Method and device for video nuclear body detection, storage medium and electronic equipment

Abstract

The embodiment of the invention discloses a method and device for video verification detection, a storage medium and electronic equipment, user equipment firstly obtains prompt item template information provided by service equipment, then starts to collect video data, and if first prompt item identification information issued by the service equipment and corresponding to a target verification action item is obtained, the target verification action item is sent to the user equipment; if yes, first target prompt information which is obtained by matching with the prompt item template information and corresponds to the target body checking action item is presented, meanwhile, face detection is conducted on the user based on the video data and a preset time interval, and if a preset condition is met, the target body checking action item is obtained. If yes, the second target prompt information obtained by matching with the prompt item template information is presented based on the second prompt item identification information corresponding to the target detection feedback item, so that the user is guided to complete video nuclear body detection, the risk of being attacked is reduced by adding unpredictable nuclear body actions into the real-time video stream, and the user experience is improved. And the safety of the nuclear body process is improved.

Description

Technical Field

[0001] The present invention relates to computer technology, and in particular to a method, device, storage medium and electronic equipment for video identity detection. Background Art

[0002] With the development of the times, real-person authentication is required in more and more business scenarios, such as financial services, e-government, social media, etc., and existing real-person authentication solutions usually use face recognition and other authentication methods to achieve it. However, with the rapid development of AIGC (Artificial Intelligence Generated Content) technology, there are more and more cases where traditional authentication methods such as face recognition are attacked by attackers using AIGC capabilities, and the situation is becoming more and more serious. Summary of the invention

[0003] The purpose of the embodiments of this specification is to provide a method, device, storage medium and electronic device for video authentication detection.

[0004] The embodiments of this specification provide a method for video authentication detection in a user device, which reduces the risk of the authentication process being attacked and improves the security of the authentication process by adding unpredictable authentication actions to the real-time video stream. The method includes:

[0005] Obtaining prompt item template information provided by a service device, wherein the prompt item template information includes prompt item identification information corresponding to a plurality of prompt items and prompt information corresponding to each prompt item identification information, wherein the plurality of prompt items include a plurality of verification action items and a plurality of detection feedback items;

[0006] Start collecting video data, and if first prompt item identification information corresponding to the target authentication action item issued by the service device is obtained, match the first prompt item identification information with the prompt item template information, determine and present first target prompt information corresponding to the target authentication action item, so as to guide the user to execute the target authentication action item, so that the service device performs video authentication detection on the target authentication action item based on the video data uploaded by the user device;

[0007] Based on the video data and a preset time interval, face detection is performed on the user to obtain a target detection feedback item corresponding to the current face of the user; if a preset condition is met, second prompt item identification information corresponding to the target detection feedback item is matched with the prompt item template information, and second target prompt information corresponding to the target detection feedback item is determined and presented to guide the user to adjust his facial posture, wherein the face detection is used to detect whether the current face of the user in the video data meets preset requirements.

[0008] Furthermore, the prompt information includes at least one of voice prompt information, text prompt information, and animation prompt information.

[0009] Further, the starting to collect video data includes:

[0010] Sending module information of one or more input modules corresponding to the user device and device fingerprint information corresponding to the user device to the service device, so that the service device determines risk indication information corresponding to the user device based on the module information and the device fingerprint information and returns the risk indication information to the user device;

[0011] If the risk indication information meets the preset conditions, start collecting video data.

[0012] Furthermore, the module information of at least one input module includes activation indication information for indicating whether the at least one input module is activated.

[0013] Furthermore, the preset condition includes at least one of the following:

[0014] The timing duration corresponding to the second target prompt information currently presented reaches the preset time interval;

[0015] The target detection feedback item is inconsistent with the historical target detection feedback item corresponding to the second target prompt information currently presented;

[0016] The target detection feedback item is consistent with the historical target detection feedback item corresponding to the second target prompt information currently presented, and the timing duration corresponding to the second target prompt information currently presented reaches the preset time interval.

[0017] Furthermore, the method further comprises:

[0018] The preset time interval provided by the service device is obtained.

[0019] Furthermore, the method further comprises:

[0020] The time interval update indication information sent by the service device is obtained, and an update operation is performed on the preset time interval according to the time interval update indication information.

[0021] The embodiment of this specification also provides a method for video authentication detection in a service device, the method comprising:

[0022] In response to satisfying a video authentication detection trigger condition, sending prompt item template information to the user equipment, the prompt item template information including prompt item identification information corresponding to a plurality of prompt items and prompt information corresponding to each prompt item identification information, the plurality of prompt items including a plurality of authentication action items and a plurality of detection feedback items;

[0023] Determine a target authentication action item that the user currently needs to execute, and send target prompt item identification information corresponding to the target authentication action item to the user device;

[0024] Video authentication detection is performed on the target authentication action item based on the video data uploaded by the user device.

[0025] Furthermore, the method further comprises:

[0026] Receiving module information of one or more input modules and device fingerprint information corresponding to the user equipment sent by the user equipment;

[0027] The risk indication information corresponding to the user equipment is determined based on the module information and the device fingerprint information, and the risk indication information is returned to the user equipment.

[0028] Further, the determining the risk indication information corresponding to the user device based on the module information and the device fingerprint information includes:

[0029] Determine historical usage information corresponding to the user device according to the device fingerprint information;

[0030] Determine risk indication information corresponding to the user equipment according to the module information and the historical usage information.

[0031] Furthermore, the step of determining the target authentication action item that the user currently needs to perform includes:

[0032] According to the detection status corresponding to at least one authentication action item executed by the user in the current video authentication detection process, a target authentication action item currently required to be executed by the user is determined from the multiple authentication action items.

[0033] Furthermore, the step of determining a target authentication action item that the user currently needs to perform from the multiple authentication action items according to the detection status corresponding to at least one authentication action item that the user has performed during the current video authentication detection process includes:

[0034] Based on the detection status corresponding to at least one authentication action item executed by the user during the video authentication detection process, and the risk level information corresponding to the multiple authentication action items, the target authentication action item currently required to be executed by the user is determined from the multiple authentication action items.

[0035] Furthermore, the method further comprises:

[0036] Sending a preset time interval to the user equipment.

