Method, device, storage medium and electronic equipment for identity verification
By combining the similarity of brightness characteristics from video and photosensors, this approach addresses the insufficient defense against video injection in existing identity verification schemes, achieving a higher standard of security identity verification and reducing the risk of attacks by malicious actors.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
- Filing Date
- 2026-02-24
- Publication Date
- 2026-06-23
AI Technical Summary
Existing identity verification schemes are insufficient in defending against video injection, making it easy for malicious actors to attack using AI-generated videos, resulting in a high rate of compromise on black samples, thus requiring improved security.
By combining the similarity judgment of the brightness characteristics of the video and the photosensitive sensor during video verification, the brightness information extracted from the video and the brightness information captured by the photosensitive sensor are dynamically similar to each other and used as the verification factor.
It reduces the rate at which malicious actors can compromise video authentication, provides higher security authentication standards, and improves user security.
Smart Images
Figure CN122265907A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to computer technology, and more particularly to a method, apparatus, storage medium, and electronic device for identity verification. Background Technology
[0002] Mobile payment has become the most commonly used payment method in people's daily lives. Common payment tools include Alipay, WeChat Pay, UnionPay QuickPass, TikTok, and payment applications from various banks. From the consumer's perspective, while the convenience brought by payment tools is important, ensuring payment security is even more crucial. In recent years, AIGC (Artificial Intelligence Generated Content) technology has developed rapidly. Black market actors can easily generate videos using AI (Artificial Intelligence) technology to simulate real users performing designated authentication actions, resulting in a continuous increase in the black sample attack rate. Due to the insufficient defense of existing authentication solutions against injected videos, it is necessary to design some verification methods that integrate multiple sensor features for implicit authentication. Summary of the Invention
[0003] The purpose of the embodiments in this specification is to provide a method, apparatus, storage medium, and electronic device for identity verification.
[0004] This specification provides a method for identity verification, innovatively designing an identity verification approach that combines the similarity of brightness characteristics of the video and the photosensitive sensor during video identity verification. Starting from the perspective that the video captured during the identity verification process naturally contains real-world ambient brightness information, the photosensitive sensor captures the ambient brightness change curve. The brightness information extracted from the video and the brightness information captured by the photosensitive sensor exhibit continuous dynamic similarity. By verifying whether the brightness change information extracted from the video and the brightness change information captured by the photosensitive sensor are consistent during the user's video identity verification, this is used as an identity verification factor. This reduces the vulnerability rate of video identity verification by malicious actors, provides a higher standard of security verification, and thus offers users greater security. The method includes: Obtain the verification video corresponding to the target user during the verification process, input multiple video frames corresponding to the verification video into a trained ambient light brightness prediction model, and obtain the first ambient light brightness change information corresponding to the multiple video frames output by the ambient light brightness prediction model. The second ambient light brightness change information corresponding to the shooting time points of the multiple video frames collected by the photosensitive sensor during the core body process is obtained; Obtain the similarity between the first ambient light brightness change information and the second ambient light brightness change information. If the similarity is less than or equal to a first preset threshold, determine that the target user has failed the identity verification.
[0005] Furthermore, the first ambient light brightness change information includes a first ambient light brightness change curve, and the second ambient light brightness change information includes the first ambient light brightness change curve.
[0006] Further, obtaining the similarity between the first ambient light brightness change information and the second ambient light brightness change information, and determining that the target user has failed the identity verification if the similarity is less than or equal to a first preset threshold, includes: Obtain the curve waveform similarity between the first ambient light brightness change curve and the second ambient light brightness change curve. If the curve waveform similarity is less than or equal to a first preset threshold, determine that the target user has failed the identity verification.
[0007] Further, the step of obtaining the waveform similarity between the first ambient light brightness change curve and the second ambient light brightness change curve, and determining that the target user has failed the identity verification if the waveform similarity is less than or equal to a first preset threshold, further includes: If the similarity of the curve waveform is greater than the first preset threshold, the dynamic change synchronization degree between the first ambient light brightness change curve and the second ambient light brightness change curve is obtained. If the dynamic change synchronization degree is less than or equal to the second preset threshold, it is determined that the target user has not passed the identity verification.
