WO2018233487A1

WO2018233487A1 - Identity authentication method, terminal and storage medium

Info

Publication number: WO2018233487A1
Application number: PCT/CN2018/090082
Authority: WO
Inventors: 潘福霞
Original assignee: 腾讯科技（深圳）有限公司
Priority date: 2017-06-22
Filing date: 2018-06-06
Publication date: 2018-12-27
Also published as: CN109117688A

Abstract

Disclosed are an identity authentication method, a terminal and a storage medium. The method comprises: receiving from a server verification information required when recording a video, and outputting the verification information on a client page; acquiring the video recorded by a user on the client page, the video containing image data of the user reading the verification information; according to the image data, performing living verification on a user image in the video; and after the living verification is passed, verifying the identity of the user according to the image data.

Description

Identity authentication method, terminal and storage medium

This application claims the priority of the Chinese Patent Application entitled "Identification Method, Apparatus and Mobile Terminal" filed on June 22, 2017 by the Chinese Patent Office, Application No. 201710479266.2.

Technical field

The present application belongs to the field of information processing technologies, and in particular, to an identity authentication method, a terminal, and a storage medium.

Background of the invention

In life, there are many scenes that need to prove their identity online. For example, the hotel has forgotten to bring ID cards, the survival verification before the old-age pension is received, and the business qualification certificate is processed online at home.

In the prior art, online authentication can be implemented through an APP (application) provided by an enterprise or a public institution. However, the method of authenticating through the APP requires an APP to be installed, which reduces the convenience of the user operation, and the APP Increased costs when promoting.

Summary of the invention

The embodiment of the present application provides an identity authentication method, a terminal, and a storage medium, which are designed to solve the problem that the authentication accuracy of the live authentication technology is easily solved by the online authentication method, and the cost increase caused by the APP authentication. .

An identity authentication method provided by an embodiment of the present application includes:

Receiving verification information required for recording a video from a server, and outputting the verification information on a client page;

Obtaining a video recorded by the user on the client page, where the video includes image data that the user reads the verification information;

Performing a live verification on the user image in the video according to the image data; and

After verification by the living body, the identity of the user is verified based on the image data.

A terminal provided by an embodiment of the present application includes a processor and a memory, where the memory stores instructions executable by the processor, and when the instruction is executed, the processor is configured to:

The embodiment of the present application further provides a computer readable storage medium storing computer readable instructions, which can cause at least one processor to perform the method as described above.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the embodiments or the prior art description will be briefly described below. Obviously, the drawings in the following description are only It is a certain embodiment of the present application, and other drawings can be obtained according to the drawings without any creative labor for those skilled in the art.

1a is a schematic structural diagram of an identity authentication system according to an embodiment of the present application;

FIG. 1b is a schematic flowchart of an identity authentication method according to a first embodiment of the present application;

2 is a schematic diagram of a prompt interface for recording a video in an embodiment of the present application;

3 is a schematic flowchart of an identity authentication method according to a second embodiment of the present application;

4 is a schematic diagram of an interface for a user to take a front photo of an identity document and prepare for uploading in the embodiment of the present application;

FIG. 5 is a schematic diagram of an interface for successfully uploading both the front photo and the reverse photo of the identity card in the embodiment of the present application; FIG.

6 is a schematic diagram of a recording interface when a user reads a verification message in an embodiment of the present application;

FIG. 7 is a schematic structural diagram of an identity authentication apparatus according to a third embodiment of the present disclosure;

FIG. 8 is a schematic structural diagram of an identity authentication apparatus according to a fourth embodiment of the present disclosure

FIG. 9 is a structural diagram of a terminal hardware for performing an identity authentication method in the present application.

Implementation

In order to make the object, the features and the advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the drawings in the embodiments of the present application. The embodiments are only a part of the embodiments of the present application, and not all of them. All other embodiments obtained by a person skilled in the art based on the embodiments of the present application without creative efforts are within the scope of the present application.

In the existing APP authentication method, the living body verification technology used requires a simple action of fixing the human body, and the action set is single and limited in number, and is easy to be solved by means of portrait modeling, thereby reducing the accuracy of living body detection, thereby reducing the identity. The accuracy of the certification.

The application scenarios of the following embodiments of the present application are online authentication user identity, that is, online real-name authentication. FIG. 1 is a schematic structural diagram of an identity authentication system according to an embodiment of the present application. As shown in FIG. 1a, the identity authentication system 100 includes a server 110, a terminal 120, and a user 130. The server 110 includes a database 111 for storing authentication photos, a database 112 for storing verification information, a live verification engine 113, and an image comparison engine 114.

