Identity authentication method, device and equipment based on privacy protection

Abstract

The embodiments of this specification provide a privacy-protection-based identity authentication method, apparatus, and device, wherein the method comprises: obtaining a target image to be subjected to privacy protection processing; if multiple faces are detected in the target image, identifying willing users who have the intention of identity authentication and unwilling users who have no intention of identity authentication among the multiple users based on the body feature information of multiple users corresponding to the determined multiple faces; performing a first desensitization processing on the faces of the unwilling users in the target image to obtain an image to be authenticated; if it is determined based on the image to be authenticated that a preset identity authentication condition is met, performing identity authentication processing based on the faces of the willing users in the image to be authenticated.

Description

Technical Field

[0001] This document relates to the field of identity authentication technology, and in particular to an identity authentication method, device and equipment based on privacy protection. Background Art

[0002] Facial recognition technology has developed rapidly and been widely used in recent years. For example, in payment, transportation, access control and other scenarios, facial recognition systems are widely used to authenticate users. Taking the train as an example, when passengers enter the station, they often line up to collect facial images. When passenger A collects his face, if passenger B behind him is closer to passenger A, passenger B's face will inevitably be collected; or when passenger A collects his face, passenger C happens to pass by, and passenger C's face will inevitably be collected. This not only easily causes the facial information of passengers B and C to be leaked, but also poses the risk of infringing the personal rights and interests of passengers B and C. Summary of the invention

[0003] One or more embodiments of the present specification provide an identity authentication method based on privacy protection. The method includes obtaining a target image to be processed for privacy protection. If multiple faces are detected in the target image, then based on the body feature information of multiple users corresponding to the multiple faces, the willing users who have the intention of identity authentication and the unwilling users who have no intention of identity authentication among the multiple users are identified. The faces of the unwilling users in the target image are subjected to a first desensitization process to obtain an image to be authenticated. If it is determined based on the image to be authenticated that a preset identity authentication condition is met, identity authentication processing is performed based on the faces of the willing users in the image to be authenticated.

[0004] One or more embodiments of the present specification provide an identity authentication method based on privacy protection. The method includes obtaining a target image to be processed for privacy protection. If multiple faces are detected in the target image based on the smart contract in the blockchain system, then the willing users who have the intention of identity authentication and the unwilling users who have no intention of identity authentication are identified among the multiple users according to the body feature information of the multiple users corresponding to the multiple faces. Based on the smart contract, a first desensitization process is performed on the faces of the unwilling users in the target image to obtain an image to be authenticated. If it is determined that the preset identity authentication conditions are met according to the image to be authenticated, identity authentication is performed according to the faces of the willing users in the image to be authenticated to obtain identity authentication result information. Identity authentication record information is generated according to the identity authentication result information, and the identity authentication record information is saved in the blockchain system.

[0005] One or more embodiments of the present specification provide an identity authentication device based on privacy protection. The device includes an acquisition module for acquiring a target image to be processed for privacy protection. The device also includes a recognition module. If multiple faces are detected in the target image, the device identifies willing users who have the intention of identity authentication and unwilling users who have no intention of identity authentication among the multiple users based on the body feature information of multiple users corresponding to the multiple faces. The device also includes a desensitization module for performing a first desensitization process on the faces of the unwilling users in the target image to obtain the image to be authenticated. The device also includes an authentication module. If it is determined that a preset identity authentication condition is met based on the image to be authenticated, the device performs identity authentication processing based on the faces of the willing users in the image to be authenticated.

[0006] One or more embodiments of the present specification provide an identity authentication device based on privacy protection. The device includes an acquisition module, which acquires a target image to be processed for privacy protection. The device also includes a recognition module. If multiple faces are detected in the target image based on the smart contract in the blockchain system, the willing users who have the intention of identity authentication and the unwilling users who have no intention of identity authentication are identified among the multiple users according to the body feature information of the multiple users corresponding to the determined multiple faces. The device also includes a desensitization module, which performs a first desensitization process on the faces of the unwilling users in the target image based on the smart contract to obtain the image to be authenticated. The device also includes an authentication module. If it is determined that the preset identity authentication conditions are met according to the image to be authenticated, the identity authentication process is performed according to the faces of the willing users in the image to be authenticated to obtain the identity authentication result information. The device also includes a saving module, which generates identity authentication record information according to the identity authentication result information, and saves the identity authentication record information in the blockchain system.

[0007] One or more embodiments of the present specification provide an identity authentication device based on privacy protection. The device includes a processor. The device also includes a memory arranged to store computer executable instructions. When the computer executable instructions are executed, the processor acquires a target image to be processed for privacy protection. If multiple faces are detected in the target image, the willing users who have the intention of identity authentication and the unwilling users who have no intention of identity authentication are identified among the multiple users based on the body feature information of the multiple users corresponding to the multiple faces. The faces of the unwilling users in the target image are subjected to a first desensitization process to obtain an image to be authenticated. If it is determined that the preset identity authentication conditions are met based on the image to be authenticated, the identity authentication process is performed based on the faces of the willing users in the image to be authenticated.

[0008] One or more embodiments of the present specification provide an identity authentication device based on privacy protection. The device includes a processor. The device also includes a memory arranged to store computer executable instructions. When the computer executable instructions are executed, the processor obtains a target image to be processed for privacy protection. If multiple faces are detected in the target image based on the smart contract in the blockchain system, the willing users who have the intention of identity authentication and the unwilling users who have no intention of identity authentication are identified among the multiple users according to the body feature information of the multiple users corresponding to the multiple faces. Based on the smart contract, the faces of the unwilling users in the target image are subjected to a first desensitization process to obtain an image to be authenticated. If it is determined that the preset identity authentication conditions are met according to the image to be authenticated, the identity authentication process is performed according to the faces of the willing users in the image to be authenticated to obtain the identity authentication result information. The identity authentication record information is generated according to the identity authentication result information, and the identity authentication record information is saved in the blockchain system.

[0009] One or more embodiments of the present specification provide a storage medium. The storage medium is used to store computer-executable instructions. When the computer-executable instructions are executed by a processor, a target image to be processed for privacy protection is obtained. If multiple faces are detected in the target image, the willing users who have the intention of identity authentication and the unwilling users who have no intention of identity authentication are identified among the multiple users based on the body feature information of the multiple users corresponding to the multiple faces. The faces of the unwilling users in the target image are subjected to a first desensitization process to obtain an image to be authenticated. If it is determined that the preset identity authentication conditions are met based on the image to be authenticated, identity authentication is performed based on the faces of the willing users in the image to be authenticated.

[0010] One or more embodiments of the present specification provide a storage medium. The storage medium is used to store computer-executable instructions. When the computer-executable instructions are executed by the processor, a target image to be processed for privacy protection is obtained. If multiple faces are detected in the target image based on the smart contract in the blockchain system, the willing users who have the intention of identity authentication and the unwilling users who have no intention of identity authentication are identified among the multiple users according to the body feature information of the multiple users corresponding to the multiple faces. A first desensitization process is performed on the faces of the unwilling users in the target image based on the smart contract to obtain an image to be authenticated. If it is determined that the preset identity authentication conditions are met according to the image to be authenticated, identity authentication is performed according to the faces of the willing users in the image to be authenticated to obtain identity authentication result information. Identity authentication record information is generated according to the identity authentication result information, and the identity authentication record information is saved in the blockchain system. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0012] Figure 1 A first flow chart of a privacy protection-based identity authentication method provided for one or more embodiments of this specification;

[0013] Figure 2 A second flow chart of an identity authentication method based on privacy protection provided for one or more embodiments of this specification;

[0014] Figure 3 A third flow chart of an identity authentication method based on privacy protection provided in one or more embodiments of this specification;

[0015] Figure 4 A fourth flow chart of an identity authentication method based on privacy protection provided in one or more embodiments of this specification;

[0016] Figure 5 A fifth flow chart of an identity authentication method based on privacy protection provided in one or more embodiments of this specification;

[0017] Figure 6 A sixth flow chart of a privacy protection-based identity authentication method provided for one or more embodiments of this specification;

[0018] Figure 7 A schematic diagram of a first module composition of an identity authentication device based on privacy protection provided in one or more embodiments of this specification;

[0019] Figure 8 A schematic diagram of a second module composition of an identity authentication device based on privacy protection provided in one or more embodiments of this specification;

[0020] Fig. 9 A schematic diagram of the structure of an identity authentication device based on privacy protection provided in one or more embodiments of this specification. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this document.

[0022] Figure 1 A flowchart of an identity authentication method based on privacy protection provided in one or more embodiments of this specification is provided. Figure 1 The method can be executed by an identity authentication device based on privacy protection (hereinafter referred to as identity authentication device).

