CN113707157A

CN113707157A - Identity verification method and device based on voiceprint recognition, electronic equipment and medium

Info

Publication number: CN113707157A
Application number: CN202111007325.9A
Authority: CN
Inventors: 马亿凯
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2021-08-30
Filing date: 2021-08-30
Publication date: 2021-11-26
Anticipated expiration: 2041-08-30
Also published as: CN113707157B

Abstract

The application relates to the technical field of artificial intelligence, and provides an identity verification method, an identity verification device, electronic equipment and a medium based on voiceprint recognition, wherein the method comprises the following steps: identifying a target area where an incoming call user is located; generating a verification password based on the corpus of the target area, and sending the verification password to the client; receiving verification voice reported by a client, and extracting a first verification voiceprint characteristic value of each word from the verification voice; inputting the first verification voiceprint characteristic values of the multiple words into a pre-trained voiceprint recognition model corresponding to the target region, and calculating the similarity of verification voice and the registered voiceprint of the incoming call user; and verifying the identity of the incoming call user according to the recognition result output by the voiceprint recognition model and the similarity obtained by calculation. According to the method and the device, the target area of the incoming call user is identified, the pronunciation characteristics of the incoming call user are considered in the subsequent voiceprint identification process, and the accuracy of voiceprint identification is improved.

Description

Identity verification method and device based on voiceprint recognition, electronic equipment and medium

Technical Field

The application relates to the technical field of artificial intelligence, in particular to an identity verification method and device based on voiceprint recognition, electronic equipment and a medium.

Background

The internet is rapidly developed, online service handling becomes an important channel, particularly telephone customer service, a user performs service handling by dialing a telephone, identity verification of the user becomes important to ensure the safety of user information, and existing incoming call service handling performs identity verification based on voiceprint recognition by verifying the identity card number and name of an incoming call user.

However, in the internet era, the identity card number and the name may have been leaked and flow into a public channel, and if the identity card number is used for verification during incoming call service handling, it is not ensured whether the incoming call user of the incoming call service is the user himself or herself, which easily causes user information to be leaked, resulting in low accuracy and safety of identity verification based on voiceprint recognition.

Therefore, there is a need to provide a method for quickly and accurately verifying the identity of an incoming call user.

Disclosure of Invention

In view of the above, it is necessary to provide an identity authentication method, apparatus, electronic device and medium based on voiceprint recognition, which improve the accuracy of voiceprint recognition by recognizing the target area of the incoming user and considering the pronunciation characteristics of the incoming user in the subsequent voiceprint recognition process.

A first aspect of the present application provides an identity verification method based on voiceprint recognition, the method including:

responding to a received user incoming call request, and identifying a target area where an incoming call user in the user incoming call request is located;

generating a verification password based on the corpus of the target area, and sending the verification password to a client corresponding to the incoming call number in the user incoming call request;

receiving verification voice reported by the client, and extracting a first verification voiceprint characteristic value of each word from the verification voice;

inputting a first verification voiceprint characteristic value of a plurality of words into a pre-trained voiceprint recognition model corresponding to the target region, and calculating the similarity between the verification voice and the registration voiceprint of the incoming call user;

and verifying the identity of the incoming call user according to the recognition result output by the voiceprint recognition model and the similarity obtained by calculation.

Optionally, the generating a verification password based on the corpus of target regions comprises:

identifying a first key pronunciation feature of the target region;

and randomly selecting a plurality of words from the corpus according to the first key pronunciation characteristics to generate a verification password.

