CN109510806B

CN109510806B - Authentication method and device

Info

Publication number: CN109510806B
Application number: CN201710835052.4A
Authority: CN
Inventors: 方硕; 李亮
Original assignee: Advanced New Technologies Co Ltd
Current assignee: Advanced New Technologies Co Ltd; Advantageous New Technologies Co Ltd
Priority date: 2017-09-15
Filing date: 2017-09-15
Publication date: 2021-12-24
Anticipated expiration: 2037-09-15
Also published as: CN109510806A

Abstract

The embodiment of the specification provides an authentication method and an authentication device, and the method comprises the following steps: determining a target account requested to be operated by a user; acquiring the current voiceprint of the user; and if the corresponding historical voiceprint exists in the target account, determining the operation authority of the user on the target account based on the matching state of the current voiceprint of the user and the historical voiceprint corresponding to the target account. Therefore, according to the technical scheme of the specification, the user can be subjected to identity verification by adopting the voiceprint recognition technology in the account operation process of the user through the customer service system, and the voiceprint is the unique biological feature of the person, namely, the voiceprint cannot be stolen, so that the security is high, and the loss caused by the fact that the information of the user is leaked and the impostor performs related operation on the account can be avoided.

Description

Authentication method and device

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to an authentication method and apparatus.

Background

With the continuous development of internet technology, more and more users handle business through a customer service system, and the customer service system can provide remote services for the users, for example, the users can consult related problems for customer service of the customer service system and apply for related operations on accounts. Currently, in the process of operating an account, for example, operations of loss reporting and loss relieving of the account, a customer service needs to verify the identity of a user, that is, to determine whether the user is an account holder, and only if the user is the account holder, the customer service performs a relevant operation on the account.

Disclosure of Invention

An object of the embodiments of the present disclosure is to provide an authentication method and apparatus, so as to implement more secure verification of an identity of a user, thereby avoiding a loss caused by a false identifier performing a related operation on an account.

In order to solve the above technical problem, the embodiments of the present specification are implemented as follows:

in a first aspect, an authentication method is provided, where the method includes:

determining a target account requested to be operated by a user;

acquiring the current voiceprint of the user;

and if the corresponding historical voiceprint exists in the target account, determining the operation authority of the user on the target account based on the matching state of the current voiceprint of the user and the historical voiceprint corresponding to the target account.

In a second aspect, an authentication apparatus is provided, the apparatus comprising:

the determining unit is used for determining a target account which is requested to be operated by a user;

the acquisition unit is used for acquiring the current voiceprint of the user;

and the authentication unit is used for determining the operation authority of the user on the target account based on the matching state of the current voiceprint of the user and the historical voiceprint corresponding to the target account under the condition that the corresponding historical voiceprint exists in the target account.

In a third aspect, an electronic device is provided, including:

a processor; and

a memory arranged to store computer executable instructions that, when executed, cause the processor to:

determining a target account requested to be operated by a user;

acquiring the current voiceprint of the user;

In a fourth aspect, a computer storage medium is provided that stores one or more programs that, when executed by an electronic device that includes a plurality of application programs, cause the electronic device to:

determining a target account requested to be operated by a user;

acquiring the current voiceprint of the user;

According to the technical scheme provided by the embodiment of the specification, the user can be authenticated by adopting the voiceprint recognition technology in the account operation process of the user through the customer service system, and the voiceprint is the unique biological characteristic of a person, namely, the voiceprint cannot be stolen, so that the security is high, and the loss caused by the fact that the information of the user is leaked and the counterfeiter performs related operation on the account can be avoided.

Drawings

In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.

FIG. 1 is a flow diagram of a method of authentication according to one embodiment of the present description;

FIG. 2 is a flow diagram of another embodiment authentication method of the present description;

FIG. 3 is a diagram of a scenario of an authentication method according to an embodiment of the present description;

FIG. 4 is a diagram of a scenario of another embodiment authentication method of the present description;

FIG. 5 is a flow diagram of another embodiment authentication method of the present description;

FIG. 6 is a diagram of a scenario of another embodiment authentication method of the present description;

FIG. 7 is a diagram of a scenario of another embodiment authentication method of the present description;

FIG. 8 is a schematic structural diagram of an electronic device according to one embodiment of the present description;

fig. 9 is a schematic structural diagram of an authentication device according to an embodiment of the present disclosure.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present specification, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without any creative effort shall fall within the protection scope of the present specification.