[0023] like Figure 1 As shown, the method comprises the following steps:

[0024] Step S102, obtaining a target image to be processed for privacy protection;

[0025] Optionally, the identity authentication device is arranged in the image acquisition device, and when the image acquisition device acquires an image related to the designated business, the identity authentication device determines the image acquired by the image acquisition device as the target image to be processed for privacy protection. Alternatively, the identity authentication device is arranged in the service end related to the designated business, and the image acquisition device sends the acquired image related to the designated business to the service end, and the identity authentication device determines the image received by the service end as the target image to be processed for privacy protection. Alternatively, the identity authentication device is separated from the service end and exists independently, and when the service end receives the image sent by the image acquisition device, the received image is sent to the identity authentication device; the identity authentication device determines the image sent by the service end as the target image to be processed for privacy protection. Among them, the designated business is a business related to identity authentication, including but not limited to payment business, transportation business, access control authentication business, and attendance punching business. Accordingly, the image acquisition device can be a terminal device such as a mobile phone, a tablet computer, a portable notebook, a desktop computer, a smart wearable device, or a device with image acquisition function such as an access control device and an attendance punching device. The server end can be an independent server or a server cluster composed of multiple servers.

[0026] Step S104, if multiple faces are detected in the target image, identifying willing users who are willing to authenticate and unwilling users who are not willing to authenticate among the multiple users according to the body feature information of the multiple users corresponding to the determined multiple faces;

[0027] Specifically, a face detection model can be pre-trained, and the acquired target image can be input into the face detection model for face detection processing to obtain face detection result information; if the face detection result information indicates that multiple faces are detected in the target image, the body feature information of multiple users corresponding to the multiple faces is determined according to the target image; and willing users who have the intention of identity authentication and unwilling users who have no intention of identity authentication among the multiple users are identified according to the determined body feature information.

[0028] Among them, the training process of the face detection model can refer to the training process of the existing face detection model, which will not be described in detail in this specification. The willing user with the intention of identity authentication is the user who autonomously performs face acquisition through the image acquisition device to perform identity authentication, and the unwilling user without the intention of identity authentication is the user who does not autonomously perform face acquisition through the image acquisition device, but is captured by the image acquisition device because he passes by the image acquisition device or happens to be within the acquisition range of the image acquisition device.

[0029] For example, in the scene of entering a station and boarding a train, each passenger lines up for identity authentication based on face recognition to enter the station. Currently, user A is operating the image acquisition device to collect faces. Since user B, who is behind user A, is too close to user A and is also within the acquisition range of the image acquisition device, the target image collected by the image acquisition device includes both the faces of user A and user B. At this time, user A is a willing user with the intention of identity authentication, and user B is an unwilling user without the intention of identity authentication.

[0030] Step S106, performing a first desensitization process on the face of the unwanted user in the target image to obtain an image to be authenticated;

[0031] In a feasible implementation, a non-face image is added to the face of the unwanted user in the target image; or a mosaic is added to the face of the unwanted user in the target image. The non-face image is, for example, a cartoon image, a landscape image, etc. The specific method of the first desensitization process can be set as needed in actual applications.

[0032] Step S108: If it is determined that the preset identity authentication condition is met according to the image to be authenticated, identity authentication processing is performed according to the face of the intended user in the image to be authenticated.

[0033] Among them, the process of identity authentication based on the face of the intended user in the image to be authenticated may vary with different application scenarios. For example, in the aforementioned scene of entering the station and taking a train, the image acquisition device can collect the identity document information of the user to be authenticated while collecting the face; the identity authentication device can obtain the corresponding reference face image based on the acquired identity document information, and perform face comparison processing based on the face image of the intended user in the image to be authenticated and the reference face image to realize the identity authentication of the user to be authenticated. For another example, in the face payment scenario, the image acquisition device can be a terminal device of the user to be authenticated with a payment application installed. The terminal device can perform face acquisition processing based on the payment operation of the user to be authenticated, and send the collected image and the determined account information of the payment application to the identity authentication device; the identity authentication device obtains the corresponding reference face image based on the received account information, and performs face comparison processing based on the face image of the intended user in the image to be authenticated and the reference face image to realize the identity authentication of the user to be authenticated. The implementation process of identity authentication based on the face of the intended user in the image to be authenticated is not specifically limited in this specification, and can be set by itself according to needs in actual applications.

[0034] In one or more embodiments of the present specification, a target image to be processed for privacy protection is obtained. If multiple faces are detected in the target image, then the willing users who have the intention of identity authentication and the unwilling users who have no intention of identity authentication are identified among the multiple users according to the body feature information of the multiple users corresponding to the multiple faces; the faces of the unwilling users in the target image are subjected to a first desensitization process to obtain the image to be authenticated; if it is determined according to the image to be authenticated that the preset identity authentication conditions are met, the identity authentication process is performed according to the faces of the willing users in the image to be authenticated. Thus, by identifying the unwilling users who have no intention of identity authentication corresponding to the target image, and performing the first desensitization process on the faces of the unwilling users in the target image and then performing the identity authentication process, not only the privacy information of the unwilling users is protected, but also the personal rights and interests of the unwilling users are effectively protected.

[0035] In order to effectively identify willing users and unwilling users, such as Figure 2 As shown, step S104 may include the following steps S104-2 to S104-10:

[0036] Step S104-2, if multiple faces are detected in the target image, for each face, detect whether the target image includes a human body key point corresponding to the face; if yes, execute step S104-4, otherwise execute step S104-8;

[0037] Step S104-4, determining the body posture information of the corresponding user according to the detected body key points, and using a pre-trained face posture regression model to determine the facial posture information of the corresponding face; determining the body posture information and the facial posture information as the body feature information of the corresponding user;

[0038] Usually, the face or shoulders of an unintentional user are not facing the image acquisition device. Based on this, the human posture information is determined based on the positional relationship between the shoulders and the eyes in this specification. Specifically, the human key points include shoulder key points. According to the coordinate information of the shoulder key points, the first distance between the shoulder key points is determined; and the eye key points of the face are detected. According to the coordinate information of the eye key points, the second distance between the eye key points is determined; and the human posture information is determined according to the first distance and the second distance. Among them, the detection method of the shoulder key points and the eye key points can adopt the existing detection method, which will not be described in detail in this specification.

[0039] Further, determining the human body posture information according to the first distance and the second distance may include: determining a ratio of the first distance to the second distance as the human body posture information.

[0040] Furthermore, using a pre-trained face posture regression model to determine the face posture information of the corresponding face may include: inputting the face image of the corresponding face into the pre-trained face posture regression model to obtain the pitch angle (pitch) and / or yaw angle (yaw) of the face, and determining the pitch angle and / or yaw angle as the face posture information of the corresponding face. The pitch angle is the angle of rotation along the x-axis, and the yaw angle is the angle of rotation along the y-axis. The training method of the face posture regression model can refer to the existing model training method, which will not be described in detail in this specification.

[0041] Step S104-6, determining whether the human body posture information and the face posture information meet the first preset condition; if so, determining that the corresponding user is a willing user with identity authentication intention; if not, determining that the corresponding user is an unintentional user without identity authentication intention, and executing step S106;

[0042] Specifically, determine whether the human body posture information is not less than the preset human body posture information, and determine whether the facial posture information is not greater than the preset facial posture information; if the determination results are both yes, determine that the human body posture information and the facial posture information meet the first preset condition, otherwise, determine that the human body posture information and the facial posture information do not meet the first preset condition.

[0043] That is to say, the ratio of the first distance to the second distance is recorded as Rbody, the pitch angle is recorded as Ap, and the yaw angle is recorded as Ay. Taking the facial posture information including Ap and Ay as an example, the threshold values ​​{TR, TAP, TAY} are set in advance. When Rbody>=TR, Ap<=TAP, and Ay<=TAY, it is determined that the first preset condition is met.

[0044] Step S104-8, using a pre-trained face posture regression model to determine the face posture information of the corresponding face, and determining the face posture information as the body feature information of the corresponding user;

[0045] Step S104-10, determining whether the facial posture information meets the second preset condition; if so, determining that the corresponding user is a willing user with identity authentication intention; if not, determining that the corresponding user is an unintentional user without identity authentication intention.

[0046] Specifically, it is determined whether the facial posture information is not greater than the preset facial posture information; if so, it is determined that the facial posture information meets the second preset condition; otherwise, it is determined that the facial posture information does not meet the second preset condition.

[0047] That is to say, the pitch angle is recorded as Ap, the yaw angle is recorded as Ay, and the facial posture information including Ap and Ay is used as an example for explanation. A threshold {TAP, TAY} is preset. When Ap<=TAP and Ay<=TAY, it is determined that the second preset condition is met.

