WO2020077885A1

WO2020077885A1 - Identity authentication method and apparatus, computer device and storage medium

Info

Publication number: WO2020077885A1
Application number: PCT/CN2019/070125
Authority: WO
Inventors: 高立志
Original assignee: 深圳壹账通智能科技有限公司
Priority date: 2018-10-17
Filing date: 2019-01-02
Publication date: 2020-04-23
Also published as: CN109543377A

Abstract

An identity authentication method, comprising: acquiring an authentication instruction, wherein the authentication instruction comprises user information; determining the user information to determine the type of a user; when the type of the user is a first type of user, generating first authentication information, and transmitting the first authentication information to a corresponding terminal according to the user information; receiving voice authentication information transmitted by the terminal; performing denoising processing on the voice authentication information to obtain valid voice authentication information; performing feature vector extraction on the valid voice authentication information to obtain text authentication information and first voiceprint information from the valid voice authentication information; and comparing the first authentication information and second voiceprint information in a voiceprint archive with the text authentication information and the first voiceprint information to determine an identity authentication result.

Description

Identity verification method, device, computer equipment and storage medium

Cross-reference of related applications

This application requires priority to be submitted to the Chinese Patent Office on October 17, 2018, with the application number 2018112114482 and the priority of the Chinese patent application titled "Identity Verification Method, Device, Computer Equipment, and Storage Medium", the entire contents of which are incorporated by reference In this application.

Technical field

This application relates to an identity verification method, device, computer equipment and storage medium.

Background technique

With the development of Internet technology, convenient interaction methods have greatly improved the user experience, while using Internet technology for interaction, it is necessary to protect the user information of each user very well, and different user rights need to be set, and authentication technology has appeared To ensure the user's information security.

At present, all major interactive platforms basically rely on verification codes to ensure the security of information in the accounts held by users. As long as there is a verification code, the user's account login password and transaction password can be modified. The verification code basically guarantees the user's The last line of defense of the information, but the traditional way of entering the verification code is that after the user obtains the verification code, the verification code is entered through the keyboard to verify the user's identity. The inventor realizes that the current authentication method cannot be used for the inconvenient use of the keyboard The user who enters the verification code performs identity verification and has low security issues.

Summary of the invention

According to various embodiments disclosed in the present application, an identity verification method, apparatus, computer equipment, and storage medium are provided.

An authentication method includes:

Obtain a verification instruction, which includes user information;

Judging the user information to determine the user type;

When the user type is the first type of user, generate first verification information, and send the first verification information to the corresponding terminal according to the user information;

Receive voice verification information sent by the terminal;

Performing noise reduction processing on the voice verification information to obtain valid voice verification information;

Performing feature vector extraction on the effective voice verification information to obtain text verification information and first voiceprint information in the effective voice verification information; and

Compare the first verification information and the second voiceprint information in the voiceprint file with the text verification information and the first voiceprint information to determine the identity verification result.

An identity verification device includes:

The instruction receiving module is used to obtain a verification instruction, and the verification instruction includes user information;

The judgment module is used to judge the user information and determine the user type;

A verification information generating module, configured to generate first verification information when the user type is the first type of user, and send the first verification information to the corresponding terminal according to the user information;

Information receiving module, used to receive voice verification information sent by the terminal;

A noise reduction module, configured to perform noise reduction processing on the voice verification information to obtain valid voice verification information;

A feature vector extraction module for extracting feature vectors of the effective voice verification information to obtain text verification information and first voiceprint information in the effective voice verification information; and

The verification module is used to compare the first verification information and the second voiceprint information in the voiceprint file with the text verification information and the first voiceprint information to determine the identity verification result.

A computer device includes a memory and one or more processors. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps of the authentication method provided in any embodiment of the present application are implemented.

One or more non-volatile computer-readable storage media storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to implement any one of the embodiments of the present application The steps of the provided authentication method.

The details of one or more embodiments of the application are set forth in the drawings and description below. Other features and advantages of this application will become apparent from the description, drawings, and claims.

BRIEF DESCRIPTION

In order to more clearly explain the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. Those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

FIG. 1 is an application scenario diagram of an identity verification method according to one or more embodiments.

FIG. 2 is a schematic flowchart of an identity verification method according to one or more embodiments.

FIG. 3 is a schematic flowchart of one step of the identity verification method according to one or more embodiments.

4 is a structural block diagram of an identity verification device according to one or more embodiments;

Figure 5 is a block diagram of a computer device in accordance with one or more embodiments.

detailed description

In order to make the technical solutions and advantages of the present application more clear, the following describes the present application in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

The identity verification method provided in this application can be applied in the application environment shown in FIG. 1. The terminal 102 communicates with the server 104 through the network through the network. When the user operates the interactive platform through the terminal 102, a verification process is triggered, and a verification instruction is issued to the server 104. The verification instruction includes user information; the server 104 judges the user information to determine the user type; when the user When the type is the first type of user, the first verification information is generated, and the first verification information is sent to the corresponding terminal 102 according to the user information; after the user views the first verification information through the terminal 102, the terminal 102 performs For identity verification, the server 104 receives the voice verification information sent by the terminal 102; extracts feature vectors from the voice verification information to obtain text verification information and first voiceprint information in the voice verification information; and converts the first verification information The second voiceprint information in the voiceprint file is compared with the text verification information and the first voiceprint information to determine the identity verification result. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server 104 may be implemented by an independent server or a server cluster composed of multiple servers.