Optionally, the training process of the voiceprint recognition model includes:

collecting a corpus of a plurality of users in each region, wherein the corpus comprises voiceprint characteristic values which pass verification and voiceprint characteristic values which do not pass verification;

acquiring a second key pronunciation characteristic of each region;

extracting a plurality of target voiceprint characteristic values from the corpus according to a second key pronunciation characteristic of each region and a preset extraction rule;

constructing a sample data set containing a positive sample and a negative sample, wherein the positive sample is a sample pair consisting of a voiceprint characteristic value which passes the verification of the same user and the target voiceprint characteristic values, and the negative sample is a sample pair consisting of a voiceprint characteristic value which does not pass the verification of different users and the target voiceprint characteristic values;

randomly dividing the sample data set into a first number of training sets and a second number of test sets;

inputting the training set into a preset neural network for training to obtain a voiceprint recognition model;

inputting the test set into the voiceprint recognition model for testing to obtain a test passing rate;

judging whether the test passing rate is greater than a preset passing rate threshold value or not;

when the test passing rate is greater than or equal to the preset passing rate threshold value, finishing training of the voiceprint recognition model;

and when the test passing rate is smaller than the preset passing rate threshold, increasing the number of the training sets and retraining the voiceprint recognition model based on the increased training sets until the test passing rate is larger than or equal to the preset passing rate threshold.

Optionally, the identifying a target area where an incoming call user in the user incoming call request is located includes:

analyzing the incoming call request of the user to obtain the identity card number of the incoming call user; extracting a plurality of key fields from the identification number, and matching a first attribution region matched with the key fields from a preset region database; determining the first attribution region as a target region where the incoming call user is located; or

Analyzing the incoming call request of the user to obtain the incoming call number of the incoming call user; identifying an operator of the incoming call number, and acquiring a second home region of the incoming call number through a data interface query service corresponding to the operator; and determining the second home region as a target region where the calling subscriber is located.

Optionally, the verifying the identity of the incoming call user according to the recognition result output by the voiceprint recognition model and the calculated similarity includes:

matching a first text in the identification result with a second text corresponding to the verification password, and comparing the calculated similarity with a preset first similarity threshold;

and when the first text in the identification result is matched with the second text corresponding to the verification password and the calculated similarity is greater than or equal to a preset first similarity threshold value, determining that the identity verification of the incoming call user is passed.

Optionally, the method further comprises:

and when the first text in the identification result is not matched with the second text corresponding to the verification password, or the calculated similarity is smaller than the preset first similarity threshold, determining that the identity verification of the incoming call user fails.

Optionally, the method further comprises:

when the identity authentication of the incoming call user is determined not to pass, identifying whether a first home region corresponding to the identity card number in the incoming call request and a second home region corresponding to the incoming call number are the same home region or not;

when a first attribution region corresponding to the identification number and a second attribution region corresponding to the incoming call number are not in the same attribution region in the incoming call request, generating a dialect combination verification password according to a corpus of the first attribution region and a corpus of the second attribution region;

sending the dialect combination verification password to a client corresponding to the incoming call number in the user incoming call request;

receiving new verification voice reported by the client, and extracting a second verification voiceprint characteristic value of each word from the new verification voice;

inputting second verification voiceprint characteristic values of a plurality of words into a pre-trained voiceprint recognition model corresponding to the first attribution region and a pre-trained voiceprint recognition model corresponding to a second attribution region respectively, and calculating first similarity of the new verification voice and the registered voiceprint of the incoming call user;

receiving a first recognition result output by a pre-trained voiceprint recognition model corresponding to the first attribution region, and receiving a second recognition result output by a pre-trained voiceprint recognition model corresponding to the second attribution region;

calculating a second similarity between a third text in the first recognition result and a fourth text corresponding to the dialect combined verification password, and calculating a third similarity between a fifth text in the second recognition result and the fourth text corresponding to the dialect combined verification password;

calculating the product of the second similarity and a preset first weight value to obtain a fourth similarity corresponding to the first attribution region;

calculating the product of the third similarity and a preset second weight value to obtain a fifth similarity corresponding to a second attribution region;

calculating the sum of the fourth similarity and the fifth similarity to obtain the similarity of the final target region;

comparing the first similarity with a preset second similarity threshold, and comparing the similarity of the final target area with a preset third similarity threshold;

and when the first similarity is greater than or equal to the preset second similarity threshold and the fourth similarity is greater than or equal to the preset third similarity threshold, determining that the identity of the incoming call user passes the secondary verification.

