Identity verification method, device and equipment

Abstract

The embodiment of the invention discloses an identity verification method, device and equipment, and the method is applied to terminal equipment, and comprises the steps: receiving an identity verification instruction for a target user; in response to the identity verification instruction, obtaining multiple rounds of video verification interaction strategies randomly generated for the target user, each round of video verification interaction strategy in the multiple rounds of video verification interaction strategies comprises but is not limited to one or more of an interaction rule based on a face video stream, an interaction rule based on a limb action video stream, an interaction rule based on identity verification of a specified certificate and an interaction rule based on identity verification of near field communication; based on multiple rounds of video verification interaction strategies, acquiring an interaction video stream generated by executing each round of video verification interaction strategy through a video acquisition component; and sending the collected interactive video stream to a server to trigger the server to perform identity verification on the target user based on the collected interactive video stream, and returning a corresponding identity verification result.

Description

Technical Field

[0001] This document relates to the field of computer technology, and in particular to an identity verification method, device and equipment. Background Art

[0002] At a time when more and more businesses rely on real-person authentication, face-based identity verification has become an indispensable part based on privacy protection. However, as the capabilities of large-scale AIGC models continue to increase, more and more attackers are using the capabilities of large-scale AIGC models to conduct deepfake attacks. The attack efficiency and capabilities of attack tools used for identity verification with AIGC will be greatly improved. There is even a trend of SaaS-based attack tools, which use the above methods to achieve the purpose of attack. To this end, a better identity verification mechanism is needed to avoid or reduce the risk of attack tools with AIGC on identity verification. Summary of the invention

[0003] The purpose of the embodiments of this specification is to provide a better identity verification mechanism, so as to avoid or reduce the risk of attack on identity verification by attack tools supported by AIGC.

[0004] In order to implement the above technical solution, the embodiments of this specification are implemented as follows: An identity verification method provided by an embodiment of the present specification is applied to a terminal device, and the method includes: receiving an identity verification instruction for a target user; in response to the identity verification instruction, obtaining a multi-round video verification interaction strategy randomly generated for the target user, each round of the multi-round video verification interaction strategy includes but is not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a designated certificate, and an interaction rule based on identity verification of a near field communication; based on the multi-round video verification interaction strategy, collecting the interaction video stream generated by executing each round of the video verification interaction strategy through a video acquisition component; sending the collected interaction video stream generated by executing each round of the video verification interaction strategy to a server, and the collected interaction video stream is used to trigger the server to perform identity verification on the target user based on the collected interaction video stream, and return a corresponding identity verification result.

[0005] An identity verification method provided in an embodiment of the present specification is applied to a server, and the method includes: receiving an identity verification request for a target user sent by a terminal device; in response to the identity verification request, randomly generating a multi-round video verification interaction strategy for the target user, and sending the multi-round video verification interaction strategy to the terminal device, wherein the multi-round video verification interaction strategy is used to trigger the terminal device to collect the interactive video stream generated by executing each round of the video verification interaction strategy based on the multi-round video verification interaction strategy through a video acquisition component, and each round of the video verification interaction strategy includes but is not limited to one or more of interaction rules based on facial video streams, interaction rules based on body movement video streams, interaction rules based on identity verification of designated certificates, and interaction rules based on identity verification of near field communication; receiving the interactive video stream generated by executing each round of the video verification interaction strategy collected by the terminal device, and verifying the identity of the target user based on the collected interactive video stream to obtain a corresponding identity verification result; and sending the identity verification result to the terminal device.

[0006] An embodiment of the present specification provides an identity verification device, the device comprising: an instruction receiving module, receiving an identity verification instruction for a target user; a multi-round video interaction determination module, responding to the identity verification instruction, obtaining a multi-round video verification interaction strategy randomly generated for the target user, each round of the multi-round video verification interaction strategy including but not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a designated certificate, and an interaction rule based on identity verification of a near field communication; a video stream acquisition module, based on the multi-round video verification interaction strategy, acquiring an interactive video stream generated by executing each round of the video verification interaction strategy through a video acquisition component; an identity verification module, sending the acquired interactive video stream generated by executing each round of the video verification interaction strategy to a server, the acquired interactive video stream being used to trigger the server to perform identity verification on the target user based on the acquired interactive video stream, and return a corresponding identity verification result.

[0007] An identity verification device provided by an embodiment of the present specification comprises: an identity verification request module, which receives an identity verification request for a target user sent by a terminal device; a multi-round video interaction generation module, which randomly generates a multi-round video verification interaction strategy for the target user in response to the identity verification request, and sends the multi-round video verification interaction strategy to the terminal device, wherein the multi-round video verification interaction strategy is used to trigger the terminal device to collect the interactive video stream generated by executing each round of the video verification interaction strategy through a video acquisition component based on the multi-round video verification interaction strategy, wherein each round of the video verification interaction strategy includes but is not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a designated certificate, and an interaction rule based on identity verification of a near field communication; an identity verification module, which receives the interactive video stream generated by executing each round of the video verification interaction strategy collected by the terminal device, and performs identity verification on the target user based on the collected interactive video stream to obtain a corresponding identity verification result; and a result sending module, which sends the identity verification result to the terminal device.

[0008] An embodiment of the present specification provides an identity verification device, which includes: a processor; and a memory arranged to store computer executable instructions, wherein when the executable instructions are executed, the processor: receives an identity verification instruction for a target user; in response to the identity verification instruction, obtains a multi-round video verification interaction strategy randomly generated for the target user, each round of the multi-round video verification interaction strategy includes but is not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity authentication of a designated certificate, and an interaction rule based on identity authentication of a near field communication; based on the multi-round video verification interaction strategy, collects the interaction video stream generated by executing each round of the video verification interaction strategy through a video acquisition component; sends the collected interaction video stream generated by executing each round of the video verification interaction strategy to a server, and the collected interaction video stream is used to trigger the server to verify the identity of the target user based on the collected interaction video stream, and return the corresponding identity verification result.

[0009] An embodiment of the present specification provides an identity verification device, the identity verification device comprising: a processor; and a memory arranged to store computer executable instructions, wherein the executable instructions, when executed, cause the processor to: receive an identity verification request for a target user sent by a terminal device; in response to the identity verification request, randomly generate a multi-round video verification interaction strategy for the target user, and send the multi-round video verification interaction strategy to the terminal device, wherein the multi-round video verification interaction strategy is used to trigger the terminal device to collect, based on the multi-round video verification interaction strategy, an interactive video stream generated by executing each round of the video verification interaction strategy through a video acquisition component, wherein each round of the video verification interaction strategy includes but is not limited to one or more of an interactive rule based on a facial video stream, an interactive rule based on a body movement video stream, an interactive rule based on identity verification of a designated certificate, and an interactive rule based on identity verification of a near field communication; receive the interactive video stream generated by executing each round of the video verification interaction strategy collected by the terminal device, and perform identity verification on the target user based on the collected interactive video stream to obtain a corresponding identity verification result; and send the identity verification result to the terminal device.

[0010] The embodiments of the present specification also provide a storage medium, which is used to store computer-executable instructions, and the executable instructions implement the following process when executed by a processor: receiving an identity verification instruction for a target user; in response to the identity verification instruction, obtaining a multi-round video verification interaction strategy randomly generated for the target user, each round of the multi-round video verification interaction strategy includes but is not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity authentication of a designated certificate, and an interaction rule based on identity authentication of a near-field communication; based on the multi-round video verification interaction strategy, collecting the interactive video stream generated by executing each round of the video verification interaction strategy through a video acquisition component; sending the collected interactive video stream generated by executing each round of the video verification interaction strategy to a server, and the collected interactive video stream is used to trigger the server to verify the identity of the target user based on the collected interactive video stream, and return the corresponding identity verification result.

[0011] The embodiments of the present specification also provide a storage medium, which is used to store computer-executable instructions. When the executable instructions are executed by a processor, the following process is implemented: receiving an identity verification request for a target user sent by a terminal device; in response to the identity verification request, randomly generating a multi-round video verification interaction strategy for the target user, and sending the multi-round video verification interaction strategy to the terminal device, wherein the multi-round video verification interaction strategy is used to trigger the terminal device to collect the interactive video stream generated by executing each round of the video verification interaction strategy based on the multi-round video verification interaction strategy through a video acquisition component, wherein each round of the video verification interaction strategy includes but is not limited to one or more of interaction rules based on facial video streams, interaction rules based on body movement video streams, interaction rules based on identity verification of designated certificates, and interaction rules based on identity verification of near field communication; receiving the interactive video stream generated by executing each round of the video verification interaction strategy collected by the terminal device, and verifying the identity of the target user based on the collected interactive video stream to obtain a corresponding identity verification result; and sending the identity verification result to the terminal device.

[0012] The embodiments of the present specification also provide a computer program product, including a computer program, which implements the following process when executed by a processor: receiving an identity verification instruction for a target user; in response to the identity verification instruction, obtaining a multi-round video verification interaction strategy randomly generated for the target user, each round of the multi-round video verification interaction strategy including but not limited to one or more of interaction rules based on facial video streams, interaction rules based on body movement video streams, interaction rules based on identity authentication of designated certificates, and interaction rules based on near field communication identity authentication; based on the multi-round video verification interaction strategy, collecting the interactive video stream generated by executing each round of the video verification interaction strategy through a video acquisition component; sending the collected interactive video stream generated by executing each round of the video verification interaction strategy to a server, the collected interactive video stream being used to trigger the server to perform identity verification on the target user based on the collected interactive video stream, and return a corresponding identity verification result.

[0013] The embodiments of the present specification also provide a computer program product, including a computer program, which implements the following process when executed by a processor: receiving an identity verification request for a target user sent by a terminal device; in response to the identity verification request, randomly generating a multi-round video verification interaction strategy for the target user, and sending the multi-round video verification interaction strategy to the terminal device, wherein the multi-round video verification interaction strategy is used to trigger the terminal device to collect the interactive video stream generated by executing each round of the video verification interaction strategy based on the multi-round video verification interaction strategy through a video acquisition component, wherein each round of the video verification interaction strategy includes but is not limited to one or more of interaction rules based on facial video streams, interaction rules based on body movement video streams, interaction rules based on identity verification of designated certificates, and interaction rules based on identity verification of near field communication; receiving the interactive video stream generated by executing each round of the video verification interaction strategy collected by the terminal device, and performing identity verification on the target user based on the collected interactive video stream to obtain a corresponding identity verification result; and sending the identity verification result to the terminal device. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the drawings required for use in the embodiments or the prior art description will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative labor. Figure 1 This is an example of an identity verification method in this specification; Figure 2 This is another identity verification method embodiment of this specification; Figure 3 This is a schematic diagram of a video verification of this manual; Figure 4 This is another schematic diagram of video verification of this manual; Figure 5 This is another identity verification method embodiment of the present specification; Figure 6 This is a schematic diagram of a video verification guide page in this manual; Figure 7 This is another identity verification method embodiment of the present specification; Figure 8 This is a schematic diagram of an identity verification process in this manual; Fig. 9 This is another identity verification method embodiment of the present specification; Fig.10 This is another identity verification method embodiment of the present specification; Fig.11 This is another identity verification method embodiment of the present specification; Fig.12 This is another identity verification method embodiment of the present specification; Fig.13 This is another identity verification method embodiment of the present specification; Fig.14 This is a schematic diagram of the interaction process between a terminal device and a server in this specification; Fig.15 This is an embodiment of an identity verification device in this specification; Fig.16 This is another embodiment of the identity verification device of this specification; Fig.17 This is an embodiment of an identity verification device in this specification. DETAILED DESCRIPTION

[0015] The embodiments of this specification provide an identity verification method, device and equipment.

[0016] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. 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 should fall within the scope of protection of this specification.

[0017] The embodiments of this specification provide an identity verification mechanism. At a time when more and more businesses rely on real-person authentication, identity verification methods based on faces have become an indispensable part. However, as the capabilities of large-model AIGC continue to increase, more and more attackers use the capabilities of large-model AIGC to conduct deep fake (i.e., Deepfake, which refers to the machine learning model of the generative adversarial network that merges and superimposes images or videos on the source image or video, and uses neural networks for sample learning to splice personal voices, facial expressions, and body movements into false content. Artificial intelligence technology) attacks, the attack efficiency and capabilities of attack tools used for identity verification under the support of AIGC will be greatly improved, and even the above-mentioned attack tools have a trend of SaaS, using the above-mentioned means to achieve the purpose of attack. To this end, it is necessary to provide a better identity verification mechanism to avoid or reduce the attack risk of identity verification by attack tools supported by AIGC. The embodiments of this specification upgrade the original identity verification mechanism based on simple static images to active interaction and real-time video stream anti-counterfeiting. The initiative, randomness, and increased information capacity brought by active interaction will greatly increase the cost of counterfeiting, thereby avoiding or reducing the attack risk of identity verification by attack tools supported by AIGC. For specific processing, please refer to the specific content in the following embodiments.