According to the embodiment of the present application, the user 130 uploads the ID card photo in the page of the public service platform displayed by the terminal 120, and identifies the identity information in the ID card photo. After the identity information is identified, the user identity is verified from the storage identity according to the identity information. The photo database 111, such as the Public Security Bureau's document library, extracts the user's authentication photo.

Further, the terminal 120 obtains a randomly generated verification code from the database 112 storing the verification information, and prompts the user to record a video that reads the verification code on the page, uploads the video to the living body verification engine 113, and performs in-vivo verification on the user. After receiving the notification message by the living body verification from the biometric verification engine 113, the user image in the video is compared with the user's authentication photo uploading image comparison engine 114 extracted from the public security bureau document library to identify the user image. Whether the person in the identity and the person in the identity photo of the user are the same person, if the same person receives the notification message confirming the identity of the user from the image matching engine 114, thereby completing the online real-name authentication of the user.

For a description of specific technical solutions, refer to the following embodiments.

Referring to FIG. 1b, FIG. 1b is a schematic flowchart of an identity authentication method according to a first embodiment of the present application. The identity authentication method may be applied to a terminal, where the terminal includes a mobile phone, a tablet computer, an intelligent authentication terminal, and the like, and has a video recording function. A terminal for network communication functions. The method includes:

S101. Receive verification information required for recording a video from a server, and output verification information on a client page.

In this embodiment, the identity authentication of the user is performed on the client page. Specifically, the client page is a page of a public service platform, such as an authentication page of a WeChat public number, and the WeChat public number is an enterprise that requires the user to perform identity verification. Public number opened by business, state agencies, etc. For example, when a user needs to authenticate online at a bank, the client page is the authentication page of the bank's WeChat public account. The client page is built using HTML5 (Hypertext Markup Language Fifth Edition, h5 for short) technology. With h5 technology, simple information collection can be done at the front end, and other complex authentication processes can be completed by calling other modules in the background. Compared with the authentication, it is necessary to download the APP developed by each certification department, which is easy to operate and low in cost.

In the client page, the verification information is output. The verification information can be randomly generated by the background server, and the client immediately pulls it to the local and outputs the information. The verification information can also be extracted from the background server and stored in the terminal locally, and then output by the client. The verification information is unique, and the specific form may be a verification code composed of a plurality of digits, for example, 5869; or a verification block composed of a plurality of Chinese characters, for example, Teng Shenheng. Since the verification information is randomly generated, non-repetitive, and unique, it is not easy to crack the verification information in a modeling or traversing manner, and the security is strong.

Further, when the verification information is output, the recording method is prompted on the client page, as shown in FIG. 2, which is a client that registers the entire electronic system of the enterprise, and displays “Please use the front camera to record on the client page. The word "video of the above number is read aloud at a constant speed" and the requirement for displaying the length of the video is as shown in Fig. 2, "the video length is controlled at 3-6 seconds".

Further, when the verification information is output, the video recording rule can be output on the client page at the same time. Specifically, the video recording rule may be displayed when the user clicks the button that triggers the recording; or the button that triggers the display of the video recording rule is set on the client page, and the video recording rule is displayed when the user clicks the button.

The video recording rules include: the specification of the facial motion when the user records the video, the specification of the facial image of the user, the regulation of the recording environment, the speech rate, the intonation, and the language of the user to read the verification information.

Specifically, the facial motion includes an eye movement that blinks when the verification information is read, and a clear lip motion is made. It should be noted that the apparent lip motion refers to the visibility of the lip motion, which enables the living body to be verified. It is accurately determined that the user is a living body, and the lip shape read from the reading can recognize the verification information read by the user. The specification of the user's face image includes: the face image is complete, and the proportion of the face occupied by the face, for example, the face occupies 3/4 of the screen. The requirements for the recording environment include: the light is appropriate, avoiding too strong or too weak; the environment is quiet, avoiding lens shake. The rules for the speed, intonation, and language of the user's reading of the verification information include: uniform speed, reading aloud, reading in Mandarin, and the like.

Outputting the video recording rule while outputting the verification information on the client page can help the user to record the qualified video as soon as possible, and improve the speed and accuracy of the authenticated user identity.

S102. Acquire a video recorded by the user on the client page, where the video includes image data of the user reading the verification information;

After the user uploads the video, the client obtains a video recorded by the user on the client page to read the verification information, and the video includes image data of the facial action specified by the video recording rule that the user performs when reading the verification information.

The video contains facial actions that are specified by the user, such as blinking, lip movements, and the like. The video also includes audio data that the user reads the verification information, and the audio data can be used to detect whether the verification information read by the user is the same as the verification information output on the client page and required to be read by the user, and is used to detect the Whether the image in the video is alive.

S103. Perform live verification on the user image in the video according to the image data.

In-vivo verification refers to the technique of verifying whether the user image in the video is an objective living entity (real person). To prevent the user image in the video as a static photo, or a 3D modeled character model, usually used to confirm the identity of the target person.