In some embodiments, as shown in FIG. 2, an identity verification method is provided. The method is applied to the server in FIG. 1 as an example for illustration, including steps S220 to S320:

Step S220: Obtain a verification instruction, and the verification instruction includes user information.

Among them, when the user operates the application platform through the terminal, the verification instruction is triggered. When the verification instruction is triggered, the user information is obtained and sent to the identity verification device together. The application platform may be an online shopping mall platform, a social platform, etc., which involves verification. The identity application platform can be used. The verification instruction refers to the instruction used to trigger the identity verification process. The user information includes: name, nickname, contact information, ID card information, etc.

Step S240, judging the user information to determine the user type.

Among them, according to the user information, the user type is judged, and the user is judged to be the first type user, the second type user, or the third type user. The first type user can refer to a user who is not suitable for entering the verification code by hand. When creating user information, obtain the user's physical state, or mark the user type of the user when creating user information, or the user who selects the verification method corresponding to the first type of user before verification; the second type of user It can refer to users with language barriers. You can obtain the user's physical status when creating user information, or mark the user type of the user when creating user information, or the user can choose a second type of user before verification. Corresponding authentication method users; the third type of users can refer to users who have difficulty in collecting fingerprint information (such as: some users do not have fingerprints or the fingerprints are relatively shallow, which is easy to identify), which can be obtained by establishing user information The user's physical state, or when creating user information, mark the user's user type, or the user before verification Optional user and the third category corresponding to the user authentication method.

Step S260, when the user type is the first type of user, first verification information is generated, and the first verification information is sent to the corresponding terminal according to the user information.

Among them, when it is determined to be the first type of user, the user's identity is comprehensively verified by using verification code verification and voiceprint verification. The first type of user is mainly for users who are not suitable for entering the verification code by hand (for example: users with hand disabilities , It will be more difficult to use the keyboard to enter, and there is no fingerprint information); the first verification information refers to a combination of numbers, letters, or characters randomly generated by the identity verification device; the first verification information is used to send to the user by SMS On the corresponding terminal.

Step S280: Receive voice verification information sent by the terminal.

Among them, when the user's terminal receives a short message with verification information, according to the first verification information in the short message, and the microphone for voice collection of the terminal receiving the verification information is turned on, the user reads out according to the first verification information, so that the terminal When collecting voice verification information, it should be noted that the terminal used to receive SMS and the terminal that collects voice verification information can be different terminals or the same terminal. The terminal that collects voice verification information must be the same as the terminal operating the application platform A terminal.

Step S300: Perform noise reduction processing on the voice verification information to obtain valid voice verification information.

Among them, the noise reduction process may be: input the acquired voice information to the noise reduction module, and the noise reduction module divides the voice information into frames according to the received voice information, obtains each frame, and passes each frame through a discrete Fourier transform (DFT) fast algorithm, output phase information and amplitude information, the amplitude information is subjected to noise estimation and amplitude calculation and then spectrally subtracted, and finally the spectrally reduced amplitude is obtained, and the spectrally reduced amplitude and phase information are obtained By outputting effective voice verification information through the inverse fast Fourier transform, the voice information that does not belong to the verification content can be removed, the recognition accuracy can be improved, and interference can be avoided when performing voiceprint feature extraction.

Step S320: Perform feature vector extraction on the effective voice verification information to obtain text verification information and first voiceprint information in the effective voice verification information.

Among them, the effective voice verification information is passed through the feature extraction module, the effective voice verification information is converted from the time domain to the frequency domain, and the voice feature vector is obtained, the feature extraction module outputs the voice feature vector, and the voice feature vector is input into the acoustic model, The acoustic model outputs the acoustic score of the speech feature vector according to the acoustic features, and inputs the acoustic score of the speech feature vector to the decoding module. The decoding module obtains the information in the language model and vocabulary. The decoding module combines the information in the language model and the vocabulary. Information, the acoustic score of the voice feature vector, output the most likely word sequence of the voice feature vector (that is, recognize the content in the voice information), and obtain text verification information; pass the effective voice verification information through the voiceprint feature extraction model, which will The voiceprint feature in the effective voice verification information is extracted to obtain the first voiceprint information.

Step S340: Compare the first verification information and the second voiceprint information in the voiceprint file with the text verification information and the first voiceprint information to determine the identity verification result.