[0048] Since the human body posture information and face posture information can reflect the state of the corresponding user when the face is collected, and the state of the user is closely related to the identity authentication intention, based on the human body posture information and face posture information, the user type corresponding to each face can be accurately identified.

[0049] In order to protect the privacy of unintentional users while enhancing the sense of security of the user to be authenticated, in one or more embodiments of this specification, Figure 3 As shown, step S108 may include the following steps S108-2 and S108-4:

[0050] Step S108-2, displaying the image to be authenticated, and if confirmation information generated by the confirmation operation of the user to be authenticated in the display interface of the image to be authenticated is obtained, it is determined that the preset identity authentication condition is met;

[0051] Specifically, when the identity authentication device is set in the image acquisition device, the image to be authenticated is displayed through the image acquisition device, and it is determined whether the confirmation information generated by the confirmation operation of the user to be authenticated in the display interface of the image to be authenticated is obtained. If so, it is determined that the preset identity authentication condition is met. When the identity authentication device is not set in the image acquisition device, the image to be authenticated is sent to the image acquisition device so that the image acquisition device acquires and displays the image to be authenticated, and when the confirmation information generated by the confirmation operation of the user to be authenticated in the display interface of the image to be authenticated is obtained, the confirmation information is sent to the identity authentication device; if the identity authentication device receives the confirmation information sent by the image acquisition device, it is determined that the preset identity authentication condition is met.

[0052] Step S108-4: performing identity authentication based on the face of the intended user in the image to be authenticated.

[0053] Furthermore, considering that the identity authentication device may make mistakes in identifying unwanted users, which may result in the identity authentication not being able to proceed smoothly. Based on this, one or more embodiments of this specification also provide a desensitization cancellation function. Figure 4 As shown, step S108 may include the following steps S108-6 to S108-14.

[0054] Step S108-6, displaying the image to be authenticated;

[0055] Step S108-8, if the desensitization cancellation information generated by the desensitization cancellation operation of the user to be authenticated in the display interface of the image to be authenticated is not obtained within the preset time period, it is determined that the preset identity authentication condition is met, and step S108-14 is executed;

[0056] Specifically, when the identity authentication device is set in the image acquisition device, the image to be authenticated is displayed through the image acquisition device, and it is determined whether the desensitization cancellation information generated by the desensitization operation of the user to be authenticated in the display interface of the image to be authenticated is obtained within the preset time period, if not, it is determined that the preset identity authentication condition is met. When the identity authentication device is not set in the image acquisition device, the image to be authenticated is sent to the image acquisition device so that the image acquisition device acquires and displays the image to be authenticated, and when the desensitization cancellation information generated by the desensitization operation of the user to be authenticated in the display interface of the image to be authenticated is obtained, the desensitization cancellation information is sent to the identity authentication device; the identity authentication device determines whether the desensitization cancellation information sent by the image acquisition device is received within the preset time period, if not, it is determined that the preset identity authentication condition is met.

[0057] Step S108-10, if desensitization cancellation information generated based on the desensitization cancellation operation of the user to be authenticated in the display interface of the image to be authenticated is obtained within the preset time period, determining the target face to be desensitized according to the desensitization cancellation information;

[0058] Specifically, the desensitization cancellation information may include the area information of the area where the desensitized information to be cancelled is located, or the desensitization cancellation information may include the identification information of the desensitized information to be obtained; accordingly, when the identity authentication device obtains the desensitization cancellation information, it determines the target face to be desensitized according to the area information or the identification information included in the desensitization cancellation information.

[0059] Step S108-12: If it is determined that the preset desensitization cancellation condition is met, the first desensitization processing is performed on the non-desensitized face in the image to be authenticated, and the target face is restored. The image after the target face is restored is determined as the image to be authenticated, and the process returns to step S108-6.

[0060] Specifically, when the identity authentication device obtains the information for canceling desensitization, the image acquisition device can prompt the user to be authenticated to perform a specified behavior and collect the user image of the specified behavior; when the identity authentication device obtains the user image of the specified behavior, the user image is matched with the target face to be desensitized; if the match is successful, it is determined that the preset desensitization cancellation condition is met. The specified behavior can be blinking, shaking the head, nodding, etc.

[0061] Step S108-14, performing identity authentication processing based on the face of the intended user in the image to be authenticated.

[0062] It should be noted that the aforementioned step S108-2 may also include step S108-10 and step S108-12. Accordingly, in step S108-12, the process returns to step S108-2.

[0063] Therefore, by displaying the image to be authenticated for confirmation by the user to be authenticated, it is possible to avoid identity authentication failure due to recognition errors by unintentional users and enhance the sense of security of the user to be authenticated.

[0064] In order to facilitate the subsequent tracing of the identity authentication process, in one or more embodiments of this specification, Figure 5 As shown, after step S108, the following steps S110 and S112 may also be included:

[0065] Step S110, performing privacy protection processing on the images of the intended user and the images of the unintended user in the target image in a graded manner to obtain images to be stored; wherein the grade of the images of the intended user is higher than the grade of the images of the unintended user;

[0066] Specifically, a pre-trained privacy protection model is used to perform a second desensitization process on the image of the intended user in the target image to obtain an intermediate image; and according to a preset encryption algorithm, the image of the unintended user in the intermediate image is encrypted to obtain an image to be stored.

[0067] When performing graded privacy protection processing on the images of the intended user and the images of the unintended user in the target image, the privacy protection processing may be performed only on the face area, or on both the face area and the body area. The training method of the privacy protection model may adopt the existing training method, which will not be described in detail in this specification. The preset encryption algorithm can be set as needed in actual applications, such as the MD5 algorithm, the RSA algorithm, etc.

[0068] Step S112, saving the image to be stored to a designated storage location.

[0069] The designated storage location may be a cloud, blockchain, etc.

[0070] Therefore, the images of the intended user and the images of the unwanted user in the target image are subjected to graded privacy protection processing, and the obtained images to be stored are saved to a designated storage location. This not only achieves the privacy protection of the intended user and the unwanted user, but also enables the saved images to be stored to be restored to obtain the original target image when business needs arise, so as to carry out subsequent related processing.

[0071] Considering that in actual applications, different users to be authenticated have different security perception levels, in order to meet the security needs of different users, in one or more embodiments of this specification, the method may further include:

[0072] The sense of security scores of the specified user group are obtained according to a preset method, and the privacy protection strategy of the identity authentication processing is adjusted according to the obtained sense of security scores.

[0073] Wherein, obtaining the sense of security score of a specified user group according to a preset method may include:

[0074] A questionnaire is issued to a designated user group, and the sense of security score of the designated user group is determined based on the response information of the questionnaire obtained; or, historical behavior data related to identity authentication of the designated user group is obtained, and the sense of security score of the designated user group is determined based on the historical behavior data. The designated user group includes a first user group that adopts a privacy protection strategy and a second user group that does not adopt a privacy protection strategy.

[0075] The questionnaire may include multiple sense of security questions and multiple privacy questions, and each question may have multiple scores for users to choose from; the answer information includes the score selected by the user, and the total score of the scores selected by the user is counted and determined as the sense of security score of the corresponding user. The specific content of the sense of security questions and privacy questions can be set according to actual needs in actual applications. For example, the sense of security questions may include: Do you think the current biometric scheme is safe? Please rate it from 1 to 10 points in terms of security; In public places, you do not use biometrics due to security concerns. Please rate it from 1 to 10 points. Privacy questions may include: Do you think there are privacy issues in the current biometric scheme? Please rate it from 1 to 10 points in terms of privacy and security (the higher the score, the safer the privacy); In public places, how much do you think the privacy protection of the biometric scheme is? Please rate it from 1 to 10 points. The questionnaire can be distributed in a way that it is sent to the client application of the specified business of each user in the specified user group, such as a payment application, a ticket purchase application, etc.

[0076] Furthermore, when the historical behavior data related to identity authentication of a specified user group is obtained, the sense of security score of the corresponding user can be determined based on the historical behavior data based on the pre-trained sense of security recognition model. The historical behavior data includes transaction information of historical face-swiping payment transactions, changes in historical face-swiping frequency, etc. The training method of the sense of security recognition model can adopt the existing training method, which will not be described in detail in this manual.

[0077] By obtaining the sense of security scores of different user groups, the differences in sense of security among different user groups can be identified, and based on the security scores, the target user groups suitable for identity authentication using the above-mentioned privacy-protection-based identity authentication method can be determined, so that the privacy protection strategy of the identity authentication processing can be adjusted to authenticate the target user groups using the above-mentioned privacy-protection-based identity authentication method.