In this step, a facial motion that conforms to the video recording rule is identified from the image data; and the user image in the video is verified in vivo according to the facial motion. That is, according to the user's facial motion in the video recorded by the user, specifically blinking or lip motion, to verify whether the user image in the video is a living body.

S104. After verification by the living body, verify the identity of the user according to the image data.

After the biometric verification, it is necessary to further confirm that the living body is the same person as the user, and therefore the identity of the user needs to be further verified based on the image data in the video.

After the user's identity is verified according to the image data, it is confirmed that the user identity authentication is successful, that is, the user real name authentication is successful.

In the embodiment of the present application, the video recorded by the user is obtained on the client page, and the user in the video is verified in vivo, and after the verification by the living body, the identity of the user is verified according to the image data in the video, and after the identity verification, Confirm that the user identity authentication is successful, which has the following technical effects:

1) Compared with various APPs specially used for identity authentication, identity authentication is performed on the client webpage, which is easy to operate and low in cost.

2) A dual verification scheme based on video recognition for live verification and image recognition based authentication is proposed, which solves the problem that the user does not carry an ID card or carry an ID card in a service that needs to be authenticated. The need to go to the counter to handle business problems, to achieve a reliable online authentication method, improve the user experience, while facilitating the handling of various business or administrative affairs.

3) With the expansion of user scale and business scenarios, ID card photo files and user self-portrait video files accumulated in various services provide traceable clues in security scenarios such as combating illegal identity fraud.

Referring to FIG. 3, FIG. 3 is a method for authenticating an identity according to a second embodiment of the present application, which may be applied to a terminal, where the method includes:

S201. Collect, in the client page, the identity information of the identity file uploaded by the user, and after determining that the identity information is recognized, the identity verification photo corresponding to the identity information is retrieved from the server;

In this embodiment, the identity authentication of the user is completed on the client page, and the page is produced by using HTML5 technology. Specifically, the client page may be an authentication page of a WeChat public number, and the WeChat public number is a public number opened by an enterprise or a state agency that requires the user to perform identity verification. For example, when a user needs to authenticate online at a bank, the client page is the authentication page of the bank's WeChat public account.

In the client page, the user is prompted to upload a photo of the identity document, and identify the name, the ID number, the issuing authority, and the textual information of the validity period of the ID file uploaded by the user, specifically, optical character recognition (OCR) (Optical Character Recognition) technology, directly convert the text of the scanned copy of the user's ID or the text on the photo into text, thereby obtaining the text information such as the name, ID number, issuing authority and validity period of the ID card. .

Further, the consistency check is performed according to the name and the ID number, that is, whether the verification name and the ID number correspond to each other; according to the legality verification by the issuing authority, that is, whether the issuing authority is a legal authority; The validity period of the certificate is verified, that is, after the consistency check, the legality check, and the validity check are passed, the authentication photo corresponding to the ID number is retrieved from the server (such as the designated platform). The authentication photo is a photo provided by the department with identification authority to verify the identity of the user. For example, the authentication photo is a personal photo uploaded by the natural person when the identity document is processed, and the photo is the same as the photo of the identity document. The designated platform may specifically be a server or database for storing the authentication photos collected by the public security organ. Further, if the consistency check, the legality check, and one or both of the validity check fail the verification, the identification failure is prompted.

Specifically, the user is prompted to upload a positive photo of the ID card, and the user takes a picture of the front side of the ID card and uploads it, as shown in FIG. 4 . After obtaining the front photo of the ID card uploaded by the user, after identifying the name and ID number of the front photo through the OCR module, the user is prompted to upload the reverse photo of the ID card, and the certificate of the reverse photo is recognized by the OCR module. After the information of the validity period of the authority and the certificate, the user is prompted to upload the ID card photo successfully, and the identified information is displayed, prompting the user to confirm whether the information is correct. If not, re-uploading the front photo of the ID card corresponding to the error message and/or The reverse photo, or, manually enter the above ID information. The specific display interface is shown in Figure 5.

S202. Receive verification information required for recording a video from a server, and output verification information on a client page.

After the identification of the ID card is passed, when the user clicks to perform the next operation, the verification information is obtained, and the verification information is output. The verification information can be randomly generated by the background server, and the client immediately pulls it to the local and outputs the information. The verification information can also be extracted from the background server and stored in the terminal locally, and directly output by the client.

The verification information is unique, and the specific form may be a verification code composed of a plurality of digits; or may be a verification block composed of a plurality of Chinese characters. Since the verification information is randomly generated, non-repetitive, and unique, it is not easy to crack the verification information in a modeling or traversing manner, and the security is strong.

