Live detection methods, systems, computer devices, and storage media

Abstract

The application relates to a living body detection method, a system, a computer device and a storage medium. The method comprises the following steps: obtaining a target risk assessment result of an object to be detected; determining a shunt proportion of a candidate living body detection strategy corresponding to the target risk assessment result; the shunt proportion of the candidate living body detection strategy is a probability that the candidate living body detection strategy is selected in advance; selecting a target living body detection strategy from the candidate living body detection strategy according to the shunt proportion of the candidate living body detection strategy; and performing living body detection on an image to be detected of the object to be detected according to the target living body detection strategy. The method can reduce the limitations of living body detection.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, system, computer device, and storage medium for detecting liveness. Background Technology

[0002] Liveness detection is a method used in identity verification scenarios to determine the true physiological characteristics of an object. In facial recognition applications, liveness detection can verify whether the object is a real, living person by using a combination of actions such as blinking, opening the mouth, shaking the head, or nodding, and by using technologies such as facial landmark localization and facial tracking, thereby improving the security of business processes.

[0003] Traditional liveness detection methods typically employ default liveness detection techniques. However, these default techniques are often unsuitable for a wide variety of business scenarios, resulting in low applicability and limitations. Summary of the Invention

[0004] Therefore, it is necessary to provide a liveness detection method, system, device, computer equipment, computer-readable storage medium, and computer program product that can reduce the limitations of the above-mentioned technical problems.

[0005] Firstly, this application provides a method for detecting liveness. The method includes:

[0006] Obtain the target risk assessment results for the subjects to be tested in vivo;

[0007] Determine the triage ratio of the candidate liveness detection strategies corresponding to the target risk assessment results; the triage ratio of the candidate liveness detection strategies is the pre-configured probability of the candidate liveness detection strategy being selected;

[0008] Based on the diversion ratio of the candidate liveness detection strategies, a target liveness detection strategy is selected from the candidate liveness detection strategies.

[0009] Liveness detection is performed on the image of the object to be detected according to the target liveness detection strategy.

[0010] Secondly, this application also provides a liveness detection system. The system includes: a risk control server, a risk calculation server, a liveness detection server, and a terminal; wherein:

[0011] The risk calculation server is used to determine the target risk assessment result of the object to be detected, and send the target risk assessment result to the risk control server.

[0012] The risk control server is used to send the target risk assessment results to the liveness detection server;

[0013] The liveness detection server is used to obtain the target risk assessment result of the object to be detected; determine the traffic splitting ratio of the candidate liveness detection strategies corresponding to the target risk assessment result; select the target liveness detection strategy from the candidate liveness detection strategies according to the traffic splitting ratio of the candidate liveness detection strategies; the traffic splitting ratio of the candidate liveness detection strategies is a pre-configured probability of the candidate liveness detection strategy being selected.

[0014] The terminal is used to acquire the image of the object to be detected and send it to the liveness detection server.

[0015] The liveness detection server is also used to perform liveness detection on the image to be detected according to the target liveness detection strategy.

[0016] In one embodiment, the liveness detection server is further configured to obtain the version information of the application client used by the object; determine the traffic splitting ratio of the liveness detection strategy corresponding to different risk assessment results under the version information; and determine the traffic splitting ratio of the candidate liveness detection strategy corresponding to the target risk assessment result from the traffic splitting ratio under the version information.

[0017] In one embodiment, the object to be detected as a liveness detection device is an object requesting to process a service; the liveness detection server is further configured to determine a corresponding liveness detection configuration package based on at least one of the processing channel of the requested service and the service type of the service to be processed; the liveness detection configuration package includes the correspondence between risk assessment results and liveness detection strategies, as well as the traffic allocation ratio of the liveness detection strategy corresponding to each risk assessment result; based on the correspondence between risk assessment results and liveness detection strategies in the liveness detection configuration package, the candidate liveness detection strategy corresponding to the target risk assessment result is determined; and the traffic allocation ratio of the candidate liveness detection strategy corresponding to the target risk assessment result is determined from the liveness detection configuration package.

[0018] In one embodiment, the risk control server is further configured to acquire at least one of the historical behavior information of the object to be detected, the environmental information of the device used by the object, and the device information, and send them to the risk server;

[0019] The risk calculation server is also used to perform risk assessment based on at least one of the historical behavior information, the environmental information, and the device information to obtain the target risk assessment result of the object.

[0020] In one embodiment, the risk calculation server is further configured to determine the anomaly of at least one of the historical behavior, equipment, and historical behavior results of the object based on at least one of the historical behavior information, the environmental information, and the device information, and obtain an anomaly determination result; if the anomaly determination result indicates that at least one of the historical behavior, equipment, and historical behavior results of the object is abnormal, then the target risk assessment result of the object is determined to be a high-risk level.

[0021] In one embodiment, the risk calculation server is further configured to determine the target risk assessment result of the object as low risk level if the anomaly determination result indicates that the object's historical behavior, device and historical behavior results are all normal and there is security information.

[0022] In one embodiment, the system further includes: a face comparison server, wherein:

[0023] The liveness detection server is also used to determine the diversion ratio of the candidate face matching strategy corresponding to the target liveness detection strategy; the diversion ratio of the candidate face matching strategy is the probability of the candidate face matching strategy being selected in a pre-configured manner; and the target face matching strategy is selected from the candidate face matching strategies according to the diversion ratio of the candidate face matching strategy.

[0024] The terminal is also used to collect facial images of the object;

[0025] The face comparison server is also used to perform face comparison processing on the face image of the object according to the target face comparison strategy after the liveness detection is completed.