[0078] In one or more embodiments of the present specification, a target image to be processed for privacy protection is obtained. If multiple faces are detected in the target image, then the willing users who have the intention of identity authentication and the unwilling users who have no intention of identity authentication are identified among the multiple users according to the body feature information of the multiple users corresponding to the multiple faces; the faces of the unwilling users in the target image are subjected to a first desensitization process to obtain the image to be authenticated; if it is determined according to the image to be authenticated that the preset identity authentication conditions are met, the identity authentication process is performed according to the faces of the willing users in the image to be authenticated. Thus, by identifying the unwilling users who have no intention of identity authentication corresponding to the target image, and performing the first desensitization process on the faces of the unwilling users in the target image and then performing the identity authentication process, not only the privacy information of the unwilling users is protected, but also the rights and interests of the unwilling users are effectively protected.

[0079] Corresponding to the identity authentication method based on privacy protection described above, based on the same technical concept, one or more embodiments of this specification also provide another identity authentication method based on privacy protection. Figure 6 A flowchart of another identity authentication method based on privacy protection provided in one or more embodiments of this specification, Figure 6 The method in can be executed by the blockchain system; Figure 6 As shown, the method comprises the following steps:

[0080] Step S202, obtaining a target image to be processed for privacy protection;

[0081] Step S204: if multiple faces are detected in the target image based on the smart contract in the blockchain system, then, according to the body feature information of multiple users corresponding to the multiple faces, identifying willing users who have the intention to authenticate their identities and unwilling users who have no intention to authenticate their identities among the multiple users;

[0082] Step S206, performing a first desensitization process on the face of the unwanted user in the target image based on the smart contract to obtain an image to be authenticated;

[0083] Taking into account the characteristics of smart contracts such as automatic execution and inability to be intervened by humans, in order to improve the efficiency and accuracy of user type recognition, this specification detects and processes the target image based on the smart contract and identifies willing users and unwilling users, and performs a first desensitization processing on the faces of unwilling users based on the smart contract.

[0084] Step S208, if it is determined that the preset identity authentication condition is met according to the image to be authenticated, identity authentication processing is performed according to the face of the intended user in the image to be authenticated to obtain identity authentication result information;

[0085] Step S210, generate identity authentication record information according to the identity authentication result information, and save the identity authentication record information in the blockchain system.

[0086] In order to facilitate the subsequent tracing of identity authentication while protecting the privacy information of the intended user and the unintended user, in one or more embodiments of this specification, after determining that the preset identity authentication condition is met according to the image to be authenticated, the following may also be included:

[0087] Performing privacy protection processing on the images of the intended user and the images of the unintended user in the target image in a graded manner to obtain images to be stored; wherein the grade of the images of the intended user is higher than the grade of the images of the unintended user;

[0088] Accordingly, identity authentication record information is generated according to the identity authentication result information, including:

[0089] Determine the query information of the identity authentication result; generate the identity authentication record information according to the identity authentication result information, the image to be stored and the query information. The query information may be the relevant information of the business corresponding to the identity authentication, such as the transaction identification information, the information of the ticket used for the ride, etc.

[0090] Furthermore, the method may also include:

[0091] Receive a query request sent by a querying party; query corresponding identity authentication record information from the blockchain system according to the query information included in the query request; send the identity authentication result information and the image to be stored in the queried identity authentication record information to the querying party.

[0092] The querying party may be a user to be authenticated, a service provider of the corresponding service, or a third-party authority for supervision, etc. After receiving the image to be stored, the querying party may restore the image to be stored according to a preset image restoration method to obtain the corresponding target image.

[0093] In one or more embodiments of the present specification, a target image to be processed for privacy protection is obtained. If multiple faces are detected in the target image based on the smart contract in the blockchain system, the willing users with the intention of identity authentication and the unwilling users without the intention of identity authentication are identified among the multiple users according to the body feature information of the multiple users corresponding to the determined multiple faces; and the faces of the unwilling users in the target image are first desensitized based on the smart contract to obtain the image to be authenticated; if it is determined that the preset identity authentication conditions are met according to the image to be authenticated, the identity authentication is performed according to the faces of the willing users in the image to be authenticated. Thus, by identifying the unwilling users without the intention of identity authentication corresponding to the target image, and performing the first desensitization on the faces of the unwilling users in the target image and then performing the identity authentication, not only the privacy information of the unwilling users is protected, but also the rights and interests of the unwilling users are effectively maintained. The identification of willing users and unwilling users based on the smart contract can improve the recognition efficiency based on the characteristics of the smart contract. In addition, the identity authentication record is saved in the blockchain, and the validity of the identity authentication record can be ensured based on the characteristics of the blockchain, thereby providing an effective basis for subsequent related processing.

[0094] Corresponding to the above Figures 2 to 5 The described identity authentication method based on privacy protection is based on the same technical concept, and one or more embodiments of this specification also provide an identity authentication device based on privacy protection. Figure 7 A schematic diagram of the module composition of an identity authentication device based on privacy protection provided in one or more embodiments of this specification, such as Figure 7 As shown, the device comprises:

[0095] An acquisition module 301 is used to acquire a target image to be processed for privacy protection;

[0096] The recognition module 302, if multiple faces are detected in the target image, identifies willing users who have the intention to authenticate their identities and unwilling users who do not have the intention to authenticate their identities among the multiple users according to the body feature information of the multiple users corresponding to the multiple faces;

[0097] The desensitization module 303 performs a first desensitization process on the face of the unwanted user in the target image to obtain an image to be authenticated;

[0098] The authentication module 304 performs an identity authentication process based on the face of the intended user in the image to be authenticated if it is determined that the preset identity authentication condition is met according to the image to be authenticated.

[0099] Optionally, the device further comprises: a determination module;

[0100] The determination module detects, for each of the human faces, whether the target image includes a human body key point corresponding to the human face;

[0101] If so, determining the human body posture information of the corresponding user according to the human body key points, and using a pre-trained face posture regression model to determine the facial posture information of the face; determining the human body posture information and the facial posture information as the body feature information of the user;

[0102] If not, a pre-trained facial posture regression model is used to determine the facial posture information of the face, and the facial posture information is determined as the body feature information of the corresponding user.

[0103] Optionally, the authentication module 304 performs display processing on the image to be authenticated;

[0104] If confirmation information generated by the confirmation operation of the user to be authenticated in the display interface of the image to be authenticated is obtained, it is determined that the preset identity authentication condition is met; or,

[0105] If the desensitization cancellation information generated by the desensitization cancellation operation of the user to be authenticated in the display interface of the image to be authenticated is not obtained within the preset time period, it is determined that the preset identity authentication condition is met.

[0106] Optionally, the device further comprises: a storage module;

[0107] The saving module performs graded privacy protection processing on the image of the intended user and the image of the unintended user in the target image to obtain the image to be stored; wherein the grade of the image of the intended user is higher than the grade of the image of the unintended user; and saves the image to be stored to a designated storage location.

[0108] Optionally, the device further comprises: an adjustment module;

[0109] The adjustment module obtains the sense of security scores of the specified user group according to a preset method; and adjusts the privacy protection strategy of the identity authentication process according to the sense of security scores.

[0110] One or more embodiments of the present specification provide an identity authentication device based on privacy protection, which obtains a target image to be processed for privacy protection. If multiple faces are detected in the target image, the willing users who have the intention of identity authentication and the unwilling users who have no intention of identity authentication are identified among the multiple users according to the body feature information of the multiple users corresponding to the multiple faces; the faces of the unwilling users in the target image are subjected to a first desensitization process to obtain an image to be authenticated; if it is determined that the preset identity authentication conditions are met according to the image to be authenticated, the identity authentication process is performed according to the faces of the willing users in the image to be authenticated. Therefore, by identifying the unwilling users who have no intention of identity authentication corresponding to the target image, and performing the first desensitization process on the faces of the unwilling users in the target image and then performing the identity authentication process, not only the privacy information of the unwilling users is protected, but also the personal rights and interests of the unwilling users are effectively protected.

[0111] Furthermore, corresponding to the above Figure 6 The described identity authentication method based on privacy protection is based on the same technical concept, and one or more embodiments of this specification also provide another identity authentication device based on privacy protection. Figure 8 A schematic diagram of the module composition of another identity authentication device based on privacy protection provided in one or more embodiments of this specification, such as Figure 8 As shown, the device comprises:

[0112] An acquisition module 401 acquires a target image to be processed for privacy protection;

[0113] The identification module 402, if multiple faces are detected in the target image based on the smart contract in the blockchain system, identifies willing users who have the intention of identity authentication and unwilling users who do not have the intention of identity authentication among the multiple users according to the body feature information of the multiple users corresponding to the multiple faces;

[0114] The desensitization module 403 performs a first desensitization process on the face of the unwanted user in the target image based on the smart contract to obtain an image to be authenticated;

[0115] The authentication module 404 performs an authentication process based on the face of the intended user in the image to be authenticated, and obtains authentication result information if it is determined that the preset authentication condition is met according to the image to be authenticated;

[0116] The saving module 405 generates identity authentication record information according to the identity authentication result information, and saves the identity authentication record information in the blockchain system.