[0018] like Figure 1 As shown, the embodiment of this specification provides an identity verification method, and the execution subject of the method can be a terminal device, wherein the terminal device can be a mobile terminal device such as a mobile phone, a tablet computer, or a computer device such as a laptop or a desktop computer, or an IoT device (specifically, a smart watch, a car device, etc.). The method can specifically include the following steps: In step S102, an identity verification instruction for a target user is received.

[0019] The target user may be any user, and in this embodiment, the target user may be a user who needs to undergo identity verification. The identity verification instruction may be an instruction for verifying the authenticity of the identity of the target user.

[0020] In implementation, the identity verification instruction can be triggered and generated in a variety of different ways. For example, it can be an identity verification instruction triggered by the target user's direct and active identity verification. Specifically, if a certain identity verification strategy needs to be tested, the target user can actively trigger the identity verification process, and the terminal device can generate an identity verification instruction for the target user. In addition, it can also be that the target user needs to verify the authenticity of the target user's identity during the execution of a certain business. For example, the target user needs to transfer money to a certain merchant. At this time, the target user's identity needs to be verified for authenticity. When the target user initiates a transfer request, the terminal device can call the identity verification strategy and generate an identity verification instruction for the target user. In addition to the above-mentioned transfer business, identity verification can also be performed during the process of the target user performing a variety of different businesses, such as payment business, business of starting a certain application, account information (or personal information) query or modification business, user registration-related business, etc., which are set according to actual conditions. Taking the scenario where the target user purchases a certain product as an example, after the target user purchases a certain product in a store of a certain merchant in a certain trading platform, the target user can settle the payment for the product. At this time, the settlement page can be displayed in the terminal device, which can include the information of the purchased product, the amount to be paid, etc. At this time, the target user can click the settlement button in the settlement page, and the application corresponding to the trading platform in the terminal device determines that the payment service needs to be processed by identity verification. The terminal device can call the identity verification strategy and obtain relevant information (such as information about the purchased product, the amount to be paid, relevant information about the target user, relevant information about the terminal device, etc.), and generate an identity verification instruction based on the above information. In actual applications, it is also possible to directly generate an identity verification instruction for the target user without obtaining the above relevant information, which can be set according to actual conditions. Based on the above processing, the terminal device can receive the identity verification instruction for the target user.

[0021] In step S104, in response to the above-mentioned identity verification instruction, a multi-round video verification interaction strategy randomly generated for the target user is obtained, and each round of video verification interaction strategy in the multi-round video verification interaction strategy includes but is not limited to one or more of interaction rules based on facial video streams, interaction rules based on body movement video streams, interaction rules based on identity verification of designated documents, and interaction rules based on identity verification of near field communication.

[0022] Among them, the multi-round video verification interaction strategy can be a multi-round video verification interaction strategy constructed by constructing a round of video verification interaction strategy through one or more interaction rules of different video streams, and the interaction rules of the video streams can include multiple types. For example, the interaction rules of the video streams can include interaction rules based on facial video streams, interaction rules based on body movement video streams, interaction rules based on identity verification of designated certificates, interaction rules based on identity verification of near field communication, etc. The interaction rules based on facial video streams can be interaction rules that make the user's facial image located in a specified area. In addition, in addition to keeping the facial image in the specified area, preset facial movements (such as opening the mouth, blinking, reading aloud, etc.) or head movements (such as shaking the head, nodding, moving, etc.) can also be performed in the above-mentioned specified area, which can be set according to actual conditions. The interaction rules based on the video stream of body movements can be interaction rules for performing specified body movements in a specified area, wherein the body movements include but are not limited to raising the left hand, raising the right hand, sliding the left hand horizontally from the right side of the specified area to the left side, sliding the right hand horizontally from the left side of the specified area to the right side, poking the left cheek with the index finger, poking the right cheek with the index finger, touching the chin with the left hand, touching the chin with the right hand, touching the forehead with the left hand, touching the forehead with the right hand, touching the ear with the left hand, touching the ear with the right hand, etc., which can be set according to actual conditions. The interaction rules based on identity authentication of specified certificates can be interaction rules for collecting the video stream of specified certificates through the terminal device for identity authentication, wherein the specified certificates can include multiple types, for example, the specified certificates can be certificates that can prove the identity of the user (such as social security card, residence permit, passport, etc.), bank card, membership card, driver's license, etc., which can be set according to actual conditions. The interaction rules for identity authentication based on near field communication can be interaction rules for obtaining information related to the user through near field communication for identity verification. For each triggered identity verification process, different users may have different randomly generated multi-round video verification interaction strategies, and the multi-round video verification interaction strategies for different users are all obtained by randomly generating.

[0023] During implementation, after the terminal device receives the identity verification instruction, it can respond to the identity verification instruction. At this time, a multi-round video verification interaction strategy randomly generated for the target user can be obtained. The processing of obtaining the multi-round video verification interaction strategy randomly generated for the target user can be implemented in a variety of ways. For example, the terminal device can store interaction rules for different video streams. When the terminal device receives the identity verification instruction, it can randomly select interaction rules for multiple video streams from the interaction rules of different video streams, and can generate multi-round video verification interaction strategies through random combinations and the like.

[0024] For example, the interaction rules based on facial video stream, the interaction rules based on body movement video stream, the interaction rules based on identity verification of designated certificates, and the interaction rules based on near field communication identity verification can be selected from the interaction rules based on facial video stream, the interaction rules based on body movement video stream, the interaction rules based on identity verification of designated certificates, and the interaction rules based on near field communication identity verification. The interaction rules based on facial video stream and the interaction rules based on body movement video stream can be combined. Since the interaction rules based on facial video stream can include making the user's facial image located in a specified area, performing preset facial movements or head movements in the specified area, etc., therefore, in order to reflect the randomness of the video verification interaction strategy finally generated, one or more of the above-mentioned interaction rules can be randomly selected, such as making the user's facial image located in a specified area, or making the user's facial image located in a specified area and performing preset facial movements in the specified area, etc. The specific settings can be made according to actual conditions. Accordingly, the interaction rules based on the body movement video stream may include a variety of different body movements. In order to reflect the randomness of the final generated video verification interaction strategy, one or more of them may be randomly selected. For example, raising the left hand, touching the chin with the left hand, and touching the ear with the left hand may be selected from the above body movements, and the specific setting may be based on actual conditions. Furthermore, the combination of the above two may include a variety of methods, such as the combined interaction rules may include making the user's facial image located in a specified area and raising the left hand at the same time; making the user's facial image located in a specified area and touching the chin with the left hand at the same time; making the user's facial image located in a specified area and touching the ear with the left hand at the same time; making the user's facial image located in a specified area and blinking in the specified area and raising the left hand at the same time, etc. In order to further reflect the randomness of the final generated video verification interaction strategy, multiple strategies can be selected from the above combinations, such as making the user's facial image located in the specified area and raising the left hand at the same time; making the user's facial image located in the specified area and touching the chin with the left hand; making the user's facial image located in the specified area and touching the ear with the left hand at the same time, and then combining them with the interaction rules based on identity authentication of the specified certificate to obtain a round of video verification interaction strategy consisting of making the user's facial image located in the specified area and raising the left hand at the same time, a round of video verification interaction strategy consisting of making the user's facial image located in the specified area and touching the chin with the left hand at the same time, a round of video verification interaction strategy consisting of making the user's facial image located in the specified area and touching the ear with the left hand at the same time, and a round of video verification interaction strategy consisting of making the user's facial image located in the specified area and touching the ear with the left hand at the same time, and a round of video verification interaction strategy based on the interaction rules for identity authentication of the specified certificate, a total of four rounds of video verification interaction strategies, that is, the terminal device can obtain multiple rounds of video verification interaction strategies randomly generated for the target user.

[0025] The above is to randomly generate a multi-round video verification interaction strategy for the target user in the terminal device. In actual applications, the processing of randomly generating a multi-round video verification interaction strategy for the target user can also be completed in other devices. For example, the terminal device can obtain the processing of randomly generating a multi-round video verification interaction strategy for the target user from the server or a designated database, and the processing of randomly generating a multi-round video verification interaction strategy for the target user can be completed in the above-mentioned server or database. The specific processing method can refer to the specific processing process in the above-mentioned terminal device, which will not be repeated here.

[0026] In step S106, based on the multi-round video verification interaction strategy, the interactive video stream generated by executing each round of the video verification interaction strategy is collected by the video collection component.

[0027] Among them, interactive video stream can be streaming data that enables audio, video and other multimedia to be played on the network in real time without downloading and waiting. The interactive video stream can be processed as a stable and continuous stream through the network. Because of the flow, the client application or plug-in can display the multimedia data before the entire file is transmitted.

[0028] In implementation, different video verification interaction strategies may correspond to different video verification interaction pages, and basic interaction page templates corresponding to different video verification interaction strategies may be pre-set. After multiple rounds of video verification interaction strategies are determined in the above manner, the content of each round of video verification interaction strategies may be analyzed, and the relevant content in each round of video verification interaction strategies may be filled into the basic interaction page template, thereby forming a video verification interaction page corresponding to each round of video verification interaction strategies. Alternatively, corresponding video verification interaction pages may be pre-set for different video verification interaction strategies, and then the video verification interaction strategies and corresponding video verification interaction pages may be stored in correspondence. For each round of video verification interaction strategy, the video verification interaction page corresponding to the video verification interaction strategy can be determined or obtained in the above manner, and the terminal device can display the video verification interaction page. The target user can interact with the terminal device in real time according to the prompt information or guidance information provided in the video verification interaction page. For example, for a video verification interaction strategy that includes making the user's facial image located in a specified area and raising the right hand at the same time, the target user can be prompted to adjust his facial image to the specified area and raise his right hand at the same time. At this time, the target user can use the above prompt information or guidance information to move the face to the specified area respectively, and can raise his right hand. In the process of the above real-time interaction, the interactive video stream of the entire process of the above processing of the target user is collected through the video acquisition component, so that the interactive video stream generated by the execution of the video verification interaction strategy can be obtained. In the above manner, the interactive video stream generated by the execution of each round of video verification interaction strategy can be obtained.

[0029] In the above manner, unpredictable multi-action factors can be added to the generated interactive video stream, thereby increasing the attack cost of identity verification.

[0030] In step S108, the collected interactive video stream generated by executing each round of video verification interaction strategy is sent to the server. The collected interactive video stream is used to trigger the server to verify the identity of the target user based on the collected interactive video stream and return the corresponding identity verification result.

[0031] In implementation, the collected interactive video stream generated by executing each round of video verification interaction strategy can be sent to the server, and the server can analyze the collected interactive video stream. In the case of continuous and uninterrupted interactive video stream, a preset algorithm (such as face recognition algorithm, action recognition algorithm, similarity algorithm, etc. under the interactive video stream) can be used to verify the face, specified body movements and documents, etc., to obtain the corresponding identity verification result, wherein only when the verification results corresponding to the interactive video stream generated by each round of video verification interaction strategy are all verified, the final identity verification result is the identity verification of the target user, otherwise, the identity verification of the target user fails. The server can send the identity verification result to the terminal device, and the terminal device can receive the identity verification result.

[0032] The embodiment of the present specification provides an identity verification method, which is applied to a terminal device, by receiving an identity verification instruction for a target user, and responding to the identity verification instruction, obtaining a multi-round video verification interaction strategy randomly generated for the target user, each round of the multi-round video verification interaction strategy includes but is not limited to an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a specified certificate, and an interaction rule based on identity verification of a near field communication. One or more of the following constructions, then, based on the multi-round video verification interaction strategy, the interactive video stream generated by executing each round of the video verification interaction strategy can be collected by a video acquisition component, and finally, the collected execution of each round of the video verification interaction strategy can be used to generate a plurality of interactive video streams. The interactive video stream generated by the frequency verification interaction strategy is sent to the server to verify the identity of the target user based on the collected interactive video stream. In this way, in the face of the attack tools supported by AIGC, a new interaction mode is adopted to counter the attacks of the attack tools supported by AIGC by adopting more abundant means. It mainly reflects the identity verification of active interaction and real-time video streams. The initiative, randomness, and increased information capacity brought by active interaction will greatly increase the cost of forgery, thereby avoiding or reducing the attack risk of identity verification by attack tools supported by AIGC, and using real-time video streams for identity verification. Unpredictable multi-action factors are added to the real-time video stream, thereby increasing the attack cost of identity verification.

[0033] In practical applications, the specific processing methods of the above step S106 can be various, and an optional processing method is provided below, such as Figure 2 As shown, the processing may specifically include the following steps S1062 to S1066.

