Method, device and electronic device for optimizing shooting parameters for identity verification

By using predictive models of behavioral feature data and initial shooting parameters in financial online identity authentication, the shooting parameters are optimized, and the problem of user failures is solved, which improves the success rate and user experience of identity verification.

CN112183270BActive Publication Date: 2024-11-08ZOLOZ PTE LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010986190.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-09-18
Publication Date
2024-11-08
Estimated Expiration
2040-09-18

AI Technical Summary

Technical Problem

During the online identity verification process in the financial field, users failed multiple shots due to image quality issues, which affected the user experience and authentication success rate.

Method used

By obtaining user behavioral characteristic data and initial shooting parameters, input them into the prediction model, and optimizing shooting parameters to improve the authentication success rate, including the prediction model of document quality threshold, face quality threshold and comparison threshold.

Benefits of technology

Improve the pass rate and user experience of identity verification, and optimize parameters through machine learning to improve the quality of the identity verification process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112183270B_ABST
    Figure CN112183270B_ABST
Patent Text Reader

Abstract

The embodiments of this specification disclose a method, device and electronic device for optimizing shooting parameters for identity authentication. The method includes: obtaining a face image of a target user and an ID image of the target user; based on the face image of the target user and the ID image of the target user, authenticating the target user; if the identity authentication of the target user fails based on the face image and the ID image of the target user, obtaining the behavior feature data of the target user within a preset time period and the first shooting parameter when the target user authenticates the identity; inputting the behavior feature data of the target user and the first shooting parameter into a prediction model of multiple parameters, and outputting target shooting parameters that match the behavior feature data of the target user and the first shooting parameter, respectively.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This document relates to the field of computer technology, and in particular to a method, device and electronic device for optimizing shooting parameters for identity authentication. Background Art

[0002] At present, in the financial field, more and more financial companies or institutions choose online identity verification to verify the identity of users and prove that "you are you". This type of verification method uses the method of photographing the user's ID card and collecting the user's facial image for matching verification to verify whether the face in the user's facial image is consistent with the face on the user's ID card, and whether the user's ID card is a real document, thereby proving that "you are you". This type of product is also called the electronic Know Your Customer (eKYC) system.

[0003] In actual application, eKYC usually requires users to take photos of their ID cards and collect their facial images. However, when taking photos of their ID cards, users often find it difficult to take photos of their ID cards and facial images with good image quality at one time due to subjective (user proficiency) or objective (light, environmental influence) reasons. In this case, users are required to take photos of their ID cards and facial images multiple times until they take photos with image quality that meets the system's recognition capabilities. In this process, if users take photos of their ID cards and facial images multiple times but fail, user identity verification will fail, which will affect the user experience. Summary of the invention

[0004] The purpose of the embodiments of this specification is to provide a method, device and electronic device for optimizing shooting parameters for identity authentication, so as to solve the problem in the prior art that when a user authenticates his / her identity, his / her identity authentication usually fails due to the user taking photos of his / her identification document and face image multiple times, thus affecting the user experience.

[0005] To solve the above technical problems, the embodiments of this specification are implemented as follows:

[0006] In the first aspect, a method for optimizing shooting parameters for identity authentication is proposed, including:

[0007] Obtaining a face image of a target user and an ID image of the target user;

[0008] Performing identity authentication on the target user based on the face image of the target user and the ID image of the target user;

[0009] If the identity authentication of the target user fails based on the face image and the ID image of the target user, then obtaining the behavior feature data of the target user within a preset time period and the first shooting parameter of the target user when performing identity authentication;

[0010] Inputting the behavior characteristic data of the target user and the first shooting parameter into a prediction model of multiple parameters, and outputting target shooting parameters matching the behavior characteristic data of the target user and the first shooting parameter respectively, so as to optimize the shooting parameters of the target user when performing identity authentication based on the target shooting parameters;

[0011] Among them, the prediction models of the multiple parameters include at least a prediction model for the document quality threshold, a prediction model for the face quality threshold and a prediction model for the comparison threshold between the document image and the face image; the prediction model of the target parameter is obtained by training with the parameter value of the target parameter during multiple identity authentications as a label and with other parameters among the multiple parameters except the target parameter as features, and the target parameter is any one of the multiple parameters.

[0012] In a second aspect, a device for optimizing shooting parameters for identity authentication is proposed, comprising:

[0013] An image acquisition module, which acquires a face image of a target user and an ID image of the target user;

[0014] An identity verification module, for verifying the identity of the target user based on a face image of the target user and an ID image of the target user;

[0015] a parameter acquisition module, which acquires the behavior characteristic data of the target user within a preset time period and the first shooting parameter of the target user when performing identity authentication if the identity authentication of the target user fails based on the face image and the ID image of the target user;

[0016] a parameter prediction module, inputting the behavior characteristic data of the target user and the first shooting parameter into a prediction model of multiple parameters, and outputting target shooting parameters that match the behavior characteristic data of the target user and the first shooting parameter, respectively, so as to optimize the shooting parameters of the target user when performing identity authentication based on the target shooting parameters;

[0017] Among them, the prediction models of the multiple parameters include at least a prediction model for the document quality threshold, a prediction model for the face quality threshold and a prediction model for the comparison threshold between the document image and the face image; the prediction model of the target parameter is obtained by training with the parameter value of the target parameter during multiple identity authentications as a label and with other parameters among the multiple parameters except the target parameter as features, and the target parameter is any one of the multiple parameters.