[0037] Furthermore, the method further comprises:

[0038] If the time interval update condition is met, generating time interval update indication information, and sending the time interval update indication information to the user equipment;

[0039] The time interval update condition includes at least one of the following:

[0040] The difficulty coefficient of the target action item that the user needs to perform currently exceeds the preset threshold;

[0041] The user characteristics of the user match the group characteristics corresponding to the special group.

[0042] The embodiment of this specification also provides a device for video authentication detection in a user equipment, including:

[0043] An acquisition module, used to obtain prompt item template information provided by a service device, wherein the prompt item template information includes prompt item identification information corresponding to a plurality of prompt items and prompt information corresponding to each prompt item identification information, wherein the plurality of prompt items include a plurality of verification action items and a plurality of detection feedback items;

[0044] A first detection module is used to start collecting video data, and if first prompt item identification information corresponding to the target authentication action item issued by the service device is obtained, the first prompt item identification information is matched with the prompt item template information, and the first target prompt information corresponding to the target authentication action item is determined and presented to guide the user to execute the target authentication action item, so that the service device performs video authentication detection on the target authentication action item based on the video data uploaded by the user device;

[0045] The second detection module is used to perform face detection on the user based on the video data and a preset time interval, obtain a target detection feedback item corresponding to the current face of the user, and if a preset condition is met, match the second prompt item identification information corresponding to the target detection feedback item with the prompt item template information, determine and present the second target prompt information corresponding to the target detection feedback item, so as to guide the user to adjust the facial posture, wherein the face detection is used to detect whether the current face of the user in the video data meets the preset requirements.

[0046] The embodiment of this specification also provides a device for video authentication detection in a service device, including:

[0047] a template sending module, configured to send prompt item template information to the user equipment in response to satisfying a video authentication detection trigger condition, wherein the prompt item template information includes prompt item identification information corresponding to a plurality of prompt items and prompt information corresponding to each prompt item identification information, wherein the plurality of prompt items include a plurality of authentication action items and a plurality of detection feedback items;

[0048] An action sending module, used to determine a target authentication action item that the user currently needs to execute, determine target prompt item identification information corresponding to the target authentication action item based on the prompt item template information, and send the target prompt item identification information to the user device;

[0049] The authentication detection module is used to perform video authentication detection on the target authentication action item based on the video data uploaded by the user equipment.

[0050] The embodiments of the present specification also provide a storage medium, wherein the storage medium stores a computer program, and the computer program is suitable for being loaded by a processor and executing the steps of the above method.

[0051] An embodiment of the present specification also provides an electronic device, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the steps of the above method.

[0052] The embodiments of the present specification also provide a computer program product having at least one instruction stored thereon, wherein the at least one instruction implements the steps of the above method when executed by a processor.

[0053] In an embodiment of the present specification, a method for user video authentication detection is proposed. By using a real-time video stream for video authentication detection and adding unpredictable authentication actions to the real-time video stream, the service device can dynamically determine and issue a first prompt item identification information corresponding to a target authentication action item in real time. The user device can determine and present the first target prompt information corresponding to the target authentication action item by matching the first prompt item identification information with the prompt item template information issued by the service device for this video authentication detection, so as to guide the user to execute the target authentication action item. Since the target authentication action item determined by the service device is unpredictable for the user device, the attack cost is greatly increased and the success rate is extremely low, thereby reducing the risk of the authentication process being attacked and improving the security of the authentication process. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A flowchart of a method for video authentication detection in a user device provided in an embodiment of this specification;

[0055] Figure 2A flowchart of a method for video authentication detection in a service device provided in an embodiment of this specification;

[0056] Figure 3 A schematic diagram of a process for video authentication detection provided as an example in an embodiment of this specification;

[0057] Figure 4 A schematic diagram of the structure of a device for video authentication detection in a user device provided in an embodiment of this specification;

[0058] Figure 5 A schematic diagram of the structure of a device for video authentication detection in a service device provided in an embodiment of this specification;

[0059] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solutions and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0061] See also Figure 1 , is a flowchart of a method for video authentication detection in a user device provided in an embodiment of this specification. In an embodiment of this specification, the method is applied to a device for video authentication detection in a user device (hereinafter referred to as "first device") or a user device / electronic device equipped with the first device. Figure 1 The process shown is described in detail, and the method for video authentication detection in the user equipment may specifically include the following steps:

[0062] S102, obtaining prompt item template information provided by a service device, wherein the prompt item template information includes prompt item identification information corresponding to a plurality of prompt items and prompt information corresponding to each prompt item identification information, wherein the plurality of prompt items include a plurality of verification action items and a plurality of detection feedback items.

[0063] The prompt item template information is used to characterize the prompt information corresponding to each prompt item in the plurality of prompt items, and the expression form of the prompt item template information includes but is not limited to a list. In some embodiments, the prompt item template information is used to indicate the mapping relationship between the verification action item, the prompt item identification information corresponding to the verification action item, and the prompt information corresponding to the verification action item, as well as the mapping relationship between the detection feedback item, the prompt item identification information corresponding to the detection feedback item, and the prompt information corresponding to the detection feedback item. This specification does not limit the specific format and expression form of the prompt item template information. In some embodiments, the service device and the user device pre-agree on the identification information and prompt information corresponding to each prompt item. Before entering the main process for each video authentication detection, the service device first determines multiple prompt items for this video authentication detection based on actual needs (it should be noted that the multiple prompt items may all be used in the detection process, or only part of them may be used. For example, this video authentication operation requires verification of 3 actions, and the prompt item template information may include information related to 4 authentication action items, thereby further ensuring the unpredictability of the authentication action and increasing the difficulty of attack for attackers). Then, based on the agreed content, the prompt item template information for this video authentication detection is determined, and the prompt item template information is sent to the user device. That is, for each video authentication detection, the prompt item template information sent by the service device to the user device may be the same or different.