The embodiment of the specification provides an authentication method and device.

First, an authentication method provided in the embodiments of the present specification is described below.

It should be noted that the method provided by the embodiment of the present specification is applicable to an electronic device, and in practical application, the electronic device may include: server and terminal equipment, this terminal equipment can include: smart mobile phone, panel computer and computer equipment, this computer equipment can include: notebook computers, desktop computers, and the like, which are not limited in this description.

Fig. 1 is a flow chart of an authentication method according to an embodiment of the present disclosure, and as shown in fig. 1, the method may include the following steps:

in S102, the target account to which the user requests the operation is determined.

In this embodiment of the present specification, the target account may be a financial account, an account of a social application, an account of a taxi-taking application, an account of a takeout delivery application, an account of a video application, and the like, where the financial account may include: bank accounts and internet financial accounts.

In this embodiment of the present specification, when a user needs to perform some operation on an account (for example, loss report or loss release), a customer service in a customer service system may be contacted, where the customer service system may include: telephone customer service system and network customer service system.

When the customer service system is a telephone customer service system, a user can dial a customer service telephone in the telephone customer service system through a mobile phone or a landline phone to establish contact with the customer service; after establishing contact with the customer service via a telephone, the user may describe which operation needs to be performed on which account, in this case, the customer service needs to determine a target account for which the user requests the operation, and S102 may include: when the user accesses through the telephone, the target account requested to be operated by the user is determined.

When the customer service system is a network customer service system, a user can contact the customer service in the network customer service system through the network; after establishing contact with the customer service through the network, the user may describe which operation needs to be performed on which account, at this time, the customer service needs to determine a target account for which the user requests the operation, and S102 may include: when a user accesses through a network, a target account requested to be operated by the user is determined.

At present, in order to improve the security of an account, a user usually binds a phone number with the account, that is, establishes a corresponding relationship between the phone number and the account. For the telephone customer service system, when a user dials a customer service telephone of the telephone customer service system through a mobile phone, the customer service in the telephone customer service system can determine an account corresponding to the incoming call number according to the incoming call number of the user, and the account corresponding to the incoming call number is used as a target account for the operation requested by the user. At this time, in an optional embodiment, the S102 may include: when a user accesses through a telephone, acquiring a relation table, wherein the relation table records the corresponding relation between an account and a telephone number; determining an account corresponding to the incoming call number of the user according to the relation table; and determining the account corresponding to the incoming call number of the user as a target account.

Preferably, in another alternative embodiment, the S102 may include: acquiring a relation table, wherein the relation table records the corresponding relation between an account and a telephone number; determining an account corresponding to the incoming call number of the user according to the relation table; prompting whether the account corresponding to the incoming call number of the user is accepted as a target account or not; and when the user agrees, determining the account corresponding to the incoming call number of the user as the target account.

At present, when registering an account, a user usually provides own identity information, such as an identification number, a telephone number, a mailbox, and the like, so that after the account is successfully registered, the account establishes a corresponding relationship with the identity information of the user. For the telephone customer service system and the network customer service system, after establishing contact with the customer service in the customer service system, the user may send a segment of voice to the customer service, describe an account to be operated in the voice, and the customer service may determine the account described in the voice as a target account, where, in an optional embodiment, the step S102 may include: acquiring a first voice of a user, wherein the first voice comprises a voice fragment for describing an account; and determining the account described by the voice segment as a target account.

In this embodiment, the first speech may be associated with at least one of the following: the target account is described by an account number, an identification number associated with the account, a mobile phone number associated with the account, and a mailbox associated with the account.

In this embodiment, after the first voice of the user is acquired, the first voice may be recognized as a text, a partial text describing the account may be extracted from the text, and the account described by the partial text may be determined as the target account.

At present, in order to improve the security of an account, a user usually binds a terminal device with the account, that is, establishes a corresponding relationship between a hardware identifier of the terminal device and the account. For the network customer service system, when a user establishes a contact with a customer service in the network customer service system through a network, the customer service in the network customer service system can determine an account corresponding to the hardware identifier of the terminal device according to the hardware identifier of the terminal device currently used by the user, and the account corresponding to the hardware identifier is used as a target account for the user to request operation.