[0018] In a third aspect, an electronic device is provided, the electronic device comprising:

[0019] Processor; and

[0020] a memory arranged to store computer executable instructions which, when executed, cause the processor to:

[0021] Obtaining a face image of a target user and an ID image of the target user;

[0022] Performing identity authentication on the target user based on the face image of the target user and the ID image of the target user;

[0023] If the identity authentication of the target user fails based on the face image and the ID image of the target user, then obtaining the behavior feature data of the target user within a preset time period and the first shooting parameter of the target user when performing identity authentication;

[0024] Inputting the behavior characteristic data of the target user and the first shooting parameter into a prediction model of multiple parameters, and outputting target shooting parameters matching the behavior characteristic data of the target user and the first shooting parameter respectively, so as to optimize the shooting parameters of the target user when performing identity authentication based on the target shooting parameters;

[0025] Among them, the prediction models of the multiple parameters include at least a prediction model for the document quality threshold, a prediction model for the face quality threshold and a prediction model for the comparison threshold between the document image and the face image; the prediction model of the target parameter is obtained by training with the parameter value of the target parameter during multiple identity authentications as a label and with other parameters among the multiple parameters except the target parameter as features, and the target parameter is any one of the multiple parameters.

[0026] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by an electronic device including a plurality of application programs, the electronic device performs the following operations:

[0027] Obtaining a face image of a target user and an ID image of the target user;

[0028] Performing identity authentication on the target user based on the face image of the target user and the ID image of the target user;

[0029] If the identity authentication of the target user fails based on the face image and the ID image of the target user, then obtaining the behavior feature data of the target user within a preset time period and the first shooting parameter of the target user when performing identity authentication;

[0030] Inputting the behavior characteristic data of the target user and the first shooting parameter into a prediction model of multiple parameters, and outputting target shooting parameters matching the behavior characteristic data of the target user and the first shooting parameter respectively, so as to optimize the shooting parameters of the target user when performing identity authentication based on the target shooting parameters;

[0031] Among them, the prediction models of the multiple parameters include at least a prediction model for the document quality threshold, a prediction model for the face quality threshold and a prediction model for the comparison threshold between the document image and the face image; the prediction model of the target parameter is obtained by training with the parameter value of the target parameter during multiple identity authentications as a label and with other parameters among the multiple parameters except the target parameter as features, and the target parameter is any one of the multiple parameters.

[0032] The embodiments of this specification adopt the above technical solutions to achieve at least the following technical effects:

[0033] By adopting the method provided in the embodiments of the present specification, when authenticating a user, a facial image of the target user and an ID image of the target user can be obtained; and based on the facial image of the target user and the ID image of the target user, the target user is authenticated; if the identity authentication of the target user fails based on the facial image and the ID image of the target user, the behavior characteristic data of the target user within a preset time period and the first shooting parameters of the target user when authenticating the user are obtained; finally, the behavior characteristic data and the first shooting parameters of the target user are input into a prediction model of multiple parameters, and target shooting parameters that match the behavior characteristic data and the first shooting parameters of the target user are output respectively, so as to optimize the shooting parameters of the target user when authenticating the user based on the target shooting parameters.

[0034] Among them, the prediction models of multiple parameters at least include prediction models of document quality threshold, prediction models of face quality threshold and prediction models of comparison threshold between document image and face image; the prediction model of target parameter is obtained by training with parameter values ​​of target parameters during multiple identity authentication as labels and with other parameters other than target parameters in multiple parameters as features, and the target parameter is any one of the multiple parameters. Since it is possible to model the main parameter factors in the identity authentication process, prediction models of document quality threshold, face quality threshold and prediction models of comparison threshold between document image and face image are obtained, it is possible to predict the optimal values ​​of the main parameters in the identity authentication process in a machine learning manner, so that the main parameters in the identity authentication process can reach a state that is better for the user experience, thereby improving the pass rate of user identity authentication and the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The illustrative embodiments and descriptions of this specification are used to explain this document and do not constitute an improper limitation of this document. In the drawings:

[0036] Figure 1 A schematic diagram of an implementation flow of a method for optimizing shooting parameters for identity authentication provided by an embodiment of this specification;

[0037] Figure 2 A schematic diagram of the training process of each parameter model in the method for optimizing shooting parameters for identity authentication provided in one embodiment of this specification;

[0038] Figure 3 A flowchart of an optimization method for shooting parameters of identity authentication provided by an embodiment of this specification applied in an actual scenario;

[0039] Figure 4 A flowchart of an optimization method for shooting parameters of identity authentication provided by an embodiment of this specification applied in an actual scenario;

[0040] Figure 5 A schematic diagram of the structure of a device for optimizing shooting parameters for identity authentication provided by an embodiment of this specification;

[0041] Figure 6 A schematic diagram of the structure of an electronic device provided in one embodiment of this specification. DETAILED DESCRIPTION

[0042] 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 document, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this document.

[0043] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0044] In order to solve the problem in the prior art that when a user authenticates his / her identity, his / her identity authentication usually fails due to the user taking photos of his / her identity document and face image multiple times, which in turn affects the user experience, an embodiment of this specification provides an optimization method for the shooting parameters of identity authentication. By adopting the method provided in the embodiment of this specification, when authenticating a user, the face image of the target user and the ID image of the target user can be obtained; and based on the face image of the target user and the ID image of the target user, the target user is authenticated; if the identity authentication of the target user fails based on the face image and the ID image of the target user, the behavior characteristic data of the target user within a preset time period and the first shooting parameter of the target user when authenticating the target user are obtained; finally, the behavior characteristic data and the first shooting parameter of the target user are input into a prediction model of multiple parameters, and the target shooting parameters matching the behavior characteristic data and the first shooting parameter of the target user are output respectively, so as to optimize the shooting parameters of the target user when authenticating the target user based on the target shooting parameters.