A second aspect of the present application provides an authentication apparatus based on voiceprint recognition, the apparatus comprising:

the identification module is used for responding to the received user incoming call request and identifying a target area where an incoming call user in the user incoming call request is located;

the generating module is used for generating a verification password based on the corpus of the target area and sending the verification password to a client corresponding to the incoming call number in the incoming call request of the user;

the receiving module is used for receiving verification voice reported by the client and extracting a first verification voiceprint characteristic value of each word from the verification voice;

the input module is used for inputting the first verification voiceprint characteristic values of the plurality of words into a pre-trained voiceprint recognition model corresponding to the target region and calculating the similarity between the verification voice and the registered voiceprint of the incoming call user;

and the verification module is used for verifying the identity of the incoming call user according to the recognition result output by the voiceprint recognition model and the similarity obtained by calculation.

A third aspect of the present application provides an electronic device comprising a processor and a memory, the processor being configured to implement the voiceprint recognition based authentication method when executing a computer program stored in the memory.

A fourth aspect of the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the voiceprint recognition based authentication method.

To sum up, according to the identity authentication method, device, electronic device and medium based on voiceprint recognition, on one hand, the authentication password is generated according to the first key pronunciation feature of the target area, so that the validity of the authentication password is improved, meanwhile, the incoming call user reads the authentication password to form the authentication voice, and the voiceprint authentication is performed by using the authentication voice, so that the accuracy of subsequent voiceprint authentication is improved; on the other hand, in the training process of the voiceprint recognition model, the second key pronunciation characteristic of each region is considered, and the voiceprint characteristic value passing verification and the voiceprint characteristic value failing verification are used as sample sets to continuously optimize the voiceprint recognition model, so that the accuracy of the voiceprint recognition model is improved, and the accuracy of the identity verification of the incoming call user is further improved; and finally, by identifying the target area of the incoming call user, the pronunciation characteristics of the incoming call user are considered in the subsequent voiceprint identification process, so that the accuracy of voiceprint identification is improved.

Drawings

Fig. 1 is a flowchart of an identity authentication method based on voiceprint recognition according to an embodiment of the present application.

Fig. 2 is a structural diagram of an authentication apparatus based on voiceprint recognition according to the second embodiment of the present application.

Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present application.

Detailed Description

In order that the above objects, features and advantages of the present application can be more clearly understood, a detailed description of the present application will be given below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

Example one

In this embodiment, the identity authentication method based on voiceprint recognition may be applied to an electronic device, and for an electronic device that needs to perform identity authentication based on voiceprint recognition, the voiceprint recognition-based identity authentication function provided by the method of the present application may be directly integrated on the electronic device, or may be run in the electronic device in the form of a Software Development Kit (SDK).

As shown in fig. 1, the identity authentication method based on voiceprint recognition specifically includes the following steps, and the order of the steps in the flowchart may be changed, and some steps may be omitted according to different requirements.

And S11, responding to the received user call request, and identifying the target area where the calling user in the user call request is located.

In this embodiment, the user incoming call request is used to represent that the user performs service handling by dialing a phone number, for example, the user may have a question about insurance terms during an application process, the user incoming call request is sent by dialing xxxxxx, and related information corresponding to the insurance terms is consulted, where the target area is used to represent an attribution area of the incoming call user.

In an optional embodiment, the identifying a target area where an incoming call user in the user incoming call request is located includes:

analyzing the incoming call request of the user to obtain the identity card number of the incoming call user;

extracting a plurality of key fields from the identification number, and matching a first attribution region matched with the key fields from a preset region database;

and determining the first attribution region as a target region where the incoming call user is located.