[0117] Optionally, the device further comprises: a processing module;

[0118] The processing module performs privacy protection processing on the image of the intended user and the image of the unintended user in the target image in a graded manner to obtain an image to be stored; wherein the grade of the image of the intended user is higher than the grade of the image of the unintended user;

[0119] The storage module determines the query information of the identity authentication result;

[0120] Identity authentication record information is generated according to the identity authentication result information, the image to be stored and the query information.

[0121] Optionally, the device further comprises: a query module;

[0122] The query module receives a query request sent by a querying party; and

[0123] According to the query information included in the query request, query corresponding identity authentication record information from the blockchain system;

[0124] The identity authentication result information in the queried identity authentication record information and the image to be stored are sent to the querying party.

[0125] The privacy protection-based identity authentication device provided by one or more embodiments of the present specification obtains a target image to be processed for privacy protection. If multiple faces are detected in the target image based on the smart contract in the blockchain system, the willing users with the willingness to authenticate and the unwilling users without the willingness to authenticate are identified among the multiple users according to the body feature information of the multiple users corresponding to the determined multiple faces; and the faces of the unwilling users in the target image are first desensitized based on the smart contract to obtain the image to be authenticated; if it is determined that the preset identity authentication conditions are met according to the image to be authenticated, the identity authentication is performed according to the faces of the willing users in the image to be authenticated. Thus, by identifying the unwilling users without the willingness to authenticate corresponding to the target image, and performing the first desensitization on the faces of the unwilling users in the target image and then performing the identity authentication, not only the privacy information of the unwilling users is protected, but also the rights and interests of the unwilling users are effectively maintained. The identification of willing users and unwilling users based on the smart contract can improve the recognition efficiency based on the characteristics of the smart contract. In addition, the identity authentication record is saved in the blockchain, and the validity of the identity authentication record can be ensured based on the characteristics of the blockchain, thereby providing an effective basis for subsequent related processing.

[0126] It should be noted that the embodiment of the identity authentication device based on privacy protection in this specification and the embodiment of the identity authentication method based on privacy protection in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the corresponding identity authentication method based on privacy protection mentioned above, and the repeated parts will not be repeated.

[0127] Further, corresponding to the above-described identity authentication method based on privacy protection, based on the same technical concept, one or more embodiments of this specification also provide an identity authentication device based on privacy protection, which is used to execute the above-described identity authentication method based on privacy protection. Fig. 9 A schematic diagram of the structure of an identity authentication device based on privacy protection provided in one or more embodiments of this specification.

[0128] like Fig. 9As shown, the identity authentication device based on privacy protection may have relatively large differences due to different configurations or performances, and may include one or more processors 501 and memory 502, and the memory 502 may store one or more storage applications or data. Among them, the memory 502 can be a short-term storage or a persistent storage. The application stored in the memory 502 may include one or more modules (not shown in the figure), and each module may include a series of computer executable instructions in the identity authentication device based on privacy protection. Furthermore, the processor 501 can be configured to communicate with the memory 502 to execute a series of computer executable instructions in the memory 502 on the identity authentication device based on privacy protection. The identity authentication device based on privacy protection may also include one or more power supplies 503, one or more wired or wireless network interfaces 504, one or more input and output interfaces 505, one or more keyboards 506, etc.

[0129] In a specific embodiment, the privacy protection-based identity authentication device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer executable instructions in the privacy protection-based identity authentication device, and the one or more programs are configured to be executed by one or more processors, including the following computer executable instructions:

[0130] Acquire a target image to be processed for privacy protection;

[0131] If multiple faces are detected in the target image, identifying willing users who are willing to authenticate their identities and unwilling users who are not willing to authenticate their identities among the multiple users according to the determined body feature information of the multiple users corresponding to the multiple faces;

[0132] Performing a first desensitization process on the face of the unwanted user in the target image to obtain an image to be authenticated;

[0133] If it is determined according to the image to be authenticated that a preset identity authentication condition is met, identity authentication processing is performed according to the face of the intended user in the image to be authenticated.

[0134] Optionally, when the computer executable instructions are executed, after detecting multiple faces in the target image, the method further includes:

[0135] For each of the human faces, detecting whether the target image includes a human body key point corresponding to the human face;

[0136] If so, determining the human body posture information of the corresponding user according to the human body key points, and using a pre-trained face posture regression model to determine the facial posture information of the face; determining the human body posture information and the facial posture information as the body feature information of the user;

[0137] If not, a pre-trained facial posture regression model is used to determine the facial posture information of the face, and the facial posture information is determined as the body feature information of the corresponding user.

[0138] Optionally, when the computer executable instructions are executed, determining that a preset identity authentication condition is satisfied according to the image to be authenticated includes:

[0139] Performing display processing on the image to be authenticated;

[0140] If confirmation information generated by the confirmation operation of the user to be authenticated in the display interface of the image to be authenticated is obtained, it is determined that the preset identity authentication condition is met; or,

[0141] If the desensitization cancellation information generated by the desensitization cancellation operation of the user to be authenticated in the display interface of the image to be authenticated is not obtained within the preset time period, it is determined that the preset identity authentication condition is met.

[0142] Optionally, when the computer executable instructions are executed, after determining that a preset identity authentication condition is satisfied according to the image to be authenticated, the instructions further include:

[0143] Performing privacy protection processing on the image of the intended user and the image of the unintended user in the target image in a graded manner to obtain an image to be stored; wherein the grade of the image of the intended user is higher than the grade of the image of the unintended user;

[0144] The image to be stored is saved to a designated storage location.

[0145] Optionally, when the computer executable instructions are executed, the method further comprises:

[0146] Obtain the sense of security score of the specified user group according to the preset method;

[0147] The privacy protection strategy of the identity authentication process is adjusted according to the sense of security score.

[0148] One or more embodiments of the present specification provide an identity authentication device based on privacy protection, which obtains a target image to be processed for privacy protection. If multiple faces are detected in the target image, the willing users who have the intention of identity authentication and the unwilling users who have no intention of identity authentication are identified among the multiple users according to the body feature information of the multiple users corresponding to the multiple faces; the faces of the unwilling users in the target image are subjected to a first desensitization process to obtain the image to be authenticated; if it is determined according to the image to be authenticated that the preset identity authentication conditions are met, the identity authentication process is performed according to the faces of the willing users in the image to be authenticated. Therefore, by identifying the unwilling users who have no intention of identity authentication corresponding to the target image, and performing the first desensitization process on the faces of the unwilling users in the target image and then performing the identity authentication process, not only the privacy information of the unwilling users is protected, but also the personal rights and interests of the unwilling users are effectively protected.

[0149] In another specific embodiment, the identity authentication device based on privacy protection includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer executable instructions for the identity authentication device based on privacy protection, and the one or more programs are configured to be executed by one or more processors, including computer executable instructions for performing the following:

[0150] Acquire a target image to be processed for privacy protection;

[0151] If multiple faces are detected in the target image based on the smart contract in the blockchain system, then, according to the body feature information of multiple users corresponding to the multiple faces, identifying willing users who have the intention of identity authentication and unwilling users who have no intention of identity authentication among the multiple users;

[0152] Performing a first desensitization process on the face of the unwanted user in the target image based on the smart contract to obtain an image to be authenticated;

[0153] If it is determined that the preset identity authentication condition is met according to the image to be authenticated, identity authentication processing is performed according to the face of the intended user in the image to be authenticated to obtain identity authentication result information;

[0154] Generate identity authentication record information according to the identity authentication result information, and save the identity authentication record information in the blockchain system.

[0155] Optionally, when the computer executable instructions are executed, after determining that a preset identity authentication condition is satisfied according to the image to be authenticated, the instructions further include:

[0156] Performing privacy protection processing on the image of the intended user and the image of the unintended user in the target image in a graded manner to obtain an image to be stored; wherein the grade of the image of the intended user is higher than the grade of the image of the unintended user;

[0157] The generating of identity authentication record information according to the identity authentication result information includes:

[0158] Determine query information of the identity authentication result;

[0159] Identity authentication record information is generated according to the identity authentication result information, the image to be stored and the query information.

[0160] Optionally, when the computer executable instructions are executed, the method further comprises:

[0161] Receiving a query request sent by a querying party;

[0162] According to the query information included in the query request, query corresponding identity authentication record information from the blockchain system;

[0163] The identity authentication result information in the queried identity authentication record information and the image to be stored are sent to the querying party.