Among them, the voiceprint file is the voiceprint file created by the user on the application platform. The specific establishment is as follows: after receiving the voiceprint file establishment instruction sent by the user through the terminal, the terminal is controlled to turn on the microphone according to the voiceprint file establishment instruction, and the user passes the microphone of the terminal After inputting the voice information, it is sent to the voice processing module of the application platform. The voice processing module extracts the voiceprint features in the digital voice information according to the received digital voice information through the voiceprint feature extraction model to obtain the voiceprint features (sound The voiceprint features may include: acoustic features, lexical features, prosodic features, language, dialect and accent information, channel information), and the acquired voiceprint features (second voiceprint information) and user information are saved to the voiceprint archive.

In the above identity verification method, by judging the user information during the identity verification process and selecting a verification method suitable for the user for identity verification, for users who cannot enter the verification code using the keyboard, the verification information is sent to the user to enable the user to pass Enter the verification information by voice, perform identity verification, extract the feature vector of the voice verification information input by the user, and obtain the text verification information and the first voiceprint information of the voice verification information, and the text verification information and the first voiceprint information of the user Perform verification and combine with analysis to get the identity verification result. No need for the user to enter the verification code on the keyboard, recognize the verification code in the voice verification information entered by the user through voice recognition, and further confirm the user's identity through voiceprint recognition, which solves the problem that the user who is not convenient to use the keyboard to enter the verification code can be authenticated, and the security Low problem.

In some embodiments, comparing the first verification information and the second voiceprint information in the voiceprint file with the text verification information and the first voiceprint information to determine the identity verification result includes steps S321 to step S324:

Step S321: Compare the similarity between the second voiceprint information in the voiceprint file and the first voiceprint information to determine the similarity probability information.

Wherein, the corresponding second voiceprint information in the voiceprint file is obtained from the database according to the user information, the second voiceprint information is entered by the user before verification, and the second voiceprint information in the voiceprint file A voiceprint information is subjected to similarity verification to obtain a similarity probability.

In step S322, the text verification information is compared with the first verification information to determine whether the verification information is consistent.

Among them, when the first verification information is digitally combined, the text verification information should also be a digital combination, if not, the verification fails, if so, compare whether the numbers in the text verification information and the first verification information are the same Whether the order of the data is consistent, the same and consistent, then pass, and if they are not the same or inconsistent, then fail.

Step S323, when the similarity probability information is greater than or equal to the preset threshold and the verification information is consistent, the identity verification is passed.

The preset threshold of the similarity probability information of the voiceprint information can be determined according to the actual limit value for determining the user's identity, which is not specifically limited here and is set according to the actual situation. When the text verification information and the first verification information are passed, it can indicate the terminal that the verified user holds the account holder for receiving SMS, and when the similarity probability information is greater than or equal to the preset threshold, it means that the currently verified user is the account The holder performs double verification to determine the identity of the user, and avoids that the non-account holder obtains the terminal of the account holder or obtains the first verification information by means of SMS interception for identity verification.

Step S324, when the similarity probability information is less than the preset threshold and / or the verification information is inconsistent, the identity verification fails.

Among them, when the text verification information and the first verification information fail, it can indicate that the verified user does not hold the terminal used by the account holder to receive the SMS or the user misreads the collected voice verification information. When the similarity probability information is less than The preset threshold indicates that the currently verified user is not the account holder. When the text verification information and the first verification information fail, but the similarity probability information is greater than or equal to the preset threshold, the verified user may read incorrectly or The authenticated user recorded the user's relevant voice verification information in advance, which may not be the account holder, there is a risk of theft, and the identity verification is not passed. When the text verification information and the first verification information pass, but the similarity probability information is less than the preset threshold, the verified user may obtain the terminal of the account holder, there is a risk of theft, and the identity verification is not passed. Perform double verification to determine the identity of the user, and avoid that the non-account holder obtains the terminal of the account holder or obtains the first verification information by means of SMS interception for identity verification.

In some embodiments, when the user type is the second-type user or the third-type user, the first verification is performed; when it is determined that the first verification is not passed, the first verification is repeated until the verification is passed, Perform the second verification; when the number of repeated verifications is greater than the preset verification number, block the account; when it is determined that the first verification is passed, perform the second verification; when it is determined that the second verification passes, the identity verification; when determined When the second verification fails, the identity verification fails.

Among them, when it is determined that the first verification is not passed, the first verification is repeated, and when repeated a certain number of times or still failed, the identity verification fails, the account is blocked, and the location information of the terminal accessing the application platform is obtained and sent to the account corresponding And save the location information; when the first verification is passed, the second verification is performed; when the second verification is not passed, the second verification is repeated, and when the repeat exceeds the first preset number of times, return to the first One-step verification starts from the beginning. When the number of first-step verification returns exceeds the second preset number of times, the identity verification fails, the account is blocked, and the location information of the terminal accessing the application platform is obtained and sent to the terminal corresponding to the account. And save the location information; when the second re-authentication is passed, the identity authentication is passed, and the first preset number of times and the second preset number of times may be the same or different. Through double verification, the security of verification is improved, and different double verification methods are selected according to different users to improve the user experience of the user.