In other optional embodiments, the identifying a target region where an incoming call user in the user incoming call request is located includes:

analyzing the incoming call request of the user to obtain the incoming call number of the incoming call user;

identifying an operator of the incoming call number, and acquiring a second home region of the incoming call number through a data interface query service corresponding to the operator;

and determining the second home region as a target region where the calling subscriber is located.

In other optional embodiments, a first home region corresponding to the identification number and a second home region corresponding to the incoming call number in the incoming call request may be identified at the same time, and when the first home region and the second home region are not the same home region, the first home region is preferentially determined as the target region where the incoming call user is located.

In the embodiment, the target area of the incoming call user is identified, and the pronunciation characteristics of the incoming call user are considered in the subsequent voiceprint identification process, so that the accuracy of voiceprint identification is improved.

And S12, generating a verification password based on the corpus of the target area, and sending the verification password to the client corresponding to the incoming call number in the user incoming call request.

In this embodiment, when receiving an incoming call request from a user, the system generates a verification password according to a corpus of a target area corresponding to an incoming call user, and sends the verification password to a client corresponding to an incoming call number in the incoming call request in a preset sending manner, for example, the verification password is sent to the client corresponding to the incoming call number in the incoming call request in a short message manner, and when receiving the verification password, the incoming call user reads the verification password to form verification voice.

In an optional embodiment, the generating a verification password based on the corpus of target regions includes:

identifying a first key pronunciation feature of the target region;

In this embodiment, the first key pronunciation feature is used to characterize a pronunciation feature specific to the target region, i.e. a pronunciation feature different from other regions.

In the embodiment, the verification password is generated according to the first key pronunciation feature of the target area, the validity of the verification password is improved, meanwhile, the incoming call user reads the verification password to form verification voice, and the verification voice is adopted for voiceprint verification, so that the accuracy of subsequent voiceprint verification is improved.

And S13, receiving the verification voice reported by the client, and extracting the first verification voiceprint characteristic value of each word from the verification voice.

In this embodiment, the verification voiceprint characteristic value includes a frequency value, a volume, a tone, and the like of each word, and after a verification voice reported by the client is received, a voiceprint recognition technology is used to extract a first verification voiceprint characteristic value of each word from the verification voice, where the voiceprint recognition technology is the prior art, and this embodiment is not described in detail herein.

S14, inputting the first verification voiceprint characteristic values of the plurality of words into a pre-trained voiceprint recognition model corresponding to the target region, and calculating the similarity between the verification voice and the registration voiceprint of the incoming call user.

In this embodiment, the voiceprint recognition model is trained in advance, and voiceprint feature values of a plurality of characters of a verification voice reported by a calling user are input into the voiceprint recognition model for recognition to obtain a recognition result, and whether the verification voice of the calling user is the voice feature of a target area is determined according to the recognition result.

Specifically, the training process of the voiceprint recognition model includes:

acquiring a second key pronunciation characteristic of each region;

In this embodiment, the corpus of each region includes a second key pronunciation feature of the user in the corresponding region, the voiceprint feature value that passes the verification and the voiceprint feature value that does not pass the verification, and the key labels are used for labeling the syllable, word, and sentence expression of the second key pronunciation feature.

In this embodiment, the second key pronunciation feature is used to characterize the pronunciation difference of each region and the pronunciation features of other regions, for example, the pronunciation of the guangdong for the flat-warped part is: and z is zh, c is ch, and s is sh, more warped tongues and a corpus without warped tongues are extracted in the process of extracting the characteristic value of the target voiceprint in the Guangdong region, and subsequent model training is carried out, so that the accuracy of voiceprint recognition model recognition is improved.

In the embodiment, in the subsequent service process, the voiceprint characteristic value which is passed through the verification of the user in the same region, the voiceprint characteristic value which is not passed through the verification and the target voiceprint characteristic values of the corresponding regions are used as new samples and are added to the sample data set, so that the diversity of the voiceprint recognition model training input samples is improved, the sample amount of the voiceprint recognition model training input is ensured, and the voiceprint recognition model is retrained based on the new sample data set. Namely, the voiceprint recognition model is continuously updated, so that the recognition rate of the voiceprint recognition model is continuously improved.