[0026] Thirdly, this application also provides a liveness detection device. The device includes:

[0027] The acquisition module is used to acquire the target risk assessment results of the object to be detected for liveness testing.

[0028] The liveness detection strategy determination module is used to determine the diversion ratio of candidate liveness detection strategies corresponding to the target risk assessment result; the diversion ratio of candidate liveness detection strategies is a pre-configured probability of the candidate liveness detection strategy being selected; and the target liveness detection strategy is selected from the candidate liveness detection strategies according to the diversion ratio of candidate liveness detection strategies.

[0029] The liveness detection module is used to perform liveness detection on the image of the object to be detected according to the target liveness detection strategy.

[0030] In one embodiment, the liveness detection strategy determination module is further configured to obtain the version information of the application client used by the object; determine the traffic splitting ratio of the liveness detection strategy corresponding to different risk assessment results under the version information; and determine the traffic splitting ratio of the candidate liveness detection strategy corresponding to the target risk assessment result from the traffic splitting ratio under the version information.

[0031] In one embodiment, the object to be detected as a liveness detection is an object requesting to process a service; the liveness strategy determination module is further configured to determine a corresponding liveness detection configuration package based on at least one of the processing channel of the requested service and the service type of the service to be processed; the liveness detection configuration package includes the correspondence between risk assessment results and liveness detection strategies, as well as the diversion ratio of the liveness detection strategy corresponding to each risk assessment result; based on the correspondence between risk assessment results and liveness detection strategies in the liveness detection configuration package, the candidate liveness detection strategy corresponding to the target risk assessment result is determined; and the diversion ratio of the candidate liveness detection strategy corresponding to the target risk assessment result is determined from the liveness detection configuration package.

[0032] In one embodiment, the device further includes:

[0033] The risk assessment module is used to acquire at least one of the following: historical behavior information of the object to be detected, environmental information of the device used by the object, and device information; and to perform a risk assessment based on at least one of the historical behavior information, environmental information, and device information to obtain the target risk assessment result of the object.

[0034] In one embodiment, the risk assessment module is further configured to determine the anomaly of at least one of the object's historical behavior, equipment, and historical behavior results based on at least one of the historical behavior information, environmental information, and equipment information, and obtain an anomaly determination result; if the anomaly determination result indicates that at least one of the object's historical behavior, equipment, and historical behavior results is abnormal, then the target risk assessment result of the object is determined to be a high-risk level.

[0035] In one embodiment, the risk assessment module is further configured to determine the target risk assessment result of the object as low risk level if the anomaly determination result indicates that the object's historical behavior, equipment, and historical behavior results are all normal and there is security information.

[0036] In one embodiment, the device further includes:

[0037] A face comparison strategy determination module is used to determine the diversion ratio of candidate face comparison strategies corresponding to the target liveness detection strategy; the diversion ratio of the candidate face comparison strategy is a pre-configured probability of the candidate face comparison strategy being selected; based on the diversion ratio of the candidate face comparison strategies, a target face comparison strategy is selected from the candidate face comparison strategies; the target face comparison strategy is used to perform face comparison processing on the face image of the object after liveness detection is completed.

[0038] Fourthly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, which, when executed by the processor, causes the processor to perform the steps of the liveness detection method described in the embodiments of this application.

[0039] Fifthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, causes the processor to perform the steps of the liveness detection method described in the embodiments of this application.

[0040] Sixthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, causes the processor to perform the steps of the liveness detection method described in the embodiments of this application.

[0041] The aforementioned liveness detection method, system, apparatus, computer equipment, storage medium, and computer program product acquire the target risk assessment results of the object to be detected, determine the diversion ratio of candidate liveness detection strategies corresponding to the target risk assessment results, select a target liveness detection strategy from the candidate liveness detection strategies according to the diversion ratio of the candidate liveness detection strategies, and perform liveness detection on the image of the object to be detected according to the target liveness detection strategy. It can select appropriate liveness detection strategies in a targeted manner according to the risk assessment results of the object to be detected, thereby enabling liveness detection to be performed on objects with different risk conditions, improving applicability and reducing limitations. Attached Figure Description

[0042] Figure 1 This is a diagram illustrating the application environment of a liveness detection method in one embodiment;

[0043] Figure 2 This is a flowchart illustrating a liveness detection method in one embodiment;

[0044] Figure 3 This is a schematic diagram of the configuration interface of the liveness detection configuration package in one embodiment;

[0045] Figure 4 This is a schematic diagram of the configuration interface of the face comparison configuration package in one embodiment;

[0046] Figure 5 This is a schematic diagram of the face comparison process in one embodiment;

[0047] Figure 6 This is a schematic diagram of the overall process of a liveness detection method in one embodiment;

[0048] Figure 7 This is an architecture diagram of a liveness detection system in one embodiment;

[0049] Figure 8 This is an architecture diagram of a liveness detection system in another embodiment;

[0050] Figure 9 This is a structural block diagram of a liveness detection device in one embodiment;

[0051] Figure 10 This is a structural block diagram of the liveness detection device in another embodiment;

[0052] Figure 11 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0054] The liveness detection method provided in this application can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with liveness detection server 104 via a network, liveness detection server 104 communicates with risk control server 106 via a network, and risk control server 106 communicates with risk calculation server 108 via a network. Risk calculation server 108 can determine the target risk assessment result of the object to be detected and send the target risk assessment result to risk control server 106. Risk control server 106 can send the target risk assessment result to liveness detection server 104. Liveness detection server 104 can obtain the target risk assessment result of the object to be detected, determine the diversion ratio of the candidate liveness detection strategies corresponding to the target risk assessment result, and select the target liveness detection strategy from the candidate liveness detection strategies according to the diversion ratio. Terminal 102 can collect the image of the object to be detected and send it to liveness detection server 104. Liveness detection server 104 can perform liveness detection on the image to be detected according to the target liveness detection strategy. The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle systems. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The liveness detection server 104, risk control server 106, and risk calculation server 108 can be implemented using independent servers or a server cluster consisting of multiple servers.