In some embodiments, the first verification or the second verification includes: generating first verification information and sending the first verification information to the corresponding terminal according to the user information; receiving the first input Second verification information; compare the second verification information with the first verification information, and when the verification information is consistent, the first verification or the second verification is passed.

Among them, when it is the first verification, the first verification information is generated, and the first verification information is sent to the corresponding terminal according to the user information; the second verification information input by the user through the terminal is received; the second verification information and the first The verification information is compared, when the verification information is consistent, the first verification is passed, when the verification information is inconsistent, the verification fails, returns to the step of generating the first verification information, and repeats the verification, when repeated a certain number of times still fails, the identity If the verification fails, the account is blocked, and the location information of the terminal accessing the application platform is obtained and sent to the terminal corresponding to the account, and the location information is saved; when it is the second verification, the first verification information is generated, and the first is generated according to the user information. The verification information is sent to the corresponding terminal; receiving the second verification information input by the user through the terminal; comparing the second verification information with the first verification information, when the verification information is consistent, the second verification passes, the identity verification passes; when the first When the double verification fails, return to the step of generating the first verification information and repeat the second verification, When repeatedly exceeding the first preset number of times, return to the first verification from the beginning and verify from the beginning. When returning the first verification from the beginning and verifying the number of times exceeds the second preset number of times, the identity verification fails, the account is blocked, and the terminal access to the application platform is obtained The location information is sent to the terminal corresponding to the account, and the location information is saved; when the second verification is passed, the identity verification is passed, and the double verification is used to improve the security of the verification, and different double verification methods are selected according to different users to improve The user's user experience.

In some embodiments, the first verification or the second verification includes sending an image acquisition instruction to the terminal to control the terminal to turn on the camera to collect the face image; receiving the face image collected by the terminal; extracting the person The feature vector of the face in the face image to obtain the first face feature vector information; compare the first face feature vector with the second face feature vector in the face file to determine the probability information of face similarity; when the person When the probability information of the face similarity is greater than or equal to the preset threshold, the first verification or the second verification is passed.

Among them, when it is the first verification, send an image collection instruction to the terminal to control the terminal to turn on the camera to collect the face image; receive the face image collected through the terminal; extract the feature vector of the face in the face image to obtain the first Face feature vector information; compare the first face feature vector with the second face feature vector in the face file to determine the face similarity probability information, when the face similarity probability information is greater than or equal to the preset threshold, The first verification pass, when the verification information is inconsistent, the verification fails, and returns to the step of sending the image acquisition instruction to the terminal, repeats the verification, and if the repeat fails a certain number of times, the identity verification fails, the account is blocked, and the terminal is obtained The location information of the access application platform is sent to the terminal corresponding to the account, and the location information is saved; when it is the second verification, the image collection instruction is sent to the terminal to control the terminal to open the camera to collect the face image; receive the person collected through the terminal Face image; extract the feature vector of the face in the face image, and obtain the first face feature vector information Compare the first face feature vector with the second face feature vector in the face file to determine the face similarity probability information, when the face similarity probability information is greater than or equal to the preset threshold, the second verification Pass, the identity verification is passed; when the second re-authentication fails, return to the step of sending the image acquisition instruction to the terminal, repeat the second re-authentication, and when the repetition exceeds the first preset number of times, return to the first re-authentication to start the verification from the beginning, When returning to the first verification from the beginning, the number of verifications exceeds the second preset number, the identity verification fails, the account is blocked, and the location information of the terminal accessing the application platform is obtained and sent to the terminal corresponding to the account, and the location information is saved; when the first When the double verification is passed, the identity verification is passed, and the double verification is used to improve the security of the verification, and different double verification methods are selected according to different users to improve the user experience of the user.

In some embodiments, the first verification or the second verification includes sending a fingerprint collection instruction to the terminal to control the terminal to collect fingerprint information; receiving the first fingerprint information sent by the terminal; and converting the first fingerprint information Compare with the second fingerprint information in the fingerprint file; if they match, the first verification or the second verification is passed.

Among them, when it is the first verification, send a fingerprint collection instruction to the terminal to control the terminal to collect fingerprint information; receive the first fingerprint information sent by the terminal; compare the first fingerprint information with the second fingerprint information in the fingerprint file, If they are consistent, the first verification is passed. When the verification information is inconsistent, the verification fails, and the step of sending a fingerprint collection instruction to the terminal is repeated. Repeat the verification. Account, and obtain the location information of the terminal accessing the application platform and send it to the terminal corresponding to the account, and save the location information; when it is the second verification, send a fingerprint collection instruction to the terminal to control the terminal to collect fingerprint information; receive the terminal The first fingerprint information; compare the first fingerprint information with the second fingerprint information in the fingerprint file, if they are consistent, the second verification passes and the identity verification passes; when the second verification fails, it returns to send the fingerprint collection to the terminal Instruction steps, repeat the second verification, when the repeat exceeds the first preset number of times, return The first re-authentication starts from the beginning. When the first re-authentication returns exceeds the second preset number of times, the identity verification fails, the account is blocked, and the location information of the terminal accessing the application platform is obtained and sent to the terminal corresponding to the account , And save the location information; when the second verification is passed, the identity verification is passed, and the double verification is adopted to improve the security of the verification, and different double verification methods are selected according to different users to improve the user experience of the user.