[0008] Furthermore, the method also includes: Obtain the screen brightness change rules corresponding to the core body process, and change the screen brightness according to the screen brightness change rules during the core body process.
[0009] Further, obtaining the screen brightness change rule corresponding to the core body process, and changing the screen brightness according to the screen brightness change rule during the core body process, includes: The current ambient light intensity is obtained through a photosensitive sensor. If the current ambient light intensity is less than or equal to a preset brightness threshold, the screen brightness change rule corresponding to the body-body process is obtained, and the screen brightness is changed according to the screen brightness change rule during the body-body process.
[0010] Furthermore, the screen brightness change rules corresponding to the process of obtaining the core body include: Based on the sensitive operations associated with the body verification process, determine the screen brightness change rules corresponding to the body verification process.
[0011] Further, determining the screen brightness change rules corresponding to the core authentication process based on the sensitive operations associated with the core authentication process includes: Based on the target user's historical identity verification information, determine the screen brightness change rules corresponding to the identity verification process.
[0012] Further, obtaining the similarity between the first ambient light brightness change information and the second ambient light brightness change information, and determining that the target user has failed the identity verification if the similarity is less than or equal to a first preset threshold, includes: If the identity verification video has passed the detection, the similarity between the first ambient light brightness change information and the second ambient light brightness change information is obtained. If the similarity is less than or equal to a first preset threshold, it is determined that the target user has not passed the identity verification.
[0013] Furthermore, the method also includes: If the similarity is greater than the first preset threshold, the identity verification video is detected, and the target user is determined to have passed the identity verification based on the detection result.
[0014] Furthermore, the method also includes: During the capture of the target video, the ambient light intensity at the capture time points of each target video frame is collected. An ambient light intensity prediction model is trained based on each target video frame and the ambient light intensity to obtain a trained ambient light intensity prediction model. The target ambient light intensity is used as the training label for each target video frame. This specification also provides an apparatus for identity verification, comprising: The first ambient light brightness module is used to obtain the verification video corresponding to the target user during the verification process, input multiple video frames corresponding to the verification video into the trained ambient light brightness prediction model, and obtain the first ambient light brightness change information corresponding to the multiple video frames output by the ambient light brightness prediction model. The second ambient light brightness module is used to obtain the second ambient light brightness change information corresponding to the shooting time points of the multiple video frames collected by the photosensitive sensor during the core body process; The identity verification module is used to obtain the similarity between the first ambient light brightness change information and the second ambient light brightness change information. If the similarity is less than or equal to a first preset threshold, it is determined that the target user has failed the identity verification.
[0015] This specification also provides a storage medium storing a computer program adapted to be loaded by a processor and to execute the steps of the method described above.
[0016] This specification also provides an electronic device, including a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to execute the steps of the method described above.
[0017] This specification also provides a computer program product that stores at least one instruction, characterized in that the at least one instruction, when executed by a processor, implements the steps of the above-described method.
[0018] According to the embodiments of this specification, an innovative authentication method is designed that combines the similarity of brightness characteristics of the video and the photosensitive sensor during video authentication. This method considers the fact that the video captured during authentication naturally contains real-world ambient brightness information. The photosensitive sensor captures the ambient brightness change curve, and the brightness information extracted from the video and captured by the photosensitive sensor exhibit continuous dynamic similarity. By verifying whether the brightness change information extracted from the video and the brightness change information captured by the photosensitive sensor are consistent during the user's video authentication process, this method serves as an authentication verification factor. This reduces the vulnerability rate of video authentication by malicious actors, provides a higher standard of security authentication, and thus offers users greater security. Attached Figure Description
[0019] Figure 1 A flowchart illustrating a method for identity verification provided in an embodiment of this specification; Figures 2-5 This is a schematic diagram of multiple video frames and the ambient light brightness variation curves extracted from the multiple video frames using an ambient light brightness prediction model. Figures 6-9 A schematic diagram of the ambient light intensity variation curve collected by the photosensitive sensor; Figure 10 A schematic diagram of a device for identity verification provided in the embodiments of this specification; Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification. Detailed Implementation
[0020] To make the objectives, technical solutions, and advantages of this specification clearer, the technical solutions of this specification will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of them. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this specification.