[0034] In step S1062, a video verification interaction text is extracted from each round of video verification interaction strategy, and the video verification interaction text is used to prompt the identity verification process of the target user.

[0035] Among them, the video verification interaction copy can include multiple types, for example, it can include prompt information such as "Please raise your left hand", "Please keep the light sufficient and the whole face in the frame", etc., it can also include schematic diagrams of body movements, such as a schematic diagram of raising the left hand, and it can also include guiding information such as "Go to settings to turn on near-field communication permissions", etc., which can be set according to actual conditions.

[0036] During implementation, when the target user starts video verification, the terminal device can send a room creation request to the server. The server can respond to the room creation request, create information such as the room number and room password to complete the creation of the room, and the server can send a message of successful room creation to the terminal device. At this time, the terminal device can enter the room based on the created room number and room password and other information. The server randomly decides on each round of video verification interaction strategy based on the risk level and preset rules, and can generate corresponding video verification interaction copy based on each round of video verification interaction strategy. Then, each round of video verification interaction strategy is sent to the terminal device, and the terminal device can extract the video verification interaction copy from each round of video verification interaction strategy.

[0037] In step S1064, based on the video verification interaction text in each round of video verification interaction strategy, a video verification interaction page corresponding to each round of video verification interaction strategy is constructed and displayed through the corresponding video verification interaction strategy.

[0038] In step S1066, the video acquisition component acquires the interactive video stream generated by the target user's interaction with the terminal device based on the video verification interaction page corresponding to each round of video verification interaction strategy.

[0039] In implementation, the specific processing process of the above steps S1062 to S1066 can be as follows: through the processing of the above step S104, a multi-round video verification interaction strategy randomly generated for the target user can be obtained, and then the terminal device can execute each round of the video verification interaction strategy in turn. Taking the above-constructed four-round video verification interaction strategy as an example, for the video verification interaction strategy consisting of making the user's facial image located in the specified area and raising the left hand at the same time, the video verification interaction strategy can be executed. Specifically, Figure 3 As shown, the terminal device can obtain the prompt information (such as "Please raise your left hand", "Please keep the light sufficient and the face fully in the frame", and the schematic diagram of the body movement (i.e., raising the left hand), etc.), the location of the designated area and other information, and can generate a video stream acquisition page, and the obtained information can be set in the video stream acquisition page. Specifically, the prompt information can be set above the designated area, and the designated area can be located in the middle area of ​​the video stream acquisition page. At the same time, the video acquisition component can be started, and the target user can move the face to the designated area according to the prompt information in the video stream acquisition page, and can raise the left hand. At this time, the interactive video stream of the entire process of the target user making the above actions can be collected through the video acquisition component, and the interactive video stream can be used as the interactive video stream generated by executing the above video verification interaction strategy.

[0040] Then, a video verification interaction strategy consisting of making the user's facial image located in the specified area and touching the chin with the left hand can be executed. Specifically, Figure 3 As shown, the terminal device can obtain the prompt information (such as "Please touch your chin with your left hand", "Please keep the light sufficient and the whole face in the frame", and the schematic diagram of touching the chin with the left hand, etc.), the location of the designated area and other information, and can generate a video stream acquisition page, and the obtained information can be set in the video stream acquisition page. Specifically, the prompt information can be set above the designated area, and the designated area can be located in the middle area of ​​the video stream acquisition page. At the same time, the video acquisition component can be started, and the target user can move the face to the designated area according to the prompt information in the video stream acquisition page, and can touch the chin with the left hand. At this time, the interactive video stream of the entire process of the target user making the above actions can be collected through the video acquisition component, and the interactive video stream can be used as the interactive video stream generated by executing the above video verification interaction strategy.

[0041] Afterwards, a video verification interaction strategy consisting of making the user's facial image located in a specified area and touching the ear with the left hand can be executed. Specifically, Figure 3As shown, the terminal device can obtain the prompt information (such as "Please touch your ear with your left hand", "Please keep the light sufficient and the whole face in the frame", and the schematic diagram of touching the ear with the left hand, etc.), the location of the designated area and other information, and can generate a video stream acquisition page, and the obtained information can be set in the video stream acquisition page. Specifically, the prompt information can be set above the designated area, and the designated area can be located in the middle area of ​​the video stream acquisition page. At the same time, the video acquisition component can be started, and the target user can move the face to the designated area according to the prompt information in the video stream acquisition page, and can touch the ear with the left hand. At this time, the interactive video stream of the entire process of the target user making the above actions can be collected through the video acquisition component, and the interactive video stream can be used as the interactive video stream generated by executing the above video verification interaction strategy.

[0042] Finally, the video verification interaction strategy based on the interactive rules for identity authentication of the specified certificate can be executed. Specifically, the terminal device can obtain the prompt information (such as "Please make sure that the certificate image is completely within the specified area", "Do not move the certificate during verification", etc.), the location of the specified area and other information, and can generate a video stream acquisition page. The above information obtained can be set in the video stream acquisition page. Specifically, for example, the prompt information can be set above the specified area, and the specified area can be located in the middle area of ​​the video stream acquisition page. At the same time, the video acquisition component can be started, and the target user can move the image of the certificate to the specified area according to the prompt information in the video stream acquisition page. At this time, the interactive video stream of the entire process of the target user making the above action can be collected through the video acquisition component, and the image of the certificate can be captured. The interactive video stream and the captured image can be used as the interactive video stream generated by executing the above video verification interaction strategy.

[0043] In addition, for executing the video verification interaction strategy consisting of the interaction rules for identity authentication based on near field communication, specifically, Figure 4 As shown, the terminal device can obtain the prompt information (such as "Please place the upper part of the phone close to the passport chip area", "Do not move the document during verification", "You can go to the phone settings to turn on NFC permissions", and can also include "Identification" and "Verification successful, face verification will begin soon", etc.), the location of the designated area and other information, and can generate a video stream acquisition page, and the above-obtained information can be set in the video stream acquisition page. Specifically, the prompt information can be set above and below the designated area, and the designated area can be located in the middle area of ​​the video stream acquisition page. At the same time, the video acquisition component can be started, and the target user can place the target document (such as Figure 4The image of the target user's passport is moved into the specified area. At this time, the interactive video stream of the entire process of the target user performing the above action can be collected by the video acquisition component, and the image of the target document can be taken. The interactive video stream and the taken image can be used as the interactive video stream generated by executing the above video verification interaction strategy.

[0044] In practical applications, the specific processing methods of the above step S104 can be varied. An optional processing method is provided below, such as Figure 5 As shown, the processing may specifically include the following steps S10402 to S10406.

[0045] In step S10402, in response to the above-mentioned identity verification instruction, video verification guidance data is obtained and displayed.

[0046] In implementation, after the terminal device receives the identity verification instruction, it can initiate the identity verification instruction to the server or the risk prevention and control system in the server. The server can perform initialization processing. After the initialization is completed, the availability of the identity verification process using the terminal device can be consulted, and the server can send the availability result to the terminal device. If the availability result indicates that the terminal device can be used for identity verification processing, at this time, the terminal device can pull up the authentication SDK. At this time, the terminal device can request the server to perform the first data rendering processing. The server can return the video verification guidance data to the terminal device, and the terminal device can display the video verification guidance data. The video verification guidance data can be data composed of images and / or text, and the video verification guidance data can also be the data of a page, for example, Figure 6 The video verification guide page is shown. The video verification guide data may be data of the video verification guide page. The video verification guide page may include the target user's identifier (eg Figure 6 "**" in the text), specified prompt information (such as Figure 6 "Video verification is about to begin", "Please ensure that the network is in good condition and complete the verification according to the prompts", "During the video verification, your facial information and other information will need to be collected. Please ensure that the verification environment has a stable signal, sufficient light, and the subject is completely in the frame without obstructions for accurate recognition" and related information of the user agreement, etc.) and user guidance data (such as Figure 6 "Agree to the agreement and start verification" and "Do not verify yet" in the verification process).

[0047] In step S10404, upon receiving an identity verification request from the target user triggered by the video verification guidance data, an identity verification request is sent to the server.

[0048] During implementation, if the target user needs to undergo identity verification, he or she can click "Agree to the agreement and start verification" in the above video verification guide page. At this time, the terminal device can obtain relevant data of the target user (such as the target user's identification, relevant information of the terminal device (such as device information of the terminal device, etc.), relevant information of the business currently executed by the target user (such as business identification, business data, etc.), etc.), and can generate an identity verification request based on the above data and send the identity verification request to the server.

[0049] In step S10406, a multi-round video verification interaction strategy randomly generated for the target user in response to the identity verification request and sent by the receiving server.

[0050] The specific processing process of the server randomly generating multiple rounds of video verification interaction strategies for the target user can refer to the specific processing process of the terminal device randomly generating multiple rounds of video verification interaction strategies for the target user, which will not be repeated here.

[0051] In practical applications, the specific processing methods of the above step S104 can be varied. An optional processing method is provided below, such as Figure 7 As shown, the processing may specifically include the following steps S10408 to S10412.

[0052] In step S10408, in response to the above-mentioned identity verification instruction, basic verification data is obtained, and the basic verification data includes relevant information of the terminal device and / or business information corresponding to the identity verification instruction.

[0053] The relevant information of the terminal device may include multiple information, such as the root permission information (or jailbreak information) of the terminal device, whether the terminal device is a risky terminal device (whether the terminal device is risky can be determined by a preset blacklist, etc.). The business information corresponding to the identity verification instruction may include multiple information, such as business identification, current business data (for example, if it is a payment business, the business data may include the payment amount, payment account information, account information of the payee, etc.), etc., which can be set according to actual conditions.

[0054] In implementation, after receiving the identity verification instruction, the terminal device can obtain relevant information of the current terminal device, and / or can also obtain the business information of the business currently executed by the target user from the application of the business corresponding to the identity verification instruction, or obtain the business information of the business currently executed by the target user from the server, or obtain the business information of the business currently executed by the target user from a designated database, etc., which can be set according to actual conditions. In addition, in order to verify the above basic verification data, relevant information such as the blacklist of the terminal device can also be obtained to determine whether the terminal device of the target user has risks.

[0055] In step S10410, if the basic verification data indicates that the target user is in a high-risk state, a multi-round video verification interaction strategy that is randomly generated for the target user and conforms to the high-risk state is obtained.

[0056] During implementation, the root permission information and blacklist related information of the terminal device currently used by the target user can be obtained. If the root permission of the current terminal device is enabled, the target user is determined to be in a high-risk state; or, the terminal device currently in use is a risky terminal device, the target user is determined to be in a high-risk state; or, the business corresponding to the identity verification instruction is a payment business, and the payment amount in the business information corresponding to the identity verification instruction exceeds a preset threshold, then the target user is determined to be in a high-risk state; or, the business corresponding to the identity verification instruction is a payment business, and the payment account information or the payee's account information in the business information corresponding to the identity verification instruction is risky account information, then the target user is determined to be in a high-risk state, etc. The specific details can also be set according to actual conditions.

[0057] Since high-risk status often requires a more stringent, more complex or more accurate way to determine the user's true identity for identity verification processing, therefore, a generation mechanism for video verification interaction strategies for high-risk status can be pre-set. The video verification interaction strategy for high-risk status can require the video verification process to be more stringent, more complex or more accurate to determine the user's true identity, etc. For example, the multi-round video verification interaction strategy for high-risk status may include a multi-round video verification interaction strategy constructed based on interaction rules of facial video streams and interaction rules of body movement video streams, and a video verification interaction strategy constructed based on interaction rules of identity authentication of near field communication. The multi-round video verification interaction strategy constructed based on interaction rules of facial video streams and interaction rules of body movement video streams may include multiple types, for example, a round of video verification interaction strategy consisting of making the user's facial image located in a specified area and raising the left hand at the same time, a round of video verification interaction strategy consisting of making the user's facial image located in the specified area and touching the chin with the left hand at the same time, a round of video verification interaction strategy consisting of making the user's facial image located in the specified area and touching the ear with the left hand at the same time, a round of video verification interaction strategy consisting of making the user's facial image located in the specified area and touching the forehead with the left hand at the same time, etc. If the basic verification data indicates that the target user is in a high-risk state, a multi-round video verification interaction strategy that meets the high-risk state can be randomly generated for the target user through the above-mentioned generation mechanism. Among them, the specific processing process of randomly generating a multi-round video verification interaction strategy that meets the high-risk state for the target user can be referred to the aforementioned specific processing process of randomly generating a multi-round video verification interaction strategy for the target user, which will not be repeated here.

[0058] In step S10412, if the basic verification data indicates that the target user is not in a high-risk state, a multi-round video verification interaction strategy randomly generated for the target user is obtained.