Further, when the verification information is output, the video recording rule is simultaneously output on the client page. The video recording rules include: the specification of the facial motion when the user records the video, the specification of the facial image of the user, the regulation of the recording environment, the speech rate, the intonation, and the language of the user to read the verification information. Output video recording rules to help users record qualified videos as quickly as possible, improving the speed and accuracy of authenticating users.

Specifically, the facial motion includes blinking and making a clear lip motion when reading the verification information. When it is necessary to explain, the obvious lip motion means that the lip movement is so obvious that the user can accurately determine the user during the verification of the living body. It is a living body, and the lip shape that is read aloud can recognize the verification information read by the user. The specification of the user's face image includes: the face image is complete, and the proportion of the face occupied by the face, for example, the face occupies 3/4 of the screen. The requirements for the recording environment include: the light is appropriate, avoiding too strong or too weak; the environment is quiet, avoiding lens shake. The rules for the speed, intonation, and language of the user's reading of the verification information include: uniform speed, reading aloud, reading in Mandarin, and the like.

S203. Acquire a video recorded by the user on the client page to read the verification information, where the video includes image data of a facial action specified by the video recording rule that is prepared when the user reads the verification information;

FIG. 6 is a schematic diagram of a recording interface when a user reads a verification message in an embodiment of the present application. As shown in FIG. 6, during the video recording process, the camera of the terminal is called to record, and the time required for recording and the recording progress time are prompted.

After the user uploads the video, the video recording rule is used to detect whether the video recorded by the user meets the specifications. If not, the user is prompted to record the video that has not passed the review, and the video recording rule is output again for the user to view and record the video again. The probability of a user recording a qualified video can be further improved.

After the video recorded by the user passes the audit, the client obtains a video recorded by the user on the client page to read the verification information, and the video includes the facial action specified by the video recording rule when the user reads the verification information. Image data.

The length of the video is the duration specified by the system, for example, 3-6 seconds. The specified duration can further improve the accuracy of the user's biometric verification. The video contains facial actions that are specified by the user, such as blinking, lip movements, and the like.

The video includes audio data that the user reads the verification information, and the audio data can be used to detect whether the verification information read by the user is the same as the verification information that is output on the client page and requires the user to read aloud.

S204. Perform live verification on the user image in the video according to the facial action.

Specifically, the living body verification engine in the background is called, and the lip action and the eye action of the face are acquired according to the facial action, and further, the facial features of the face can be acquired.

In an embodiment, according to the lip action, it is determined whether the verification information read by the user and the output verification information are consistent, that is, whether the verification information read by the user image in the video is correct. More specifically, determining a lip shape change feature when the user reads a plurality of characters in the verification information, and matching the lip shape change feature with the preset lip shape feature, for example, when the matching degree reaches a preset value, for example, reaching 70%, Then, it is confirmed that the verification information read by the user is consistent with the verification information output.

It should be noted that the characters may include one or more of a number, a foreign language letter, and a Chinese character. The output verification information is selected from a living body verification database corresponding to the living body verification engine, and the characters in the lip verification action are read in the living body verification database, so that the set verification information includes a plurality of characters. When the plurality of characters are read out one by one, the lip feature distinguishing degree of each character reaches a preset standard, and the preset standard means that the characters that are read aloud can be accurately distinguished according to the lip shape, so as to complete the living body verification.

The preset lip features are also stored in the biometric verification database corresponding to the biometric verification engine. Generally, the lip feature is stored in the biometric verification database in the form of an image. When the lip matching is performed, the lip image of each character is captured in the video of the reading verification information recorded by the user, and each lip is respectively The shape image is matched with the image of the corresponding lip feature in the living body verification database, the matching degree of each lip image is calculated, and the matching degree of each lip image is weighted and summed to obtain a user's reading. The matching degree of the verification information and the output verification information is consistent.

In another embodiment, according to the facial motion, the eye motion of the facial is acquired; according to the eye motion, whether the user makes an eye motion that meets the requirements of the video recording rule; if the user makes an eye that meets the requirements of the video recording rule For the part action, confirm the verification by the living body.

Further, when the user reads the verification information, the change feature of the pupil is matched with the pupil change feature included in the preset blink action, and when the matching degree reaches the preset value, the user is confirmed to comply with the video recording rule. Blinking action. The preset value is generally 70%, and may be other values, which are not limited herein.

It should be noted that when an eye closes the eye when blinking, the image of the eye that is obtained is an image without a pupil, and the moment of opening the eye is an image with a pupil, and therefore, according to the variation characteristics of the pupil The pupil change features included in the blink action are matched to confirm whether the user has made a blink action that meets the video recording rules.