[0021] Please see Figure 1This is a schematic flowchart illustrating a method for identity verification provided in an embodiment of this specification. In this embodiment, the method is applied to an identity verification device (hereinafter referred to as a "identity verification device") or an electronic device equipped with an identity verification device. The following will focus on... Figure 1 The process shown will be described in detail. The method for identity verification may specifically include the following steps: S102, obtain the verification video corresponding to the target user during the verification process, input multiple video frames corresponding to the verification video into the trained ambient light brightness prediction model, and obtain the first ambient light brightness change information corresponding to the multiple video frames output by the ambient light brightness prediction model.
[0022] In some embodiments, the identity verification video is a real-time dynamic video of the target user captured by a camera during the identity verification process. It is a real-person, live identity verification method. Its core purpose is to thoroughly confirm that the operator is the target user and that the operation is real-time and voluntary, thereby preventing impersonation behaviors such as photo and video re-encoding, AI (Artificial Intelligence) face swapping, and proxy operation. The identity verification process refers to the process of verifying the identity of the target user.
[0023] In some embodiments, the multiple video frames corresponding to the identity verification video may be all the video frames of the identity verification video, or they may be a portion of the video frames selected from all the video frames of the identity verification video. This example embodiment does not impose any special limitations on the specific selection method.
[0024] In some embodiments, multiple video frames corresponding to the core video are input into a trained ambient light brightness prediction model to obtain first ambient light brightness change information corresponding to the multiple video frames output by the ambient light brightness prediction model. The first ambient light brightness change information is used to characterize the change of ambient light brightness in each video frame in the multiple video frames. For example, the first ambient light brightness change information includes an ordered sequence containing the ambient light brightness in each video frame, arranged in the order of the multiple video frames. This example embodiment does not impose special limitations on the model structure, model parameters, and training method of the ambient light brightness prediction model.
[0025] S104, obtain the second ambient light brightness change information corresponding to the shooting time points of the multiple video frames collected by the photosensitive sensor during the core body process.
[0026] In some embodiments, while acquiring the identity verification video taken by the target user via a camera during the identity verification process, an ambient light brightness corresponding to the shooting time of each of the multiple video frames is collected by a photosensor. Based on the ambient light brightness corresponding to the shooting time of each video frame, corresponding second ambient light brightness change information is obtained. The second ambient light brightness change information is used to characterize the change in ambient light brightness corresponding to the shooting time of each video frame in the multiple video frames. For example, the second ambient light brightness change information includes an ordered sequence containing the ambient light brightness corresponding to the shooting time of each video frame, arranged in the order of the multiple video frames. According to the scheme of the embodiments of this specification, steps S102 and S104 are executed simultaneously, rather than sequentially.
[0027] S106, obtain the similarity between the first ambient light brightness change information and the second ambient light brightness change information. If the similarity is less than or equal to a first preset threshold, determine that the target user has not passed the identity verification.
[0028] In some embodiments, if the first ambient light brightness change information and the second ambient light brightness change information are compared for similarity to obtain the similarity between the two, for example, if the first ambient light brightness change information is an ordered sequence containing multiple ambient light brightnesses and the second ambient light brightness change information is also an ordered sequence containing multiple ambient light brightnesses, the similarity between the two ordered sequences is obtained by comparing their similarity.
[0029] In some embodiments, if the similarity between the two is less than or equal to a first preset threshold, it indicates that the verification video was not collected in real time during the current verification process. The verification video may originate from AIGC injection or video playback injection taken at other times. It can be directly determined that the target user has failed the verification. If the similarity between the two is greater than the first preset threshold, it indicates that the verification video was collected in real time during the current verification process. However, it cannot be directly determined that the target user has passed the verification. It is necessary to determine whether the target user has passed the verification based on the detection result of the verification video. In this example embodiment, the specific detection method of the verification video is not specifically limited.