[0059] In implementation, if the basic verification data indicates that the target user is not in a high-risk state, a multi-round video verification interaction strategy can be randomly generated for the target user through a default generation mechanism. For example, a multi-round video verification interaction strategy constructed based on an interaction rule of a facial video stream and an interaction rule of a body movement video stream, and a video verification interaction strategy constructed based on an interaction rule of identity verification of a specified certificate can be randomly generated. The multi-round video verification interaction strategy constructed based on an interaction rule of a facial video stream and an interaction rule of a body movement video stream can include multiple, but relatively simple, video verification interaction strategies, for example, can include making the user's facial image position The two-round video verification interaction strategies include one round of video verification interaction strategy consisting of raising the left hand while being in the specified area, and one round of video verification interaction strategy consisting of making the user's facial image in the specified area and touching the chin with the left hand. Or, the three-round video verification interaction strategies may include one round of video verification interaction strategy consisting of making the user's facial image in the specified area and raising the left hand while being in the specified area, one round of video verification interaction strategy consisting of making the user's facial image in the specified area and touching the chin with the left hand while being in the specified area, and one round of video verification interaction strategy consisting of making the user's facial image in the specified area and touching the ear with the left hand while being in the specified area. The specific settings can be made according to actual conditions.

[0060] In practical applications, the multi-round video verification interaction strategy includes a multi-round video verification interaction strategy consisting of interaction rules based on facial video streams and interaction rules based on body movement video streams corresponding to each of a variety of different body movements, as well as a video verification interaction strategy based on interaction rules for identity verification of designated documents. Alternatively, the multi-round video verification interaction strategy includes a multi-round video verification interaction strategy consisting of interaction rules based on facial video streams and interaction rules based on body movement video streams corresponding to each of a variety of different body movements, as well as a video verification interaction strategy based on interaction rules for identity verification of near field communication.

[0061] In implementation, considering that physical certificates (or physical certificates) are difficult to prepare (i.e., difficult to obtain, difficult to forge, etc.), and considering that near field communication can more accurately identify the true situation of physical certificates, and thus more accurately determine the true identity of the target user, a multi-round video verification interaction strategy consisting of an interaction rule based on a facial video stream and an interaction rule based on a body movement video stream corresponding to each of a plurality of different body movements, and a multi-round video verification interaction strategy consisting of an interaction rule based on identity verification of near field communication can be set as a multi-round video verification interaction strategy that meets high-risk conditions. A multi-round video verification interaction strategy consisting of an interaction rule based on a facial video stream and an interaction rule based on a body movement video stream corresponding to each of a plurality of different body movements, and a multi-round video verification interaction strategy consisting of an interaction rule based on identity verification of a specified certificate can be set as a multi-round video verification interaction strategy that meets non-high-risk conditions.

[0062] It should be noted that, in actual applications, multi-round video verification interaction strategies that meet high-risk conditions and multi-round video verification interaction strategies for non-high-risk conditions can be constructed not only in the above-mentioned manner, but also in other combination methods. For example, a multi-round video verification interaction strategy consisting of interaction rules based on facial video streams and interaction rules based on limb movement video streams corresponding to each of a variety of different limb movements, a video verification interaction strategy consisting of interaction rules based on near-field communication identity authentication and a video verification interaction strategy consisting of interaction rules based on identity authentication of designated certificates can be set as a multi-round video verification interaction strategy that meets high-risk conditions. The specific content of the multi-round video verification interaction strategy can also be randomly adjusted according to actual conditions.

[0063] In actual applications, a variety of different body movements include arm movements, and movements of arms and other body parts other than arms. The interactive rules based on identity authentication of designated documents include collecting images of designated documents and video streams during the collection process, and verifying the identity through the images of designated documents and video streams during the collection process. The interactive rules for identity authentication based on near-field communication include reading pre-written information in the target document of the target user through the near-field communication component of the terminal device, and verifying the identity through the read information.

[0064] Among them, the near field communication component may include multiple types, such as radio frequency identification (RFID) communication components, Bluetooth communication components, infrared communication components, etc., which may be set according to actual conditions. The target certificate may be a certificate with a component (such as a chip or a tag, etc.) whose information can be read by the near field communication component, and the target certificate may include multiple types, such as a passport, etc.

[0065] In actual applications, before verifying the identity of the target user through the collected interactive video stream, or after obtaining the identity verification result of the target user through the collected interactive video stream, multiple anti-injection protections can be performed using bypass methods such as device information to ensure the security of identity verification. For details, please refer to the processing of steps A2 to A6 below.

[0066] In step A2, the device information of the terminal device is obtained.

[0067] Among them, the device information of the terminal device may include multiple types, for example, the model of the terminal device, hardware configuration information (which may include CPU model, screen size, GPU model, etc.), and the identification of the terminal device (which may include MAC address, name, etc.).

[0068] In step A4, the device information of the terminal device is compared with the device information of the historical terminal devices used by the target user, or the device information of the terminal device is compared with the reference device information of the terminal device to obtain a corresponding comparison result.

[0069] In implementation, in order to verify the device information of the target user's terminal device, the device information of the historical terminal devices used by the target user can be obtained, and the hardware configuration information of the terminal device with the same model as the current terminal device can also be obtained as the reference device information.

[0070] The model of the terminal device currently used by the target user can be compared with the model of the historical terminal device used by the target user. If the models of the two are the same, the device information of the current terminal device (which may include the CPU model, screen size, GPU model, etc.) can be further compared with the relevant information of the historical terminal device. In addition, the hardware configuration information of the current terminal device can be compared with the benchmark device information composed of the hardware configuration information of the terminal device of the same model. If the two are the same through the above comparison, it indicates that the terminal device does not have an attack risk. Otherwise, it can be determined that the terminal device has an attack risk. For example, if the hardware configuration information of the current terminal device is different from the benchmark device information composed of the hardware configuration information of the terminal device of the same model, it is determined that the terminal device has an attack risk, or if the model of the terminal device currently in use is different from the model of the historical terminal device, it is determined that the terminal device has an attack risk, etc. The corresponding comparison results can be obtained in the above manner.

[0071] In step A6, if the comparison result indicates that the terminal device has an attack risk, it is determined that the identity verification result for the target user is failed.

[0072] In implementation, Figure 8As shown, if the above comparison result indicates that the terminal device is at risk of attack, the identity verification result for the target user is determined to be failed. At this time, if the identity verification process of the target user through the collected interactive video stream has not been started or completed, the subsequent identity verification process can be stopped, and the identity verification result for the target user can be directly set to failed. If the identity verification process of the target user through the collected interactive video stream has been completed, then regardless of the result of the identity verification of the target user through the collected interactive video stream, it can be determined that the identity verification result for the target user is failed. If the comparison result indicates that the terminal device does not have an attack risk, and at this time, the identity verification process of the target user through the collected interactive video stream has not been started or completed, the identity verification process of the target user through the collected interactive video stream can be continued, or if the comparison result indicates that the terminal device does not have an attack risk, and at this time, the identity verification process of the target user through the collected interactive video stream has been completed, the identity verification result for the target user can be determined based on the identity verification result and the comparison result of the identity verification process of the target user through the collected interactive video stream. Specifically, if the identity verification result based on the identity verification process of the target user through the collected interactive video stream is a verification pass, and the comparison result indicates that the terminal device does not have an attack risk, the identity verification result for the target user is determined to be a verification pass, otherwise, the identity verification result for the target user is determined to be a verification failure. The above steps A2 to A6 are used to determine whether the attacker is using other terminal devices to perform injections and other behaviors.

[0073] In addition, in actual applications, a threshold number of times the identity verification process is performed can be pre-set. When the number of times the target user triggers the identity verification process exceeds the threshold number, a corresponding prompt message can be generated. Figure K shows a prompt message page, which includes prompt messages such as "The number of times has reached the upper limit" and "Please go to the computer to reapply". Through the above prompt messages, the target user can reapply for identity verification.

[0074] In practical applications, the specific processing methods of the above step S108 can be varied. An optional processing method is provided below, such as Fig. 9 As shown, the processing may specifically include the following steps S1082 to S1086.

[0075] In step S1082, the interactive video stream generated by executing each round of video verification interaction strategy is transmitted from the video acquisition component to the trusted execution environment of the terminal device through the trusted application for performing identity verification processing on the terminal device, wherein the trusted execution environment is provided with data processing rules for performing data protection processing on the interactive video stream collected for identity verification.

[0076] Among them, the trusted execution environment can be TEE (Trusted Execution Environment), which can be implemented by designated hardware devices and programs written in a predetermined programming language (i.e., it can be implemented in the form of hardware + software), or by programs written in a predetermined programming language (i.e., it can be implemented in the form of software), etc., and can be set specifically according to actual conditions. The trusted execution environment can be a data processing environment that is secure and isolated from other environments, that is, the processing performed in the trusted execution environment, and the data generated during the data processing process, etc. cannot be accessed by other execution environments or applications outside the executable environment. The trusted execution environment can be a secure operating environment for data processing. The trusted application can be a pre-specified trusted application that can be used to perform identity verification processing, such as a financial payment application, an instant messaging application, or a pre-developed application, etc. The trusted application can be an application that needs to be installed in the terminal device, or a code program pre-implanted in a hardware device of the terminal device, or a program that runs in the background of the operating system of the terminal device in the form of a plug-in, etc., and can be set specifically according to actual conditions. The data processing rules may be rules that can perform data protection processing on the interactive video stream collected for identity verification. The data processing rules may be set in a variety of different ways. For example, they may be set based on pre-set anti-tampering rules for the interactive video stream collected for identity verification, or they may be set based on the identity of the target user, or they may be set for the corresponding business category. The specific setting may be based on actual conditions. Moreover, the data processing rules may be pre-set in the trusted execution environment of the terminal device. In order to ensure the security of the data processing rules, the data processing rules may be ciphertext. In the trusted execution environment, the ciphertext of the data processing rules may be decrypted or signed. After determining that the data processing rules have not been tampered with, the data processing rules may be stored in the trusted execution environment.

[0077] In implementation, in order to ensure the security of the interactive video stream during transmission and prevent the interactive video stream from being obtained by any application in the rich execution environment, a trusted application for performing identity verification processing can be set up, and the interactive video stream can be temporarily protected by the trusted application. For example, other unauthorized applications can be prevented from accessing the interactive video stream to protect the data, or the interactive video stream can be processed in a predetermined manner to obtain the processed interactive video stream to protect the data. After the interactive video stream is collected, the terminal device can start the trusted application. The trusted application can be pre-set with a security interface, and correspondingly, the trusted execution environment of the terminal device can also be set with a corresponding security interface. Through the security interface between the trusted application and the trusted execution environment, a secure data transmission channel can be established between the trusted application and the trusted execution environment. The trusted application can extract the interactive video stream from the video acquisition component, and can transmit the interactive video stream to the trusted execution environment of the terminal device through the above-mentioned security interface and data transmission channel. The security of the interactive video stream during transmission can be guaranteed by setting the above-mentioned trusted application, security interface and data transmission channel.

[0078] In step S1084, in the trusted execution environment, data protection processing is performed on the interactive video stream according to the data processing rules to obtain a processed interactive video stream.

[0079] In implementation, in order to ensure that the interactive video stream is not leaked during the processing, the interactive video stream can be processed for data protection in a trusted execution environment. The specific data protection processing process may include multiple processes, such as signature processing, encryption processing, or hash calculation. In a trusted execution environment, the terminal device can analyze the interactive video stream, for example, the service category corresponding to the interactive video stream can be determined, and then the corresponding data processing rules can be obtained based on the determined service category and other related information. In a trusted execution environment, the interactive video stream can be processed for data protection using the obtained data processing rules. Since the above processing is performed in a trusted execution environment, it will not be known by other execution environments of the terminal device or any application in the terminal device, and then, the interactive video stream in the executable environment after data protection processing will not be obtained by any software program or hardware device outside the trusted execution environment, thereby ensuring the accuracy and security of the interactive video stream (will not be tampered with or leaked). In actual applications, the data protection processing method for the interactive video stream does not only include the above method, but also includes many other implementable methods, which will not be repeated here.

[0080] The above-mentioned data protection processing for the interactive video stream is only one feasible processing method. In actual applications, data protection processing for the interactive video stream can also be performed through various other processing methods. Different processing methods can be used to perform data protection processing on the interactive video stream according to different data processing rules. Moreover, different data processing rules may have different specific processes for data protection processing of the interactive video stream, which can be set according to actual conditions. The embodiments of this specification do not limit this.

[0081] In step S1086, the processed interactive video stream is obtained from the trusted execution environment based on the trusted application, and the processed interactive video stream is sent to the server. The processed interactive video stream is used to trigger the server to perform a credibility check on the processed interactive video stream. After the check passes, the identity of the target user is verified based on the processed interactive video stream, and the corresponding identity verification result is returned.