[0055] In one embodiment, such as Figure 2 As shown, a liveness detection method is provided, including the following steps:

[0056] Step 202: Obtain the target risk assessment results of the object to be tested for liveness detection.

[0057] The object to be detected for liveness detection is the entity that needs to undergo liveness detection. Liveness detection is a method used in identity verification scenarios to determine the true physiological characteristics of an object. In facial recognition applications, liveness detection can verify whether the object is a real, living person by using combined actions such as blinking, opening their mouth, shaking their head, or nodding, and employing technologies such as facial landmark localization and facial tracking, thereby improving the security of business processes. The object can be a person or an animal, without limitation. The target risk assessment result refers to the risk assessment result obtained by performing a risk assessment on the object to be detected for liveness detection.

[0058] In one embodiment, the target risk assessment result may include at least one of high-risk level, medium-risk level, and low-risk level.

[0059] In one embodiment, the risk calculation server can determine the target risk assessment result of the object to be detected as a liveness detection object and send the target risk assessment result to the risk control server. The risk control server can then send the target risk assessment result to the liveness detection server, which can then obtain the target risk assessment result of the object to be detected as a liveness detection object.

[0060] The risk calculation server is the server for the risk calculation system. The risk calculation system is used to determine the risk assessment results of an object. The risk control server is the server for the risk control system. The risk control system is used to acquire and transmit risk control information. The liveness detection server is the server for the liveness detection system. The liveness detection system is used to perform liveness detection.

[0061] In one embodiment, the risk control server can also determine a risk control result code based on the target risk assessment result, and send the risk control result code and the target risk assessment result to the liveness detection server. The risk control result code is an identifier used to indicate whether liveness detection is rejected.

[0062] In one embodiment, if the risk control result code indicates rejection of liveness detection, the liveness detection server may refuse to perform liveness detection on the object to be detected. In another embodiment, if the risk control result code indicates no rejection of liveness detection, the liveness detection server may continue to execute step 204 and subsequent steps.

[0063] Step 204: Determine the triage ratio of candidate liveness detection strategies corresponding to the target risk assessment results; the triage ratio of candidate liveness detection strategies is the probability of a pre-configured candidate liveness detection strategy being selected.

[0064] Among them, the candidate liveness detection strategy refers to the liveness detection strategy configured according to the target risk assessment results.

[0065] In one embodiment, a liveness detection configuration package can be pre-established. The liveness detection server can determine the traffic allocation ratio of candidate liveness detection strategies corresponding to the target risk assessment result from the liveness detection configuration package. The liveness detection configuration package includes the correspondence between risk assessment results and liveness detection strategies, as well as the traffic allocation ratio of the liveness detection strategy corresponding to each risk assessment result. Figure 3 The image shown is a schematic diagram of the configuration interface for the liveness detection configuration package, which displays the information configured in the liveness detection configuration package.

[0066] In one embodiment, the liveness detection server can determine the candidate liveness detection strategy corresponding to the target risk assessment result based on the correspondence between the risk assessment result and the liveness detection strategy in the liveness detection configuration package, and determine the traffic distribution ratio of the candidate liveness detection strategy corresponding to the target risk assessment result from the liveness detection configuration package.

[0067] In one embodiment, each risk assessment result corresponds to at least one (i.e., one or more) liveness detection strategies. Therefore, a target risk assessment result corresponds to at least one (i.e., one or more) candidate liveness detection strategies. The triage ratio of each liveness detection strategy corresponding to each risk assessment result represents the probability that each liveness detection strategy corresponding to that risk assessment result is selected.

[0068] For example, such as Figure 3 As shown, corresponding diversion ratios are configured for different liveness detection strategies corresponding to different risk assessment results. For example, a high-risk level corresponds to one liveness detection strategy—Manufacturer A's flash liveness strategy, so the diversion ratio for Manufacturer A's flash liveness strategy corresponding to the high-risk level is 100%. As another example, a medium-risk level corresponds to two liveness detection strategies—Manufacturer B's action liveness strategy and Manufacturer A's optical liveness strategy, so the diversion ratio for Manufacturer B's action liveness strategy corresponding to the medium-risk level is 30%, and the diversion ratio for Manufacturer A's optical liveness strategy corresponding to the medium-risk level is 70%. Figure 3 The term "catch-all" refers to situations where the target risk assessment result does not fall into the high-risk, medium-risk, or low-risk categories.

[0069] In one embodiment, different liveness detection strategies may be provided by different manufacturers or employ different liveness detection methods. For example: Figure 3 The configured liveness detection strategies include Manufacturer A's flash liveness strategy, Manufacturer B's motion liveness strategy, Manufacturer A's light liveness strategy, and Manufacturer B's blink liveness strategy. Among them, the flash liveness strategy, motion liveness strategy, light liveness strategy, and blink liveness strategy all employ different liveness detection methods.

[0070] Step 206: Select the target liveness detection strategy from the candidate liveness detection strategies according to the diversion ratio of the candidate liveness detection strategies.

[0071] The target liveness detection strategy refers to the liveness detection strategy selected from the candidate liveness detection strategies.

[0072] In one embodiment, the liveness detection server can randomly select a target liveness detection strategy from the candidate liveness detection strategies according to the traffic distribution ratio of the candidate liveness detection strategies.