In the embodiment, in the training process of the voiceprint recognition model, the second key pronunciation characteristic of each region is considered, and the voiceprint characteristic value passing verification and the voiceprint characteristic value failing verification are used as the sample set to continuously optimize the voiceprint recognition model, so that the accuracy of the voiceprint recognition model is improved, and the accuracy of the identity verification of the incoming call user is further improved.

In an optional embodiment, the calculating the similarity between the verification voiceprint and the registered voiceprint of the incoming call user includes:

extracting a first voiceprint feature of the verification voice and extracting a second voiceprint feature of the registration voiceprint;

and calculating the similarity between the first voiceprint feature and the second voiceprint feature by adopting a preset similarity algorithm.

In this embodiment, the preset similarity algorithm may be a cosine similarity algorithm, a chebyshev similarity algorithm, an euclidean distance similarity algorithm, or the like, and the embodiment of the present application is not limited herein.

And S15, verifying the identity of the incoming call user according to the recognition result output by the voiceprint recognition model and the calculated similarity.

In this embodiment, when the verification voice of the incoming call user belongs to the pronunciation of the target area, and the verification voice of the incoming call user is similar to the registered voiceprint, it is determined that the identity verification of the incoming call user passes.

In an optional embodiment, the verifying the identity of the incoming call user according to the recognition result output by the voiceprint recognition model and the calculated similarity includes:

Further, the method further comprises:

In other optional embodiments, to further ensure the accuracy of the authentication of the user and improve the satisfaction of the user, the method further includes:

Further, the method further comprises:

and when the first similarity is smaller than the preset second similarity threshold, or the similarity of the final target area is smaller than the preset third similarity threshold, determining that the identity secondary verification of the incoming call user does not pass.

Further, the method further comprises:

and terminating the identity authentication when the first home region corresponding to the identity card number and the second home region corresponding to the incoming call number in the incoming call request are the same home region.

In this embodiment, a first similarity threshold, a second similarity threshold, and a third similarity threshold may be preset, and specifically, the preset first similarity threshold, the preset second similarity threshold, and the preset third similarity threshold are obtained based on machine learning.

In this embodiment, since the home region corresponding to the identification number of the incoming call user is a birth region and the home region of the mobile phone number is a growth region, when the identity of the incoming call user is not verified for the first time, it is determined whether the identity needs to be verified for the second time by identifying whether the first home region corresponding to the identification number and the second home region corresponding to the incoming call number in the incoming call request are the same home region, and when the identity is verified for the second time, a first weight value may be set in advance for the first home region corresponding to the identification number and a second weight value may be set for the second home region corresponding to the mobile phone number, so as to ensure the correctness of the similarity of the final target region obtained by calculation, and further improve the accuracy of the user identity verification and the satisfaction of the incoming call user.

In summary, in the identity authentication method based on voiceprint recognition described in this embodiment, on one hand, an authentication password is generated based on the corpus of the target area, and is sent to the client corresponding to the incoming call number in the user incoming call request, and is generated according to the first key pronunciation feature of the target area, so as to improve the validity of the authentication password, and meanwhile, the incoming call user reads the authentication password to form an authentication voice, and performs voiceprint authentication by using the authentication voice, so as to improve the accuracy of subsequent voiceprint authentication; on the other hand, the first verification voiceprint characteristic values of the multiple words are input into a pre-trained voiceprint recognition model corresponding to the target region, the second key pronunciation characteristic of each region is considered in the training process of the voiceprint recognition model, and the voiceprint characteristic values which pass verification and the voiceprint characteristic values which do not pass verification are used as sample sets to continuously optimize the voiceprint recognition model, so that the accuracy of the voiceprint recognition model is improved, and the accuracy of the identity verification of the incoming call user is further improved; and finally, identifying the target area where the incoming call user in the user incoming call request is located, and considering the pronunciation characteristics of the incoming call user in the subsequent voiceprint identification process by identifying the target area of the incoming call user, thereby improving the accuracy of voiceprint identification.