[0082] In implementation, by performing data protection processing on the interactive video stream in a trusted execution environment, after obtaining the processed interactive video stream, a trusted application can be triggered so that the trusted application obtains the processed interactive video stream from the trusted execution environment, and can provide the processed interactive video stream to the server. In this way, the processes of obtaining the interactive video stream, performing data protection processing on the interactive video stream, and providing the processed interactive video stream to the server are all completed in the trusted execution environment or trusted application, thereby not only achieving data protection processing of the interactive video stream, but also ensuring the security of the interactive video stream during processing in the terminal device.

[0083] After the server receives the processed interactive video stream, it can perform a credibility check on the processed interactive video stream. For example, it can calculate the verification value (such as a hash value, etc.) corresponding to the above interactive video stream, and compare the calculated verification value with the pre-recorded verification value. If the two verification values ​​are the same, it can be determined that the verification result of the interactive video stream is credible, that is, it can be determined that the interactive video stream has not been tampered with and the verification has passed. At this time, the identity of the target user can be verified based on the processed interactive video stream. If the two verification values ​​are different, it can be determined that the verification result of the interactive video stream is unreliable and the verification has not passed. The risk of injection attacks can be avoided to a certain extent by processing the above steps S1082 to S1086.

[0084] The embodiment of the present specification provides an identity verification method, which is applied to a terminal device, by receiving an identity verification instruction for a target user, and responding to the identity verification instruction, obtaining a multi-round video verification interaction strategy randomly generated for the target user, each round of the multi-round video verification interaction strategy includes but is not limited to an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a specified certificate, and an interaction rule based on identity verification of a near field communication. One or more of the following constructions, then, based on the multi-round video verification interaction strategy, the interactive video stream generated by executing each round of the video verification interaction strategy can be collected by a video acquisition component, and finally, the collected execution of each round of the video verification interaction strategy can be used to generate a plurality of interactive video streams. The interactive video stream generated by the frequency verification interaction strategy is sent to the server to verify the identity of the target user based on the collected interactive video stream. In this way, in the face of the attack tools supported by AIGC, a new interaction mode is adopted to counter the attacks of the attack tools supported by AIGC by adopting more abundant means. It mainly reflects the identity verification of active interaction and real-time video streams. The initiative, randomness, and increased information capacity brought by active interaction will greatly increase the cost of forgery, thereby avoiding or reducing the attack risk of identity verification by attack tools supported by AIGC, and using real-time video streams for identity verification. Unpredictable multi-action factors are added to the real-time video stream, thereby increasing the attack cost of identity verification.

[0085] In addition, the use of certificates has been increased in the verification process, not only in the verification of images and video streams of certificates, but also in the verification of data reading through near-field communication, which increases the difficulty of material preparation for attackers and increases the cost of attacks. In addition, the bypass verification mode is difficult to simulate when the attacker does not know the terminal devices commonly used by the attacker. At the same time, the attacker's terminal device is tested by means of scene device information, thereby avoiding or reducing the risk of attack on identity verification by attack tools supported by AIGC, and improving the security and reliability of identity verification.

[0086] like Fig.10 As shown, the embodiment of this specification provides an identity verification method, and the execution subject of the method can be a server, wherein the server can be an independent server or a server cluster. The method can specifically include the following steps: In step S1002, an identity verification request for a target user sent by a terminal device is received.

[0087] In implementation, when the target user needs to be authenticated, the target user triggers the terminal device to generate an identity authentication instruction for the target user when executing a specified service or testing an identity authentication policy, and the terminal device can receive the identity authentication instruction. The terminal device can respond to the identity authentication instruction, obtain and display the video authentication guidance data, and send an identity authentication request to the server when receiving the identity authentication request triggered by the target user based on the video authentication guidance data. The server can receive the identity authentication request for the target user sent by the terminal device.

[0088] In step S1004, in response to the above-mentioned identity verification request, a multi-round video verification interaction strategy is randomly generated for the target user, and the multi-round video verification interaction strategy is sent to the terminal device. The multi-round video verification interaction strategy is used to trigger the terminal device to collect the interactive video stream generated by executing each round of video verification interaction strategy based on the multi-round video verification interaction strategy through the video acquisition component. Each round of video verification interaction strategy includes but is not limited to one or more of interaction rules based on facial video streams, interaction rules based on body movement video streams, interaction rules based on identity authentication of designated documents, and interaction rules based on identity authentication of near field communication.

[0089] During implementation, after receiving an identity verification request for a target user sent by a terminal device, the server can respond to the identity verification request. At this time, a multi-round video verification interaction strategy can be randomly generated for the target user. The process of randomly generating a multi-round video verification interaction strategy for the target user can be implemented in a variety of ways. For example, the server can store interaction rules for different video streams. When the server receives the identity verification request, it can randomly select interaction rules for multiple video streams from the interaction rules of different video streams, and can generate multi-round video verification interaction strategies through random combinations and the like.

[0090] For example, the interaction rules based on facial video stream, the interaction rules based on body movement video stream, the interaction rules based on identity verification of designated certificates, and the interaction rules based on identity verification of near field communication can be selected from the interaction rules based on facial video stream, the interaction rules based on body movement video stream, the interaction rules based on identity verification of designated certificates, and the interaction rules based on near field communication identity verification. The interaction rules based on facial video stream and the interaction rules based on body movement video stream can be combined. Since the interaction rules based on facial video stream can include making the user's facial image located in a designated area, performing preset facial movements or head movements in the designated area, etc., one or more of the above interaction rules can also be randomly selected, such as making the user's facial image located in a designated area, or making the user's facial image located in a designated area, and performing preset facial movements in the designated area, etc., which can be set specifically according to actual conditions. Correspondingly, the interaction rules based on body movement video stream can include a variety of different body movements, and one or more of them can be randomly selected. Furthermore, the combination of the above two may include multiple methods, and multiple methods can be selected from the above combinations to generate a round of video verification interaction strategies respectively, and then obtain multiple rounds of video verification interaction strategies, that is, the server can randomly generate multiple rounds of video verification interaction strategies for the target user.

[0091] In step S1006, the interactive video stream generated by executing each round of video verification interaction strategy collected by the terminal device is received, and the identity of the target user is verified based on the collected interactive video stream to obtain a corresponding identity verification result.

[0092] During implementation, the terminal device can collect the interactive video stream generated by executing each round of video verification interaction strategy based on multiple rounds of video verification interaction strategy through the video acquisition component, and can send the collected interactive video stream generated by executing each round of video verification interaction strategy to the server. The server can receive the interactive video stream generated by executing each round of video verification interaction strategy collected by the terminal device. The server can analyze the collected interactive video stream. In the case of continuous and uninterrupted interactive video stream, preset algorithms (such as face recognition algorithm, action recognition algorithm, similarity algorithm, etc. under interactive video stream, specifically, frame difference algorithm (which can be an algorithm for obtaining the target contour by performing a difference operation on two adjacent frames in an image sequence in a video stream), edge detection algorithm, background difference detection algorithm, optical flow method (which can be an algorithm for determining the change of each pixel position by using the time domain change and correlation of pixel intensity data in an image sequence), etc.) can be used to verify the face, specified body movements and documents, etc., and obtain corresponding identity verification results. Among them, only when the verification results corresponding to the interactive video streams generated by each round of video verification interaction strategy are all verified, the final identity verification result is the identity verification of the target user passed, otherwise, the identity verification of the target user fails.

[0093] In step S1008, the identity verification result is sent to the terminal device.

[0094] The embodiment of the present specification provides an identity verification method, which is applied to a server, and receives an identity verification request for a target user sent by a terminal device. In response to the identity verification request, a multi-round video verification interaction strategy is randomly generated for the target user, and the multi-round video verification interaction strategy is sent to the terminal device. The multi-round video verification interaction strategy is used to trigger the terminal device to collect the interactive video stream generated by executing each round of the video verification interaction strategy based on the multi-round video verification interaction strategy through a video acquisition component. Each round of the video verification interaction strategy includes but is not limited to one or more of the interaction rules based on the facial video stream, the interaction rules based on the body movement video stream, the interaction rules based on the identity verification of a specified certificate, and the interaction rules based on the identity verification of a near field communication. Then, the terminal device can be received. The end device collects the interactive video stream generated by executing each round of video verification interaction strategy, and verifies the identity of the target user based on the collected interactive video stream to obtain the corresponding identity verification result. In this way, in the face of attack tools supported by AIGC, a new interaction mode is adopted to counter the attacks of attack tools supported by AIGC by adopting more abundant means, which mainly reflects the active interaction and identity verification of real-time video streams. The initiative, randomness, and increased information capacity brought by active interaction will greatly increase the cost of forgery, thereby avoiding or reducing the attack risk of identity verification by attack tools supported by AIGC, and using real-time video streams for identity verification. Unpredictable multi-action factors are added to the real-time video stream, thereby increasing the attack cost of identity verification.

[0095] In practical applications, the identity of the target user is verified based on the collected interactive video stream in the above step S1006, and the specific processing method for obtaining the corresponding identity verification result can be various. The following is an optional processing method, such as Fig.11 As shown, the processing may specifically include the following steps S10062 and S10064.

[0096] In step S10062, based on the collected interactive video streams generated by executing each round of video verification interaction strategy, the detection results corresponding to the interactive video streams generated by executing each round of video verification interaction strategy are determined through a video stream detection model, and the video stream detection model is used to detect and process the content of the interactive video stream.

[0097] The video stream detection model can be constructed by a variety of different machine learning networks, for example, a video stream detection model can be constructed by a convolutional neural network, or a video stream detection model can be constructed by a recurrent neural network, etc., which can be set according to actual conditions. The video stream detection model can be used to quickly implement various visual algorithms and applications, such as face recognition, object recognition, motion evaluation, 3D detection, and visual SLAM (Simultaneous Localization And Mapping), so as to detect and process the content of interactive video streams.

[0098] In implementation, sample data for training a video stream detection model can be obtained, and the sample data can be used to train the video stream detection model to obtain a trained video stream detection model. The collected interactive video streams generated by executing each round of video verification interaction strategy can be input into the video stream detection model respectively, and the content of the interactive video stream generated by executing each round of video verification interaction strategy can be detected and processed through different network layers and algorithms set in the video stream detection model, thereby realizing face recognition and detection, object recognition and detection, and other processing, and finally obtaining corresponding detection results. In practical applications, the obtained detection results can include information such as the confidence of face recognition and the confidence of object recognition.

[0099] In step S10064, based on the preset video stream processing strategy and the detection results corresponding to the interactive video stream generated by executing each round of video verification interaction strategy, the identity verification result of the target user is determined. The video stream processing strategy includes a video stream processing strategy based on a preset threshold and / or a data caching strategy.

[0100] The video stream processing strategy based on the preset threshold may be a strategy for comparing the value corresponding to the specified item in the detection result with the preset threshold. The data caching strategy may be a strategy for caching the specified data in the detection result.

[0101] In implementation, based on a video stream processing strategy with a preset threshold, the numerical value corresponding to a specified item in the detection result is compared with a preset threshold. If the numerical value corresponding to the specified item in the detection result is greater than the preset threshold, it can be determined that the detection of the specified item has passed. In this way, the detection result of each item in the detection result can be determined, and facial data, body movement data, images of specified documents, etc. can be cached through a data caching strategy. The identity verification result of the target user can be determined through the corresponding results of the above processing.

[0102] In practical applications, the specific processing methods of the above step S10062 can be varied. An optional processing method is provided below, such as Fig.12 As shown, the processing may specifically include the following steps S1006202 to S1006206.

[0103] In step S1006202, based on the collected interactive video stream, the environmental information of the video shooting environment in which the target user is currently located is determined.

[0104] The environmental information may include multiple information, such as the brightness and darkness in the video shooting environment, the lighting direction information, the lighting intensity information, the information of surrounding buildings, etc., which can be set according to the actual situation.

[0105] In step S1006204, if it is determined based on the environmental information that there is an attack risk in the identity verification of the target user, then the identity verification result of the target user is determined to be failed.

[0106] In implementation, for example, if the lighting direction and lighting intensity distribution in the environmental information are obviously inconsistent with the conventional lighting direction and / or lighting intensity distribution, it can be determined that there is an attack risk in the identity verification of the target user. At this time, it can be determined that the identity verification result for the target user is failed, and the specific setting can be based on actual conditions.

[0107] In step S1006206, if it is determined based on environmental information that there is no attack risk for the identity verification of the target user, then based on the collected interactive video streams generated by executing each round of video verification interaction strategies, the detection results corresponding to the interactive video streams generated by executing each round of video verification interaction strategies are determined through a video stream detection model.

[0108] In practical applications, the specific processing methods of the above step S10062 can be varied. An optional processing method is provided below, such as Fig.13 As shown, the processing may specifically include the following steps S1006208 and S1006210.