[0073] For example, if the diversion ratio of candidate liveness detection strategy a corresponding to the target risk assessment result is 30%, and the diversion ratio of candidate liveness detection strategy b corresponding to the target risk assessment result is 70%, then with a diversion ratio of 30% for candidate liveness detection strategy a and 70% for candidate liveness detection strategy b, one liveness detection strategy is randomly selected from candidate liveness detection strategy a and candidate liveness detection strategy b according to the ratio as the target liveness detection strategy.

[0074] Step 208: Perform liveness detection on the image of the object to be detected according to the target liveness detection strategy.

[0075] Among them, the image to be detected is the image obtained by image acquisition of the object to be detected during the liveness detection stage.

[0076] In one embodiment, the terminal used by the object to be detected can acquire an image of the object to be detected, obtain an image to be detected, and send the image to be detected to a liveness detection server. The liveness detection server can perform liveness detection on the image to be detected of the object to be detected according to the target liveness detection strategy.

[0077] In one embodiment, the liveness detection server can send the selected target liveness detection strategy to the terminal, the terminal can load the software development kit (SDK) of the target liveness detection strategy, the terminal can perform front-end liveness detection on the image to be detected based on the software development kit, and the liveness detection server can perform back-end liveness detection on the image to be detected.

[0078] The aforementioned liveness detection method obtains the target risk assessment result of the object to be detected, determines the triage ratio of candidate liveness detection strategies corresponding to the target risk assessment result, selects the target liveness detection strategy from the candidate liveness detection strategies based on the triage ratio, and performs liveness detection on the image of the object to be detected according to the target liveness detection strategy. This method can selectively choose appropriate liveness detection strategies based on the risk assessment result of the object to be detected, thereby enabling adaptive liveness detection for objects with different risk profiles, improving applicability and reducing limitations. Furthermore, it avoids the problem of low liveness detection conversion rates caused by uniformly adopting highly secure liveness detection strategies, improving the conversion rate of liveness detection while ensuring safety.

[0079] In one embodiment, determining the traffic splitting ratio of candidate liveness detection strategies corresponding to the target risk assessment result includes: obtaining the version information of the application client used by the object; determining the traffic splitting ratio of liveness detection strategies corresponding to different risk assessment results under the version information; and determining the traffic splitting ratio of candidate liveness detection strategies corresponding to the target risk assessment result from the traffic splitting ratio under the version information.

[0080] The application client is set in the terminal used by the object.

[0081] In one embodiment, the version information can be the application client's version identifier, such as the version number.

[0082] In one embodiment, the correspondence between risk assessment results and liveness detection strategies, as well as the traffic allocation ratio of liveness detection strategies corresponding to each risk assessment result, can be pre-configured for different versions of information.

[0083] In one embodiment, a liveness detection configuration package can be pre-established. The liveness detection server can obtain the version information of the application client used by the object, determine the traffic allocation ratio of the liveness detection strategy corresponding to different risk assessment results under that version information from the liveness detection configuration package, and then determine the traffic allocation ratio of the candidate liveness detection strategy corresponding to the target risk assessment result from the traffic allocation ratio under the version information. The liveness detection configuration package contains the correspondence between risk assessment results and liveness detection strategies under different version information, as well as the traffic allocation ratio of the liveness detection strategy corresponding to each risk assessment result.

[0084] In the above embodiments, the diversion ratio of the candidate liveness detection strategy corresponding to the target risk assessment result can be determined under the version information of the application client used by the object. Targeted configurations have been made for different version information, which is more flexible, improves the applicability to different versions of application clients, and reduces limitations.

[0085] In one embodiment, the object to be detected for liveness detection is an object requesting to process a service; the method further includes: determining a corresponding liveness detection configuration package based on at least one of the processing channel for requesting to process the service and the service type of the service to be processed; the liveness detection configuration package contains the correspondence between risk assessment results and liveness detection strategies, as well as the diversion ratio of the liveness detection strategy corresponding to each risk assessment result; determining the diversion ratio of the candidate liveness detection strategy corresponding to the target risk assessment result includes: determining the candidate liveness detection strategy corresponding to the target risk assessment result based on the correspondence between risk assessment results and liveness detection strategies in the liveness detection configuration package; and determining the diversion ratio of the candidate liveness detection strategy corresponding to the target risk assessment result from the liveness detection configuration package.

[0086] Among them, the processing channel is the tool used to request the processing of business.

[0087] In one embodiment, the processing channel can be any of an application (app), a mini-program, or a webpage.

[0088] In one embodiment, the business type can be any of the following: login, transaction, or modification of login credentials. Login credentials can be any of the following: mobile phone number, email address, or username. Transaction can be any of the following: payment or loan.

[0089] In one embodiment, liveness detection configuration packages can be pre-configured for at least one of different processing channels and business types. The liveness detection server can determine the corresponding liveness detection configuration package based on at least one of the processing channel requesting the service and the business type of the service to be processed.

[0090] For example, if the business type is a loan and the processing channel is an app, then the liveness detection server can determine the liveness detection configuration package corresponding to the loan and the app, that is, Figure 3 The "Loan App Tiered Package" is used to determine the diversion ratio of candidate liveness detection strategies corresponding to the target risk assessment results based on the liveness detection configuration package.

[0091] In the above embodiments, a corresponding liveness detection configuration package is determined based on at least one of the processing channel for the requested business and the business type of the business to be processed. Then, the diversion ratio of the candidate liveness detection strategy corresponding to the target risk assessment result is determined based on the liveness detection configuration package. This can improve the applicability to different processing channels and business types and reduce limitations.