[0064] In some embodiments, a prompt item identification information is used to identify the corresponding prompt item, and the prompt item identification information can be expressed as, for example, name information that can identify the prompt item, a serial number, a code obtained based on the prompt item related information, etc. In some embodiments, the authentication action item is used to represent the authentication action that the user needs to perform during the video authentication detection process, such as raising the head, raising the hand, touching the head, etc. During the video authentication detection process, the service device determines in real time the authentication action item that the user currently needs to perform by running a cloud algorithm. In some embodiments, the detection feedback item is used to represent the detection feedback content determined in real time by the user device through face detection of the user, such as too far from the screen, too close to the screen, too dark optical fiber, meeting preset requirements, etc. During the video authentication detection process, the user device runs an end-side algorithm to perform face detection on the current face of the user in the real-time video stream.

[0065] In some embodiments, the prompt information includes at least one of voice prompt information, text prompt information, and animation prompt information. In some embodiments, the service device can determine what types of prompt information each prompt item in this video authentication detection corresponds to based on the user characteristics of the user device. For example, if the user is a hearing-impaired user, the prompt information corresponding to each prompt item includes text prompt information and animation prompt information. This can provide a multi-dimensional interaction method based on the actual needs of users, facilitate different groups of users to perform video authentication detection, improve user experience, and especially greatly improve the detection efficiency of special groups.

[0066] In some embodiments, after receiving the prompt item template information, the user device feeds back a response message indicating successful reception to the service device. In some embodiments, the service device sends the prompt item template information to the user device and also sends the preset interval time for this video authentication detection to the user device.

[0067] S104, start collecting video data, and if the first prompt item identification information corresponding to the target verification action item issued by the service device is obtained, match the first prompt item identification information with the prompt item template information, determine and present the first target prompt information corresponding to the target verification action item, so as to guide the user to execute the target verification action item, so that the service device performs video verification detection on the target verification action item based on the video data uploaded by the user device.

[0068] In some embodiments, the user device starts to collect video data in real time after activating the camera. In some embodiments, when entering the video identity detection page and successfully waking up the camera, the video identity detection will enter the main link, and the main link will be processed in parallel from two directions: one direction is the end-side link, that is, the link executed by the user device. The end-side link is used to detect whether the current face is conducive to cloud algorithm detection (that is, whether it meets the preset requirements for cloud algorithm detection, which will be described in detail below). Through various end-side detections and real-time feedback, the user is guided to better complete the video identity. The end-side link has a lower priority. The other direction is the cloud link, which is used for stage control and sends prompt item identification information corresponding to different identity action items for different stages. The cloud link has a higher priority.

[0069] In some embodiments, after the user device obtains the latest content sent by the service device, it first determines whether the content received this time is the same as the content received last time. If they are the same (that is, there is no update), feedback information is sent to the server to request the server to send new content. If they are different (that is, there is an update), it first determines whether the end instruction is issued. If so, the video authentication detection is terminated immediately. Otherwise, it is determined that the first prompt item identification information is issued, and the matching operation is performed based on the first prompt item identification information to guide the user to execute the authentication action item corresponding to the first prompt item identification information in the page. In some embodiments, after the user device obtains the latest content sent by the service device, it first determines whether it is an end instruction. If not, it determines whether it is the same as the content received last time. It should be noted that no matter at which stage of the video authentication detection, as long as the end instruction issued by the service device is received, the user device will immediately end the video authentication detection.

[0070] In some embodiments, the user device uploads the collected video data in real time, so that the service device performs video authentication detection on the target authentication action item based on the video data.

[0071] S106, performing face detection on the user based on the video data and a preset time interval, obtaining a target detection feedback item corresponding to the current face of the user, and if a preset condition is met, matching the second prompt item identification information corresponding to the target detection feedback item with the prompt item template information, determining and presenting the second target prompt information corresponding to the target detection feedback item, so as to guide the user to adjust the facial posture, wherein the face detection is used to detect whether the current face of the user in the video data meets the preset requirements.

[0072] The user device may obtain the preset time interval in a variety of ways. For example, the preset time interval may be sent by the service device to the user device. For another example, the preset time interval is pre-agreed upon by the service device and the user device. For another example, if the service device sends the prompt item template information and at the same time sends the preset time interval for this video authentication detection, the user device uses the preset time interval sent by the service device. If the service device does not send the preset time interval this time, the user device uses the pre-agreed preset time interval.

[0073] The user device performs face detection on the user in the end-side link based on the real-time collected video data and the preset time interval to detect whether the current face is conducive to cloud algorithm detection (that is, whether it meets the preset requirements), and determines the target detection feedback item based on the real-time detection result. In some embodiments, the preset requirements include but are not limited to any requirements that are conducive to cloud algorithm detection, such as the distance between the face and the screen is within a normal range, the current light is within a normal range, etc. In some embodiments, the target detection feedback item is used to characterize the feedback content determined by the user device based on the current real-time detection result, for example, the distance is too far, the distance is too close, the light is too dark, etc.

[0074] As an example, after entering the video authentication detection page and successfully waking up the camera, the page presents the first target prompt information corresponding to the authentication action item based on the content sent by the service device. At the same time, the user device starts to obtain video data frame by frame and perform end-side algorithm detection. The target detection feedback item determined by the end-side algorithm detection for the current frame indicates "the distance is too far", then the prompt item identification information corresponding to the target detection feedback item is first mapped, and then the second target prompt information corresponding to the prompt item identification information is obtained in the prompt item template information (including voice prompt information, text prompt information and animation prompt information), and then the second target prompt information is presented on the page to guide the user to move closer.

[0075] In some embodiments, the user device performs face detection based on a preset time interval, and the timing starts when the face detection is first started. If the preset time interval is exceeded, the prompt information presented on the page is updated and the timing is restarted. If the preset time interval is not exceeded, it is determined whether to update the prompt information presented on the page and restart the timing depending on the specific situation. The details will be described in detail in subsequent embodiments.

[0076] It should be noted that after the start of video data collection, there is no strict sequential relationship between the operation of determining and presenting the first target prompt information corresponding to the target authentication action item in step S104 and the operation of step S106. For example, the user device may immediately and continuously execute step S106 to perform face detection after starting to collect video data, and then, after receiving the content sent by the service device, perform the operation of determining and presenting the first target prompt information corresponding to the target authentication action item based on the content.