In some embodiments, before obtaining the verification instruction, the method further includes the steps of obtaining a file information creation instruction; controlling the terminal to collect user file information according to the file information establishment instruction; receiving the file information collected by the terminal, and processing the file information, Save the file information to the database.

Among them, the user can collect information and establish file information when establishing an account. The file information includes fingerprint files, face files, voiceprint files, etc. Users can create files based on the verification method they choose.

In the above identity verification method, by judging the user information in the process of identity verification, and selecting a verification method suitable for the user to perform identity verification, when the user is a first-type user, the voiceprint verification and the verification code verification are performed on the user. It makes the user who is not suitable for entering the verification code by hand and the user who cannot use the keyboard to enter the verification code; when the user is the second type of user, instead of using voice to enter verification information, face recognition, fingerprint recognition or verification code keyboard can be used Choose two of the input methods for double verification; when the user is the third type of user, instead of fingerprint identification, you can use face recognition and verification code keyboard input for double verification; avoid non-account holding Misappropriation of the account holder ’s account can improve the accuracy of verifying the user ’s identity and also improve the user ’s experience.

In some embodiments, an identity verification method uses the first type of user as a user who is not suitable for entering a verification code by hand, the second type of user as a user with language barriers, and the third type of user as a user with fingerprint information collection difficulties For users, the identity verification method is applied as an example when the user performs payment on the financial platform.

Before verification, collect voiceprint information of the first type of user, establish voiceprint file, collect face information and fingerprint information of the second type of user, establish face file and fingerprint file, collect fingerprint information of the third type of user, establish Fingerprint file.

The wealth management platform obtains the verification instruction, which includes user information, judges the user information, determines the user type, and generates first verification information when the user type is the first type of user, and sends the first verification information to the user information according to the user information Corresponding terminal, the wealth management platform receives the voice verification information sent by the terminal, performs noise reduction processing on the voice verification information to obtain valid voice verification information, extracts feature vectors from the valid voice verification information, and obtains text verification information and The first voiceprint information compares the second voiceprint information in the voiceprint file with the first voiceprint information to determine the similarity probability information, compares the text verification information with the first verification information, and determines the verification information Whether it is consistent, when the similarity probability information is greater than or equal to the preset threshold and the verification information is consistent, the identity verification is passed; when the similarity probability information is less than the preset threshold and / or the verification information is inconsistent, the identity verification is not passed.

When the user type is the second type of user, the first verification information is generated, and the first verification information is sent to the corresponding terminal according to the user information, the second verification information input by the user through the terminal is received, and the second verification information and the first Compare the verification information, when the verification information is consistent, control the terminal to turn on the face recognition function; receive the face image collected through the terminal; extract the feature vector of the face in the face image to obtain the first face feature vector information, Compare the first face feature vector with the second face feature vector in the face file to determine the face similarity probability information; when the face similarity probability information is greater than or equal to the preset threshold, the identity verification is passed; when the person When the probability information of the face similarity is less than the preset threshold, the identity verification fails.

When the user type is the third type of user, control the terminal to enable the fingerprint recognition function, receive the first fingerprint information sent by the terminal, and compare the first fingerprint information with the second fingerprint information in the fingerprint file. When the fingerprint information is consistent, control The terminal enables the face recognition function, receives the face image collected through the terminal; extracts the face feature vector in the face image, obtains the first face feature vector information, and compares the first face feature vector with the The second face feature vector is compared to determine the probability information of face similarity. When the probability information of face similarity is greater than or equal to the preset threshold, the identity verification is passed. When the probability information of face similarity is less than the preset threshold, the identity verification Fail.

It should be understood that although the steps in the flowcharts of FIGS. 2-3 are displayed in order according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless clearly stated in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in FIGS. 2-3 may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed and completed at the same time, but may be executed at different times. These sub-steps or stages The execution order of is not necessarily sequential, but may be executed in turn or alternately with at least a part of other steps or sub-steps or stages of other steps.

In some embodiments, as shown in FIG. 4, an identity verification device is provided, including: an instruction receiving module 300, a judgment module 310, a verification information generating module 320, an information receiving module 330, a noise reduction module 340, and feature vector extraction Module 350, verification module 360, in which:

The instruction receiving module 300 is used to obtain the verification instruction, and the verification instruction includes user information; the judgment module 310 is used to judge the user information and determine the user type; and the verification information generation module 320 is used when the user type is the first type of user , Generate the first verification information and send the first verification information to the corresponding terminal according to the user information; the information receiving module 330 is used to receive the voice verification information sent by the terminal; the noise reduction module 340 is used to verify the voice The information is subjected to noise reduction processing to obtain valid voice verification information; the feature vector extraction module 350 is used to extract feature vectors from the valid voice verification information to obtain the text verification information and the first voiceprint information in the valid voice verification information; the verification module 360 , Used to compare the first verification information and the second voiceprint information in the voiceprint file with the text verification information and the first voiceprint information to determine the identity verification result.