Further, determining whether the acquired facial features, eye movements, and lip movements meet the preset living body feature information, wherein the preset living body feature information is stored in the living body verification database as standard information for confirming that the image in the video is a living body. . If the verification information read by the user is consistent with the output verification information, and the user makes a blinking action that complies with the video recording rule, the confirmation is confirmed by the living body. Further, it is also possible to confirm the verification by the living body when the acquired facial features, eye movements, and lip movements are all consistent with the preset living body characteristic information.

Further, the audio data of the reading verification information in the video may be combined, and the lip action is used to jointly determine whether the verification information read by the user and the output verification information are consistent, that is, the user is judged to read aloud according to the audio data. Whether the verification information and the output verification information are consistent, and whether the verification information read by the user and the output verification information are consistent according to the lip action, and the determination results are the same, then the verification of the user's reading is confirmed. The information and the output verification information are consistent, and the accuracy of determining the consistency is further increased.

The living body verification in this embodiment is simpler than the prior art, such as fixing a limited nod, shaking head, looking left, and looking to the right, resulting in a single and limited number of actions, which is easy to be modeled by portrait. The method of simulating the 3D model and other methods to crack, with higher verification accuracy. It can block illegal identity authentication by criminals posing as users by means of photos, videos, human head models, etc. The living body verification method in this embodiment can effectively improve the verification accuracy, and at the same time ensure that the user image in the video is the verification pass rate when the real person is recorded, and the labor cost is greatly reduced.

On the other hand, in the identity authentication scenario, sometimes the authentication subject is an elderly person, a minor, a patient, or other group that is not suitable for strong interactive recording of video. The embodiment of the present application adopts only voice, blinking, and lip-moving methods. It is simple and convenient to verify the recording of the video. Users can complete the video recording in one time and with the help of other family members, which is convenient for the identity authentication of the above groups.

S205. After verification by the living body, verify the identity of the user according to the image data;

After the in vivo verification, it is further necessary to confirm that the living body is the same person as the user, and therefore the identity of the user needs to be further verified based on the image data in the video.

Specifically, after the living body is verified, the image that the user reaches the preset definition is obtained from the image data, that is, a sufficiently clear image is captured in the video file, and the image is compared by calling the background image comparison engine. The image of the preset definition is compared with the authentication photo retrieved from the specified platform, that is, the image taken from the video and the authentication photo are compared with a 1 to 1 picture. When the similarity between the image reaching the preset definition and the authentication photo reaches a preset threshold, it is determined that the person in the image is the same person as the person in the authentication photo. For example, when the degree of similarity reaches 70%, it is confirmed that the person in the image is the same person as the person in the authentication photo, that is, authenticated. Confirming the identity of the user based on the authentication photo provided by the official department with identity authority can further improve the accuracy of the user identity authentication.

S206. If the identity is verified, the user identity authentication is confirmed to be successful.

After the user's identity is verified according to the image data, it is confirmed that the user identity authentication is successful, that is, the user real name authentication is successful. If the authentication fails, the user returns to the home page of the client page, and prompts the user to perform identity authentication again, that is, step S201 is performed.

Further, the user identity authentication result is output on the client page to inform the user that the identity authentication succeeds or fails. It can improve the convenience of user operations and improve the user experience.

It should be noted that the system for implementing the identity authentication method in the embodiment of the present application is based on the LAPM (Linux+Apache+Php+Mysql) open source architecture, that is, using Linux as the operating system, Apache as the web server, and Php as the server-side script interpreter. , MySQL as a database. The system can be deployed in the cloud of the service provider, can be deployed on the client-side machine, or part of the system can be deployed in the cloud of the service provider, and another part can be deployed on the customer side, for example, a positive photo that will identify the user's identity document and The OCR module of the reverse photo, the recording module for recording video, the biometric verification module for in-vivo verification of the video in the video are deployed in the cloud of the service provider, and the module for authenticating the photo to the designated platform, and 1 ratio 1 The picture matching module is deployed to the client side, and the client side may be the machine of the public security department.

In the embodiment of the present application, using the h5 technology, the identity information collection can be completed at the front end, and the living body verification of the video in the video is completed by calling the live verification module in the background, and the photo is realized by calling a module that can obtain the identity verification photo. Calling, by calling the 1 to 1 picture comparison module to achieve user authentication, can avoid the cost of developing and promoting the APP, the user can pay attention to the public number to complete the identity authentication on the public number page, and the operation is simple and cost-effective.

In the embodiment of the present application, the video recorded by the user is obtained on the client page, and the user in the video is verified in vivo according to the facial action made by the user according to the rule, and after the verification by the living body, according to the video The image data verifies the identity of the user, and after confirming the identity, the user identity authentication is successful, and the identity authentication is performed on the client webpage compared to various APPs specifically used for identity authentication, the operation is simple and the cost is low, and the living body is Verification requires the user to make the specified facial movements. Compared with the existing simple head movements, the accuracy of the living body verification can be effectively improved, and the user image in the video is verified as the verification pass rate of the real person recording, which greatly reduces the manual cost.