[0077] According to the scheme in the embodiments of this specification, before starting to collect video data, the user device will first receive the prompt item template information provided by the service device for this video authentication detection. After starting to collect video data, the content sent by the service device is matched with the prompt item template information in real time to guide the user to execute the target authentication action item, and the user's face is detected in real time, and when the preset conditions are met, the target detection feedback item obtained by the face detection is matched with the prompt item template information to guide the user to adjust the face posture for video authentication detection. In this process, the content sent by the service device is unpredictable, that is, the authentication actions that the user needs to perform at each stage are unpredictable. By adding unpredictable authentication actions to the real-time video stream, multiple rounds of action interactions are required in the video authentication detection process and there is action uncertainty, which makes it impossible for attackers to predict the authentication actions, greatly reducing the risk of being attacked and improving the security of the authentication process.

[0078] In some embodiments, the start of collecting video data includes: sending module information of one or more input modules corresponding to the user device and device fingerprint information corresponding to the user device to the service device, so that the service device determines the risk indication information corresponding to the user device based on the module information and the device fingerprint information and returns it to the user device; if the risk indication information meets the preset conditions, start collecting video data. In some embodiments, after activating the camera, the user device will first send the module information of one or more input modules and the fingerprint information corresponding to the user device to the service device, so that the service device can decide whether the current user device is at risk. If the risk indication information fed back by the service device indicates a high risk (or indicates the end of detection), the video authentication detection is directly ended. If the risk indication information meets the preset conditions (for example, the risk level indicated by the risk indication information is lower than the preset level, the risk indication information indicates low risk or no risk, etc.), start collecting video data.

[0079] In some embodiments, the input module refers to a module for user video or audio input in the user device, including, for example, a camera, a microphone, etc. In some embodiments, the module information of at least one input module includes activation indication information for indicating whether the at least one input module is activated. As an example, after the user device activates the camera, the full camera (front camera, rear camera), microphone, activation indication information (used to indicate that the front camera is activated), and device fingerprint information of the user device are provided to the service device.

[0080] The device fingerprint information is used to uniquely identify the user device. In some embodiments, the device fingerprint information is calculated based on device-related information, for example, the name, model, function and other characteristics of the user device are combined to calculate the device fingerprint information of the user device. By reporting the module information of one or more input templates and the device fingerprint information, the service device can determine the risk indication information through multiple dimensions, thereby performing more accurate risk prevention and control.

[0081] In some embodiments, the risk indication information is determined by the service device based on the module information and the historical usage information of the user device, and the historical usage information is obtained based on the device fingerprint information. By further combining the historical usage of the user device to make risk decisions, the accuracy of risk prevention and control can be improved, the attack cost of the attacker can be increased, and it is difficult for the attacker to carry out the attack.

[0082] In some embodiments, the preset condition includes at least one of the following:

[0083] The timing duration corresponding to the second target prompt information currently presented reaches the preset time interval;

[0084] The target detection feedback item is inconsistent with the historical target detection feedback item corresponding to the second target prompt information currently presented;

[0085] The target detection feedback item is consistent with the historical target detection feedback item corresponding to the second target prompt information currently presented, and the timing duration corresponding to the second target prompt information currently presented reaches the preset time interval.

[0086] In some embodiments, the timing duration refers to the timing result obtained at the current time starting from the time when the second target prompt information is presented. As an example, after the user device starts timing based on the currently presented second target prompt information, after performing a terminal-side algorithm detection on each frame of video data, it will determine whether the timing duration has reached the preset time interval. Once the timing duration reaches the preset time interval, it will determine the latest second target prompt information based on the latest determined target feedback detection item by matching it with the prompt item template information, and present the second target prompt information to guide the user, and at the same time restart the timing from zero.

[0087] As another example, after the user device starts timing based on the currently presented second target prompt information, after performing terminal-side algorithm detection on each frame of video data, it will first determine whether the latest target detection feedback item is consistent with the historical target detection feedback item corresponding to the currently presented second target prompt information. If they are inconsistent (that is, the terminal-side detection result has been updated), the latest second target prompt information is determined directly based on the latest determined target feedback detection item by matching it with the prompt item template information, and the second target prompt information is presented to guide the user, and the timing is restarted from zero at the same time.

[0088] As another example, after the user device starts timing based on the currently presented second target prompt information, after performing terminal-side algorithm detection on each frame of video data, it will first determine whether the latest target detection feedback item is consistent with the historical target detection feedback item corresponding to the currently presented second target prompt information. If they are consistent (that is, the terminal-side detection result has not been updated), the operation of updating the presented prompt information is not performed, but the next frame of video data is continued to be detected, and so on, until it is detected that the terminal-side detection result has not been updated but the preset time interval has been reached, then the second target prompt information is re-determined and presented (since no update has occurred, the second target prompt information determined last time can also be used directly) to guide the user, and at the same time the timing is restarted from zero.

[0089] It should be noted that the above-mentioned preset conditions are only examples and not limitations of the scheme of this specification. Those skilled in the art should understand that the preset conditions can be set based on actual needs to determine whether to update the prompt content based on the preset conditions, so as to better guide users to complete video authentication detection.

[0090] In some embodiments, the method further comprises: obtaining the preset time interval provided by the service device. In some embodiments, the service device sends the preset time interval while sending the prompt item template information to the user device, and the user device receives the prompt template information and the preset time interval sent by the service device.

[0091] In some embodiments, the method further includes: obtaining time interval update indication information issued by the service device, and performing an update operation on the preset time interval according to the time interval update indication information. In some embodiments, the time interval update indication information is used to indicate the update of the preset time interval, and the update operation may be only for the current authentication action that the user needs to perform (that is, after the detection of this authentication action is completed, the original preset time interval is still used), or for all subsequent detections starting from the current time. Therefore, in special circumstances, the preset time interval can be updated to ensure that the user has enough time to complete the authentication action. For example, for special groups such as the disabled, more time may be required to perform more difficult authentication actions. In this way, a longer preset time interval can be used for these more difficult authentication actions. The scheme of updating the time interval can facilitate all groups to successfully complete the authentication detection through its flexibility.