[0030] According to the embodiments of this specification, an innovative authentication method is designed that combines the similarity of brightness characteristics of the video and the photosensitive sensor during video authentication. Starting from the perspective that the video captured during the authentication process inevitably contains real-world ambient brightness information, the photosensitive sensor captures the ambient brightness change curve. The brightness information extracted from the video and the brightness information captured by the photosensitive sensor exhibit continuous dynamic similarity. By verifying whether the brightness change information extracted from the video and the brightness change information captured by the photosensitive sensor are consistent during the user's video authentication, this is used as an authentication verification factor. This reduces the vulnerability rate of video authentication to malicious attacks, provides a higher standard of security authentication, and thus offers users greater security.
[0031] In some embodiments, the first ambient light brightness change information includes a first ambient light brightness change curve, and the second ambient light brightness change information includes the first ambient light brightness change curve. In some embodiments, the first ambient light brightness change information may be a curve with the horizontal axis representing each video frame or the time point corresponding to each video frame and the vertical axis representing the ambient light brightness, i.e., the first ambient light brightness change curve. In some embodiments, the second ambient light brightness change information may be a curve with the horizontal axis representing each video frame or the shooting time corresponding to each video frame and the vertical axis representing the ambient light brightness, i.e., the second ambient light brightness change curve. In some embodiments, the first ambient light brightness change curve and the second ambient light brightness change curve are compared for similarity to obtain the similarity between them. For example, statistical algorithms such as KL divergence are used to obtain the statistical similarity between the two curves.
[0032] In some embodiments, obtaining the similarity between the first ambient light brightness change information and the second ambient light brightness change information, and determining that the target user has failed the identity verification if the similarity is less than or equal to a first preset threshold, includes: obtaining the waveform similarity between the first ambient light brightness change curve and the second ambient light brightness change curve; if the waveform similarity is less than or equal to the first preset threshold, determining that the target user has failed the identity verification. In some embodiments, a waveform similarity comparison is performed between the first ambient light brightness change curve and the second ambient light brightness change curve to obtain the waveform similarity between the two; if the waveform similarity is less than or equal to the first preset threshold, it can be directly determined that the target user has failed the identity verification.
[0033] In some embodiments, obtaining the waveform similarity between the first ambient light brightness change curve and the second ambient light brightness change curve, and determining that the target user has failed the identity verification if the waveform similarity is less than or equal to a first preset threshold, further includes: if the waveform similarity is greater than the first preset threshold, obtaining the dynamic change synchronization degree between the first ambient light brightness change curve and the second ambient light brightness change curve; if the dynamic change synchronization degree is less than or equal to a second preset threshold, determining that the target user has failed the identity verification. In some embodiments, if the waveform similarity between the two curves is greater than the first preset threshold, it is also necessary to further obtain the dynamic change synchronization degree between the first ambient light brightness change curve and the second ambient light brightness change curve. If the dynamic change synchronization degree is less than or equal to the second preset threshold, it can be directly determined that the target user has failed the identity verification. Here, the dynamic change synchronization degree between the two curves is used to quantify the degree of fit and time correlation of the trend, rhythm, and amplitude fluctuations of the two curves as they change with independent variables (such as time and space), focusing on the synchronicity of changes rather than simple numerical similarity.
[0034] In some embodiments, the method further includes: obtaining a screen brightness change rule corresponding to the identity verification process, and changing the screen brightness according to the screen brightness change rule during the identity verification process. In some embodiments, a screen brightness change rule may be randomly generated for the identity verification process of the target user, or a screen brightness change rule may be randomly selected from multiple preset screen brightness change rules for the identity verification process of the target user, wherein the screen brightness change rule is used to characterize how the screen brightness is changed. In some embodiments, during the identity verification process of the target user, the screen brightness is actively changed according to the screen brightness change rule, so that the screen brightness change is reflected in the first ambient light brightness change information and the second ambient light brightness change information.