[0045] Among them, the prediction models of multiple parameters at least include prediction models of document quality threshold, prediction models of face quality threshold and prediction models of comparison threshold between document image and face image; the prediction model of target parameter is obtained by training with parameter values ​​of target parameters during multiple identity authentication as labels and with other parameters other than target parameters in multiple parameters as features, and the target parameter is any one of the multiple parameters. Since it is possible to model the main parameter factors in the identity authentication process, prediction models of document quality threshold, face quality threshold and prediction models of comparison threshold between document image and face image are obtained, it is possible to predict the optimal values ​​of the main parameters in the identity authentication process in a machine learning manner, so that the main parameters in the identity authentication process can reach a state that is better for the user experience, thereby improving the pass rate of user identity authentication and the user experience.

[0046] The execution subject of the method for optimizing shooting parameters for identity authentication provided in the embodiments of this specification may be, but is not limited to, a terminal device, a server, a personal computer, etc., which can be configured to execute at least one of the terminals of the method provided in the embodiments of the present invention.

[0047] For ease of description, the following takes the method's execution subject as a terminal device capable of executing the method as an example to introduce the implementation of the method. It can be understood that the method's execution subject as a terminal device is only an exemplary description and should not be understood as a limitation on the method.

[0048] Specifically, a schematic diagram of an implementation flow of a method for optimizing shooting parameters for identity authentication provided in one or more embodiments of this specification is as follows: Figure 1 As shown, including:

[0049] S110, obtaining a face image of a target user and an ID image of the target user.

[0050] It should be understood that when the target user performs identity authentication, it is usually necessary to verify the authenticity of the target user's identity, that is, to prove that the target user has not been impersonated by others, and to protect the target user's legitimate rights and interests. The specific implementation method of identity authentication for the target user is usually to obtain the image of the certificate uploaded by the target user (such as an identity card, passport, etc. that can prove the user's identity) and the collected face image of the target user, and then determine whether the face in the face image of the target user is consistent with the face in the certificate image of the target user.

[0051] S120, performing identity authentication on the target user based on the face image of the target user and the ID image of the target user.

[0052] Based on the target user's facial image and the target user's ID image, the target user's identity is authenticated. Specifically, the face in the target user's facial image and the face in the target user's ID image can be obtained, and then it is determined whether the face in the target user's facial image and the face in the target user's ID image match (i.e., whether they are consistent), that is, whether the similarity is greater than or equal to a preset similarity threshold, such as whether the similarity reaches more than 80%. If the face in the target user's facial image and the face in the target user's ID image match, the target user's identity can be authenticated; if the face in the target user's facial image and the face in the target user's ID image do not match, it can be determined that the target user's identity authentication has failed.

[0053] S130, if the identity authentication of the target user fails based on the face image and the ID image of the target user, then obtain the behavior feature data of the target user within a preset time period and the first shooting parameter when the target user performs identity authentication.

[0054] It should be understood that in order to avoid the situation where the target user's face image and ID image collected multiple times do not match each other, resulting in multiple failures in the target user's identity authentication, thereby affecting the target user's user experience, the embodiment of this specification can set a preset threshold value, which is used to indicate that after the target user's identity authentication fails several times, it can trigger the acquisition of the target user's behavior feature data within a preset time period and the first shooting parameters when the target user performs identity authentication, and then enter the mode of optimizing the parameters when the target user performs identity authentication. Among them, the preset threshold value can be set to 1, or it can be set to an integer greater than 1. When the preset threshold value is set to 1, as long as it is determined that the target user's identity authentication fails, the mode of optimizing the parameters when the target user performs identity authentication can be entered.

[0055] Specifically, if the identity authentication of the target user fails based on the face image and the ID image of the target user, the behavior feature data of the target user within a preset time period and the first shooting parameter of the target user during the identity authentication are obtained, including:

[0056] If the number of failed identity authentications of the target user based on the target user's facial image and ID image is greater than or equal to a preset threshold, the target user's behavior feature data within a preset time period and the first shooting parameters of the target user during identity authentication are obtained.

[0057] S140, inputting the behavior characteristic data and the first shooting parameter of the target user into a prediction model of multiple parameters, and outputting target shooting parameters that match the behavior characteristic data and the first shooting parameter of the target user respectively, so as to optimize the shooting parameters when the target user performs identity authentication based on the target shooting parameters.

[0058] Among them, the prediction models of multiple parameters include at least a prediction model for the document quality threshold, a prediction model for the face quality threshold and a prediction model for the comparison threshold between the document image and the face image; the prediction model of the target parameter is obtained by training with the parameter value of the target parameter during multiple identity authentications as a label and with other parameters among the multiple parameters except the target parameter as features, and the target parameter is any one of the multiple parameters.

[0059] Among them, the face quality threshold is used to determine whether the quality of the collected face is qualified; the document quality threshold is used to determine whether the quality of the collected document image is qualified; the comparison threshold is used to determine whether the face in the document image is consistent with the face in the face image.

[0060] Specifically, the prediction model for the above-mentioned document quality threshold is obtained by taking the document quality threshold during multiple identity authentications as a label and training with parameters other than the document quality among multiple parameters as features; the prediction model for the face quality threshold is obtained by taking the face quality threshold during multiple identity authentications as a label and training with parameters other than the face quality threshold among multiple parameters as features; the prediction model for the comparison threshold between the document image and the face image is obtained by taking the comparison threshold between the document image and the face image during multiple identity authentications as a label and training with parameters other than the comparison threshold between the document image and the face image among multiple parameters as features.