[0092] Figure 2 A flowchart of a method for video authentication detection in a service device provided in an embodiment of this specification. In an embodiment of this specification, the method is applied to a device for video authentication detection in a service device (hereinafter referred to as "second device") or a service device / electronic device equipped with the second device. Figure 2 The process shown is described in detail, and the method for video authentication detection in the service device may specifically include the following steps:

[0093] S202, in response to satisfying the video authentication detection trigger condition, sending prompt item template information to the user device, the prompt item template information including prompt item identification information corresponding to a plurality of prompt items and prompt information corresponding to each prompt item identification information, the plurality of prompt items including a plurality of authentication action items and a plurality of detection feedback items.

[0094] In some embodiments, the video authentication detection trigger condition includes any condition for triggering the service device to start the video authentication detection, such as the service device receiving a video authentication detection request from the user device. The implementation method of the service device sending the prompt item template information to the user device has been described in detail in the above embodiments and will not be repeated here.

[0095] S204, determining a target authentication action item that the user currently needs to execute, and sending target prompt item identification information corresponding to the target authentication action item to the user device.

[0096] In some embodiments, the service device randomly determines an undetected authentication action item from the multiple authentication action items corresponding to the current video authentication detection as the target authentication action item that the user currently needs to perform. For example, the current video authentication detection corresponds to three authentication action items: raising head, raising hand, and touching head. In the first stage, the service device randomly determines the target authentication action item as "raising hand". When the "raising hand" action detection is completed, the service device randomly determines the target authentication action item as "raising head" from the remaining two authentication action items in the second stage. In some embodiments, the service device dynamically determines the target authentication action item that the user currently needs to perform based on the detection status of at least one authentication action that the user has performed in the current video authentication detection. The specific implementation method will be described in detail in subsequent embodiments. It should be noted that the above-mentioned implementation method of determining the target verification action item is only an example. Any implementation method for dynamically determining the target verification action item that the user currently needs to execute (for example, the first target verification action item that the user needs to execute is randomly determined, the second target verification action item is dynamically determined based on the risk level information of the first target verification action item, and the third target verification action item is randomly determined) should be included in the protection scope of this application.

[0097] In some embodiments, the prompt item template information includes a mapping relationship between the authentication action item, the prompt item identification information corresponding to the authentication action item, and the prompt information corresponding to the authentication action item. After determining the target authentication action item, the service device determines the prompt item identification information corresponding to the target authentication action item based on the mapping relationship and sends it to the user device. In some embodiments, the authentication action item itself can be used as the prompt item identification information. After the service device determines the authentication action item, it directly sends the authentication action item as the prompt item identification information to the user device.

[0098] S206: Perform video authentication detection on the target authentication action item based on the video data uploaded by the user device.

[0099] In some embodiments, the user device uploads the video data it has collected in real time. After the service device sends the prompt item identification information corresponding to the target action item, it will perform a video verification detection on the target verification action item based on the video data uploaded in real time by the user device. If the target verification action item is successfully detected, a detection completion indication for the target detection action item can be sent to the user device; if the detection of the last target verification action item is completed, it is determined that the user has completed the video verification detection, and an indication that the detection has passed can be sent to the user device, indicating the end of the detection.

[0100] In some embodiments, the method further includes: receiving module information of one or more input modules sent by the user device and device fingerprint information corresponding to the user device; determining risk indication information corresponding to the user device based on the module information and the device fingerprint information, and returning the risk indication information to the user device. The module information, device fingerprint information, and risk indication information have been described in detail in the aforementioned embodiments and will not be repeated here. In some embodiments, the service device may input the module information and device fingerprint information into a large artificial intelligence model to obtain risk indication information about the user device input by the large model. In some embodiments, a large amount of historical video authentication detection information related to user devices is stored in the service device to facilitate risk decision-making.

[0101] In some embodiments, the risk indication information corresponding to the user device is determined based on the module information and the device fingerprint information, including: determining the historical usage information corresponding to the user device according to the device fingerprint information; determining the risk indication information corresponding to the user device according to the module information and the historical usage information. In some embodiments, the historical usage information is used to indicate the historical usage of the user device for video identity detection, including, for example, detection time, detection results, input modules activated during detection, etc. As an example, the service device queries and obtains the historical usage information of the user device according to the device fingerprint information of the user device. The historical usage information indicates that the user device has a large amount of virtual camera usage information, and the cumulative number of uses has reached a preset number threshold. If it is determined that the user device has a high risk, the service device will generate risk indication information to indicate that the user device user needs to end the process immediately. After receiving the risk indication information, the user device will immediately end the process and prompt the relevant parties (such as upstream products, users, etc.) for risk. In some embodiments, after each video identity detection is completed, the service device will have relevant information (including device fingerprint information, module information, detection result information, etc.) of this video identity detection to facilitate subsequent risk decisions.

[0102] In some embodiments, the determination of the target verification action item that the user currently needs to perform includes: determining the target verification action item that the user currently needs to perform from the multiple verification action items based on the detection situation corresponding to at least one verification action item that the user has performed during the current video verification detection process. In some embodiments, the detection situation includes but is not limited to the detection result, the duration used for the detection, etc. In some embodiments, if the most recent target verification action item fails to be detected successfully within a preset time, then in the next stage, one may first be selected from other undetected verification action items as the target verification action item. In some embodiments, if the time used for the most recent detection of a target verification action item is less than the preset time, then in the next stage, one may be selected from multiple optional verification action items of higher difficulty (i.e., verification action items that have not yet been detected) as the target verification action item.

[0103] In some embodiments, the target authentication action item that the user currently needs to execute is determined from the multiple authentication action items according to the detection situation corresponding to at least one authentication action item that the user has executed during the current video authentication detection process, including: determining the target authentication action item that the user currently needs to execute from the multiple authentication action items according to the detection situation corresponding to at least one authentication action item that the user has executed during the current video authentication detection process, and the risk level information corresponding to the multiple authentication action items. In some embodiments, the risk level information is used to indicate the risk level of the authentication action item. The higher the risk level, the easier it is to be attacked. Conversely, the lower the risk level, the less likely it is to be attacked. The risk level information can characterize the execution difficulty of the authentication action item to a certain extent. The higher the execution difficulty of the authentication action item, the lower the risk level of the accompanying shadow, that is, the higher the execution difficulty of the authentication action item, the less likely it is to be attacked. As an example, the service device determines that the risk level information of the completed authentication action item is high based on the detection status of at least one authentication action item that has been executed, and then selects (randomly selects, or selects the one with the lowest risk level) an authentication action item from multiple authentication action items that have not yet completed the detection and have a lower risk level as the target authentication action item that the user currently needs to execute. By combining the risk level information to determine the target authentication action item, it is possible to ensure that authentication action items of different risk levels are detected, thereby improving the accuracy of the authentication detection results.