[0092] In one embodiment, the method further includes: acquiring at least one of the historical behavior information of the object to be detected, environmental information of the device used by the object, and device information; and performing a risk assessment based on at least one of the historical behavior information, environmental information, and device information to obtain the target risk assessment result of the object.

[0093] Among these, historical behavior information refers to information about the past behavior of the object to be detected. Environmental information refers to information about the environment in which the device used by the object exists. Device information refers to information about the device itself used by the object. The device used by the object refers to the terminal used by the object.

[0094] In one embodiment, historical behavior information may include at least one of historical operation information and historical transaction information.

[0095] In one embodiment, environmental information may include at least one of IP address, location information, time information, and network information.

[0096] In one embodiment, device information may include at least one of device identifier, device model, and application client version information.

[0097] In one embodiment, the risk control server can obtain at least one of the following: historical behavior information of the object to be detected, environmental information of the device used by the object, and device information. It then sends this information to the risk calculation server. The risk calculation server can perform a risk assessment based on at least one of the historical behavior information, environmental information, and device information to obtain the target risk assessment result for the object. The target risk assessment result is then returned to the risk control server, which can send the target risk assessment result to the liveness detection server. The liveness detection server can then execute step 204 based on the target risk assessment result.

[0098] In one embodiment, the terminal used by the object can send at least one of environmental information and device information to the liveness detection server, which in turn can send at least one of the environmental information and device information to the risk control server. The risk control server can obtain the object's historical behavior information from the client system server. The risk control server can then send at least one of the environmental information, device information, and historical behavior information to the risk calculation server.

[0099] In the above embodiments, risk assessment based on at least one of historical behavior information, environmental information, and equipment information can more accurately obtain the target risk assessment results for the object.

[0100] Figure 6 This is a schematic diagram of the overall process of the liveness detection method in the above embodiments. When a user enters the liveness detection component of the terminal, the terminal sends environmental and device information to the liveness detection server. The liveness detection server sends the face pre-screening event to the risk control server and also transmits the environmental and device information to the risk control server. The risk control server obtains historical behavior information, environmental information, and device information and sends them to the risk calculation server. The risk calculation server performs a risk assessment, obtains the target risk assessment result, and sends it to the risk control server. The risk control server can return the risk control result code and the risk assessment result to the liveness detection server. The liveness detection server obtains the corresponding traffic splitting ratio based on the risk assessment result. Based on the traffic splitting ratio and client version information, it outputs the target liveness detection strategy and sends it to the terminal and the risk control server. The terminal can load the SDK corresponding to the target liveness detection strategy.

[0101] In one embodiment, risk assessment based on at least one of historical behavior information, environmental information, and equipment information to obtain the target risk assessment result of the object includes: determining the anomaly of at least one of the object's historical behavior, equipment, and historical behavior results based on at least one of historical behavior information, environmental information, and equipment information to obtain an anomaly determination result; if the anomaly determination result indicates that at least one of the object's historical behavior, equipment, and historical behavior results is abnormal, then the target risk assessment result of the object is determined to be of a high-risk level.

[0102] In one embodiment, the abnormality of the device includes at least one of the following: abnormal device information and high-risk business type.

[0103] In one embodiment, anomalies in historical behavior results include at least one of historical identity verification failures and historical business failures.

[0104] In the above embodiments, if at least one of the object's historical behavior, equipment, and historical behavior results is abnormal, the target risk assessment result of the object is determined to be of a high-risk level, thus accurately determining the target risk assessment result of the object.

[0105] In one embodiment, the risk assessment based on at least one of historical behavior information, environmental information, and equipment information to obtain the target risk assessment result of the object further includes: if the anomaly determination result indicates that the object's historical behavior, equipment, and historical behavior results are all normal and there is safety information, then the target risk assessment result of the object is determined to be a low-risk level.

[0106] In one embodiment, "device normal" includes at least one of "device information normal" and "normal business type".

[0107] In one embodiment, a normal historical behavior result includes at least one of historical identity verification success and historical business success.

[0108] In one embodiment, the security information includes at least one of device information security and security business type. Device information security refers to the device's past security history. For example, if a device has passed a liveness detection test in the past, then its device information is secure. Security business type refers to a business type that is secure. For example, if a business type involves a manual verification step, then that business type is secure.

[0109] In one embodiment, the risk assessment result may include a high-risk level, a medium-risk level, and a low-risk level. If the target risk assessment result of the object is neither a high-risk level nor a low-risk level, then the target risk assessment result of the object is determined to be a medium-risk level. In one embodiment, if the anomaly determination result indicates that the object's historical behavior, equipment, and historical behavior results are all normal, and there is no safety information, then the target risk assessment result of the object is determined to be a medium-risk level.

[0110] In the above embodiments, if the anomaly determination result indicates that the object's historical behavior, equipment, and historical behavior results are all normal and there is security information, then the target risk assessment result of the object is determined to be low risk level, and the target risk assessment result of the object can be accurately determined.

[0111] In one embodiment, the method further includes: determining the diversion ratio of candidate face matching strategies corresponding to the target liveness detection strategy; the diversion ratio of candidate face matching strategies is the probability of a pre-configured candidate face matching strategy being selected; selecting a target face matching strategy from the candidate face matching strategies according to the diversion ratio of the candidate face matching strategies; the target face matching strategy is used to perform face matching processing on the face image of the object after liveness detection is completed.

[0112] Different face comparison strategies can come from different face comparison vendors.

[0113] In one embodiment, the correspondence between the liveness detection strategy and the face comparison strategy, as well as the diversion ratio of the face comparison strategy corresponding to the liveness detection strategy, can be pre-configured.