[0061] Optionally, the prediction model of multiple parameters may further include at least one of the following:

[0062] A prediction model for screen brightness, where the prediction model for screen brightness is obtained by training using screen brightness values ​​during multiple identity authentications as labels and using other parameters among multiple parameters except screen brightness as features;

[0063] The prediction model of the copy is obtained by training with the copy during multiple identity verifications as labels and with other parameters of the multiple parameters except the copy as features;

[0064] A color style prediction model, where the color style prediction model is trained using the color styles during multiple identity authentications as labels and using other parameters among multiple parameters except the color style as features;

[0065] The prediction model of the certificate forgery threshold is obtained by training with the certificate forgery threshold during multiple identity authentications as a label and with other parameters among multiple parameters except the certificate forgery threshold as features.

[0066] Among them, the above-mentioned screen brightness is the screen brightness of the terminal used by the target user when performing identity authentication; the copy is specifically the copy used to guide the target user to complete identity authentication; the color style is the color style of the identity authentication page when the target user performs identity authentication; the document forgery threshold refers to the threshold that can determine that the target user's document image is forged when the target user performs identity authentication.

[0067] like Figure 2 As shown, it is a schematic diagram of the training process of each parameter model in the optimization method of the shooting parameters of the identity authentication provided by an embodiment of this specification. Figure 2 In the prediction model of multiple parameters ( Figure 2 The parameter model includes: the prediction model of screen brightness parameters ( Figure 2 Referred to as screen brightness model), copywriting prediction model ( Figure 2 The prediction model of the document quality threshold ( Figure 2The document quality threshold model), the prediction model of the comparison threshold ( Figure 2 Referred to as comparison threshold model), face quality threshold prediction model ( Figure 2 The face quality threshold model is referred to as face quality threshold model) and other parameter models (including but not limited to the prediction model of color style and the prediction model of document forgery threshold).

[0068] Taking the prediction model of screen brightness parameters as an example, the training process of the prediction model of screen brightness parameters may include: first, when collecting multiple identity authentications within a historical time period, all the parameters listed above (including environmental parameters) and user behavior data are used as features, the screen brightness of successful identity authentication within the historical time period is used as a label, and other parameters are used as features; then, based on the above multiple identity authentications, the screen brightness of successful identity authentication is used as a label, and other parameters (all parameters except the screen brightness parameter) are used as features to train a prediction model for screen brightness parameters (specifically, it can be a regression model).

[0069] The training process of the prediction model of other parameters is similar and will not be repeated here in the embodiments of this specification.

[0070] Optionally, in order to further improve the security level when the target user performs identity authentication, when optimizing the shooting parameters when the target user performs identity authentication, the embodiments of this specification may determine whether there is a security risk based on the target user's behavior characteristic data and the shooting parameters when the target user performs identity authentication. Specifically, the target user's behavior characteristic data and the first shooting parameter when the target user performs identity authentication are input into a prediction model of multiple parameters, and target shooting parameters matching the target user's behavior characteristic data and the first shooting parameter are output respectively, including:

[0071] Determine whether there is a security risk for the target user during identity authentication, where the security risk includes at least one of a security risk of the identity authentication device and a security risk of being attacked;

[0072] If there is no security risk for the target user during identity authentication, the behavior feature data and the first shooting parameter of the target user are input into a prediction model of multiple parameters, and target shooting parameters matching the behavior feature data and the first shooting parameter of the target user are output respectively.

[0073] Optionally, the behavior characteristic data of the target user and the first shooting parameter are input into a prediction model of multiple parameters, and target shooting parameters matching the behavior characteristic data of the target user and the first shooting parameter are output respectively, including:

[0074] Extracting a first document quality threshold, a first face quality threshold, a first comparison threshold between the first document quality and the first face quality, and an environmental parameter when the target user performs identity authentication from the behavior feature data of the target user and the first shooting parameter;

[0075] Inputting the first face quality threshold, the first comparison threshold and the environmental parameters into a prediction model of the document quality threshold, and outputting a target document quality threshold that matches the first face quality threshold and the first comparison threshold;

[0076] Inputting the first face quality threshold, the first comparison threshold and the environmental parameter into a prediction model of the face quality threshold, and outputting a target face quality threshold that matches the first face quality threshold and the first comparison threshold;

[0077] The first document quality threshold, the first face quality threshold and the environmental parameters are input into a prediction model of the comparison threshold, and a target comparison threshold matching the first document quality threshold and the first face quality threshold is output.

[0078] The environmental parameters include, but are not limited to, the ambient brightness, ambient pressure, ambient humidity, device temperature, time, and other parameters when the target user performs identity authentication.

[0079] Optionally, in order to improve the pass rate of identity authentication of the target user, after the behavior feature data and the first shooting parameter of the target user are input into a prediction model of multiple parameters and the target shooting parameters matching the behavior feature data and the first shooting parameter of the target user are output respectively, the method provided in the embodiment of this specification further includes:

[0080] According to the target shooting parameters, adjust the shooting parameters when the target user performs identity authentication;

[0081] After adjusting the shooting parameters for the target user to authenticate, a face image and a certificate image of the target user are obtained;

[0082] The target user's identity is authenticated based on the target user's face image and ID image after adjusting the shooting parameters.