[0104] In some embodiments, the method further includes: sending a preset time interval to the user device. In some embodiments, the service device sends the preset time interval while sending the prompt item template information to the user device. In some embodiments, the service device may determine it based on the user information corresponding to the user, for example, dynamically determined based on the user's historical payment portrait, historical identity verification status, etc. In some embodiments, the service device may determine the preset time interval based on an agreement with the user device and in combination with actual needs. In some embodiments, the service device may determine the preset time interval based on the configuration information, and the preset time interval uses all user devices, or may determine the preset time intervals corresponding to different types of user devices based on the configuration information, and then send the preset time interval corresponding to the user device to the user device.

[0105] In some embodiments, the method further includes: if the time interval update condition is met, generating time interval update indication information, and sending the time interval update indication information to the user device; the time interval update condition includes at least one of the following: the difficulty coefficient corresponding to the target identity verification action item currently required to be performed by the user exceeds a preset threshold; the user characteristics of the user match the group characteristics corresponding to the special group. The time interval update indication information has been described in detail in the above embodiments and will not be repeated here. In some embodiments, the time interval update condition includes any condition for triggering the update of the preset time interval. In some embodiments, if the difficulty coefficient corresponding to the target identity verification action item currently required to be performed by the user exceeds a preset threshold, it can be confirmed that the time interval update condition is met; further, if the difficulty coefficient corresponding to the target identity verification action item currently required to be performed by the user exceeds the preset threshold, it can be further combined with the detection of the identity verification action item that the user has performed to evaluate the time required for the user to perform the target identity verification action item. If the required time is greater than or equal to the current preset time interval, it is confirmed that the time interval update condition is met. In some embodiments, if user characteristics are collected based on video data, or user characteristics are queried based on user-related information, if the user characteristics match the group characteristics of special groups (such as hearing-impaired groups, visually impaired groups, elderly groups, etc., which take longer to perform identification actions than ordinary people), then the user is considered to belong to the matched characteristic group, and it is determined that the time interval update condition is met. It should be noted that the above time interval update condition is only distance, not restriction.

[0106] Figure 3 The present invention provides an example of a flow chart for video authentication detection in accordance with an embodiment of the present invention. Figure 3 It mainly shows the interaction between the user equipment and the server (ie, the service device) and the detection logic executed by the user equipment side, as follows:

[0107] 1) When the user device enters the page for video authentication detection, the server will first send the prompt item template information and the preset interval time to the user device, and the user device will receive the prompt item template information and the preset interval time (that is, Figure 3 "Getting the prompt item template and interval time" as shown);

[0108] 2) After the camera is activated, the user device obtains terminal information such as the camera, microphone, and device fingerprint (i.e., the module information and device fingerprint information mentioned above) and sends it to the server, so that the server can decide whether the current user device is at risk. If the risk indication information fed back by the server indicates that the risk is low or no risk, the subsequent process continues;

[0109] 3) Entering the main link, the main link will be processed in parallel from two directions: the end-side link is used to detect whether the current face is conducive to cloud-side algorithm detection, and to make real-time feedback through various end-side detections (that is, the process of obtaining target detection feedback items, determining and presenting the second target prompt information), to guide users to better complete video authentication; the cloud link is to perform stage control and issue different action contents at different stages (that is, the target prompt item identification information corresponding to the target authentication action item), so as to guide the page on the user device side based on the action content issued by the server.

[0110] In this example, the server determines the content to be sent based on the cloud algorithm. After the user device receives the latest content sent by the server, it will first determine whether the server response is updated (that is, whether the latest content sent by the server has changed from the content sent last time). If there is no update, it will feedback to the server; if there is an update, it will further determine whether it is an end indication. If it is an end indication, it will directly exit the process. If it is not an end indication, it will perform page guidance based on the latest content sent. After entering the page guidance based on the content sent by the server, the target prompt information will be determined based on the content sent by the server and the prompt item template information.

[0111] In this example, for the end-side link, the user device will obtain video data frame by frame and perform end-side algorithm detection to detect faces. If the end-side detection is updated (that is, the target feedback detection item determined by the current detection is different from the target feedback detection item determined by the most recent detection), the page guidance process is entered to update the prompt content. If the end-side detection is not updated, it is determined whether the interval time has been exceeded. If not, data will continue to be obtained frame by frame. If exceeded, page guidance will be restarted based on the latest target feedback detection item (the timing will be restarted from zero each time the page guidance starts). After entering the page guidance based on the end-side detection result, the target prompt information will be determined by matching the latest target feedback detection item on the end with the prompt item template information.

[0112] Figure 4A schematic diagram of a structure of a device for video authentication detection in a user device provided in an embodiment of this specification, the device for video authentication detection in a user device (hereinafter referred to as "first device 1") can be implemented as all or part of an electronic device through software, hardware or a combination of both. According to some embodiments, the first device 1 includes an acquisition module 11, a first detection module 12 and a second detection module 13.

[0113] An acquisition module 11 is used to obtain prompt item template information provided by a service device, wherein the prompt item template information includes prompt item identification information corresponding to a plurality of prompt items and prompt information corresponding to each prompt item identification information, wherein the plurality of prompt items include a plurality of verification action items and a plurality of detection feedback items;

[0114] The first detection module 12 is used to start collecting video data. If the first prompt item identification information corresponding to the target authentication action item issued by the service device is obtained, the first prompt item identification information is matched with the prompt item template information, and the first target prompt information corresponding to the target authentication action item is determined and presented to guide the user to execute the target authentication action item, so that the service device performs video authentication detection on the target authentication action item based on the video data uploaded by the user device;

[0115] The second detection module 13 is used to perform face detection on the user based on the video data and a preset time interval, obtain a target detection feedback item corresponding to the current face of the user, and if a preset condition is met, match the second prompt item identification information corresponding to the target detection feedback item with the prompt item template information, determine and present the second target prompt information corresponding to the target detection feedback item, so as to guide the user to adjust the facial posture, wherein the face detection is used to detect whether the current face of the user in the video data meets the preset requirements.