[0035] In some embodiments, obtaining the screen brightness change rule corresponding to the identity verification process, and changing the screen brightness according to the screen brightness change rule during the identity verification process, includes: obtaining the current ambient light brightness collected by a photosensor; if the current ambient light brightness is less than or equal to a preset brightness threshold, obtaining the screen brightness change rule corresponding to the identity verification process, and changing the screen brightness according to the screen brightness change rule during the identity verification process. In some embodiments, the current ambient light brightness collected by the photosensor is only used to obtain the screen brightness change rule corresponding to the identity verification process for the target user if the current ambient light brightness is less than or equal to the preset brightness threshold, and only then will the screen brightness be actively changed according to the screen brightness change rule during the identity verification process for the target user.
[0036] In some embodiments, obtaining the screen brightness change rules corresponding to the identity verification process includes: determining the screen brightness change rules corresponding to the identity verification process based on the sensitive operations associated with the identity verification process. In some embodiments, the screen brightness change rules corresponding to the identity verification process of a target user can be determined based on the sensitive operations associated with the identity verification process. For example, the higher the sensitivity level of the sensitive operation, the more complex the corresponding screen brightness change rule; the lower the sensitivity level of the sensitive operation, the simpler the corresponding screen brightness change rule.
[0037] In some embodiments, determining the screen brightness change rule corresponding to the identity verification process based on the sensitive operations associated with the identity verification process includes: determining the screen brightness change rule corresponding to the identity verification process based on the historical identity verification information of the target user. In some embodiments, the screen brightness change rule corresponding to the identity verification process of the target user can be determined based on the historical identity verification information of the target user. For example, the earlier the target user's most recent successful identity verification, the more complex the corresponding screen brightness change rule. Similarly, the fewer times the target user has successfully passed identity verification within a recent preset time range, the more complex the corresponding screen brightness change rule. Likewise, the later the target user's most recent failed identity verification, the more complex the corresponding screen brightness change rule. And the more times the target user has failed identity verification within a recent preset time range, the more complex the corresponding screen brightness change rule.
[0038] In some embodiments, obtaining the similarity between the first ambient light brightness change information and the second ambient light brightness change information, and determining that the target user has failed the identity verification if the similarity is less than or equal to a first preset threshold, includes: if the identity verification video has passed the detection, obtaining the similarity between the first ambient light brightness change information and the second ambient light brightness change information; if the similarity is less than or equal to the first preset threshold, determining that the target user has failed the identity verification. In some embodiments, the identity verification video is detected first. Only if the identity verification video has passed the detection will the similarity comparison between the first ambient light brightness change information and the second ambient light brightness change information be performed. If the similarity between the two is less than or equal to the first preset threshold, it is determined that the target user has failed the identity verification; otherwise, if the identity verification video has failed the detection, it is directly determined that the target user has failed the identity verification.
[0039] In some embodiments, the method further includes: if the similarity is greater than the first preset threshold, detecting the identity verification video, and determining whether the target user has passed the identity verification based on the detection result. In some embodiments, the similarity between the first ambient light brightness change information and the second ambient light brightness change information is first compared. If the similarity between the two is less than or equal to the first preset threshold, it is directly determined that the target user has failed the identity verification. If the similarity between the two is greater than the first preset threshold, the identity verification video needs to be further detected. Then, it is determined whether the target user has passed the identity verification based on the corresponding detection result. If the identity verification video passes the detection, it is determined that the target user has passed the identity verification. If the identity verification video fails the detection, it is determined that the target user has failed the identity verification.
[0040] In some embodiments, the method further includes: acquiring the target ambient light intensity at the shooting time points of each target video frame corresponding to the target video during the shooting process of the target video; training an ambient light intensity prediction model based on each target video frame and the target ambient light intensity to obtain a trained ambient light intensity prediction model, wherein the target ambient light intensity is used as the training label for each target video frame. In some embodiments, the target ambient light intensity at the shooting time points of each target video frame corresponding to the target video is simultaneously acquired via a photosensor during the shooting process of the target video. Here, the target video includes, but is not limited to, any video, and not only the target video itself. In some embodiments, each target video frame corresponding to the target video is used as training data, and the target ambient light brightness corresponding to the shooting time point of each target video frame is used as the training label corresponding to the training data. The ambient light brightness prediction model is trained according to the training data and the corresponding training label to obtain the trained ambient light brightness prediction model. This allows the trained ambient light brightness prediction model to extract the corresponding ambient light brightness change information (e.g., ambient light brightness change curve) from multiple video frames input to the model. In this example embodiment, no special limitations are made on the model structure, model parameters and training method of the ambient light brightness prediction model.