[0114] In one embodiment, a face comparison configuration package can be pre-configured, which includes the correspondence between liveness detection strategies and face comparison strategies, as well as the traffic splitting ratio of the face comparison strategies corresponding to the liveness detection strategies.

[0115] In one embodiment, the liveness detection server can determine the candidate face comparison strategy corresponding to the target liveness detection strategy based on the correspondence between the liveness detection strategy and the face comparison strategy, and determine the diversion ratio of the candidate face comparison strategy corresponding to the target liveness detection strategy based on the diversion ratio of the face comparison strategy corresponding to the liveness detection strategy.

[0116] In one embodiment, the liveness detection server can randomly select the target face comparison strategy from the candidate face comparison strategies according to the diversion ratio of the candidate face comparison strategies.

[0117] For example: Figure 4In the diagram, the diversion ratio of vendor A's flash liveness strategy to vendor C or vendor A's active face matching strategy is 50%, and the diversion ratio of vendor D's active face matching strategy is also 50%. Therefore, when selecting an active face matching strategy corresponding to vendor A's flash liveness strategy, there is a 50% probability of selecting vendor C or vendor A's active face matching strategy, and a 50% probability of selecting vendor D's active face matching strategy. Similarly, in the diagram, the diversion ratio of vendor A's flash liveness strategy to vendor A's passive face matching strategy is 50%, and the diversion ratio of vendor B's passive face matching strategy is also 50%. Therefore, when selecting a passive face matching strategy corresponding to vendor A's flash liveness strategy, there is a 50% probability of selecting vendor A's passive face matching strategy, and a 50% probability of selecting vendor B's passive face matching strategy.

[0118] In one embodiment, the terminal can collect the face image of the object, and the face comparison server can perform face comparison processing on the face image of the object according to the target face comparison strategy after the liveness detection is completed.

[0119] In one embodiment, the liveness detection server can determine the corresponding face comparison configuration package based on the processing channel and business type, and then determine the diversion ratio of the candidate face comparison strategy corresponding to the target liveness detection strategy based on the determined face comparison configuration package.

[0120] like Figure 5 The diagram shows the process of face comparison. After the liveness detection is passed, the corresponding face comparison configuration package is determined according to the processing channel and business type. Then, the target face comparison strategy is selected from the face comparison configuration package according to the target liveness detection strategy. Finally, face comparison is performed according to the target face comparison strategy.

[0121] In the above embodiments, the diversion ratio of the candidate face comparison strategy corresponding to the target liveness detection strategy is determined. Based on the diversion ratio of the candidate face comparison strategy, the target face comparison strategy is selected from the candidate face comparison strategies. This allows the target face comparison strategy to be used to perform face comparison processing on the object's face image after liveness detection is completed, making the liveness detection strategy and face comparison strategy more compatible, thereby improving the pass rate and reducing costs.

[0122] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0123] Based on the same inventive concept, this application also provides a liveness detection system for implementing the liveness detection method described above. The solution provided by this system is similar to the implementation described in the above method; therefore, the specific limitations of one or more liveness detection system embodiments provided below can be found in the limitations of the liveness detection method described above, and will not be repeated here.

[0124] In one embodiment, such as Figure 7 As shown, a liveness detection system 700 is provided, including: a risk control server 702, a risk calculation server 704, a liveness detection server 706, and a terminal 708, wherein:

[0125] Risk calculation server 704 is used to determine the target risk assessment result of the object to be detected and send the target risk assessment result to the risk control server.

[0126] Risk control server 702 is used to send the target risk assessment results to the liveness detection server.

[0127] The liveness detection server 706 is used to obtain the target risk assessment result of the object to be detected; determine the diversion ratio of the candidate liveness detection strategies corresponding to the target risk assessment result; select the target liveness detection strategy from the candidate liveness detection strategies according to the diversion ratio of the candidate liveness detection strategies; the diversion ratio of the candidate liveness detection strategies is the probability of a pre-configured candidate liveness detection strategy being selected.

[0128] Terminal 708 is used to acquire the image of the object to be detected and send it to the liveness detection server.

[0129] The liveness detection server 706 is also used to perform liveness detection on the image to be detected according to the target liveness detection strategy.

[0130] In one embodiment, the liveness detection server 706 is further configured to obtain the version information of the application client used by the object; determine the traffic splitting ratio of the liveness detection strategy corresponding to different risk assessment results under the version information; and determine the traffic splitting ratio of the candidate liveness detection strategy corresponding to the target risk assessment result from the traffic splitting ratio under the version information.

[0131] In one embodiment, the object to be detected as a liveness detection device is an object requesting to process a service; the liveness detection server 706 is further configured to determine a corresponding liveness detection configuration package based on at least one of the processing channel of the requested service and the service type of the service to be processed; the liveness detection configuration package includes the correspondence between risk assessment results and liveness detection strategies, as well as the traffic allocation ratio of the liveness detection strategy corresponding to each risk assessment result; based on the correspondence between risk assessment results and liveness detection strategies in the liveness detection configuration package, the candidate liveness detection strategy corresponding to the target risk assessment result is determined; and the traffic allocation ratio of the candidate liveness detection strategy corresponding to the target risk assessment result is determined from the liveness detection configuration package.

[0132] In one embodiment, the risk control server 702 is further configured to acquire at least one of the historical behavior information of the object to be detected, the environmental information of the device used by the object, and the device information, and send them to the risk server.

[0133] The risk calculation server 704 is also used to perform risk assessment based on at least one of historical behavior information, environmental information, and equipment information to obtain the target risk assessment result of the object.