[0116] In some embodiments, the prompt information includes at least one of voice prompt information, text prompt information, and animation prompt information.

[0117] In some embodiments, the starting to collect video data includes:

[0118] Sending module information of one or more input modules corresponding to the user device and device fingerprint information corresponding to the user device to the service device, so that the service device determines risk indication information corresponding to the user device based on the module information and the device fingerprint information and returns the risk indication information to the user device;

[0119] If the risk indication information meets the preset conditions, start collecting video data.

[0120] In some embodiments, the module information of at least one input module includes activation indication information for indicating whether the at least one input module is activated.

[0121] In some embodiments, the preset condition includes at least one of the following:

[0122] The timing duration corresponding to the second target prompt information currently presented reaches the preset time interval;

[0123] The target detection feedback item is inconsistent with the historical target detection feedback item corresponding to the second target prompt information currently presented;

[0124] The target detection feedback item is consistent with the historical target detection feedback item corresponding to the second target prompt information currently presented, and the timing duration corresponding to the second target prompt information currently presented reaches the preset time interval.

[0125] In some embodiments, the first device 1 is further used for:

[0126] The preset time interval provided by the service device is obtained.

[0127] In some embodiments, the first device 1 is further used for:

[0128] The time interval update indication information sent by the service device is obtained, and an update operation is performed on the preset time interval according to the time interval update indication information.

[0129] Figure 5 A schematic diagram of a structure of a device for video authentication detection in a service device provided in an embodiment of this specification, the device for video authentication detection in a service device (hereinafter referred to as "second device 2") can be implemented as all or part of an electronic device through software, hardware or a combination of both. According to some embodiments, the second device 2 includes a template sending module 21, an action sending module 22 and an authentication detection module 23.

[0130] The template sending module 21 is used for sending prompt item template information to the user equipment in response to satisfying the video authentication detection trigger condition, wherein the prompt item template information includes prompt item identification information corresponding to a plurality of prompt items and prompt information corresponding to each prompt item identification information, wherein the plurality of prompt items include a plurality of authentication action items and a plurality of detection feedback items;

[0131] An action sending module 22 is used to determine a target authentication action item that the user currently needs to execute, determine target prompt item identification information corresponding to the target authentication action item based on the prompt item template information, and send the target prompt item identification information to the user device;

[0132] The authentication detection module 23 is used to perform video authentication detection on the target authentication action item based on the video data uploaded by the user equipment.

[0133] In some embodiments, the second device 2 is further used for:

[0134] Receiving module information of one or more input modules and device fingerprint information corresponding to the user equipment sent by the user equipment;

[0135] The risk indication information corresponding to the user equipment is determined based on the module information and the device fingerprint information, and the risk indication information is returned to the user equipment.

[0136] In some embodiments, determining the risk indication information corresponding to the user device based on the module information and the device fingerprint information includes:

[0137] Determine historical usage information corresponding to the user device according to the device fingerprint information;

[0138] Determine risk indication information corresponding to the user equipment according to the module information and the historical usage information.

[0139] In some embodiments, determining the target action item that the user currently needs to perform includes:

[0140] According to the detection status corresponding to at least one authentication action item executed by the user in the current video authentication detection process, a target authentication action item currently required to be executed by the user is determined from the multiple authentication action items.

[0141] In some embodiments, the step of determining a target authentication action item that the user currently needs to perform from the multiple authentication action items based on the detection status corresponding to at least one authentication action item that the user has performed during the current video authentication detection process includes:

[0142] Based on the detection status corresponding to at least one authentication action item executed by the user during the video authentication detection process, and the risk level information corresponding to the multiple authentication action items, the target authentication action item currently required to be executed by the user is determined from the multiple authentication action items.

[0143] In some embodiments, the second device 2 is further used for:

[0144] Sending a preset time interval to the user equipment.

[0145] In some embodiments, the second device 2 is further used for:

[0146] If the time interval update condition is met, generating time interval update indication information, and sending the time interval update indication information to the user equipment;

[0147] The time interval update condition includes at least one of the following:

[0148] The difficulty coefficient of the target action item that the user needs to perform currently exceeds the preset threshold;

[0149] The user characteristics of the user match the group characteristics corresponding to the special group.

[0150] The above device embodiments correspond to the method embodiments. For specific descriptions, please refer to the description of the method embodiments, which will not be repeated here. The device embodiments are obtained based on the corresponding method embodiments and have the same technical effects as the corresponding method embodiments. For specific descriptions, please refer to the corresponding method embodiments.

[0151] The embodiment of the present specification also provides a computer storage medium, which can store multiple instructions, and the instructions are suitable for being loaded by a processor to execute the method of the embodiment of the present specification.

[0152] The embodiments of the present specification also provide a computer program product, which stores at least one instruction, and the at least one instruction is loaded by the processor to execute the method of the embodiments of the present specification.

[0153] The embodiments of this specification also provide Figure 6 The structural diagram of the electronic device shown in FIG. Figure 6 At the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to implement the above method.

[0154] 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.

[0155] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, 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.) that contain computer-usable program code.

[0156] This specification is described with reference to the flowcharts and / or block diagrams of the 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 the 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 data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0157] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0158] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0159] 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.

[0160] This 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. This 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.

[0161] 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.

[0162] The above description is only an embodiment of the present specification and is not intended to limit the present specification. For those skilled in the art, the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims of the present specification.