[0164] The privacy protection-based identity authentication device provided by one or more embodiments of the present specification obtains a target image to be processed for privacy protection. If multiple faces are detected in the target image based on the smart contract in the blockchain system, the willing users with the willingness to authenticate and the unwilling users without the willingness to authenticate are identified among the multiple users according to the body feature information of the multiple users corresponding to the determined multiple faces; and the faces of the unwilling users in the target image are first desensitized based on the smart contract to obtain the image to be authenticated; if it is determined that the preset identity authentication conditions are met according to the image to be authenticated, the identity authentication is performed according to the faces of the willing users in the image to be authenticated. Thus, by identifying the unwilling users without the willingness to authenticate corresponding to the target image, and performing the first desensitization on the faces of the unwilling users in the target image and then performing the identity authentication, not only the privacy information of the unwilling users is protected, but also the rights and interests of the unwilling users are effectively maintained. The identification of willing users and unwilling users based on the smart contract can improve the recognition efficiency based on the characteristics of the smart contract. In addition, the identity authentication record is saved in the blockchain, and the validity of the identity authentication record can be ensured based on the characteristics of the blockchain, thereby providing an effective basis for subsequent related processing.

[0165] It should be noted that the embodiment of the identity authentication device based on privacy protection in this specification and the embodiment of the identity authentication method based on privacy protection in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the corresponding identity authentication method based on privacy protection mentioned above, and the repeated parts will not be repeated.

[0166] Furthermore, corresponding to the privacy protection-based identity authentication method described above, based on the same technical concept, one or more embodiments of this specification further provide a storage medium for storing computer executable instructions. In a specific embodiment, the storage medium may be a USB flash drive, an optical disk, a hard disk, etc. When the computer executable instructions stored in the storage medium are executed by the processor, the following process can be implemented:

[0167] Acquire a target image to be processed for privacy protection;

[0168] If multiple faces are detected in the target image, identifying willing users who are willing to authenticate their identities and unwilling users who are not willing to authenticate their identities among the multiple users according to the determined body feature information of the multiple users corresponding to the multiple faces;

[0169] Performing a first desensitization process on the face of the unwanted user in the target image to obtain an image to be authenticated;

[0170] If it is determined according to the image to be authenticated that a preset identity authentication condition is met, identity authentication processing is performed according to the face of the intended user in the image to be authenticated.

[0171] Optionally, when the computer executable instructions stored in the storage medium are executed by the processor, after detecting multiple faces in the target image, the method further includes:

[0172] For each of the human faces, detecting whether the target image includes a human body key point corresponding to the human face;

[0173] If so, determining the human body posture information of the corresponding user according to the human body key points, and using a pre-trained face posture regression model to determine the facial posture information of the face; determining the human body posture information and the facial posture information as the body feature information of the user;

[0174] If not, a pre-trained facial posture regression model is used to determine the facial posture information of the face, and the facial posture information is determined as the body feature information of the corresponding user.

[0175] Optionally, when the computer executable instructions stored in the storage medium are executed by the processor, determining that a preset identity authentication condition is satisfied according to the image to be authenticated includes:

[0176] Performing display processing on the image to be authenticated;

[0177] If confirmation information generated by the confirmation operation of the user to be authenticated in the display interface of the image to be authenticated is obtained, it is determined that the preset identity authentication condition is met; or,

[0178] If the desensitization cancellation information generated by the desensitization cancellation operation of the user to be authenticated in the display interface of the image to be authenticated is not obtained within the preset time period, it is determined that the preset identity authentication condition is met.

[0179] Optionally, when the computer executable instructions stored in the storage medium are executed by the processor, after determining that the preset identity authentication condition is met according to the image to be authenticated, the following further comprises:

[0180] Performing privacy protection processing on the image of the intended user and the image of the unintended user in the target image in a graded manner to obtain an image to be stored; wherein the grade of the image of the intended user is higher than the grade of the image of the unintended user;

[0181] The image to be stored is saved to a designated storage location.

[0182] Optionally, when the computer executable instructions stored in the storage medium are executed by the processor, the method further includes:

[0183] Obtain the sense of security score of the specified user group according to the preset method;

[0184] The privacy protection strategy of the identity authentication process is adjusted according to the sense of security score.

[0185] When the computer executable instructions stored in the storage medium provided in one or more embodiments of the present specification are executed by the processor, a target image to be processed for privacy protection is obtained. If multiple faces are detected in the target image, the willing users who have the intention of identity authentication and the unwilling users who have no intention of identity authentication are identified among the multiple users according to the body feature information of the multiple users corresponding to the multiple faces; the faces of the unwilling users in the target image are subjected to a first desensitization process to obtain the image to be authenticated; if it is determined according to the image to be authenticated that the preset identity authentication conditions are met, the identity authentication process is performed according to the faces of the willing users in the image to be authenticated. Therefore, by identifying the unwilling users who have no intention of identity authentication corresponding to the target image, and performing the first desensitization process on the faces of the unwilling users in the target image and then performing the identity authentication process, not only the privacy information of the unwilling users is protected, but also the personal rights and interests of the unwilling users are effectively protected.

[0186] In another specific embodiment, the storage medium may be a USB flash drive, an optical disk, a hard disk, etc. When the computer executable instructions stored in the storage medium are executed by the processor, the following process can be implemented:

[0187] Acquire a target image to be processed for privacy protection;

[0188] If multiple faces are detected in the target image based on the smart contract in the blockchain system, then, according to the body feature information of multiple users corresponding to the multiple faces, identifying willing users who have the intention of identity authentication and unwilling users who have no intention of identity authentication among the multiple users;

[0189] Performing a first desensitization process on the face of the unwanted user in the target image based on the smart contract to obtain an image to be authenticated;

[0190] If it is determined that the preset identity authentication condition is met according to the image to be authenticated, identity authentication processing is performed according to the face of the intended user in the image to be authenticated to obtain identity authentication result information;

[0191] Generate identity authentication record information according to the identity authentication result information, and save the identity authentication record information in the blockchain system.

[0192] Optionally, when the computer executable instructions stored in the storage medium are executed by the processor, after determining that the preset identity authentication condition is met according to the image to be authenticated, the following further comprises:

[0193] Performing privacy protection processing on the image of the intended user and the image of the unintended user in the target image in a graded manner to obtain an image to be stored; wherein the grade of the image of the intended user is higher than the grade of the image of the unintended user;

[0194] The generating of identity authentication record information according to the identity authentication result information includes:

[0195] Determine query information of the identity authentication result;

[0196] Identity authentication record information is generated according to the identity authentication result information, the image to be stored and the query information.

[0197] Optionally, when the computer executable instructions stored in the storage medium are executed by the processor, the method further includes:

[0198] Receiving a query request sent by a querying party;

[0199] According to the query information included in the query request, query corresponding identity authentication record information from the blockchain system;

[0200] The identity authentication result information in the queried identity authentication record information and the image to be stored are sent to the querying party.

[0201] When the computer executable instructions stored in the storage medium provided in one or more embodiments of the present specification are executed by the processor, the target image to be processed for privacy protection is obtained. If multiple faces are detected in the target image based on the smart contract in the blockchain system, the willing users with the willingness to authenticate and the unwilling users without the willingness to authenticate are identified among the multiple users according to the body feature information of the multiple users corresponding to the determined multiple faces; and the faces of the unwilling users in the target image are first desensitized based on the smart contract to obtain the image to be authenticated; if it is determined that the preset authentication conditions are met according to the image to be authenticated, the identity authentication is performed according to the faces of the willing users in the image to be authenticated. Thus, by identifying the unwilling users without the willingness to authenticate corresponding to the target image, and performing the first desensitization on the faces of the unwilling users in the target image and then performing the identity authentication, not only the privacy information of the unwilling users is protected, but also the rights and interests of the unwilling users are effectively maintained. The identification of willing users and unwilling users based on the smart contract can improve the recognition efficiency based on the characteristics of the smart contract. In addition, the identity authentication record is saved in the blockchain, and the validity of the identity authentication record can be ensured based on the characteristics of the blockchain, thereby providing an effective basis for subsequent related processing.

[0202] It should be noted that the embodiment of the storage medium in this specification and the embodiment of the identity authentication method based on privacy protection in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the aforementioned corresponding implementation of the identity authentication method based on privacy protection, and the repeated parts will not be repeated.

[0203] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0204] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0205] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0206] 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.

[0207] For the convenience of description, the above devices are described in terms of functions and are divided into various units. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0208] It should be understood by those skilled in the art that one or more embodiments of this specification may be provided as a method, system or computer program product. Therefore, one or more embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0209] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0210] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0211] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0212] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0213] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0214] 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.

[0215] 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.

[0216] One or more embodiments of the present specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of the present specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0217] 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.

[0218] The above description is only an embodiment of this document and is not intended to limit this document. For those skilled in the art, this document may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this document should be included in the scope of the claims of this document.