In some embodiments, the verification module 360 includes: a similarity comparison unit for comparing the similarity between the second voiceprint information in the voiceprint file and the first voiceprint information to determine the similarity probability information; the comparison unit, It is used to compare the text verification information with the first verification information to determine whether the verification information is consistent; the judgment unit is used when the similarity probability information is greater than or equal to a preset threshold and the verification information is consistent, the identity verification is passed, when the similarity probability When the information is less than the preset threshold and / or the verification information is inconsistent, the identity verification fails.

In some embodiments, the judging module 310 is also used to perform the first verification when the user type is the second type user or the third type user; when it is determined that the first verification is passed, the second verification is performed; when it is determined When the first verification fails, the first verification is repeated until the verification is passed, and the second verification is performed; when the number of repeated verifications is greater than the preset number of verifications, the account is blocked; when the second verification is determined to pass, the identity verification Passed; when it is determined that the second verification fails, the identity verification fails.

In some embodiments, a verification information verification module is also included. When performing the first verification method or the second verification method, the verification information verification module is called. The verification information verification module is used to generate the first verification information, and according to the user The information sends the first verification information to the corresponding terminal; receives the second verification information input by the user through the terminal; compares the second verification information with the first verification information, when the verification information is consistent, the first verification or the second verification Verified.

In some embodiments, it also includes a face verification module. When performing the first double verification or the second double verification, the face verification module is called, and the face verification module is used to send an image acquisition instruction to the terminal to control The terminal turns on the camera to collect the face image; receives the face image collected through the terminal; extracts the face feature vector in the face image to obtain the first face feature vector information; the first face feature vector and the face file in the face file The second face feature vector is compared to determine the probability information of face similarity; when the probability information of face similarity is greater than or equal to a preset threshold, the first verification or the second verification is passed.

In some embodiments, a fingerprint verification module is also included, which performs the first verification or the second verification, calling the fingerprint verification module, which is used to send fingerprint collection instructions to the terminal to control the terminal to collect fingerprints Information; receiving the first fingerprint information sent by the terminal; comparing the first fingerprint information with the second fingerprint information in the fingerprint file; if they match, the first verification or the second verification is passed.

In some embodiments, it also includes a file creation module, which is used to obtain a file information creation instruction; according to the file information creation instruction, the terminal is controlled to collect the user's file information; receiving the file information collected by the terminal, the file information is processed After processing, save the file information to the database.

The above-mentioned identity verification device judges the user information in the process of identity verification and selects a verification method suitable for the user to perform identity verification. When the user is the first type of user, the voiceprint verification and verification code verification are performed on the user. It makes the user who is not suitable for entering the verification code by hand and the user who cannot use the keyboard to enter the verification code; when the user is the second type of user, instead of using voice to enter verification information, face recognition, fingerprint recognition or verification code keyboard can be used Choose two of the input methods for double verification; when the user is the third type of user, instead of fingerprint identification, you can use face recognition and verification code keyboard input for double verification; avoid non-account holding Misappropriation of the account holder ’s account can improve the accuracy of verifying the user ’s identity and also improve the user ’s experience.

For the specific limitation of the identity verification device, please refer to the above definition of the identity verification method, which will not be repeated here. Each module in the above-mentioned identity verification device may be implemented in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in the hardware or independent of the processor in the computer device, or may be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

In some embodiments, a computer device is provided. The computer device may be a server, and its internal structure may be shown in FIG. 5. The computer device includes a processor, memory, network interface, and database connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer-readable instructions, and a database. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in the non-volatile storage medium. The database of the computer device is used to store data such as user information and user profile information. The network interface of the computer device is used to communicate with external terminals through a network connection. The computer readable instructions are executed by the processor to implement an authentication method.

Those skilled in the art can understand that the structure shown in FIG. 5 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Include more or less components than shown in the figure, or combine certain components, or have a different arrangement of components.

A person of ordinary skill in the art may understand that all or part of the process in the method of the foregoing embodiments may be completed by instructing relevant hardware through computer-readable instructions, and the computer-readable instructions may be stored in a non-volatile computer In the readable storage medium, when the computer-readable instructions are executed, they may include the processes of the foregoing method embodiments. Wherein, any reference to the memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Synchlink DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

The technical features of the above embodiments can be arbitrarily combined. To simplify the description, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, all It is considered as the scope described in this specification.