[0041] Figures 2-5 This diagram illustrates multiple video frames and the ambient light intensity variation curves extracted from these frames using an ambient light intensity prediction model. The upper half of each diagram shows the multiple video frames, and the lower half shows the ambient light intensity variation curves extracted from them. It should be noted that... Figures 2-5 The video frames shown are not actual video frames obtained in the scene, but are only used as examples to illustrate the changes in ambient light brightness extracted from multiple video frames.
[0042] like Figures 2-5 As shown, Figure 2The ambient light intensity variation curve shown represents the gradual darkening of the ambient light intensity across multiple video frames. Figure 3 The ambient light brightness variation curve shown represents the gradual brightening of the ambient light brightness across multiple video frames. Figure 4 The ambient light brightness variation curve shown represents the ambient light brightness of multiple video frames first becoming brighter and then darker. Figure 5 The ambient light brightness variation curve shown indicates that the ambient light brightness remains almost constant across multiple video frames.
[0043] Figures 6-9 This is a schematic diagram of the ambient light intensity variation curve collected by a photosensor.
[0044] like Figures 6-9 As shown, Figure 6 The ambient light intensity variation curve shown represents the constant ambient light intensity collected by the photosensor. Figure 7 The ambient light intensity change curve shown represents the brightening of the ambient light intensity collected by the photosensor. Figure 8 The ambient light intensity change curve shown represents the dimming of the ambient light intensity collected by the photosensor. Figure 9 The ambient light intensity variation curve shown represents the frequent changes in ambient light intensity collected by the photosensitive sensor.
[0045] Figure 10 This is a schematic diagram of a device for identity verification provided in an embodiment of this specification. This device (hereinafter referred to as "identity verification device 1") can be implemented as all or part of an electronic device through software, hardware, or a combination of both. According to some embodiments, the identity verification device 1 includes a first ambient light brightness module 11, a second ambient light brightness module 12, and an identity verification module 13.
[0046] The first ambient light brightness module 11 is used to obtain the verification video corresponding to the target user during the verification process, input multiple video frames corresponding to the verification video into the trained ambient light brightness prediction model, and obtain the first ambient light brightness change information corresponding to the multiple video frames output by the ambient light brightness prediction model. The second ambient light brightness module 12 is used to obtain the second ambient light brightness change information corresponding to the shooting time points of the multiple video frames collected by the photosensitive sensor during the core body process; The identity verification module 13 is used to obtain the similarity between the first ambient light brightness change information and the second ambient light brightness change information. If the similarity is less than or equal to a first preset threshold, it is determined that the target user has not passed the identity verification.
[0047] In some embodiments, the first ambient light brightness change information includes a first ambient light brightness change curve, and the second ambient light brightness change information includes the first ambient light brightness change curve.
[0048] In some embodiments, obtaining the similarity between the first ambient light brightness change information and the second ambient light brightness change information, and determining that the target user has failed the identity verification if the similarity is less than or equal to a first preset threshold, includes: obtaining the curve waveform similarity between the first ambient light brightness change curve and the second ambient light brightness change curve, and determining that the target user has failed the identity verification if the curve waveform similarity is less than or equal to a first preset threshold.
[0049] In some embodiments, obtaining the waveform similarity between the first ambient light brightness change curve and the second ambient light brightness change curve, and determining that the target user has failed the identity verification if the waveform similarity is less than or equal to a first preset threshold, further includes: if the waveform similarity is greater than the first preset threshold, obtaining the dynamic change synchronization degree between the first ambient light brightness change curve and the second ambient light brightness change curve; if the dynamic change synchronization degree is less than or equal to a second preset threshold, determining that the target user has failed the identity verification.