Referring to FIG. 7, FIG. 7 is an identity authentication apparatus according to a third embodiment of the present application. For convenience of description, only parts related to the embodiments of the present application are shown. The device 300 can be built in a terminal. The device 300 includes an output module 301, an acquisition video module 302, a biometric verification module 303, and an identity verification module 304.

The output module 301 is configured to receive verification information required for recording a video from a server, and output verification information on the client page;

The verification information can be randomly generated by the background server, and the client immediately pulls it to the local and outputs the information. The verification information can also be extracted from the background server and stored in the terminal locally, and then output by the client. The verification information is unique, and the specific form may be a verification code composed of a plurality of digits, or a verification block composed of a plurality of Chinese characters. Since the verification information is randomly generated, non-repetitive, and unique, it is not easy to crack the verification information in a modeling or traversing manner, and the security is strong.

The obtaining video module 302 is configured to obtain a video recorded by the user on the client page, where the video includes image data of the user reading the verification information;

The biometric verification module 303 is configured to perform biometric verification on the user image in the video according to the image data acquired by the acquisition video module 302.

The identity verification module 304 is configured to verify the identity of the user according to the image data acquired by the acquisition video module 302 after the biometric verification module 303 passes the biometric verification.

The device in the embodiment of the present application is used to perform the foregoing method in the embodiment of FIG. 1b, and the technical details not described are the same as those in the foregoing embodiment shown in FIG. 1b, and details are not described herein again.

Referring to FIG. 8, FIG. 8 is an identity authentication apparatus according to a fourth embodiment of the present application. For convenience of description, only parts related to the embodiments of the present application are shown. The device 400 can be built in the terminal, and the device 400 shown in this embodiment is different from the device 300 shown in FIG. 7 in that:

The output module 301 is further configured to output a video recording rule on the client page;

The biometric verification module 303 is further configured to: identify, from the image data, a facial motion that conforms to the video recording rule output by the output module 301; and perform a living verification on the user image in the video according to the facial motion.

In an embodiment, the biometric verification module 303 may further include:

a first obtaining submodule 3031, configured to acquire a lip motion of the facial according to the facial motion;

The determining sub-module 3032 is configured to determine, according to the lip action, whether the verification information read by the user and the output verification information are consistent;

The first confirmation sub-module 3033 is configured to confirm the verification by the living body if the determination sub-module 3032 determines that the verification information read by the user and the output verification information are identical.

Further, the output verification information is a plurality of characters whose lip shape distinguishing degree reaches a preset standard when reading aloud, and the determining sub-module 3032 is specifically configured to determine a lip shape change feature when the user reads a plurality of characters in the verification information; The lip shape change feature is matched with the preset lip shape feature; when the matching degree reaches the preset value, it is confirmed that the verification information read by the user is consistent with the output verification information.

Further, the determining sub-module 3032 is specifically configured to: intercept a lip image of each character from the image data; respectively match each lip image with an image of the preset lip feature, and calculate each lip image. The degree of matching is obtained by weighting and matching the matching degrees of the respective lip images, and obtaining the matching degree for determining the verification information of the user reading and the output verification information.

In another embodiment, the biometric verification module 303 can further include:

The first obtaining sub-module 3031 is configured to acquire an eye motion of the face according to the facial motion;

The determining sub-module 3032 is configured to determine, according to the eye movement, whether the user makes an eye movement that meets the requirements of the video recording rule;

The first confirmation sub-module 3033 is configured to confirm the verification by the living body if the user makes an eye movement that meets the requirements of the video recording rule.

Further, the determining sub-module 3032 is specifically configured to match the change feature of the pupil when the user reads the verification information, and match the pupil change feature included in the preset blink action, and when the matching degree reaches the preset value, confirm the The user makes a blinking action that complies with the video recording rules.

Further, the video further includes the audio data of the user reading the verification information, and the determining sub-module 3032 is further configured to determine, according to the audio data, whether the verification information read by the user and the output verification information are consistent, in the video. User image for live verification.

Further, the apparatus 400 further includes:

The collecting module 401 is configured to collect identity information of the identity file uploaded by the user in the client page, and determine that the identity information is identified.

Further, the apparatus 400 further includes:

The retrieving module 402 is configured to retrieve, from the server, an authentication photo corresponding to the identity information collected by the collection module 401.

Further, the identity verification module 304 further includes:

The second obtaining sub-module 3041 is configured to obtain, from the image data, an image that the user reaches the preset definition.

The comparison sub-module 3042 is configured to compare the image that reaches the preset resolution with the identity verification photo obtained by the retrieval module 402;

The second confirmation sub-module 3043 is configured to confirm the identity verification when the similarity between the image reaching the preset resolution and the identity verification photo reaches a preset threshold.