[0134] In one embodiment, the risk calculation server 704 is further configured to determine the anomaly of at least one of the object's historical behavior, equipment, and historical behavior results based on at least one of historical behavior information, environmental information, and equipment information, and obtain an anomaly determination result; if the anomaly determination result indicates that at least one of the object's historical behavior, equipment, and historical behavior results is abnormal, then the target risk assessment result of the object is determined to be of a high-risk level.

[0135] In one embodiment, the risk calculation server 704 is further configured to determine the target risk assessment result of the object as low risk level if the anomaly determination result indicates that the object's historical behavior, equipment and historical behavior results are all normal and there is security information.

[0136] In one embodiment, such as Figure 8 As shown, system 700 also includes: face comparison server 710, wherein:

[0137] The liveness detection server 706 is also used to determine the diversion ratio of the candidate face matching strategy corresponding to the target liveness detection strategy; the diversion ratio of the candidate face matching strategy is the probability of a pre-configured candidate face matching strategy being selected; and the target face matching strategy is selected from the candidate face matching strategies according to the diversion ratio of the candidate face matching strategies.

[0138] Terminal 708 is also used to collect facial images of the subject.

[0139] The face comparison server 710 is also used to perform face comparison processing on the face image of the object according to the target face comparison strategy after the liveness detection is completed.

[0140] The aforementioned liveness detection system acquires the target risk assessment results of the object to be detected, determines the triage ratio of candidate liveness detection strategies corresponding to the target risk assessment results, selects the target liveness detection strategy from the candidate strategies based on the triage ratio, and performs liveness detection on the image of the object to be detected according to the target liveness detection strategy. This allows for targeted selection of appropriate liveness detection strategies based on the risk assessment results of the object to be detected, thereby enabling adaptive liveness detection for objects with different risk profiles, improving applicability and reducing limitations. Furthermore, it avoids the problem of low liveness detection conversion rates caused by uniformly adopting highly secure liveness detection strategies, improving the conversion rate of liveness detection while ensuring safety.

[0141] Based on the same inventive concept, this application also provides a liveness detection device for implementing the liveness detection method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the liveness detection device provided below can be found in the limitations of the liveness detection method described above, and will not be repeated here.

[0142] In one embodiment, such as Figure 9 As shown, a liveness detection device 900 is provided, including: an acquisition module 902, a liveness strategy determination module 904, and a liveness detection module 906, wherein:

[0143] The acquisition module 902 is used to acquire the target risk assessment results of the object to be detected in a live body.

[0144] The liveness detection strategy determination module 904 is used to determine the diversion ratio of candidate liveness detection strategies corresponding to the target risk assessment results; the diversion ratio of candidate liveness detection strategies is the probability of a pre-configured candidate liveness detection strategy being selected; and the target liveness detection strategy is selected from the candidate liveness detection strategies according to the diversion ratio of candidate liveness detection strategies.

[0145] The liveness detection module 906 is used to perform liveness detection on the image of the object to be detected according to the target liveness detection strategy.

[0146] In one embodiment, the liveness policy determination module 904 is further configured to obtain the version information of the application client used by the object; determine the diversion ratio of the liveness detection strategy corresponding to different risk assessment results under the version information; and determine the diversion ratio of the candidate liveness detection strategy corresponding to the target risk assessment result from the diversion ratio under the version information.

[0147] In one embodiment, the object to be detected for liveness detection is the object requesting to process a service; the liveness strategy determination module 904 is further configured to determine a corresponding liveness detection configuration package based on at least one of the processing channel of the requested service and the service type of the service to be processed; the liveness detection configuration package contains the correspondence between risk assessment results and liveness detection strategies, as well as the diversion ratio of the liveness detection strategy corresponding to each risk assessment result; based on the correspondence between risk assessment results and liveness detection strategies in the liveness detection configuration package, the candidate liveness detection strategy corresponding to the target risk assessment result is determined; from the liveness detection configuration package, the diversion ratio of the candidate liveness detection strategy corresponding to the target risk assessment result is determined.

[0148] In one embodiment, such as Figure 10 As shown, the device 900 also includes:

[0149] The risk assessment module 908 is used to acquire at least one of the following: historical behavior information of the object to be detected, environmental information of the equipment used by the object, and equipment information; and to conduct a risk assessment based on at least one of the historical behavior information, environmental information, and equipment information to obtain the target risk assessment result of the object.

[0150] In one embodiment, the risk assessment module 908 is further configured to determine the anomaly of at least one of the object's historical behavior, equipment, and historical behavior results based on at least one of historical behavior information, environmental information, and equipment information, and obtain an anomaly determination result; if the anomaly determination result indicates that at least one of the object's historical behavior, equipment, and historical behavior results is abnormal, then the target risk assessment result of the object is determined to be of a high-risk level.

[0151] In one embodiment, the risk assessment module 908 is further configured to determine the target risk assessment result of the object as low risk level if the anomaly determination result indicates that the object's historical behavior, equipment and historical behavior results are all normal and there is safety information.

[0152] In one embodiment, such as Figure 10 As shown, the device 900 also includes:

[0153] The face comparison strategy determination module 910 is used to determine the diversion ratio of candidate face comparison strategies corresponding to the target liveness detection strategy; the diversion ratio of candidate face comparison strategies is the probability of a pre-configured candidate face comparison strategy being selected; based on the diversion ratio of candidate face comparison strategies, the target face comparison strategy is selected from the candidate face comparison strategies; the target face comparison strategy is used to perform face comparison processing on the face image of the object after liveness detection is completed.