[0109] In step S1006208, the collected interactive video stream generated by executing each round of video verification interaction strategy is preprocessed to obtain a preprocessed interactive video stream, and the preprocessing includes one or more of decoding the interactive video stream, compressing the interactive video stream, converting the image frames in the interactive video stream, and merging multiple image frames in the interactive video stream.

[0110] In step S1006210, each pre-processed interactive video stream is input into the video stream detection model respectively to obtain the detection result corresponding to the interactive video stream generated by executing each round of video verification interaction strategy.

[0111] The embodiment of the present specification provides an identity verification method, which is applied to a server, and receives an identity verification request for a target user sent by a terminal device. In response to the identity verification request, a multi-round video verification interaction strategy is randomly generated for the target user, and the multi-round video verification interaction strategy is sent to the terminal device. The multi-round video verification interaction strategy is used to trigger the terminal device to collect the interactive video stream generated by executing each round of the video verification interaction strategy based on the multi-round video verification interaction strategy through a video acquisition component. Each round of the video verification interaction strategy includes but is not limited to one or more of the interaction rules based on the facial video stream, the interaction rules based on the body movement video stream, the interaction rules based on the identity verification of a specified certificate, and the interaction rules based on the identity verification of a near field communication. Then, the terminal device can be received. The end device collects the interactive video stream generated by executing each round of video verification interaction strategy, and verifies the identity of the target user based on the collected interactive video stream to obtain the corresponding identity verification result. In this way, in the face of attack tools supported by AIGC, a new interaction mode is adopted to counter the attacks of attack tools supported by AIGC by adopting more abundant means, which mainly reflects the active interaction and identity verification of real-time video streams. The initiative, randomness, and increased information capacity brought by active interaction will greatly increase the cost of forgery, thereby avoiding or reducing the attack risk of identity verification by attack tools supported by AIGC, and using real-time video streams for identity verification. Unpredictable multi-action factors are added to the real-time video stream, thereby increasing the attack cost of identity verification.

[0112] In addition, the use of certificates has been increased in the verification process, not only in the verification of images and video streams of certificates, but also in the verification of data reading through near-field communication, which increases the difficulty of material preparation for attackers and increases the cost of attacks. In addition, the bypass verification mode is difficult to simulate when the attacker does not know the terminal devices commonly used by the attacker. At the same time, the attacker's terminal device is tested by means of scene device information, thereby avoiding or reducing the risk of attack on identity verification by attack tools supported by AIGC, and improving the security and reliability of identity verification.

[0113] In order to better illustrate the above process, the following is an interaction diagram between the terminal device and the server to illustrate the identity verification process. Fig.14As shown, the business front end and the audit SDK / front end can be set in the terminal device, the business system / risk prevention and control system, Mobile IC / IFC Identity Cloud (mobile integrated circuit / IFC identity cloud), Mobilevideo / IFC Identity Video (mobile video / IFC identity video) and zmc (model platform, set in the video stream detection model). The user can trigger the identity verification mechanism, the terminal device can initiate an identity verification instruction to the business system / risk prevention and control system in the server, the business system / risk prevention and control system can initialize the Mobile IC / IFC Identity Cloud, after the initialization is completed, it can request the Mobile video / IFC Identity Video to inquire about the availability of the identity verification process using the terminal device, and the server can send the availability result to the terminal device. If the availability result indicates that the terminal device can be used for identity verification, at this time, the terminal device can pull up the identity SDK, at this time, the terminal device can request the Mobile video / IFC Identity Video in the server to perform the first data rendering process, and the server can return the video verification guide page to the terminal device. When the target user starts video verification, the terminal device can send a request to create a room to Mobile IC / IFC Identity Cloud. The server can respond to the request and create information such as the room number and room password through Mobile video / IFC Identity Video to complete the creation of the room. The server can send a message of successful room creation to the terminal device. At this time, the terminal device can enter the room based on the created room number and room password. The Mobile video / IFCIdentity Video in the server can randomly decide each round of video verification interaction strategy based on the risk level and preset rules, and can generate corresponding video verification interaction copy based on each round of video verification interaction strategy, and then send each round of video verification interaction strategy to the terminal device. After that, multiple rounds of video verification interaction strategies can be executed to obtain corresponding identity verification results. For details, please refer to the aforementioned related content and Fig.14 , I will not go into details here.

[0114] The embodiment of the present specification provides an identity verification method, which receives an identity verification instruction for a target user, responds to the identity verification instruction, obtains a multi-round video verification interaction strategy randomly generated for the target user, each round of the multi-round video verification interaction strategy includes but is not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a specified certificate, and an interaction rule based on identity verification of a near field communication. Then, based on the multi-round video verification interaction strategy, the interactive video stream generated by executing each round of the video verification interaction strategy can be collected by a video acquisition component, and finally, the collected interactive video streams generated by executing each round of the video verification interaction strategy can be collected. The interactive video stream generated by the mutual strategy is sent to the server to verify the identity of the target user based on the collected interactive video stream. In this way, in the face of attack tools supported by AIGC, a new interactive mode is adopted to counter the attacks of attack tools supported by AIGC by adopting more abundant means. It mainly reflects the identity verification of active interaction and real-time video streams. The initiative, randomness, and increased information capacity brought by active interaction will greatly increase the cost of forgery, thereby avoiding or reducing the attack risk of identity verification by attack tools supported by AIGC, and using real-time video streams for identity verification. Unpredictable multi-action factors are added to the real-time video stream, thereby increasing the attack cost of identity verification.

[0115] In addition, the use of certificates has been increased in the verification process, not only in the verification of images and video streams of certificates, but also in the verification of data reading through near-field communication, which increases the difficulty of material preparation for attackers and increases the cost of attacks. In addition, the bypass verification mode is difficult to simulate when the attacker does not know the terminal devices commonly used by the attacker. At the same time, the attacker's terminal device is tested by means of scene device information, thereby avoiding or reducing the risk of attack on identity verification by attack tools supported by AIGC, and improving the security and reliability of identity verification.

[0116] The above is the identity verification method provided in the embodiment of this specification. Based on the same idea, the embodiment of this specification also provides an identity verification device, such as Fig.15 shown.

[0117] The identity verification device includes: an instruction receiving module 1501, a multi-round video interaction determination module 1502, a video stream acquisition module 1503 and an identity verification module 1504, wherein: The instruction receiving module 1501 receives an identity verification instruction for a target user; The multi-round video interaction determination module 1502, in response to the identity verification instruction, obtains a multi-round video verification interaction strategy randomly generated for the target user, wherein each round of the multi-round video verification interaction strategy includes but is not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a designated certificate, and an interaction rule based on identity verification of a near field communication; The video stream acquisition module 1503, based on the multi-round video verification interaction strategy, acquires the interactive video stream generated by executing each round of the video verification interaction strategy through the video acquisition component; The identity verification module 1504 sends the collected interactive video stream generated by executing each round of video verification interaction strategy to the server. The collected interactive video stream is used to trigger the server to verify the identity of the target user based on the collected interactive video stream and return the corresponding identity verification result.

[0118] In the embodiment of this specification, the video stream acquisition module 1503 includes: An interactive copy acquisition unit extracts a video verification interactive copy from each round of the video verification interactive strategy, wherein the video verification interactive copy is used to prompt the target user to perform identity verification processing; An interactive page construction unit, based on the video verification interaction copy in each round of the video verification interaction strategy, constructs and displays the video verification interaction page corresponding to each round of the video verification interaction strategy through the corresponding video verification interaction strategy; The video stream acquisition unit acquires the interactive video stream generated by the interaction between the target user and the device based on the video verification interaction page corresponding to each round of video verification interaction strategy through a video acquisition component.

[0119] In the embodiment of this specification, the multi-round video interaction determination module 1502 includes: a guidance unit, in response to the identity verification instruction, acquiring and displaying video verification guidance data; a verification request unit, which, upon receiving an identity verification request triggered by the target user based on the video verification guidance data, sends the identity verification request to the server; An interaction strategy receiving unit receives a multi-round video verification interaction strategy randomly generated for the target user in response to the identity verification request and sent by the server.

[0120] In the embodiment of this specification, the multi-round video interaction determination module 1502 includes: a data acquisition unit, in response to the identity verification instruction, acquiring basic verification data, the basic verification data including relevant information of the device and / or business information corresponding to the identity verification instruction; A first interaction strategy determination unit, if the basic verification data indicates that the target user is in a high-risk state, obtains a multi-round video verification interaction strategy that is randomly generated for the target user and meets the high-risk state; The second interaction strategy determination unit obtains a multi-round video verification interaction strategy randomly generated for the target user if the basic verification data indicates that the target user is not in a high-risk state.

[0121] In an embodiment of the present specification, the multi-round video verification interaction strategy includes a multi-round video verification interaction strategy consisting of interaction rules based on facial video streams and interaction rules based on body movement video streams corresponding to each of a variety of different body movements, and a video verification interaction strategy consisting of interaction rules based on identity verification of a designated certificate, or the multi-round video verification interaction strategy includes a multi-round video verification interaction strategy consisting of interaction rules based on facial video streams and interaction rules based on body movement video streams corresponding to each of a variety of different body movements, and a video verification interaction strategy consisting of interaction rules based on identity verification of near field communication.

[0122] In the embodiments of the present specification, the plurality of different body movements include arm movements, movements of a combination of the arm and other body parts other than the arm, the interaction rules based on identity authentication of a designated document include rules for collecting an image of the designated document and a video stream during the collection process, and performing identity verification through the image of the designated document and the video stream during the collection process, and the interaction rules for identity authentication based on near-field communication include rules for reading information pre-written in the target document of the target user through the near-field communication component of the device, and performing identity verification through the read information.

[0123] In the embodiment of this specification, the device further includes: A device information acquisition module, which acquires device information of the device; An information comparison module compares the device information of the device with the device information of the historical terminal device used by the target user, or compares the device information of the device with the reference device information of the device to obtain a corresponding comparison result; The verification result determination module determines that the identity verification result for the target user is failed if the comparison result indicates that the device has an attack risk.

[0124] In the embodiment of this specification, the identity verification module 1504 includes: A video stream transmission unit, which transmits the collected interactive video stream generated by executing each round of video verification interaction strategy from the video acquisition component to the trusted execution environment of the device through a trusted application for performing identity verification processing on the device, wherein the trusted execution environment is provided with a data processing rule for performing data protection processing on the interactive video stream collected for identity verification; A data protection unit, in the trusted execution environment, performs data protection processing on the interactive video stream according to the data processing rule to obtain a processed interactive video stream; An identity verification unit obtains the processed interactive video stream from the trusted execution environment based on the trusted application, and sends the processed interactive video stream to the server, wherein the processed interactive video stream is used to trigger the server to perform a credibility check on the processed interactive video stream, and after the check is passed, performs an identity verification on the target user based on the processed interactive video stream, and returns a corresponding identity verification result.

[0125] The embodiment of the present specification provides an identity verification device, which receives an identity verification instruction for a target user, responds to the identity verification instruction, obtains a multi-round video verification interaction strategy randomly generated for the target user, each round of the multi-round video verification interaction strategy includes but is not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a specified certificate, and an interaction rule based on identity verification of a near field communication. Then, based on the multi-round video verification interaction strategy, the interactive video stream generated by executing each round of the video verification interaction strategy can be collected by a video acquisition component, and finally, the collected execution of each round of the video verification interaction strategy can be The interactive video stream generated by the mutual strategy is sent to the server to verify the identity of the target user based on the collected interactive video stream. In this way, in the face of attack tools supported by AIGC, a new interactive mode is adopted to counter the attacks of attack tools supported by AIGC by adopting more abundant means. It mainly reflects the identity verification of active interaction and real-time video streams. The initiative, randomness, and increased information capacity brought by active interaction will greatly increase the cost of forgery, thereby avoiding or reducing the attack risk of identity verification by attack tools supported by AIGC, and using real-time video streams for identity verification. Unpredictable multi-action factors are added to the real-time video stream, thereby increasing the attack cost of identity verification.

[0126] In addition, the use of certificates has been increased in the verification process, not only in the verification of images and video streams of certificates, but also in the verification of data reading through near-field communication, which increases the difficulty of material preparation for attackers and increases the cost of attacks. In addition, the bypass verification mode is difficult to simulate when the attacker does not know the terminal devices commonly used by the attacker. At the same time, the attacker's terminal device is tested by means of scene device information, thereby avoiding or reducing the risk of attack on identity verification by attack tools supported by AIGC, and improving the security and reliability of identity verification.

[0127] Based on the same idea, the embodiment of this specification also provides an identity verification device, such as Fig.16 shown.