Claims

1. An identity authentication method based on privacy protection, comprising: Acquire a target image to be processed for privacy protection; If multiple faces are detected in the target image, identifying willing users who are willing to authenticate their identities and unwilling users who are not willing to authenticate their identities among the multiple users according to the determined body feature information of the multiple users corresponding to the multiple faces; Performing a first desensitization process on the face of the unwanted user in the target image to obtain an image to be authenticated; If it is determined that the preset identity authentication condition is met according to the image to be authenticated, identity authentication processing is performed according to the face of the intended user in the image to be authenticated; Wherein, determining that a preset identity authentication condition is satisfied according to the image to be authenticated includes: Performing display processing on the image to be authenticated; If confirmation information generated by the confirmation operation of the user to be authenticated in the display interface of the image to be authenticated is obtained, it is determined that the preset identity authentication condition is met; or, If the desensitization cancellation information generated by the desensitization cancellation operation of the user to be authenticated in the display interface of the image to be authenticated is not obtained within the preset time period, it is determined that the preset identity authentication condition is met; If desensitization cancellation information generated by the desensitization cancellation operation of the to-be-authenticated user in the display interface of the to-be-authenticated image is obtained, the target face to be desensitized is determined according to the desensitization cancellation information; the desensitization cancellation information includes: area information of the area where the desensitization information to be canceled is located; If it is determined that the preset desensitization cancellation condition is met, the first desensitization processing is performed on the non-desensitized face in the image to be authenticated, and the target face is restored, and the image after the target face is restored is determined as the image to be authenticated.

2. The method according to claim 1, after detecting multiple faces in the target image, further comprising: For each of the human faces, detecting whether the target image includes a human body key point corresponding to the human face; If so, determining the human body posture information of the corresponding user according to the human body key points, and using a pre-trained face posture regression model to determine the facial posture information of the face; determining the human body posture information and the facial posture information as the body feature information of the user; If not, a pre-trained face posture regression model is used to determine the face posture information of the face, and the face posture information is determined as the body feature information of the corresponding user.

3. The method according to claim 2, wherein the human body key points include shoulder key points, and the step of determining the human body posture information of the corresponding user according to the human body key points comprises: Determine a first distance between the shoulder key points according to the coordinate information of the shoulder key points; Detecting binocular key points of the face, and determining a second distance between the binocular key points according to coordinate information of the binocular key points; Human body posture information is determined according to the first distance and the second distance.

4. The method according to claim 2, wherein the step of identifying willing users who are willing to authenticate their identities and unwilling users who are not willing to authenticate their identities among the multiple users based on the determined body feature information of the multiple users corresponding to the multiple faces comprises: When the body feature information includes the human body posture information and the facial posture information, determining whether the human body posture information and the facial posture information meet a first preset condition; if so, determining that the corresponding user is a willing user with an identity authentication intention; if not, determining that the corresponding user is an unintentional user without an identity authentication intention; When the body feature information includes the facial posture information, determine whether the facial posture information meets the second preset condition; if so, determine that the corresponding user is a willing user with the intention of identity authentication; if not, determine that the corresponding user is an unintentional user without the intention of identity authentication.

5. According to the method of claim 1, performing a first desensitization process on the face of the unwanted user in the target image to obtain the image to be authenticated comprises: Performing a non-face image adding process on the face of the unwanted user in the target image; or, A mosaic is added to the face of the unwanted user in the target image.

6. The method according to claim 5, after determining the target face to be de-desensitized according to the de-desensitization information, further comprising: If a user image of the specified behavior of the user to be authenticated is obtained, and the face in the user image successfully matches the target face, it is determined that the preset desensitization cancellation condition is met.

7. The method according to claim 1, after determining that the image to be authenticated satisfies a preset identity authentication condition, further comprising: Performing privacy protection processing on the image of the intended user and the image of the unintended user in the target image in a graded manner to obtain an image to be stored; wherein the grade of the image of the intended user is higher than the grade of the image of the unintended user; The image to be stored is saved to a designated storage location.

8. The method according to claim 7, performing hierarchical privacy protection processing on the image of the intended user and the image of the unintended user in the target image to obtain the image to be stored, comprising: Using a pre-trained privacy protection model, perform a second desensitization process on the image of the intended user in the target image to obtain an intermediate image; According to a preset encryption algorithm, the image of the unwanted user in the intermediate image is encrypted to obtain an image to be stored.

9. The method according to claim 1, further comprising: Obtain the sense of security score of the specified user group according to the preset method; The privacy protection strategy of the identity authentication process is adjusted according to the sense of security score.

10. The method according to claim 9, wherein obtaining the sense of security score of the specified user group according to a preset method comprises: Sending a questionnaire to a designated user group, and determining a sense of security score of the designated user group based on the obtained response information of the questionnaire; or, Acquire historical behavior data related to identity authentication of a specified user group, and determine a sense of security score of the specified user group based on the historical behavior data; The designated user group includes a first user group that adopts the privacy protection policy and a second user group that does not adopt the privacy protection policy.

11. An identity authentication method based on privacy protection, comprising: Acquire a target image to be processed for privacy protection; If multiple faces are detected in the target image based on the smart contract in the blockchain system, then, according to the body feature information of multiple users corresponding to the multiple faces, identifying willing users who have the intention of identity authentication and unwilling users who have no intention of identity authentication among the multiple users; Performing a first desensitization process on the face of the unwanted user in the target image based on the smart contract to obtain an image to be authenticated; If it is determined that the preset identity authentication condition is met according to the image to be authenticated, identity authentication processing is performed according to the face of the intended user in the image to be authenticated to obtain identity authentication result information; Generate identity authentication record information according to the identity authentication result information, and save the identity authentication record information in the blockchain system; Wherein, determining that a preset identity authentication condition is satisfied according to the image to be authenticated includes: Performing display processing on the image to be authenticated; If confirmation information generated by the confirmation operation of the user to be authenticated in the display interface of the image to be authenticated is obtained, it is determined that the preset identity authentication condition is met; or, If the desensitization cancellation information generated by the desensitization cancellation operation of the user to be authenticated in the display interface of the image to be authenticated is not obtained within the preset time period, it is determined that the preset identity authentication condition is met; If desensitization cancellation information generated by the desensitization cancellation operation of the to-be-authenticated user in the display interface of the to-be-authenticated image is obtained, the target face to be desensitized is determined according to the desensitization cancellation information; the desensitization cancellation information includes: area information of the area where the desensitization information to be canceled is located; If it is determined that the preset desensitization cancellation condition is met, the first desensitization processing is performed on the non-desensitized face in the image to be authenticated, and the target face is restored, and the image after the target face is restored is determined as the image to be authenticated.

12. The method according to claim 11, after determining that the image to be authenticated satisfies a preset identity authentication condition, further comprising: Performing privacy protection processing on the image of the intended user and the image of the unintended user in the target image in a graded manner to obtain an image to be stored; wherein the grade of the image of the intended user is higher than the grade of the image of the unintended user; The generating of identity authentication record information according to the identity authentication result information includes: Determine query information of the identity authentication result; Identity authentication record information is generated according to the identity authentication result information, the image to be stored and the query information.

13. The method according to claim 12, further comprising: Receiving a query request sent by a querying party; According to the query information included in the query request, query corresponding identity authentication record information from the blockchain system; The identity authentication result information in the queried identity authentication record information and the image to be stored are sent to the querying party.

14. An identity authentication device based on privacy protection, comprising: An acquisition module, for acquiring a target image to be processed for privacy protection; a recognition module, if multiple faces are detected in the target image, identifying willing users who have the intention to authenticate their identities and unwilling users who have no intention to authenticate their identities among the multiple users according to the determined body feature information of the multiple users corresponding to the multiple faces; A desensitization module performs a first desensitization process on the face of the unwanted user in the target image to obtain an image to be authenticated; an authentication module, which performs identity authentication processing based on the face of the intended user in the image to be authenticated, if it is determined that the preset identity authentication condition is met according to the image to be authenticated; Wherein, determining that a preset identity authentication condition is satisfied according to the image to be authenticated includes: Performing display processing on the image to be authenticated; If confirmation information generated by the confirmation operation of the user to be authenticated in the display interface of the image to be authenticated is obtained, it is determined that the preset identity authentication condition is met; or, If the desensitization cancellation information generated by the desensitization cancellation operation of the user to be authenticated in the display interface of the image to be authenticated is not obtained within the preset time period, it is determined that the preset identity authentication condition is met; If desensitization cancellation information generated by the desensitization cancellation operation of the to-be-authenticated user in the display interface of the to-be-authenticated image is obtained, the target face to be desensitized is determined according to the desensitization cancellation information; the desensitization cancellation information includes: area information of the area where the desensitization information to be canceled is located; If it is determined that the preset desensitization cancellation condition is met, the first desensitization processing is performed on the non-desensitized face in the image to be authenticated, and the target face is restored, and the image after the target face is restored is determined as the image to be authenticated.