Example two

In some embodiments, the voiceprint recognition based authentication apparatus 20 may include a plurality of functional modules composed of program code segments. The program code of each program segment in the voiceprint recognition based authentication apparatus 20 can be stored in the memory of the electronic device and executed by the at least one processor to perform (see fig. 1 for details) the voiceprint recognition based authentication function.

In this embodiment, the identity authentication apparatus 20 based on voiceprint recognition may be divided into a plurality of functional modules according to the functions performed by the apparatus. The functional module may include: an identification module 201, a generation module 202, a reception module 203, an input module 204, a verification module 205, a determination module 206, and a termination module 207. A module as referred to herein is a series of computer readable instruction segments stored in a memory capable of being executed by at least one processor and capable of performing a fixed function. In the present embodiment, the functions of the modules will be described in detail in the following embodiments.

The identifying module 201 is configured to identify, in response to a received user incoming call request, a target area where an incoming call user in the user incoming call request is located.

In an optional embodiment, the identifying module 201 identifying the target area where the incoming call user in the user incoming call request is located includes:

In other alternative embodiments, the identifying module 201 identifies the target area where the incoming call user in the user incoming call request is located includes:

In other optional embodiments, the identifying module 201 may identify a first home region corresponding to the identification number and a second home region corresponding to the incoming call number in the incoming call request at the same time, and preferentially determine the first home region as a target region where the incoming call user is located when the first home region and the second home region are not the same home region.

A generating module 202, configured to generate a verification password based on the corpus of the target region, and send the verification password to the client corresponding to the incoming call number in the user incoming call request.

In an alternative embodiment, the generating module 202 generating the verification password based on the corpus of the target region includes:

identifying a first key pronunciation feature of the target region;

A receiving module 203, configured to receive verification voices reported by the client, and extract a first verification voiceprint characteristic value of each word from the verification voices.

The input module 204 is configured to input the first verification voiceprint feature values of the multiple words into a pre-trained voiceprint recognition model corresponding to the target region, and calculate a similarity between the verification voice and the registered voiceprint of the incoming call user.

acquiring a second key pronunciation characteristic of each region;

In an optional embodiment, the input module 204 calculating the similarity between the verification voiceprint and the registered voiceprint of the incoming user includes:

And the verification module 205 is configured to verify the identity of the incoming call user according to the recognition result output by the voiceprint recognition model and the calculated similarity.

In an optional embodiment, the verifying module 205 verifies the identity of the incoming call user according to the recognition result output by the voiceprint recognition model and the calculated similarity, where the verifying module includes:

A determining module 206, configured to determine that the identity authentication of the incoming call user fails when the first text in the identification result is not matched with the second text corresponding to the authentication password, or the calculated similarity is smaller than the preset first similarity threshold.