Claims

1. A method for video authentication detection, applied to a user device, comprising: Obtaining prompt item template information provided by a service device, wherein the prompt item template information includes prompt item identification information corresponding to a plurality of prompt items and prompt information corresponding to each prompt item identification information, wherein the plurality of prompt items include a plurality of verification action items and a plurality of detection feedback items; Start collecting video data, and if first prompt item identification information corresponding to the target authentication action item issued by the service device is obtained, match the first prompt item identification information with the prompt item template information, determine and present first target prompt information corresponding to the target authentication action item, so as to guide the user to execute the target authentication action item, so that the service device performs video authentication detection on the target authentication action item based on the video data uploaded by the user device; Based on the collected video data and a preset time interval, face detection is performed on the user to obtain a target detection feedback item corresponding to the current face of the user; if a preset condition is met, the second prompt item identification information corresponding to the target detection feedback item is matched with the prompt item template information, and the second target prompt information corresponding to the target detection feedback item is determined and presented to guide the user to adjust the facial posture, wherein the face detection is used to detect whether the current face of the user in the video data meets the preset requirements.

2. According to the method of claim 1, the prompt information includes at least one of voice prompt information, text prompt information, and animation prompt information.

3. The method according to claim 1, wherein starting to collect video data comprises: Sending module information of one or more input modules corresponding to the user device and device fingerprint information corresponding to the user device to the service device, so that the service device determines risk indication information corresponding to the user device based on the module information and the device fingerprint information and returns the risk indication information to the user device; If the risk indication information meets the preset conditions, start collecting video data. 4 . The method according to claim 3 , wherein the module information of at least one input module comprises activation indication information for indicating whether the at least one input module is activated.

5. The method according to claim 1, wherein the preset condition comprises at least one of the following: The timing duration corresponding to the second target prompt information currently presented reaches the preset time interval; The target detection feedback item is inconsistent with the historical target detection feedback item corresponding to the second target prompt information currently presented; The target detection feedback item is consistent with the historical target detection feedback item corresponding to the second target prompt information currently presented, and the timing duration corresponding to the second target prompt information currently presented reaches the preset time interval.

6. The method according to claim 1, further comprising: The preset time interval provided by the service device is obtained.

7. The method according to claim 6, further comprising: The time interval update indication information sent by the service device is obtained, and an update operation is performed on the preset time interval according to the time interval update indication information.

8. A method for video authentication detection, applied to a service device, comprising: In response to satisfying a video authentication detection trigger condition, sending prompt item template information to the user equipment, the prompt item template information including prompt item identification information corresponding to a plurality of prompt items and prompt information corresponding to each prompt item identification information, the plurality of prompt items including a plurality of authentication action items and a plurality of detection feedback items; Determine a target authentication action item that the user currently needs to execute, and send target prompt item identification information corresponding to the target authentication action item to the user device; Video authentication detection is performed on the target authentication action item based on the video data uploaded by the user device.

9. The method according to claim 8, further comprising: Receiving module information of one or more input modules and device fingerprint information corresponding to the user equipment sent by the user equipment; The risk indication information corresponding to the user equipment is determined based on the module information and the device fingerprint information, and the risk indication information is returned to the user equipment.

10. The method according to claim 9, wherein determining the risk indication information corresponding to the user device based on the module information and the device fingerprint information comprises: Determine historical usage information corresponding to the user device according to the device fingerprint information; Determine risk indication information corresponding to the user equipment according to the module information and the historical usage information.

11. The method according to claim 8, wherein determining the target action item that the user currently needs to perform comprises: According to the detection status corresponding to at least one authentication action item executed by the user in the current video authentication detection process, a target authentication action item currently required to be executed by the user is determined from the multiple authentication action items.

12. The method according to claim 11, wherein the step of determining a target authentication action item that the user currently needs to perform from the plurality of authentication action items based on the detection status corresponding to at least one authentication action item that the user has performed during the current video authentication detection process comprises: Based on the detection status corresponding to at least one authentication action item executed by the user during the video authentication detection process, and the risk level information corresponding to the multiple authentication action items, the target authentication action item currently required to be executed by the user is determined from the multiple authentication action items.

13. The method according to claim 8, further comprising: Sending a preset time interval to the user equipment.

14. The method according to claim 13, further comprising: If the time interval update condition is met, generating time interval update indication information, and sending the time interval update indication information to the user equipment; The time interval update condition includes at least one of the following: The difficulty coefficient of the target action item that the user needs to perform currently exceeds the preset threshold; The user characteristics of the user match the group characteristics corresponding to the special group.

15. A device for video authentication detection in a user device, comprising: An acquisition module, used to obtain prompt item template information provided by a service device, wherein the prompt item template information includes prompt item identification information corresponding to a plurality of prompt items and prompt information corresponding to each prompt item identification information, wherein the plurality of prompt items include a plurality of verification action items and a plurality of detection feedback items; A first detection module is used to start collecting video data, and if first prompt item identification information corresponding to the target authentication action item issued by the service device is obtained, the first prompt item identification information is matched with the prompt item template information, and the first target prompt information corresponding to the target authentication action item is determined and presented to guide the user to execute the target authentication action item, so that the service device performs video authentication detection on the target authentication action item based on the video data uploaded by the user device; The second detection module is used to perform face detection on the user based on the video data and a preset time interval, obtain a target detection feedback item corresponding to the current face of the user, and if a preset condition is met, match the second prompt item identification information corresponding to the target detection feedback item with the prompt item template information, determine and present the second target prompt information corresponding to the target detection feedback item, so as to guide the user to adjust the facial posture, wherein the face detection is used to detect whether the current face of the user in the video data meets the preset requirements.

16. A device for video authentication detection in a service device, comprising: a template sending module, configured to send prompt item template information to the user equipment in response to satisfying a video authentication detection trigger condition, wherein the prompt item template information includes prompt item identification information corresponding to a plurality of prompt items and prompt information corresponding to each prompt item identification information, wherein the plurality of prompt items include a plurality of authentication action items and a plurality of detection feedback items; An action sending module, used to determine a target authentication action item that the user currently needs to execute, determine target prompt item identification information corresponding to the target authentication action item based on the prompt item template information, and send the target prompt item identification information to the user device; The authentication detection module is used to perform video authentication detection on the target authentication action item based on the video data uploaded by the user equipment.

17. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 14 are implemented.

18. An electronic device, characterized in that: include: A processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the steps of the method as claimed in any one of claims 1 to 14.

19. A computer program product having at least one instruction stored thereon, characterized in that: When the at least one instruction is executed by the processor, the steps of the method described in any one of claims 1 to 14 are implemented.

Images