[0154] The aforementioned liveness detection device acquires the target risk assessment results of the object to be detected, determines the triage ratio of candidate liveness detection strategies corresponding to the target risk assessment results, selects a target liveness detection strategy from the candidate strategies based on the triage ratio, and performs liveness detection on the image of the object to be detected according to the target liveness detection strategy. This allows for targeted selection of appropriate liveness detection strategies based on the risk assessment results of the object to be detected, thereby enabling adaptive liveness detection for objects with different risk profiles, improving applicability and reducing limitations. Furthermore, it avoids the problem of low liveness detection conversion rates caused by uniformly adopting highly secure liveness detection strategies, improving the conversion rate of liveness detection while ensuring safety.

[0155] Each module in the aforementioned liveness detection device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0156] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 11 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores data. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a liveness detection method.

[0157] Those skilled in the art will understand that Figure 11The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0158] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0159] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0160] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0161] It should be noted that the object information (including but not limited to object device information, object personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the object or fully authorized by all parties.

[0162] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0163] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0164] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for detecting liveness, characterized in that, The method includes: Obtain the target risk assessment results for the subjects to be tested in vivo; Determine the triage ratio of the candidate liveness detection strategies corresponding to the target risk assessment results; the triage ratio of the candidate liveness detection strategies is the pre-configured probability of the candidate liveness detection strategy being selected; If the diversion ratio corresponding to the target risk assessment result is not 100%, a target liveness detection strategy is randomly selected from the candidate liveness detection strategies according to the diversion ratio of the candidate liveness detection strategies; if the diversion ratio is 100%, a target liveness detection strategy with a diversion ratio of 100% is selected from the candidate liveness detection strategies. Liveness detection is performed on the image of the object to be detected according to the target liveness detection strategy.

2. The method according to claim 1, characterized in that, The process of determining the triage ratio of candidate liveness detection strategies corresponding to the target risk assessment result includes: Obtain the version information of the application client used by the object; Determine the triage ratio of the liveness detection strategy corresponding to different risk assessment results under the aforementioned version information; From the diversion ratios under the version information, determine the diversion ratio of the candidate liveness detection strategy corresponding to the target risk assessment result.

3. The method according to claim 1, characterized in that, The object to be detected as a liveness test is the object requesting service; the method further includes: Based on at least one of the processing channels for the requested business and the business type of the business to be processed, a corresponding liveness detection configuration package is determined; the liveness detection configuration package includes the correspondence between risk assessment results and liveness detection strategies, as well as the diversion ratio of the liveness detection strategy corresponding to each risk assessment result; The process of determining the triage ratio of candidate liveness detection strategies corresponding to the target risk assessment result includes: Based on the correspondence between the risk assessment results and the liveness detection strategies in the liveness detection configuration package, the candidate liveness detection strategies corresponding to the target risk assessment results are determined. From the liveness detection configuration package, determine the triage ratio of the candidate liveness detection strategies corresponding to the target risk assessment results.

4. The method according to claim 1, characterized in that, The method further includes: Acquire at least one of the following: historical behavior information of the object to be detected as a liveness detection subject, environmental information of the device used by the object, and device information; A risk assessment is performed based on at least one of the historical behavior information, the environmental information, and the equipment information to obtain the target risk assessment result for the object.

5. The method according to claim 4, characterized in that, The step of performing a risk assessment based on at least one of the historical behavior information, the environmental information, and the equipment information to obtain the target risk assessment result for the object includes: Based on at least one of the historical behavior information, the environmental information, and the device information, an anomaly determination is made on at least one of the historical behavior, device, and historical behavior results of the object to obtain an anomaly determination result; If the anomaly determination result indicates that at least one of the object's historical behavior, equipment, and historical behavior results is abnormal, then the target risk assessment result of the object is determined to be of a high-risk level.

6. The method according to claim 5, characterized in that, The step of conducting a risk assessment based on at least one of the historical behavior information, the environmental information, and the equipment information to obtain the target risk assessment result for the object further includes: If the anomaly determination result indicates that the object's historical behavior, equipment, and historical behavior results are all normal and that there is security information, then the target risk assessment result of the object is determined to be low risk level.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: Determine the diversion ratio of the candidate face matching strategy corresponding to the target liveness detection strategy; the diversion ratio of the candidate face matching strategy is the pre-configured probability of the candidate face matching strategy being selected. Based on the diversion ratio of the candidate face comparison strategy, a target face comparison strategy is selected from the candidate face comparison strategies; the target face comparison strategy is used to perform face comparison processing on the face image of the object after liveness detection is completed.

8. A liveness detection system, characterized in that, The system includes a risk control server, a risk calculation server, a liveness detection server, and a terminal; wherein: The risk calculation server is used to determine the target risk assessment result of the object to be detected, and send the target risk assessment result to the risk control server. The risk control server is used to send the target risk assessment results to the liveness detection server; The liveness detection server is configured to: acquire the target risk assessment result of the object to be detected; determine the traffic allocation ratio of the candidate liveness detection strategies corresponding to the target risk assessment result; when the traffic allocation ratio corresponding to the target risk assessment result is not 100%, randomly select a target liveness detection strategy from the candidate liveness detection strategies according to the traffic allocation ratio of the candidate liveness detection strategies; when the traffic allocation ratio is 100%, select a target liveness detection strategy with a traffic allocation ratio of 100% from the candidate liveness detection strategies; the traffic allocation ratio of the candidate liveness detection strategy is a pre-configured probability of the candidate liveness detection strategy being selected. The terminal is used to acquire the image of the object to be detected and send it to the liveness detection server. The liveness detection server is also used to perform liveness detection on the image to be detected according to the target liveness detection strategy.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images