[0050] In some embodiments, the identity verification device 1 is further configured to: obtain the screen brightness change rules corresponding to the identity verification process, and change the screen brightness according to the screen brightness change rules during the identity verification process.
[0051] In some embodiments, obtaining the screen brightness change rule corresponding to the body verification process and changing the screen brightness according to the screen brightness change rule during the body verification process includes: obtaining the current ambient light brightness collected by a photosensitive sensor; if the current ambient light brightness is less than or equal to a preset brightness threshold, obtaining the screen brightness change rule corresponding to the body verification process and changing the screen brightness according to the screen brightness change rule during the body verification process.
[0052] In some embodiments, obtaining the screen brightness change rule corresponding to the authentication process includes: determining the screen brightness change rule corresponding to the authentication process based on the sensitive operations associated with the authentication process.
[0053] In some embodiments, determining the screen brightness change rule corresponding to the identity verification process based on the sensitive operations associated with the identity verification process includes: determining the screen brightness change rule corresponding to the identity verification process based on the historical identity verification information of the target user.
[0054] In some embodiments, obtaining the similarity between the first ambient light brightness change information and the second ambient light brightness change information, and determining that the target user has failed the identity verification if the similarity is less than or equal to a first preset threshold, includes: if the identity verification video has passed the detection, obtaining the similarity between the first ambient light brightness change information and the second ambient light brightness change information, and determining that the target user has failed the identity verification if the similarity is less than or equal to a first preset threshold.
[0055] In some embodiments, the identity verification device 1 is further configured to: if the similarity is greater than the first preset threshold, detect the identity verification video, and determine whether the target user has passed the identity verification based on the detection result.
[0056] In some embodiments, the identity verification device 1 is further configured to: collect the target ambient light brightness corresponding to the shooting time point of each target video frame corresponding to the target video during the shooting process of the target video, train the ambient light brightness prediction model according to each target video frame and the target ambient light brightness, and obtain the trained ambient light brightness prediction model, wherein the target ambient light brightness is used as the training label of each target video frame.
[0057] The above-described apparatus embodiments correspond to the aforementioned method embodiments. For detailed descriptions, please refer to the description in the method embodiments section; further details will not be repeated here. The apparatus embodiments are derived from the corresponding method embodiments and have the same technical effects. For detailed descriptions, please refer to the corresponding method embodiments.
[0058] This specification also provides a computer storage medium storing a computer program thereon, which, when executed by a processor, implements the method described in this specification.
[0059] This specification also provides a computer program product that stores at least one instruction, which is loaded by the processor and executes the method described in this specification embodiment.
[0060] This specification also provides an electronic device, including a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and execute the method described in the embodiments of this specification.
[0061] The embodiments in this specification also provide Figure 11 The diagram shows the structure of the electronic device. Figure 11At the hardware level, the electronic device includes a processor, internal bus, network interface, memory, and non-volatile memory, and may also include other hardware required for business operations. The processor reads the corresponding computer program from the non-volatile memory into memory and then runs it to implement the above method.
[0062] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.
[0063] Those skilled in the art will understand that embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied 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.
[0064] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0065] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0066] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0067] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0068] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.
[0069] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.
[0070] The above description is merely an embodiment of this specification and is not intended to limit this specification. Various modifications and variations can be made to this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of the claims of this specification.
Claims
1. A method for identity verification, comprising: Obtain the verification video corresponding to the target user during the verification process, input multiple video frames corresponding to the verification video into a trained ambient light brightness prediction model, and obtain the first ambient light brightness change information corresponding to the multiple video frames output by the ambient light brightness prediction model. The second ambient light brightness change information corresponding to the shooting time points of the multiple video frames collected by the photosensitive sensor during the core body process is obtained; Obtain the similarity between the first ambient light brightness change information and the second ambient light brightness change information. If the similarity is less than or equal to a first preset threshold, determine that the target user has failed the identity verification.