[0128] The identity verification device comprises: an identity verification request module 1601, a multi-round video interaction generation module 1602, an identity verification module 1603 and a result sending module 1604, wherein: The identity verification request module 1601 receives an identity verification request for a target user sent by a terminal device; The multi-round video interaction generation module 1602 randomly generates a multi-round video verification interaction strategy for the target user in response to the identity verification request, and sends the multi-round video verification interaction strategy to the terminal device, wherein the multi-round video verification interaction strategy is used to trigger the terminal device to collect the interactive video stream generated by executing each round of the video verification interaction strategy based on the multi-round video verification interaction strategy through a video acquisition component, wherein each round of the video verification interaction strategy includes but is not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a specified certificate, and an interaction rule based on identity verification of a near field communication; The identity verification module 1603 receives the interactive video stream generated by executing each round of the video verification interaction strategy collected by the terminal device, and performs identity verification on the target user based on the collected interactive video stream to obtain a corresponding identity verification result; The result sending module 1604 sends the identity verification result to the terminal device.

[0129] In the embodiment of this specification, the identity verification module 1603 includes: A video stream detection unit, based on the collected interactive video stream generated by executing each round of the video verification interaction strategy, determines the detection result corresponding to the interactive video stream generated by executing each round of the video verification interaction strategy through a video stream detection model, wherein the video stream detection model is used to detect and process the content of the interactive video stream; The identity verification unit determines the identity verification result of the target user based on a preset video stream processing strategy and the detection result corresponding to the interactive video stream generated by executing each round of video verification interaction strategy. The video stream processing strategy includes a video stream processing strategy based on a preset threshold and / or a data caching strategy.

[0130] In an embodiment of the present specification, the video stream detection unit determines the environmental information of the video shooting environment in which the target user is currently located based on the collected interactive video stream; if it is determined based on the environmental information that there is an attack risk for the identity verification of the target user, then the identity verification result for the target user is determined to be failed; if it is determined based on the environmental information that there is no attack risk for the identity verification of the target user, then based on the collected interactive video stream generated by executing each round of video verification interaction strategy, the detection result corresponding to the interactive video stream generated by executing each round of video verification interaction strategy is determined through a video stream detection model.

[0131] In an embodiment of the present specification, the video stream detection unit preprocesses the collected interactive video stream generated by executing each round of video verification interaction strategy to obtain a preprocessed interactive video stream, and the preprocessing includes one or more of decoding the interactive video stream, compressing the interactive video stream, converting the image frames in the interactive video stream, and merging the multiple image frames in the interactive video stream; each preprocessed interactive video stream is respectively input into the video stream detection model to obtain the detection result corresponding to the interactive video stream generated by executing each round of video verification interaction strategy.

[0132] The embodiment of the present specification provides an identity verification device, which receives an identity verification request for a target user sent by a terminal device, responds to the identity verification request, randomly generates a multi-round video verification interaction strategy for the target user, and sends the multi-round video verification interaction strategy to the terminal device, wherein the multi-round video verification interaction strategy is used to trigger the terminal device to collect and execute the interactive video stream generated by each round of the video verification interaction strategy based on the multi-round video verification interaction strategy through a video acquisition component, wherein each round of the video verification interaction strategy includes but is not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a specified certificate, and an interaction rule based on identity verification of a near field communication. Then, the terminal device can receive the interaction rule. The interactive video stream generated by each round of video verification interaction strategy is collected, and the target user is verified based on the collected interactive video stream to obtain the corresponding identity verification result. In this way, in the face of attack tools supported by AIGC, a new interaction mode is adopted to counter the attacks of attack tools supported by AIGC by adopting more abundant means. It mainly reflects the identity verification of active interaction and real-time video stream. The initiative, randomness, and increased information capacity brought by active interaction will greatly increase the cost of forgery, thereby avoiding or reducing the attack risk of identity verification by attack tools supported by AIGC, and using real-time video stream for identity verification. Unpredictable multi-action factors are added to the real-time video stream, thereby increasing the attack cost of identity verification.

[0133] In addition, the use of certificates has been increased in the verification process, not only in the verification of images and video streams of certificates, but also in the verification of data reading through near-field communication, which increases the difficulty of material preparation for attackers and increases the cost of attacks. In addition, the bypass verification mode is difficult to simulate when the attacker does not know the terminal devices commonly used by the attacker. At the same time, the attacker's terminal device is tested by means of scene device information, thereby avoiding or reducing the risk of attack on identity verification by attack tools supported by AIGC, and improving the security and reliability of identity verification.

[0134] The above is an identity verification device provided in the embodiment of this specification. Based on the same idea, the embodiment of this specification also provides an identity verification device, such as Fig.17 shown.

[0135] The identity verification device may provide a terminal device or a server, etc. for the above-mentioned embodiment.

[0136] The identity verification device may have relatively large differences due to different configurations or performances, and may include one or more processors 1701 and memory 1702, and the memory 1702 may store one or more storage applications or data. Among them, the memory 1702 may be a short-term storage or a persistent storage. The application stored in the memory 1702 may include one or more modules (not shown in the figure), and each module may include a series of computer executable instructions in the identity verification device. Furthermore, the processor 1701 may be configured to communicate with the memory 1702 to execute a series of computer executable instructions in the memory 1702 on the identity verification device. The identity verification device may also include one or more power supplies 1703, one or more wired or wireless network interfaces 1704, one or more input and output interfaces 1705, and one or more keyboards 1706.

[0137] Specifically in this embodiment, the identity verification device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer executable instructions in the identity verification device, and the one or more programs are configured to be executed by one or more processors, including computer executable instructions for performing the following: Receive identity verification instructions for target users; In response to the identity verification instruction, obtaining a multi-round video verification interaction strategy randomly generated for the target user, each of the multi-round video verification interaction strategies including but not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a designated certificate, and an interaction rule based on identity verification of near field communication; Based on the multi-round video verification interaction strategy, the interactive video stream generated by executing each round of the video verification interaction strategy is collected by a video collection component; The collected interactive video stream generated by executing each round of video verification interaction strategy is sent to the server. The collected interactive video stream is used to trigger the server to verify the identity of the target user based on the collected interactive video stream and return the corresponding identity verification result.

[0138] In addition, specifically in this embodiment, the identity verification device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer executable instructions in the identity verification device, and the one or more programs are configured to be executed by one or more processors, including computer executable instructions for performing the following: Receiving an identity verification request for a target user sent by a terminal device; In response to the identity verification request, a multi-round video verification interaction strategy is randomly generated for the target user, and the multi-round video verification interaction strategy is sent to the terminal device, wherein the multi-round video verification interaction strategy is used to trigger the terminal device to collect the interactive video stream generated by executing each round of the video verification interaction strategy based on the multi-round video verification interaction strategy through a video acquisition component, wherein each round of the video verification interaction strategy includes but is not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a specified certificate, and an interaction rule based on identity verification of a near field communication; Receiving the interactive video stream generated by executing each round of video verification interaction strategy collected by the terminal device, and performing identity verification on the target user based on the collected interactive video stream to obtain a corresponding identity verification result; Send the identity verification result to the terminal device.

[0139] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the identity verification device embodiment, 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.

[0140] The embodiment of the present specification provides an identity verification device, which receives an identity verification instruction for a target user, responds to the identity verification instruction, obtains a multi-round video verification interaction strategy randomly generated for the target user, each round of the multi-round video verification interaction strategy includes but is not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a specified certificate, and an interaction rule based on identity verification of a near field communication. Then, based on the multi-round video verification interaction strategy, the interactive video stream generated by executing each round of the video verification interaction strategy can be collected by a video acquisition component, and finally, the collected interactive video streams generated by executing each round of the video verification interaction strategy can be collected. The interactive video stream generated by the mutual strategy is sent to the server to verify the identity of the target user based on the collected interactive video stream. In this way, in the face of attack tools supported by AIGC, a new interactive mode is adopted to counter the attacks of attack tools supported by AIGC by adopting more abundant means. It mainly reflects the identity verification of active interaction and real-time video streams. The initiative, randomness, and increased information capacity brought by active interaction will greatly increase the cost of forgery, thereby avoiding or reducing the attack risk of identity verification by attack tools supported by AIGC, and using real-time video streams for identity verification. Unpredictable multi-action factors are added to the real-time video stream, thereby increasing the attack cost of identity verification.

[0141] Furthermore, based on the above Figures 1 to 14 In one embodiment, the present specification further provides a storage medium for storing computer executable instruction information. In a specific embodiment, the storage medium may be a USB flash drive, an optical disk, a hard disk, etc. When the computer executable instruction information stored in the storage medium is executed by the processor, the following process can be implemented: Receive identity verification instructions for target users; In response to the identity verification instruction, obtaining a multi-round video verification interaction strategy randomly generated for the target user, each of the multi-round video verification interaction strategies including but not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a designated certificate, and an interaction rule based on identity verification of near field communication; Based on the multi-round video verification interaction strategy, the interactive video stream generated by executing each round of the video verification interaction strategy is collected by a video collection component; The collected interactive video stream generated by executing each round of video verification interaction strategy is sent to the server. The collected interactive video stream is used to trigger the server to verify the identity of the target user based on the collected interactive video stream and return the corresponding identity verification result.

[0142] In addition, in another specific embodiment, the storage medium may be a USB flash drive, an optical disk, a hard disk, etc., and the computer executable instruction information stored in the storage medium can implement the following process when executed by the processor: Receiving an identity verification request for a target user sent by a terminal device; In response to the identity verification request, a multi-round video verification interaction strategy is randomly generated for the target user, and the multi-round video verification interaction strategy is sent to the terminal device, wherein the multi-round video verification interaction strategy is used to trigger the terminal device to collect the interactive video stream generated by executing each round of the video verification interaction strategy based on the multi-round video verification interaction strategy through a video acquisition component, wherein each round of the video verification interaction strategy includes but is not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a specified certificate, and an interaction rule based on identity verification of a near field communication; Receiving the interactive video stream generated by executing each round of video verification interaction strategy collected by the terminal device, and performing identity verification on the target user based on the collected interactive video stream to obtain a corresponding identity verification result; Send the identity verification result to the terminal device.

[0143] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the above-mentioned storage medium embodiment, 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.

[0144] The embodiment of the present specification provides a storage medium, which receives an identity verification instruction for a target user, and in response to the identity verification instruction, obtains a multi-round video verification interaction strategy randomly generated for the target user, wherein each round of the multi-round video verification interaction strategy includes but is not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a specified certificate, and an interaction rule based on identity verification of a near field communication. Then, based on the multi-round video verification interaction strategy, the interactive video stream generated by executing each round of the video verification interaction strategy can be collected by a video acquisition component, and finally, the collected execution of each round of the video verification interaction strategy can be The interactive video stream generated by the strategy is sent to the server to verify the identity of the target user based on the collected interactive video stream. In this way, in the face of attack tools supported by AIGC, a new interactive mode is adopted to counter the attacks of attack tools supported by AIGC by adopting more abundant means. It mainly reflects the identity verification of active interaction and real-time video streams. The initiative, randomness, and increased information capacity brought by active interaction will greatly increase the cost of forgery, thereby avoiding or reducing the attack risk of identity verification by attack tools supported by AIGC, and using real-time video streams for identity verification. Unpredictable multi-action factors are added to the real-time video stream, thereby increasing the attack cost of identity verification.

[0145] Furthermore, based on the above Figures 1 to 14 In one or more embodiments of the present specification, a computer program product is provided, including a computer program. When the computer program in the computer program product is executed by a processor, the following process can be implemented: Receive identity verification instructions for target users; In response to the identity verification instruction, obtaining a multi-round video verification interaction strategy randomly generated for the target user, each of the multi-round video verification interaction strategies including but not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a designated certificate, and an interaction rule based on identity verification of near field communication; Based on the multi-round video verification interaction strategy, the interactive video stream generated by executing each round of the video verification interaction strategy is collected by a video collection component; The collected interactive video stream generated by executing each round of video verification interaction strategy is sent to the server. The collected interactive video stream is used to trigger the server to verify the identity of the target user based on the collected interactive video stream and return the corresponding identity verification result.

[0146] In addition, in another specific embodiment, the computer program product includes a computer program, and when the computer program in the computer program product is executed by a processor, it can implement the following process: Receiving an identity verification request for a target user sent by a terminal device; In response to the identity verification request, a multi-round video verification interaction strategy is randomly generated for the target user, and the multi-round video verification interaction strategy is sent to the terminal device, wherein the multi-round video verification interaction strategy is used to trigger the terminal device to collect the interactive video stream generated by executing each round of the video verification interaction strategy based on the multi-round video verification interaction strategy through a video acquisition component, wherein each round of the video verification interaction strategy includes but is not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a specified certificate, and an interaction rule based on identity verification of a near field communication; Receiving the interactive video stream generated by executing each round of video verification interaction strategy collected by the terminal device, and performing identity verification on the target user based on the collected interactive video stream to obtain a corresponding identity verification result; Send the identity verification result to the terminal device.

[0147] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the above-mentioned computer program product embodiment, 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.

