number corresponding to the second resolution; The image acquisition process is performed according to the preset resolution, specifically including: The camera is controlled to capture the image of the first frame number according to the first resolution, and to capture the image of the second frame number according to the second resolution.

13. A risk identification device, comprising: An image acquisition module is used to acquire multiple frames of images to be recognized provided by the terminal; A resolution determination module, used to determine the resolution of multiple frames of images to be identified; A determination module, used to determine whether the resolution of the multiple image frames matches a preset resolution; The preset resolution includes at least a first resolution and a second resolution; The risk confirmation module is used to determine that there is a risk in the multiple frames of images to be identified if the resolution of the multiple frames of images does not match the preset resolution.

14. A risk identification device, comprising: An instruction acquisition module, used for acquiring image acquisition instructions; An acquisition module, used to acquire images according to a preset resolution based on the image acquisition instruction; The preset resolution includes at least a first resolution and a second resolution; An image sending module is used to send multiple frames of images to be identified to a server; The server is used to execute the method according to claim 1.

15. A risk identification device, comprising: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: Obtain multiple frames of images to be recognized provided by the terminal; Determine the image resolution of multiple frames of the multiple frames of images to be recognized; Determine whether the resolution of the multiple frames of images matches a preset resolution; the preset resolution includes at least a first resolution and a second resolution; If the resolution of the multiple frames of images does not match the preset resolution, it is determined that there is a risk in the multiple frames of images to be identified.

16. A risk identification device, comprising: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: Get image acquisition instructions; Based on the image acquisition instruction, an image is acquired according to a preset resolution; the preset resolution includes at least a first resolution and a second resolution; Send multiple frames of images to be identified to a server; the server is used to execute the method described in claim 1.

17. A computer-readable medium having computer-readable instructions stored thereon, wherein the computer-readable instructions can be executed by a processor to implement the risk identification method according to any one of claims 1 to 12.

Images