2. The method according to claim 1, wherein the first ambient light brightness change information includes a first ambient light brightness change curve, and the second ambient light brightness change information includes the first ambient light brightness change curve.
3. The method according to claim 2, wherein obtaining the similarity between the first ambient light brightness change information and the second ambient light brightness change information, and determining that the target user has failed the identity verification if the similarity is less than or equal to a first preset threshold, includes: Obtain the curve waveform similarity between the first ambient light brightness change curve and the second ambient light brightness change curve. If the curve waveform similarity is less than or equal to a first preset threshold, determine that the target user has failed the identity verification.
4. The method according to claim 3, wherein obtaining the waveform similarity between the first ambient light intensity change curve and the second ambient light intensity change curve, and determining that the target user has failed the identity verification if the waveform similarity is less than or equal to a first preset threshold, further includes: If the similarity of the curve waveform is greater than the first preset threshold, the dynamic change synchronization degree between the first ambient light brightness change curve and the second ambient light brightness change curve is obtained. If the dynamic change synchronization degree is less than or equal to the second preset threshold, it is determined that the target user has not passed the identity verification.
5. The method according to claim 1, further comprising: Obtain the screen brightness change rules corresponding to the core body process, and change the screen brightness according to the screen brightness change rules during the core body process.
6. The method according to claim 5, wherein obtaining the screen brightness change rule corresponding to the body-building process, and changing the screen brightness according to the screen brightness change rule during the body-building process, includes: The current ambient light intensity is obtained through a photosensitive sensor. If the current ambient light intensity is less than or equal to a preset brightness threshold, the screen brightness change rule corresponding to the body-body process is obtained, and the screen brightness is changed according to the screen brightness change rule during the body-body process.
7. The method according to claim 5 or 6, wherein obtaining the screen brightness change rule corresponding to the core process includes: Based on the sensitive operations associated with the body-locking process, determine the screen brightness change rules corresponding to the body-locking process.
8. The method according to claim 5 or 6, wherein determining the screen brightness change rule corresponding to the authentication process based on the sensitive operation associated with the authentication process includes: Based on the target user's historical identity verification information, determine the screen brightness change rules corresponding to the identity verification process.
9. The method according to claim 1, wherein obtaining the similarity between the first ambient light brightness change information and the second ambient light brightness change information, and determining that the target user has failed the identity verification if the similarity is less than or equal to a first preset threshold, comprises: If the identity verification video has passed the detection, the similarity between the first ambient light brightness change information and the second ambient light brightness change information is obtained. If the similarity is less than or equal to a first preset threshold, it is determined that the target user has not passed the identity verification.
10. The method according to claim 1, further comprising: If the similarity is greater than the first preset threshold, the identity verification video is detected, and the target user is determined to have passed the identity verification based on the detection result.
11. The method according to claim 1, further comprising: During the shooting of the target video, the target ambient light intensity at the shooting time point of each target video frame is collected. The ambient light intensity prediction model is trained based on each target video frame and the target ambient light intensity to obtain a trained ambient light intensity prediction model. The target ambient light intensity is used as the training label for each target video frame.
12. An apparatus for identity verification, comprising: The first ambient light brightness module is used to obtain the verification video corresponding to the target user during the verification process, input multiple video frames corresponding to the verification video into the trained ambient light brightness prediction model, and obtain the first ambient light brightness change information corresponding to the multiple video frames output by the ambient light brightness prediction model. The second ambient light brightness module is used to obtain the second ambient light brightness change information corresponding to the shooting time points of the multiple video frames collected by the photosensitive sensor during the core body process; The identity verification module is used to obtain the similarity between the first ambient light brightness change information and the second ambient light brightness change information. If the similarity is less than or equal to a first preset threshold, it is determined that the target user has failed the identity verification.
13. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 11.
14. An electronic device, characterized in that, include: A processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to execute the steps of the method as claimed in any one of claims 1 to 11.
15. A computer program product having at least one instruction stored thereon, characterized in that, When the at least one instruction is executed by the processor, it implements the steps of the method according to any one of claims 1 to 11.