In other optional embodiments, in order to further ensure the accuracy of the authentication of the user and improve the satisfaction of the user, when it is determined that the authentication of the incoming call user does not pass, identifying whether a first home region corresponding to the identification number and a second home region corresponding to the incoming call number in the incoming call request are the same home region; when a first attribution region corresponding to the identification number and a second attribution region corresponding to the incoming call number are not in the same attribution region in the incoming call request, generating a dialect combination verification password according to a corpus of the first attribution region and a corpus of the second attribution region; sending the dialect combination verification password to a client corresponding to the incoming call number in the user incoming call request; receiving new verification voice reported by the client, and extracting a second verification voiceprint characteristic value of each word from the new verification voice; inputting second verification voiceprint characteristic values of a plurality of words into a pre-trained voiceprint recognition model corresponding to the first attribution region and a pre-trained voiceprint recognition model corresponding to a second attribution region respectively, and calculating first similarity of the new verification voice and the registered voiceprint of the incoming call user; receiving a first recognition result output by a pre-trained voiceprint recognition model corresponding to the first attribution region, and receiving a second recognition result output by a pre-trained voiceprint recognition model corresponding to the second attribution region; calculating a second similarity between a third text in the first recognition result and a fourth text corresponding to the dialect combined verification password, and calculating a third similarity between a fifth text in the second recognition result and the fourth text corresponding to the dialect combined verification password; calculating the product of the second similarity and a preset first weight value to obtain a fourth similarity corresponding to the first attribution region; calculating the product of the third similarity and a preset second weight value to obtain a fifth similarity corresponding to a second attribution region; calculating the sum of the fourth similarity and the fifth similarity to obtain the similarity of the final target region; comparing the first similarity with a preset second similarity threshold, and comparing the similarity of the final target area with a preset third similarity threshold; and when the first similarity is greater than or equal to the preset second similarity threshold and the fourth similarity is greater than or equal to the preset third similarity threshold, determining that the identity of the incoming call user passes the secondary verification.

Further, the determining module 206 is further configured to determine that the identity secondary verification of the incoming call user fails when the first similarity is smaller than the preset second similarity threshold, or the similarity of the final target area is smaller than the preset third similarity threshold.

Further, the terminating module 207 is configured to terminate the identity authentication when the first home region corresponding to the identification number in the incoming call request and the second home region corresponding to the incoming call number are the same home region.

In summary, in the identity authentication device based on voiceprint recognition according to the embodiment, on one hand, an authentication password is generated based on the corpus of the target area, the authentication password is sent to the client corresponding to the incoming call number in the user incoming call request, the authentication password is generated according to the first key pronunciation feature of the target area, the validity of the authentication password is improved, meanwhile, the incoming call user reads the authentication password to form an authentication voice, and the authentication voice is used for voiceprint authentication, so that the accuracy of subsequent voiceprint authentication is improved; on the other hand, the first verification voiceprint characteristic values of the multiple words are input into a pre-trained voiceprint recognition model corresponding to the target region, the second key pronunciation characteristic of each region is considered in the training process of the voiceprint recognition model, and the voiceprint characteristic values which pass verification and the voiceprint characteristic values which do not pass verification are used as sample sets to continuously optimize the voiceprint recognition model, so that the accuracy of the voiceprint recognition model is improved, and the accuracy of the identity verification of the incoming call user is further improved; and finally, identifying the target area where the incoming call user in the user incoming call request is located, and considering the pronunciation characteristics of the incoming call user in the subsequent voiceprint identification process by identifying the target area of the incoming call user, thereby improving the accuracy of voiceprint identification.

EXAMPLE III

Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present application. In the preferred embodiment of the present application, the electronic device 3 comprises a memory 31, at least one processor 32, at least one communication bus 33, and a transceiver 34.

It will be appreciated by those skilled in the art that the configuration of the electronic device shown in fig. 3 does not constitute a limitation of the embodiments of the present application, and may be a bus-type configuration or a star-type configuration, and that the electronic device 3 may include more or less hardware or software than those shown, or a different arrangement of components.

In some embodiments, the electronic device 3 is an electronic device capable of automatically performing numerical calculation and/or information processing according to instructions set or stored in advance, and the hardware thereof includes but is not limited to a microprocessor, an application specific integrated circuit, a programmable gate array, a digital processor, an embedded device, and the like. The electronic device 3 may also include a client device, which includes, but is not limited to, any electronic product that can interact with a client through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device, for example, a personal computer, a tablet computer, a smart phone, a digital camera, and the like.

It should be noted that the electronic device 3 is only an example, and other existing or future electronic products, such as those that can be adapted to the present application, should also be included in the scope of protection of the present application, and are included by reference.