[0148] The embodiment of the present specification provides a computer program product, which receives an identity verification instruction for a target user, and in response to the identity verification instruction, obtains a multi-round video verification interaction strategy randomly generated for the target user, wherein each round of the multi-round video verification interaction strategy includes but is not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a designated certificate, and an interaction rule based on identity verification of a near field communication. Then, based on the multi-round video verification interaction strategy, the interactive video stream generated by executing each round of the video verification interaction strategy can be collected by a video acquisition component, and finally, the collected interactive video stream generated by executing each round of the video verification interaction strategy can be collected. The interactive video stream generated by the interactive strategy is sent to the server to verify the identity of the target user based on the collected interactive video stream. In this way, in the face of attack tools supported by AIGC, a new interactive mode is adopted to counter the attacks of attack tools supported by AIGC by adopting more abundant means. It mainly reflects the identity verification of active interaction and real-time video streams. The initiative, randomness, and increased information capacity brought by active interaction will greatly increase the cost of forgery, thereby avoiding or reducing the attack risk of identity verification by attack tools supported by AIGC, and using real-time video streams for identity verification. Unpredictable multi-action factors are added to the real-time video stream, thereby increasing the attack cost of identity verification.

[0149] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0150] 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 a hardware entity module. 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 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.

[0151] 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.

[0152] 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.

[0153] For the convenience of description, the above devices are described in terms of functions and are divided into various units. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0154] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, one or more embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, one or more embodiments of this specification 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.

[0155] The embodiments of this specification are described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes 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 fraud case serial and parallel device to produce a machine, so that the instructions executed by the processor of the computer or other programmable fraud case serial and parallel device generate instructions for implementing the processes in the process. 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.

[0156] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable fraud case serial and parallel device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including 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.

[0157] These computer program instructions may also be loaded onto a computer or other programmable device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide 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.

[0158] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0159] 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.

[0160] 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 tape 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.

[0161] 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.

[0162] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, one or more embodiments of this specification may be in the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Furthermore, one or more embodiments of this specification may be in 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.

[0163] One or more embodiments of the present specification 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. One or more embodiments of the present specification 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.

[0164] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, 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.

[0165] The above description is only an embodiment of this specification and is not intended to limit this document. For those skilled in the art, this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this specification should be included in the scope of the claims of this specification.

Claims

1. An identity verification method, applied to a terminal device, comprising: Receive identity verification instructions for target users; In response to the identity verification instruction, obtaining a multi-round video verification interaction strategy randomly generated for the target user, each of the multi-round video verification interaction strategies including but not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a designated certificate, and an interaction rule based on identity verification of near field communication; Based on the multi-round video verification interaction strategy, the interactive video stream generated by executing each round of the video verification interaction strategy is collected by a video collection component; The collected interactive video stream generated by executing each round of video verification interaction strategy is sent to the server. The collected interactive video stream is used to trigger the server to verify the identity of the target user based on the collected interactive video stream and return the corresponding identity verification result.

2. The method according to claim 1, wherein the step of collecting the interactive video stream generated by executing each round of the video verification interaction strategy through a video acquisition component based on the multiple rounds of video verification interaction strategy comprises: Extracting a video verification interaction copy from each round of the video verification interaction strategy, wherein the video verification interaction copy is used to prompt the target user to perform identity verification processing; Based on the video verification interaction copy in each round of the video verification interaction strategy, construct and display the video verification interaction page corresponding to each round of the video verification interaction strategy through the corresponding video verification interaction strategy; The interactive video stream generated by the interaction between the target user and the terminal device based on the video verification interaction page corresponding to each round of video verification interaction strategy is collected through the video collection component.

3. The method according to claim 2, wherein in response to the identity verification instruction, obtaining a multi-round video verification interaction strategy randomly generated for the target user comprises: In response to the identity verification instruction, acquiring and displaying video verification guidance data; Upon receiving an identity verification request triggered by the target user based on the video verification guidance data, sending the identity verification request to the server; Receive a multi-round video verification interaction strategy randomly generated for the target user in response to the identity verification request and sent by the server.

4. The method according to claim 2, wherein in response to the identity verification instruction, obtaining a multi-round video verification interaction strategy randomly generated for the target user comprises: In response to the identity verification instruction, basic verification data is acquired, where the basic verification data includes relevant information of the terminal device and / or business information corresponding to the identity verification instruction; If the basic verification data indicates that the target user is in a high-risk state, obtaining a multi-round video verification interaction strategy that is randomly generated for the target user and meets the high-risk state; If the basic verification data indicates that the target user is not in a high-risk state, a multi-round video verification interaction strategy randomly generated for the target user is obtained.

5. According to the method described in any one of claims 1 to 4, the multi-round video verification interaction strategy includes a multi-round video verification interaction strategy consisting of interaction rules based on facial video streams and interaction rules based on body movement video streams corresponding to each of a variety of different body movements, and a video verification interaction strategy consisting of interaction rules based on identity verification of a designated certificate, or the multi-round video verification interaction strategy includes a multi-round video verification interaction strategy consisting of interaction rules based on facial video streams and interaction rules based on body movement video streams corresponding to each of a variety of different body movements, and a video verification interaction strategy consisting of interaction rules based on identity verification of near field communication.

6. According to the method of claim 5, the multiple different body movements include arm movements, movements of the arm combined with other body parts outside the arm, the interaction rules based on identity authentication of the designated document include collecting the image of the designated document and the video stream during the collection process, and performing identity verification through the image of the designated document and the video stream during the collection process; the interaction rules based on identity authentication through near-field communication include reading information pre-written in the target document of the target user through the near-field communication component of the terminal device, and performing identity verification through the read information.

7. The method according to claim 6, further comprising: Acquire device information of the terminal device; Comparing the device information of the terminal device with the device information of the historical terminal device used by the target user, or comparing the device information of the terminal device with the reference device information of the terminal device, to obtain a corresponding comparison result; If the comparison result indicates that the terminal device has an attack risk, it is determined that the identity verification result for the target user is failed.

8. The method according to claim 6, wherein the step of sending the collected interactive video stream generated by executing each round of the video verification interactive strategy to the server comprises: The interactive video stream generated by executing each round of video verification interaction strategy is transmitted from the video acquisition component to the trusted execution environment of the terminal device through the trusted application for executing identity verification processing on the terminal device, wherein the trusted execution environment is provided with data processing rules for performing data protection processing on the interactive video stream collected for identity verification; In the trusted execution environment, performing data protection processing on the interactive video stream according to the data processing rule to obtain a processed interactive video stream; Based on the trusted application, the processed interactive video stream is obtained from the trusted execution environment, and the processed interactive video stream is sent to the server. The processed interactive video stream is used to trigger the server to perform a credibility check on the processed interactive video stream, and after the check passes, the identity of the target user is verified based on the processed interactive video stream, and the corresponding identity verification result is returned.

9. An identity verification method, applied to a server, comprising: Receiving an identity verification request for a target user sent by a terminal device; In response to the identity verification request, a multi-round video verification interaction strategy is randomly generated for the target user, and the multi-round video verification interaction strategy is sent to the terminal device, wherein the multi-round video verification interaction strategy is used to trigger the terminal device to collect the interactive video stream generated by executing each round of the video verification interaction strategy based on the multi-round video verification interaction strategy through a video acquisition component, wherein each round of the video verification interaction strategy includes but is not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a specified certificate, and an interaction rule based on identity verification of a near field communication; Receiving the interactive video stream generated by executing each round of video verification interaction strategy collected by the terminal device, and performing identity verification on the target user based on the collected interactive video stream to obtain a corresponding identity verification result; Send the identity verification result to the terminal device.

10. The method according to claim 9, wherein the identity verification of the target user based on the collected interactive video stream to obtain a corresponding identity verification result comprises: Based on the collected interactive video streams generated by executing each round of the video verification interaction strategy, a detection result corresponding to the interactive video stream generated by executing each round of the video verification interaction strategy is determined by a video stream detection model, wherein the video stream detection model is used to detect and process the content of the interactive video stream; Based on a preset video stream processing strategy and the detection results corresponding to the interactive video stream generated by executing each round of video verification interaction strategy, the identity verification result of the target user is determined. The video stream processing strategy includes a video stream processing strategy based on a preset threshold and / or a data caching strategy.

11. The method according to claim 10, wherein the detection result corresponding to the interactive video stream generated by executing each round of the video verification interaction strategy based on the collected interactive video stream generated by executing each round of the video verification interaction strategy is determined by a video stream detection model, comprising: Based on the collected interactive video stream, determining environmental information of the video shooting environment in which the target user is currently located; If it is determined based on the environmental information that there is an attack risk in the identity verification of the target user, determining that the identity verification result of the target user is failed; If it is determined based on the environmental information that there is no attack risk for the identity verification of the target user, then based on the collected interactive video streams generated by executing each round of video verification interaction strategies, the detection results corresponding to the interactive video streams generated by executing each round of video verification interaction strategies are determined through a video stream detection model.

12. The method according to claim 10 or 11, wherein the detection result corresponding to the interactive video stream generated by executing each round of the video verification interaction strategy based on the collected interactive video stream generated by executing each round of the video verification interaction strategy is determined by a video stream detection model, comprising: Preprocessing the collected interactive video stream generated by executing each round of video verification interaction strategy to obtain a preprocessed interactive video stream, wherein the preprocessing includes one or more of decoding the interactive video stream, compressing the interactive video stream, converting the image frames in the interactive video stream, and merging multiple image frames in the interactive video stream; Each preprocessed interactive video stream is input into the video stream detection model respectively to obtain the detection result corresponding to the interactive video stream generated by executing each round of video verification interaction strategy.

13. An identity verification device, comprising: An instruction receiving module receives an identity verification instruction for a target user; A multi-round video interaction determination module, in response to the identity verification instruction, obtains a multi-round video verification interaction strategy randomly generated for the target user, wherein each round of the multi-round video verification interaction strategy includes but is not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a designated certificate, and an interaction rule based on identity verification of near field communication; A video stream acquisition module, based on the multi-round video verification interaction strategy, acquires the interactive video stream generated by executing each round of the video verification interaction strategy through a video acquisition component; The identity verification module sends the collected interactive video stream generated by executing each round of video verification interaction strategy to the server. The collected interactive video stream is used to trigger the server to verify the identity of the target user based on the collected interactive video stream and return the corresponding identity verification result.

14. An identity verification device, comprising: An identity verification request module receives an identity verification request for a target user sent by a terminal device; A multi-round video interaction generation module randomly generates a multi-round video verification interaction strategy for the target user in response to the identity verification request, and sends the multi-round video verification interaction strategy to the terminal device, wherein the multi-round video verification interaction strategy is used to trigger the terminal device to collect the interactive video stream generated by executing each round of the video verification interaction strategy based on the multi-round video verification interaction strategy through a video acquisition component, wherein each round of the video verification interaction strategy includes but is not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a specified certificate, and an interaction rule based on identity verification of near field communication; An identity verification module receives the interactive video stream generated by executing each round of video verification interaction strategy collected by the terminal device, and performs identity verification on the target user based on the collected interactive video stream to obtain a corresponding identity verification result; A result sending module sends the identity verification result to the terminal device.

15. An identity verification device, comprising: processor; as well as a memory arranged to store computer executable instructions which, when executed, cause the processor to: Receive identity verification instructions for target users; In response to the identity verification instruction, obtaining a multi-round video verification interaction strategy randomly generated for the target user, each of the multi-round video verification interaction strategies including but not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a designated certificate, and an interaction rule based on identity verification of near field communication; Based on the multi-round video verification interaction strategy, the interactive video stream generated by executing each round of the video verification interaction strategy is collected by a video collection component; The collected interactive video stream generated by executing each round of video verification interaction strategy is sent to the server. The collected interactive video stream is used to trigger the server to verify the identity of the target user based on the collected interactive video stream and return the corresponding identity verification result.

16. An identity verification device, comprising: processor; as well as a memory arranged to store computer executable instructions which, when executed, cause the processor to: Receiving an identity verification request for a target user sent by a terminal device; In response to the identity verification request, a multi-round video verification interaction strategy is randomly generated for the target user, and the multi-round video verification interaction strategy is sent to the terminal device, wherein the multi-round video verification interaction strategy is used to trigger the terminal device to collect the interactive video stream generated by executing each round of the video verification interaction strategy based on the multi-round video verification interaction strategy through a video acquisition component, wherein each round of the video verification interaction strategy includes but is not limited to one or more of an interaction rule based on a facial video stream, an interaction rule based on a body movement video stream, an interaction rule based on identity verification of a specified certificate, and an interaction rule based on identity verification of a near field communication; Receiving the interactive video stream generated by executing each round of video verification interaction strategy collected by the terminal device, and performing identity verification on the target user based on the collected interactive video stream to obtain a corresponding identity verification result; Send the identity verification result to the terminal device.

Images