[0083] Optionally, a parameter adjustment scheme can be generated by determining the difference between the current first shooting parameter value and the predicted preferred parameter value, and if the difference between the two exceeds a certain threshold, the current first shooting parameter value is adjusted, otherwise, no adjustment is required. In particular, the preferred parameter value can be an optimal parameter value.

[0084] Specifically, according to the target shooting parameters, the shooting parameters of the target user when performing identity authentication are adjusted, including:

[0085] Based on the target shooting parameter and the first shooting parameter, respectively determine a document quality difference between the first document quality threshold and the target document quality threshold, a face quality difference between the first face quality threshold and the target human quality threshold, and a comparison difference between the first comparison threshold and the target comparison threshold;

[0086] If the certificate quality difference is greater than or equal to the certificate quality threshold, the certificate quality threshold for identity authentication of the target user is adjusted according to the target certificate quality threshold;

[0087] If the face quality difference is greater than or equal to the face quality threshold, the face quality threshold for the target user to authenticate is adjusted according to the target face quality threshold;

[0088] If the comparison difference is greater than or equal to the comparison threshold, the comparison threshold for identity authentication of the target user is adjusted according to the target comparison threshold.

[0089] like Figure 3 and Figure 4 The figure is a flowchart of an optimization method for shooting parameters of identity authentication provided by an embodiment of the present specification, which is applied in an actual scenario.

[0090] in, Figure 3 A schematic diagram of a process for optimizing shooting parameters for identity authentication of a target user after the number of identity authentication failures of the target user is greater than or equal to a preset threshold in order to determine the process based on the face image and the ID image of the target user, including:

[0091] S1, collects in real time the ID image, face image, environmental parameters and other parameter data taken during the identity authentication of the target user in the historical time period, and records them in the parameter library;

[0092] S2, when the number of failed identity authentication of the target user exceeds the preset threshold, the parameter optimization process is triggered to start, and the recent behavior feature data of the target user is read;

[0093] S3, inputting the recent behavior feature data of the target user and the shooting parameters of the target user during identity authentication into the parameter model group for prediction, and obtaining a set of optimized parameter adjustment schemes;

[0094] S4, adjusting the shooting parameters of the target user during identity authentication according to the optimized parameter adjustment scheme, and guiding the target user to complete identity authentication again until the identity authentication is passed.

[0095] like Figure 4 As shown, it is a flowchart of a complete set of optimization methods for shooting parameters of identity authentication provided in an embodiment of this specification, which is applied to an actual scenario, including:

[0096] S41, when starting the parameter optimization process, determining whether there are security risks in the current environment, including the security of the device and the risk level of user attacks;

[0097] S42, if there is no security risk in the current environment, the parameter optimization process is started, all recent data are input into each parameter model in the parameter model, and the optimal value of each parameter in the current environment is predicted;

[0098] S43, determining the parameter to be adjusted by judging the difference between the actual value of the parameter under the current environment and the predicted preferred value of the parameter. Specifically, the parameter to be adjusted can be determined by comparing the ratio between the preferred value of the parameter and the actual value of the parameter;

[0099] S44, output parameter adjustment plan.

[0100] It should be understood that the preferred value of each parameter in the current environment in step S42 can be determined in a variety of ways, and the embodiments of this specification do not limit this. In particular, the preferred value of the parameter in the current environment can be the optimal value of the corresponding parameter.

[0101] By adopting the method provided in the embodiments of the present specification, when authenticating a user, a facial image of the target user and an ID image of the target user can be obtained; and based on the facial image of the target user and the ID image of the target user, the target user is authenticated; if the identity authentication of the target user fails based on the facial image and the ID image of the target user, the behavior characteristic data of the target user within a preset time period and the first shooting parameters of the target user when authenticating the user are obtained; finally, the behavior characteristic data and the first shooting parameters of the target user are input into a prediction model of multiple parameters, and target shooting parameters that match the behavior characteristic data and the first shooting parameters of the target user are output respectively, so as to optimize the shooting parameters of the target user when authenticating the user based on the target shooting parameters.

[0102] Among them, the prediction models of multiple parameters at least include prediction models of document quality threshold, prediction models of face quality threshold and prediction models of comparison threshold between document image and face image; the prediction model of target parameter is obtained by training with parameter values ​​of target parameters during multiple identity authentication as labels and with other parameters other than target parameters in multiple parameters as features, and the target parameter is any one of the multiple parameters. Since it is possible to model the main parameter factors in the identity authentication process, prediction models of document quality threshold, face quality threshold and prediction models of comparison threshold between document image and face image are obtained, it is possible to predict the optimal values ​​of the main parameters in the identity authentication process in a machine learning manner, so that the main parameters in the identity authentication process can reach a state that is better for the user experience, thereby improving the pass rate of user identity authentication and the user experience.

[0103] Figure 5 1 is a schematic diagram of a structure of an optimization device 500 for shooting parameters of identity authentication provided by one or more embodiments of this specification, including:

[0104] An image acquisition module 510 is used to acquire a face image of a target user and an ID image of the target user;

[0105] An identity verification module 520 is configured to verify the identity of the target user based on the face image of the target user and the ID image of the target user;

[0106] The parameter acquisition module 530 acquires the behavior characteristic data of the target user within a preset time period and the first shooting parameter of the target user when performing identity authentication if the identity authentication of the target user fails based on the face image and the ID image of the target user;

[0107] The parameter prediction module 540 inputs the behavior characteristic data of the target user and the first shooting parameter into a prediction model of multiple parameters, and outputs target shooting parameters that match the behavior characteristic data of the target user and the first shooting parameter, respectively, so as to optimize the shooting parameters of the target user when performing identity authentication based on the target shooting parameters;

[0108] Among them, the prediction models of the multiple parameters include at least a prediction model for the document quality threshold, a prediction model for the face quality threshold and a prediction model for the comparison threshold between the document image and the face image; the prediction model of the target parameter is obtained by training with the parameter value of the target parameter during multiple identity authentications as a label and with other parameters among the multiple parameters except the target parameter as features, and the target parameter is any one of the multiple parameters.