The above-mentioned embodiments only express several implementations of the present application, and their descriptions are more specific and detailed, but they should not be understood as limiting the scope of the invention patent. It should be noted that, for those of ordinary skill in the art, without departing from the concept of the present application, a number of modifications and improvements can also be made, which all fall within the protection scope of the present application. Therefore, the protection scope of the patent of this application shall be subject to the appended claims.

Claims

An authentication method, including:

Obtain a verification instruction, which includes user information;

Judging the user information to determine the user type;

When the user type is the first type of user, generate first verification information, and send the first verification information to the corresponding terminal according to the user information;

Receive voice verification information sent by the terminal;

Performing noise reduction processing on the voice verification information to obtain valid voice verification information;

Performing feature vector extraction on the effective voice verification information to obtain text verification information and first voiceprint information in the effective voice verification information; and

Compare the first verification information and the second voiceprint information in the voiceprint file with the text verification information and the first voiceprint information to determine the identity verification result.
The identity verification method according to claim 1, wherein the first verification information and the second voiceprint information in the voiceprint file are compared with the text verification information and the first voiceprint information to determine Identity verification results, including:

Comparing the similarity between the second voiceprint information in the voiceprint file and the first voiceprint information to determine similarity probability information;

Comparing the text verification information with the first verification information to determine whether the verification information is consistent;

When the similarity probability information is greater than or equal to the preset threshold and the verification information is consistent, the identity verification is passed; and

When the similarity probability information is less than the preset threshold and / or the verification information is inconsistent, the identity verification fails.
The identity verification method according to claim 1, wherein when the user type is a second type user or a third type user, the first re-authentication is performed;

When it is determined that the first verification is passed, the second verification is performed;

When it is determined that the first verification fails, the first verification is repeated until the verification is passed, and the second verification is performed;

When the number of repeated verifications is greater than the preset number of verifications, the account is blocked;

When it is determined that the second verification is passed, the identity verification is passed; and

When it is determined that the second verification fails, the identity verification fails.
The identity verification method according to claim 3, wherein the method of performing the first re-authentication or the method of performing the second re-authentication includes:

Generate first verification information, and send the first verification information to the corresponding terminal according to the user information;

Receiving the second verification information input by the user through the terminal; and

The second verification information is compared with the first verification information, and when the verification information is consistent, the first verification or the second verification is passed.
The identity verification method according to claim 3, wherein the first re-authentication method or the second re-authentication method includes:

Send image acquisition instructions to the terminal to control the terminal to turn on the camera to collect face images;

Receive face images collected through the terminal;

Extracting the feature vector of the human face in the human face image to obtain the first human face feature vector information;

Comparing the first face feature vector with the second face feature vector in the face file to determine the probability information of face similarity; and

When the probability information of the face similarity is greater than or equal to a preset threshold, the first verification or the second verification is passed.
The identity verification method according to claim 3, wherein the first re-authentication method or the second re-authentication method includes:

Send fingerprint collection instructions to the terminal to control the terminal to collect fingerprint information;

Receive the first fingerprint information sent by the terminal;

Compare the first fingerprint information with the second fingerprint information in the fingerprint file; and

If they match, the first verification or the second verification is passed.
The identity verification method according to any one of claims 1 to 6, wherein, before obtaining the verification instruction, the method further comprises the steps of:

Get file information creation instructions;

Control the terminal to collect the user's file information according to the file information creation instruction; and

After receiving the archive information collected by the terminal, processing the archive information, and storing the archive information in a database.
An identity verification device, including:

The instruction receiving module is used to obtain a verification instruction, and the verification instruction includes user information;

The judgment module is used to judge the user information and determine the user type;

A verification information generating module, configured to generate first verification information when the user type is the first type of user, and send the first verification information to the corresponding terminal according to the user information;

Information receiving module, used to receive voice verification information sent by the terminal;

A noise reduction module, configured to perform noise reduction processing on the voice verification information to obtain valid voice verification information;

A feature vector extraction module for extracting feature vectors of the effective voice verification information to obtain text verification information and first voiceprint information in the effective voice verification information; and

The verification module is used to compare the first verification information and the second voiceprint information in the voiceprint file with the text verification information and the first voiceprint information to determine the identity verification result.
The apparatus according to claim 8, wherein the verification module 360 comprises:

A similarity comparison unit, configured to compare similarity between the second voiceprint information in the voiceprint file and the first voiceprint information to determine similarity probability information;

A comparison unit, configured to compare the text verification information with the first verification information to determine whether the verification information is consistent; and

The judging unit is used for identity verification when the similarity probability information is greater than or equal to a preset threshold and the verification information is consistent, and when the similarity probability information is less than the preset threshold and / or verification information is inconsistent, the identity verification .
A computer device includes a memory and one or more processors. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the one or more processors, the one or more Each processor performs the following steps:

Obtain a verification instruction, which includes user information;

Judging the user information to determine the user type;

When the user type is the first type of user, generate first verification information, and send the first verification information to the corresponding terminal according to the user information;

Receive voice verification information sent by the terminal;