Further, the collecting module 401 is specifically configured to: in the client page, identify the name, the ID number, the issuing authority, and the text information of the validity period of the ID file uploaded by the user.

The apparatus 400 can further include:

The identity information verification module 403 is configured to perform consistency check according to the name and the ID number collected by the collection module 401, perform legality verification according to the issuing authority, and perform validity verification according to the validity period of the certificate;

The retrieving module 402 is further configured to: after the identity verification module 403 passes the consistency check, the validity check, and the validity check, retrieve the identity verification photo corresponding to the ID number from the server.

For the technical details that are not described in the embodiments of the present application, refer to the descriptions of the foregoing embodiments shown in FIG. 1b, FIG. 3, and FIG. 7, and details are not described herein again.

FIG. 9 is a schematic structural diagram of a terminal for performing identity authentication according to an embodiment of the present disclosure.

The terminal described in this embodiment includes:

At least one input device 51; at least one output device 52; at least one processor 53, such as a central processing unit; and, memory 54.

The input device 51, the output device 52, the processor 53, and the memory 54 are connected via a bus 55.

The input device 51 can be specifically a camera, a touch panel, a physical button or a mouse, and the like. The output device 52 can specifically be a display screen.

The memory 54 may be a high speed random access memory (RAM) memory or a non-volatile memory such as a magnetic disk memory. The memory 54 is for storing a set of executable program code, the processor 53 is coupled to the memory 54, and the input device 51, the output device 52, and the processor 53 are configured to perform the following operations through the executable program code stored in the memory 54:

The code is executed by the processor 53 to execute the identity authentication method as described in the foregoing embodiments shown in Figs. 1b and 3.

Specifically, receiving verification information required for recording a video from a server, and outputting the verification information on a client page; acquiring a video recorded by the user on the client page, where the video includes the user reading the verification Image data of the information; performing biometric verification on the user image in the video according to the image data; and, after verification by the living body, verifying the identity of the user according to the image data.

In the various embodiments provided by the present application, it should be understood that the disclosed methods and apparatus may be implemented in other manners. For example, the embodiment of the device described above is merely illustrative. For example, the division of the module is only a logical function division. In actual implementation, there may be another division manner, for example, multiple modules or components may be combined. Or it can be integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication link shown or discussed may be an indirect coupling or communication link through some interface, device or module, and may be in an electrical, mechanical or other form.

The modules described as separate components may or may not be physically separated. The components displayed as modules may or may not be physical modules, that is, may be located in one place, or may be distributed to multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules.

The integrated modules, if implemented in the form of software functional modules and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application, in essence or the contribution to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium. A number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

The embodiment of the present application also discloses a storage medium in which a data processing program for executing any of the above embodiments of the present invention is stored.

It should be noted that, for the foregoing method embodiments, for the sake of brevity, they are all described as a series of action combinations, but those skilled in the art should understand that the present application is not limited by the described action sequence. Because certain steps may be performed in other sequences or concurrently in accordance with the present application. In the following, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

In the above embodiments, the descriptions of the various embodiments are all focused, and the parts that are not detailed in a certain embodiment can be referred to the related descriptions of other embodiments.

The above is a description of the identity authentication method, the identity authentication device, and the terminal provided by the present application. For those skilled in the art, according to the idea of the embodiment of the present application, there are changes in the specific implementation manner and application scope. The contents of this specification are not to be construed as limiting the application.

Claims

An identity authentication method, which is characterized by being applied to a terminal, including:

Receiving verification information required for recording a video from a server, and outputting the verification information on a client page;

Obtaining a video recorded by the user on the client page, where the video includes image data that the user reads the verification information;

Performing a live verification on the user image in the video according to the image data; and

After verification by the living body, the identity of the user is verified based on the image data.
The method of claim 1 further comprising:

Outputting a video recording rule on the client page;

The performing biometric verification on the user image in the video according to the image data includes:

Recognizing a facial action conforming to the video recording rule from the image data;

Performing a live verification on the user image in the video according to the facial motion.
The method according to claim 2, wherein the performing biometric verification on the user image in the video according to the facial action comprises:

Obtaining a lip motion of the face according to the facial motion;

Determining, according to the lip action, whether the verification information read by the user and the output verification information are consistent;

If the verification information read by the user is consistent with the output verification information, it is confirmed by the biometric verification.
The method according to claim 3, wherein the output verification information is a plurality of characters whose lip-shaped feature discrimination degree reaches a preset standard when reading aloud, and the judging according to the lip action Whether the verification information read by the user and the output verification information are consistent, including:

Determining a lip shape change characteristic when the user reads a plurality of characters in the verification information;