[0109] Optionally, in one implementation, the parameter prediction module 540 is used to:

[0110] Determine whether there is a security risk for the target user during identity authentication, wherein the security risk includes at least one of a security risk of an identity authentication device and a security risk of being attacked;

[0111] If there is no security risk during identity authentication of the target user, the behavior characteristic data of the target user and the first shooting parameter are input into a prediction model of multiple parameters, and target shooting parameters matching the behavior characteristic data of the target user and the first shooting parameter are output respectively.

[0112] Optionally, in one implementation, the parameter prediction module 540 is used to:

[0113] Extracting a first document quality threshold, a first face quality threshold, a first comparison threshold between the first document quality and the first face quality, and environmental parameters when the target user performs identity authentication from the behavior feature data of the target user and the first shooting parameters;

[0114] Inputting the first face quality threshold, the first comparison threshold, and the environmental parameter into the prediction model of the document quality threshold, and outputting a target document quality threshold that matches the first face quality threshold and the first comparison threshold;

[0115] Inputting the first face quality threshold, the first comparison threshold, and the environmental parameter into a prediction model for the face quality threshold, and outputting a target face quality threshold that matches the first face quality threshold and the first comparison threshold;

[0116] The first document quality threshold, the first face quality threshold and the environmental parameters are input into a prediction model of the comparison threshold, and a target comparison threshold that matches the first document quality threshold and the first face quality threshold is output.

[0117] Optionally, in one embodiment, the device further comprises:

[0118] A parameter adjustment module, which adjusts the shooting parameters of the target user when performing identity authentication according to the target shooting parameters;

[0119] An image acquisition module, which acquires a face image and an ID image of the target user after adjusting the shooting parameters when the target user performs identity authentication;

[0120] The identity verification module verifies the identity of the target user based on the face image and the ID image of the target user after adjusting the shooting parameters.

[0121] Optionally, in one implementation, the parameter adjustment module is used to:

[0122] Based on the target shooting parameter and the first shooting parameter, respectively determine a document quality difference between the first document quality threshold and the target document quality threshold, a face quality difference between the first face quality threshold and the target human quality threshold, and a comparison difference between the first comparison threshold and the target comparison threshold;

[0123] If the certificate quality difference is greater than or equal to the certificate quality threshold, adjusting the certificate quality threshold for identity authentication of the target user according to the target certificate quality threshold;

[0124] If the face quality difference is greater than or equal to the face quality threshold, adjusting the face quality threshold for identity authentication of the target user according to the target face quality threshold;

[0125] If the comparison difference is greater than or equal to the comparison threshold, the comparison threshold for identity verification of the target user is adjusted according to the target comparison threshold.

[0126] Optionally, in one implementation, the parameter acquisition module 530 is used to:

[0127] If the number of failed identity authentications of the target user based on the face image and ID image of the target user is greater than or equal to a preset threshold, the behavior characteristic data of the target user within a preset time period and the first shooting parameters of the target user when performing identity authentication are obtained.

[0128] Optionally, in one embodiment, the prediction model of the multiple parameters further includes at least one of the following:

[0129] A prediction model for screen brightness, wherein the prediction model for screen brightness is obtained by training using screen brightness values ​​during multiple identity authentications as labels and using other parameters of the multiple parameters except the screen brightness as features;

[0130] A prediction model of the copy, wherein the prediction model of the copy is obtained by training with the copy during multiple identity verifications as labels and with other parameters of the multiple parameters except the copy as features;

[0131] A color style prediction model, wherein the color style prediction model is obtained by training using color styles during multiple identity authentications as labels and using other parameters of the multiple parameters except the color style as features;

[0132] The prediction model of the certificate forgery threshold is obtained by training with the certificate forgery threshold during multiple identity authentications as a label and with other parameters of the multiple parameters except the certificate forgery threshold as features.

[0133] The device 500 for optimizing the shooting parameters for identity authentication can achieve Figure 1 to Figure 4 For details, please refer to Figure 1 The method for optimizing the shooting parameters for identity authentication in the illustrated embodiment will not be described in detail.

[0134] Figure 6 This is a schematic diagram of the structure of an electronic device provided by an embodiment of this specification. Figure 6 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0135] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0136] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0137] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming an optimization device for the shooting parameters of identity authentication at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0138] Obtaining a face image of a target user and an ID image of the target user;

[0139] Performing identity authentication on the target user based on the face image of the target user and the ID image of the target user;

[0140] If the identity authentication of the target user fails based on the face image and the ID image of the target user, then obtaining the behavior feature data of the target user within a preset time period and the first shooting parameter of the target user when performing identity authentication;

[0141] Inputting the behavior characteristic data of the target user and the first shooting parameter into a prediction model of multiple parameters, and outputting target shooting parameters matching the behavior characteristic data of the target user and the first shooting parameter respectively, so as to optimize the shooting parameters of the target user when performing identity authentication based on the target shooting parameters;

[0142] Among them, the prediction models of the multiple parameters include at least a prediction model for the document quality threshold, a prediction model for the face quality threshold and a prediction model for the comparison threshold between the document image and the face image; the prediction model of the target parameter is obtained by training with the parameter value of the target parameter during multiple identity authentications as a label and with other parameters among the multiple parameters except the target parameter as features, and the target parameter is any one of the multiple parameters.