Performing noise reduction processing on the voice verification information to obtain valid voice verification information;

Performing feature vector extraction on the effective voice verification information to obtain text verification information and first voiceprint information in the effective voice verification information; and

Compare the first verification information and the second voiceprint information in the voiceprint file with the text verification information and the first voiceprint information to determine the identity verification result.
The computer device of claim 10, wherein the processor further executes the following steps when executing the computer-readable instructions:

Comparing the similarity between the second voiceprint information in the voiceprint file and the first voiceprint information to determine similarity probability information;

Comparing the text verification information with the first verification information to determine whether the verification information is consistent;

When the similarity probability information is greater than or equal to the preset threshold and the verification information is consistent, the identity verification is passed; and

When the similarity probability information is less than the preset threshold and / or the verification information is inconsistent, the identity verification fails.
The computer device of claim 10, wherein the processor further executes the following steps when executing the computer-readable instructions:

When the user type is the second type user or the third type user, the first verification is performed;

When it is determined that the first verification is passed, the second verification is performed;

When it is determined that the first verification fails, the first verification is repeated until the verification is passed, and the second verification is performed;

When the number of repeated verifications is greater than the preset number of verifications, the account is blocked;

When it is determined that the second verification is passed, the identity verification is passed; and

When it is determined that the second verification fails, the identity verification fails.
The computer device of claim 12, wherein the processor further executes the following steps when executing the computer-readable instructions:

Generate first verification information, and send the first verification information to the corresponding terminal according to the user information;

Receiving the second verification information input by the user through the terminal; and

The second verification information is compared with the first verification information, and when the verification information is consistent, the first verification or the second verification is passed.
The computer device of claim 12, wherein the processor further executes the following steps when executing the computer-readable instructions:

Send image acquisition instructions to the terminal to control the terminal to turn on the camera to collect face images;

Receive face images collected through the terminal;

Extracting the feature vector of the human face in the human face image to obtain the first human face feature vector information;

Comparing the first face feature vector with the second face feature vector in the face file to determine the probability information of face similarity; and

When the probability information of the face similarity is greater than or equal to a preset threshold, the first verification or the second verification is passed.
The computer device of claim 12, wherein the processor further executes the following steps when executing the computer-readable instructions:

Send fingerprint collection instructions to the terminal to control the terminal to collect fingerprint information;

Receive the first fingerprint information sent by the terminal;

Compare the first fingerprint information with the second fingerprint information in the fingerprint file; and

If they match, the first verification or the second verification is passed.
One or more non-volatile computer-readable storage media storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to perform the following steps:

Obtain a verification instruction, which includes user information;

Judging the user information to determine the user type;

When the user type is the first type of user, generate first verification information, and send the first verification information to the corresponding terminal according to the user information;

Receive voice verification information sent by the terminal;

Performing noise reduction processing on the voice verification information to obtain valid voice verification information;

Performing feature vector extraction on the effective voice verification information to obtain text verification information and first voiceprint information in the effective voice verification information; and

Compare the first verification information and the second voiceprint information in the voiceprint file with the text verification information and the first voiceprint information to determine the identity verification result.
The storage medium according to claim 16, wherein when the computer-readable instructions are executed by the processor, the following steps are further performed:

Comparing the similarity between the second voiceprint information in the voiceprint file and the first voiceprint information to determine similarity probability information;

Comparing the text verification information with the first verification information to determine whether the verification information is consistent;

When the similarity probability information is greater than or equal to the preset threshold and the verification information is consistent, the identity verification is passed; and

When the similarity probability information is less than the preset threshold and / or the verification information is inconsistent, the identity verification fails.
The storage medium according to claim 16, wherein when the computer-readable instructions are executed by the processor, the following steps are further performed:

When the user type is the second type user or the third type user, the first verification is performed;

When it is determined that the first verification is passed, the second verification is performed;

When it is determined that the first verification fails, the first verification is repeated until the verification is passed, and the second verification is performed;

When the number of repeated verifications is greater than the preset number of verifications, the account is blocked;

When it is determined that the second verification is passed, the identity verification is passed; and

When it is determined that the second verification fails, the identity verification fails.
The storage medium according to claim 18, wherein when the computer-readable instructions are executed by the processor, the following steps are further performed:

Generate first verification information, and send the first verification information to the corresponding terminal according to the user information;

Receiving the second verification information input by the user through the terminal; and

The second verification information is compared with the first verification information, and when the verification information is consistent, the first verification or the second verification is passed.
The storage medium according to claim 18, wherein when the computer-readable instructions are executed by the processor, the following steps are further performed:

Send image acquisition instructions to the terminal to control the terminal to turn on the camera to collect face images;

Receive face images collected through the terminal;

Extracting the feature vector of the human face in the human face image to obtain the first human face feature vector information;

Comparing the first face feature vector with the second face feature vector in the face file to determine the probability information of face similarity; and

When the probability information of the face similarity is greater than or equal to a preset threshold, the first verification or the second verification is passed.