15. An identity authentication device based on privacy protection, comprising: An acquisition module, for acquiring a target image to be processed for privacy protection; an identification module, which, if multiple faces are detected in the target image based on the smart contract in the blockchain system, identifies willing users who have the intention of identity authentication and unwilling users who do not have the intention of identity authentication among the multiple users according to the body feature information of the multiple users corresponding to the multiple faces; A desensitization module, performing a first desensitization process on the face of the unwanted user in the target image based on the smart contract to obtain an image to be authenticated; The authentication module performs an identity authentication process based on the face of the intended user in the image to be authenticated, and obtains identity authentication result information if it is determined that the preset identity authentication condition is met according to the image to be authenticated; A saving module generates identity authentication record information according to the identity authentication result information, and saves the identity authentication record information in the blockchain system; Wherein, determining that a preset identity authentication condition is satisfied according to the image to be authenticated includes: Performing display processing on the image to be authenticated; If confirmation information generated by the confirmation operation of the user to be authenticated in the display interface of the image to be authenticated is obtained, it is determined that the preset identity authentication condition is met; or, If the desensitization cancellation information generated by the desensitization cancellation operation of the user to be authenticated in the display interface of the image to be authenticated is not obtained within the preset time period, it is determined that the preset identity authentication condition is met; If desensitization cancellation information generated by the desensitization cancellation operation of the to-be-authenticated user in the display interface of the to-be-authenticated image is obtained, the target face to be desensitized is determined according to the desensitization cancellation information; the desensitization cancellation information includes: area information of the area where the desensitization information to be canceled is located; If it is determined that the preset desensitization cancellation condition is met, the first desensitization processing is performed on the non-desensitized face in the image to be authenticated, and the target face is restored, and the image after the target face is restored is determined as the image to be authenticated.

16. An identity authentication device based on privacy protection, comprising: processor; as well as, a memory arranged to store computer executable instructions which, when executed, cause the processor to: Acquire a target image to be processed for privacy protection; If multiple faces are detected in the target image, identifying willing users who are willing to authenticate their identities and unwilling users who are not willing to authenticate their identities among the multiple users according to the determined body feature information of the multiple users corresponding to the multiple faces; Performing a first desensitization process on the face of the unwanted user in the target image to obtain an image to be authenticated; If it is determined that the preset identity authentication condition is met according to the image to be authenticated, identity authentication processing is performed according to the face of the intended user in the image to be authenticated; Wherein, determining that a preset identity authentication condition is satisfied according to the image to be authenticated includes: Performing display processing on the image to be authenticated; If confirmation information generated by the confirmation operation of the user to be authenticated in the display interface of the image to be authenticated is obtained, it is determined that the preset identity authentication condition is met; or, If the desensitization cancellation information generated by the desensitization cancellation operation of the user to be authenticated in the display interface of the image to be authenticated is not obtained within the preset time period, it is determined that the preset identity authentication condition is met; If desensitization cancellation information generated by the desensitization cancellation operation of the to-be-authenticated user in the display interface of the to-be-authenticated image is obtained, the target face to be desensitized is determined according to the desensitization cancellation information; the desensitization cancellation information includes: area information of the area where the desensitization information to be canceled is located; If it is determined that the preset desensitization cancellation condition is met, the first desensitization processing is performed on the non-desensitized face in the image to be authenticated, and the target face is restored, and the image after the target face is restored is determined as the image to be authenticated.

17. An identity authentication device based on privacy protection, comprising: processor; as well as, a memory arranged to store computer executable instructions which, when executed, cause the processor to: Acquire a target image to be processed for privacy protection; If multiple faces are detected in the target image based on the smart contract in the blockchain system, then, according to the body feature information of multiple users corresponding to the multiple faces, identifying willing users who have the intention of identity authentication and unwilling users who have no intention of identity authentication among the multiple users; Performing a first desensitization process on the face of the unwanted user in the target image based on the smart contract to obtain an image to be authenticated; If it is determined that the preset identity authentication condition is met according to the image to be authenticated, identity authentication processing is performed according to the face of the intended user in the image to be authenticated to obtain identity authentication result information; Generate identity authentication record information according to the identity authentication result information, and save the identity authentication record information in the blockchain system; Wherein, determining that a preset identity authentication condition is satisfied according to the image to be authenticated includes: Performing display processing on the image to be authenticated; If confirmation information generated by the confirmation operation of the user to be authenticated in the display interface of the image to be authenticated is obtained, it is determined that the preset identity authentication condition is met; or, If the desensitization cancellation information generated by the desensitization cancellation operation of the user to be authenticated in the display interface of the image to be authenticated is not obtained within the preset time period, it is determined that the preset identity authentication condition is met; If desensitization cancellation information generated by the desensitization cancellation operation of the to-be-authenticated user in the display interface of the to-be-authenticated image is obtained, the target face to be desensitized is determined according to the desensitization cancellation information; the desensitization cancellation information includes: area information of the area where the desensitization information to be canceled is located; If it is determined that the preset desensitization cancellation condition is met, the first desensitization processing is performed on the non-desensitized face in the image to be authenticated, and the target face is restored, and the image after the target face is restored is determined as the image to be authenticated.

18. A storage medium for storing computer executable instructions, wherein the computer executable instructions, when executed by a processor, implement the following process: Acquire a target image to be processed for privacy protection; If multiple faces are detected in the target image, identifying willing users who are willing to authenticate their identities and unwilling users who are not willing to authenticate their identities among the multiple users according to the determined body feature information of the multiple users corresponding to the multiple faces; Performing a first desensitization process on the face of the unwanted user in the target image to obtain an image to be authenticated; If it is determined that the preset identity authentication condition is met according to the image to be authenticated, identity authentication processing is performed according to the face of the intended user in the image to be authenticated; Wherein, determining that a preset identity authentication condition is satisfied according to the image to be authenticated includes: Performing display processing on the image to be authenticated; If confirmation information generated by the confirmation operation of the user to be authenticated in the display interface of the image to be authenticated is obtained, it is determined that the preset identity authentication condition is met; or, If the desensitization cancellation information generated by the desensitization cancellation operation of the user to be authenticated in the display interface of the image to be authenticated is not obtained within the preset time period, it is determined that the preset identity authentication condition is met; If desensitization cancellation information generated by the desensitization cancellation operation of the to-be-authenticated user in the display interface of the to-be-authenticated image is obtained, the target face to be desensitized is determined according to the desensitization cancellation information; the desensitization cancellation information includes: area information of the area where the desensitization information to be canceled is located; If it is determined that the preset desensitization cancellation condition is met, the first desensitization processing is performed on the non-desensitized face in the image to be authenticated, and the target face is restored, and the image after the target face is restored is determined as the image to be authenticated.

19. A storage medium for storing computer executable instructions, wherein the computer executable instructions, when executed by a processor, implement the following process: Acquire a target image to be processed for privacy protection; If multiple faces are detected in the target image based on the smart contract in the blockchain system, then, according to the body feature information of multiple users corresponding to the multiple faces, identifying willing users who have the intention of identity authentication and unwilling users who have no intention of identity authentication among the multiple users; Performing a first desensitization process on the face of the unwanted user in the target image based on the smart contract to obtain an image to be authenticated; If it is determined that the preset identity authentication condition is met according to the image to be authenticated, identity authentication processing is performed according to the face of the intended user in the image to be authenticated to obtain identity authentication result information; Generate identity authentication record information according to the identity authentication result information, and save the identity authentication record information in the blockchain system; Wherein, determining that a preset identity authentication condition is satisfied according to the image to be authenticated includes: Performing display processing on the image to be authenticated; If confirmation information generated by the confirmation operation of the user to be authenticated in the display interface of the image to be authenticated is obtained, it is determined that the preset identity authentication condition is met; or, If the desensitization cancellation information generated by the desensitization cancellation operation of the user to be authenticated in the display interface of the image to be authenticated is not obtained within the preset time period, it is determined that the preset identity authentication condition is met; If desensitization cancellation information generated by the desensitization cancellation operation of the to-be-authenticated user in the display interface of the to-be-authenticated image is obtained, the target face to be desensitized is determined according to the desensitization cancellation information; the desensitization cancellation information includes: area information of the area where the desensitization information to be canceled is located; If it is determined that the preset desensitization cancellation condition is met, the first desensitization processing is performed on the non-desensitized face in the image to be authenticated, and the target face is restored, and the image after the target face is restored is determined as the image to be authenticated.

Images