[0143] The above is as in this manual Figure 1The optimization method of the shooting parameters of identity authentication disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in one or more embodiments of this specification can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in conjunction with one or more embodiments of this specification can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in a decoding processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0144] The electronic device may also perform Figure 1 Method and device for optimizing shooting parameters based on identity authentication Figure 1 The functions of the illustrated embodiments will not be described in detail in the embodiments of this specification.

[0145] Of course, in addition to software implementation, the electronic device of this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0146] The embodiment of the present specification also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by a portable electronic device including a plurality of application programs, enable the portable electronic device to execute Figure 1 The method of the embodiment shown is specifically used to perform the following operations:

[0147] Obtaining a face image of a target user and an ID image of the target user;

[0148] Performing identity authentication on the target user based on the face image of the target user and the ID image of the target user;

[0149] If the identity authentication of the target user fails based on the face image and the ID image of the target user, then obtaining the behavior feature data of the target user within a preset time period and the first shooting parameter of the target user when performing identity authentication;

[0150] Inputting the behavior characteristic data of the target user and the first shooting parameter into a prediction model of multiple parameters, and outputting target shooting parameters matching the behavior characteristic data of the target user and the first shooting parameter respectively, so as to optimize the shooting parameters of the target user when performing identity authentication based on the target shooting parameters;

[0151] Among them, the prediction models of the multiple parameters include at least a prediction model for the document quality threshold, a prediction model for the face quality threshold and a prediction model for the comparison threshold between the document image and the face image; the prediction model of the target parameter is obtained by training with the parameter value of the target parameter during multiple identity authentications as a label and with other parameters among the multiple parameters except the target parameter as features, and the target parameter is any one of the multiple parameters.

[0152] In short, the above description is only a preferred embodiment of this specification and is not intended to limit the protection scope of this specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the protection scope of one or more embodiments of this specification.

[0153] 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.

[0154] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0155] 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.

[0156] 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.

Claims

1. A method for optimizing shooting parameters for identity authentication, comprising: Obtaining a face image of a target user and an ID image of the target user; Performing identity authentication on the target user based on the face image of the target user and the ID image of the target user; If the identity authentication of the target user fails based on the face image and the ID image of the target user, then obtaining the behavior feature data of the target user within a preset time period and the first shooting parameter of the target user when performing identity authentication; Inputting the behavior characteristic data of the target user and the first shooting parameter into a prediction model of multiple parameters, and outputting target shooting parameters matching the behavior characteristic data of the target user and the first shooting parameter respectively, so as to optimize the shooting parameters of the target user when performing identity authentication based on the target shooting parameters; Among them, the prediction models of the multiple parameters include at least a prediction model for the document quality threshold, a prediction model for the face quality threshold and a prediction model for the comparison threshold between the document image and the face image; the prediction model of the target parameter is obtained by training with the parameter value of the target parameter during multiple identity authentications as a label and with other parameters among the multiple parameters except the target parameter as features, the target parameter is any one of the multiple parameters, and the target shooting parameters include a target document quality threshold, a target face quality threshold and a target comparison threshold.

2. The method according to claim 1, inputting the behavior characteristic data of the target user and the first shooting parameter into a prediction model of multiple parameters, and outputting target shooting parameters matching the behavior characteristic data of the target user and the first shooting parameter respectively, comprising: Determine whether there is a security risk for the target user during identity authentication, wherein the security risk includes at least one of a security risk of an identity authentication device and a security risk of being attacked; If there is no security risk during identity authentication of the target user, the behavior characteristic data of the target user and the first shooting parameter are input into a prediction model of multiple parameters, and target shooting parameters matching the behavior characteristic data of the target user and the first shooting parameter are output respectively.

3. The method according to any one of claims 1 or 2, wherein the behavior characteristic data of the target user and the first shooting parameter are input into a prediction model of multiple parameters, and target shooting parameters matching the behavior characteristic data of the target user and the first shooting parameter are output respectively, comprising: Extracting a first document quality threshold, a first face quality threshold, a first comparison threshold between the first document quality and the first face quality, and environmental parameters when the target user performs identity authentication from the behavior feature data of the target user and the first shooting parameters; Inputting the first face quality threshold, the first comparison threshold, and the environmental parameter into the prediction model of the document quality threshold, and outputting a target document quality threshold that matches the first face quality threshold and the first comparison threshold; Inputting the first face quality threshold, the first comparison threshold, and the environmental parameter into a prediction model for the face quality threshold, and outputting a target face quality threshold that matches the first face quality threshold and the first comparison threshold; The first document quality threshold, the first face quality threshold and the environmental parameters are input into a prediction model of the comparison threshold, and a target comparison threshold that matches the first document quality threshold and the first face quality threshold is output.

4. The method according to claim 3, after inputting the behavior characteristic data of the target user and the first shooting parameter into a prediction model of multiple parameters and outputting target shooting parameters matching the behavior characteristic data of the target user and the first shooting parameter respectively, the method further comprises: According to the target shooting parameters, adjusting the shooting parameters of the target user when performing identity authentication; After adjusting the shooting parameters of the target user for identity authentication, obtaining a face image and a certificate image of the target user; The target user's identity is authenticated based on the face image and the ID image of the target user after the shooting parameters are adjusted.