Matching the lip change feature to a preset lip feature;

When the matching degree reaches the preset value, it is confirmed that the verification information read by the user is consistent with the output verification information.
The method of claim 4 wherein said matching said lip change feature to a preset lip feature comprises:

Extracting a lip image of each character from the image data;

Each lip image is matched with the image of the preset lip feature, and the matching degree of each lip image is calculated, and the matching degree of each lip image is weighted and summed to obtain the user. The degree of matching between the verification information read aloud and the verification information output.
The method according to claim 2, wherein the performing biometric verification on the user image in the video according to the facial action comprises:

Obtaining an eye movement of the face according to the facial motion;

Determining, according to the eye movement, whether the user makes an eye movement that meets the requirements of the video recording rule;

If the user makes an eye movement that meets the requirements of the video recording rule, it is confirmed by the living body verification.
The method according to claim 6, wherein the determining, according to the eye movement, whether the user makes an eye movement that meets the video recording rule, comprises:

Matching the change feature of the pupil when the user reads the verification information to the pupil change feature included in the preset blink action, and confirming that the user meets the video when the matching degree reaches the preset value The blinking action specified by the recording rules.
The method according to claim 1, wherein the video further comprises audio data that the user reads the verification information, and the method further comprises:

And determining, according to the audio data, whether the verification information read by the user and the output verification information are consistent to perform biometric verification on the user image in the video.
The method according to any one of claims 1 to 8, further comprising:

In the client page, the identity information of the identity file uploaded by the user is collected, and the identity information is determined to be identified.
The method of claim 9 further comprising:

Retrieving an authentication photo corresponding to the identity information to the server;

After the verification by the living body, verifying the identity of the user according to the image data includes:

Obtaining, from the image data, an image that the user reaches a preset definition;

Comparing the image reaching the preset definition with the authentication photo;

When the similarity of the image reaching the preset definition and the authentication photo reaches a preset threshold, the verification is passed.
The method according to claim 10, wherein the collecting the identity information of the identity file uploaded by the user and determining that the identity information is identified by:

In the client page, identifying the name, the ID number, the issuing authority, and the textual information of the validity period of the ID file uploaded by the user;

According to the name and ID number, the consistency check is performed, the legality verification is performed according to the issuing authority, and the validity check is performed according to the validity period of the certificate;

The requesting the identity verification photo corresponding to the identity information to the server includes:

After the consistency check, the legality check, and the validity check, the identity verification photo corresponding to the ID number is retrieved from the server.
A terminal, comprising: a processor and a memory, wherein the memory stores instructions executable by the processor, and when the instruction is executed, the processor is configured to:

Receiving verification information required for recording a video from a server, and outputting the verification information on a client page;

Obtaining a video recorded by the user on the client page, where the video includes image data that the user reads the verification information;

Performing a live verification on the user image in the video according to the image data; and

After verification by the living body, the identity of the user is verified based on the image data.
The terminal according to claim 12, wherein when the instruction is executed, the processor is further configured to:

Outputting a video recording rule on the client page;

Recognizing a facial action conforming to the video recording rule from the image data;

Performing a live verification on the user image in the video according to the facial motion.
The terminal according to claim 13, wherein when the instruction is executed, the processor is further configured to:

Obtaining a lip motion of the face according to the facial motion;

Determining, according to the lip action, whether the verification information read by the user and the output verification information are consistent;

If the verification information read by the user is consistent with the output verification information, it is confirmed by the biometric verification.
The terminal according to claim 13, wherein when the instruction is executed, the processor is further configured to:

Obtaining an eye movement of the face according to the facial motion;

Determining, according to the eye movement, whether the user makes an eye movement that meets the requirements of the video recording rule;

If the user makes an eye movement that meets the requirements of the video recording rule, it is confirmed by the living body verification.
The terminal according to claim 12, wherein the video further comprises audio data that the user reads the verification information, and when the instruction is executed, the processor is further configured to:

And determining, according to the audio data, whether the verification information read by the user and the output verification information are consistent to perform biometric verification on the user image in the video.
The terminal according to any one of claims 12 to 16, wherein when the instruction is executed, the processor is further configured to:

In the client page, the identity information of the identity file uploaded by the user is collected, and the identity information is determined to be identified.
The terminal according to claim 17, wherein when the instruction is executed, the processor is further configured to:

Retrieving an authentication photo corresponding to the identity information to the server;

Obtaining, from the image data, an image that the user reaches a preset definition;

Comparing the image reaching the preset definition with the authentication photo;

When the similarity of the image reaching the preset definition and the authentication photo reaches a preset threshold, the verification is passed.
A computer readable storage medium, characterized by storing computer readable instructions, which may cause at least one processor to perform the method of any one of claims 1 to 11.