In some embodiments, the memory 31 is used for storing program codes and various data, such as the voiceprint recognition based authentication apparatus 20 installed in the electronic device 3, and realizes high-speed and automatic access to programs or data during the operation of the electronic device 3. The Memory 31 includes a Read-Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an electronically Erasable rewritable Read-Only Memory (Electrically-Erasable Programmable Read-Only Memory (EEPROM)), an optical Read-Only disk (CD-ROM) or other optical disk Memory, a magnetic disk Memory, a tape Memory, or any other medium readable by a computer capable of carrying or storing data.

In some embodiments, the at least one processor 32 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The at least one processor 32 is a Control Unit (Control Unit) of the electronic device 3, connects various components of the electronic device 3 by using various interfaces and lines, and executes various functions and processes data of the electronic device 3 by running or executing programs or modules stored in the memory 31 and calling data stored in the memory 31.

In some embodiments, the at least one communication bus 33 is arranged to enable connection communication between the memory 31 and the at least one processor 32 or the like.

Although not shown, the electronic device 3 may further include a power supply (such as a battery) for supplying power to each component, and optionally, the power supply may be logically connected to the at least one processor 32 through a power management device, so as to implement functions of managing charging, discharging, and power consumption through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 3 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.

It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.

The integrated unit implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, an electronic device, or a network device) or a processor (processor) to execute parts of the methods according to the embodiments of the present application.

In a further embodiment, in conjunction with fig. 2, the at least one processor 32 may execute operating means of the electronic device 3 and various installed applications (such as the voiceprint recognition based authentication apparatus 20), program code, and the like, for example, the above-mentioned modules.

The memory 31 has program code stored therein, and the at least one processor 32 can call the program code stored in the memory 31 to perform related functions. For example, the respective modules illustrated in fig. 2 are program codes stored in the memory 31 and executed by the at least one processor 32, so as to implement the functions of the respective modules for the purpose of identity verification based on voiceprint recognition.

Illustratively, the program code may be partitioned into one or more modules/units that are stored in the memory 31 and executed by the processor 32 to accomplish the present application. The one or more modules/units may be a series of computer readable instruction segments capable of performing certain functions, which are used for describing the execution process of the program code in the electronic device 3. For example, the program code may be partitioned into an identification module 201, a generation module 202, a reception module 203, an input module 204, a verification module 205, a determination module 206, and a termination module 207.

In one embodiment of the present application, the memory 31 stores a plurality of computer readable instructions that are executed by the at least one processor 32 to implement a voiceprint recognition based authentication function.

Specifically, the at least one processor 32 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1, and details are not repeated here.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, functional modules in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.

It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or that the singular does not exclude the plural. A plurality of units or means recited in the present application may also be implemented by one unit or means through software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.

Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present application and not for limiting, and although the present application is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present application without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. An identity authentication method based on voiceprint recognition, the method comprising:

2. The method of claim 1, wherein generating a verification password based on the corpus of target regions comprises:

identifying a first key pronunciation feature of the target region;

3. The identity verification method based on voiceprint recognition according to claim 1, wherein the training process of the voiceprint recognition model comprises:

acquiring a second key pronunciation characteristic of each region;

4. The identity verification method based on voiceprint recognition, according to claim 1, wherein the recognizing the target area where the incoming call user in the user incoming call request is located comprises:

5. The identity verification method based on voiceprint recognition according to claim 1 or 4, wherein the verifying the identity of the incoming call user according to the recognition result output by the voiceprint recognition model and the calculated similarity comprises:

6. The voiceprint recognition based authentication method of claim 5, wherein said method further comprises:

7. The voiceprint recognition based authentication method of claim 6, wherein said method further comprises:

8. An authentication apparatus based on voiceprint recognition, the apparatus comprising:

9. An electronic device, characterized in that the electronic device comprises a processor and a memory, the processor being configured to implement the voiceprint recognition based authentication method of any one of claims 1 to 7 when executing the computer program stored in the memory.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a voiceprint recognition based authentication method according to any one of claims 1 to 7.