5. The method according to claim 4, adjusting the shooting parameters of the target user when performing identity authentication according to the target shooting parameters, comprising: Based on the target shooting parameter and the first shooting parameter, respectively determine a document quality difference between the first document quality threshold and the target document quality threshold, a face quality difference between the first face quality threshold and the target face quality threshold, and a comparison difference between the first comparison threshold and the target comparison threshold; If the certificate quality difference is greater than or equal to the certificate quality threshold, adjusting the certificate quality threshold for identity authentication of the target user according to the target certificate quality threshold; If the face quality difference is greater than or equal to the face quality threshold, adjusting the face quality threshold for identity authentication of the target user according to the target face quality threshold; If the comparison difference is greater than or equal to the comparison threshold, the comparison threshold for identity verification of the target user is adjusted according to the target comparison threshold.

6. The method according to claim 1, if the identity authentication of the target user fails based on the face image and the ID image of the target user, obtaining the behavior characteristic data of the target user within a preset time period and the first shooting parameter of the target user when performing identity authentication, comprises: If the number of failed identity authentications of the target user based on the face image and ID image of the target user is greater than or equal to a preset threshold, the behavior characteristic data of the target user within a preset time period and the first shooting parameters of the target user when performing identity authentication are obtained.

7. The method of claim 1, wherein the prediction model of the multiple parameters further comprises at least one of the following: A prediction model for screen brightness, wherein the prediction model for screen brightness is obtained by training using screen brightness values ​​during multiple identity authentications as labels and using other parameters of the multiple parameters except the screen brightness as features; A prediction model of the copy, wherein the prediction model of the copy is obtained by training with the copy during multiple identity verifications as labels and with other parameters of the multiple parameters except the copy as features; A color style prediction model, wherein the color style prediction model is obtained by training using color styles during multiple identity authentications as labels and using other parameters of the multiple parameters except the color style as features; The prediction model of the certificate forgery threshold is obtained by training with the certificate forgery threshold during multiple identity authentications as a label and with other parameters of the multiple parameters except the certificate forgery threshold as features.

8. A device for optimizing shooting parameters for identity authentication, comprising: An image acquisition module, which acquires a face image of a target user and an ID image of the target user; An identity verification module, for verifying the identity of the target user based on a face image of the target user and an ID image of the target user; a parameter acquisition module, which acquires the behavior characteristic data of the target user within a preset time period and the first shooting parameter of the target user when performing identity authentication if the identity authentication of the target user fails based on the face image and the ID image of the target user; a parameter prediction module, inputting the behavior characteristic data of the target user and the first shooting parameter into a prediction model of multiple parameters, and outputting target shooting parameters that match the behavior characteristic data of the target user and the first shooting parameter, respectively, so as to optimize the shooting parameters of the target user when performing identity authentication based on the target shooting parameters; Among them, the prediction models of the multiple parameters include at least a prediction model for the document quality threshold, a prediction model for the face quality threshold and a prediction model for the comparison threshold between the document image and the face image; the prediction model of the target parameter is obtained by training with the parameter value of the target parameter during multiple identity authentications as a label and with other parameters among the multiple parameters except the target parameter as features, the target parameter is any one of the multiple parameters, and the target shooting parameters include a target document quality threshold, a target face quality threshold and a target comparison threshold.

9. An electronic device, comprising: processor; as well as a memory arranged to store computer executable instructions which, when executed, cause the processor to: Obtaining a face image of a target user and an ID image of the target user; Performing identity authentication on the target user based on the face image of the target user and the ID image of the target user; If the identity authentication of the target user fails based on the face image and the ID image of the target user, then obtaining the behavior feature data of the target user within a preset time period and the first shooting parameter of the target user when performing identity authentication; Inputting the behavior characteristic data of the target user and the first shooting parameter into a prediction model of multiple parameters, and outputting target shooting parameters matching the behavior characteristic data of the target user and the first shooting parameter respectively, so as to optimize the shooting parameters of the target user when performing identity authentication based on the target shooting parameters; Among them, the prediction models of the multiple parameters include at least a prediction model for the document quality threshold, a prediction model for the face quality threshold and a prediction model for the comparison threshold between the document image and the face image; the prediction model of the target parameter is obtained by training with the parameter value of the target parameter during multiple identity authentications as a label and with other parameters among the multiple parameters except the target parameter as features, the target parameter is any one of the multiple parameters, and the target shooting parameters include a target document quality threshold, a target face quality threshold and a target comparison threshold.

10. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, causes the electronic device to perform the following operations: Obtaining a face image of a target user and an ID image of the target user; Performing identity authentication on the target user based on the face image of the target user and the ID image of the target user; If the identity authentication of the target user fails based on the face image and the ID image of the target user, then obtaining the behavior feature data of the target user within a preset time period and the first shooting parameter of the target user when performing identity authentication; Inputting the behavior characteristic data of the target user and the first shooting parameter into a prediction model of multiple parameters, and outputting target shooting parameters matching the behavior characteristic data of the target user and the first shooting parameter respectively, so as to optimize the shooting parameters of the target user when performing identity authentication based on the target shooting parameters; Among them, the prediction models of the multiple parameters include at least a prediction model for the document quality threshold, a prediction model for the face quality threshold and a prediction model for the comparison threshold between the document image and the face image; the prediction model of the target parameter is obtained by training with the parameter value of the target parameter during multiple identity authentications as a label and with other parameters among the multiple parameters except the target parameter as features, the target parameter is any one of the multiple parameters, and the target shooting parameters include a target document quality threshold, a target face quality threshold and a target comparison threshold.