In S104, the current voiceprint of the user is acquired.

Voiceprint (Voiceprint), which is a spectrum of sound waves carrying verbal information displayed by an electro-acoustic instrument, is also a unique biometric feature, similar to a fingerprint. Voiceprint Recognition (Voiceprint Recognition) is a kind of biometric technology, and is a service for performing identity Recognition according to the sound wave characteristics of a speaker, and the identity Recognition is independent of accent and language, and can be used for identification and confirmation of the speaker.

In this embodiment of the present specification, the customer service may prompt the user to input a speech, and then extract a voiceprint of the user based on the speech input by the user, where the step S104 may include the following steps: s10, S12 and S14, wherein,

in S10, a second voice of the user is acquired.

In this embodiment of the present disclosure, in order to achieve a better recognition effect, the customer service may instruct the user to pronounce according to a predetermined content, that is, to require cooperation of the user, in this case, the step S10 may include: instructing the user to pronounce according to the second designated content; and receiving the voice which is obtained by the user according to the pronunciation of the second designated content.

For example, during a user's call with customer service, customer service instructs the user to pronounce at "0942051666", at which point the user needs to pronounce at "0942051666".

In this embodiment of the present disclosure, in order to identify the user identity according to the voice and facilitate the user to use without the user' S perception, the customer service may not specify the pronunciation content of the user, in this case, the step S10 may include: and acquiring the voice randomly sounded by the user.

In S12, acoustic features are extracted from the second speech.

In embodiments of the present description, the acoustic features may include: spectrum, cepstrum, formants, pitch, reflection coefficients, and the like.

In this embodiment of the present specification, in order to improve the accuracy of feature extraction, it is required to first determine whether a second voice meets some specified conditions, if the second voice meets the specified conditions, extract an acoustic feature from the second voice, and if the second voice does not meet the specified conditions, abandon the extraction of the acoustic feature from the second voice, and continue to obtain a new voice or perform a conventional authentication procedure, where the step S12 may include:

when the second voice meets the set condition, extracting acoustic features from the second voice; wherein the setting condition comprises at least one of the following: the duration of the second voice reaches a duration threshold, the noise of the second voice is lower than a noise threshold, the volume of the second voice reaches a volume threshold, and the number of conversation people in the second voice is 1.

Alternatively, when the setting condition includes: when the duration of the second voice reaches the duration threshold and the noise of the second voice is lower than the noise threshold, the customer service may first determine whether the duration of the second voice reaches the duration threshold, further determine whether the noise of the second voice is lower than the noise threshold if the duration of the second voice reaches the duration threshold, and enter a conventional authentication process if the duration of the second voice does not reach the duration threshold; and if the noise of the second voice is lower than the noise threshold, extracting acoustic features from the second voice, and if the noise of the second voice is not lower than the noise threshold, entering the traditional authentication process.

In S14, a voiceprint for characterizing the identity of the user is extracted from the acoustic features.

In this embodiment of the present specification, a conventional authentication process refers to a customer service asking and answering to verify an identity, specifically, the customer service may present a series of related questions to a user, and determine whether the user is an account holder by verifying whether an answer given by the user is correct, where the questions may include: 8 digits after the account holder's identification number, the phone number, four digits after the bound bank card number, and so on. In addition, in the customer service system, the user is prompted to input a query password for authentication.

In S106, if the corresponding history voiceprint exists in the target account, the operation authority of the user on the target account is determined based on the matching state of the current voiceprint of the user and the history voiceprint corresponding to the target account.

In this embodiment of the present specification, the history voiceprint corresponding to the target account may include: a voiceprint model of a target account holder.

In order to realize voiceprint recognition, in the embodiment of the present specification, a voiceprint library may be established in advance, a voiceprint model of a plurality of account holders is stored in the voiceprint library, and a correspondence between an account and the voiceprint model in the voiceprint library is recorded.

Optionally, when the voiceprint library is established, the user may be required to pronounce according to the specified content, and the voiceprint model of each user is accurately established one by one.

Optionally, when the voiceprint library is established, the user's pronunciation content may not be specified, and a voiceprint model of each user is established according to the user's pronunciation content.

In the embodiment of the present specification, after a target account requested to be operated by a user is determined, whether a corresponding historical voiceprint exists in the target account can be determined according to a correspondence between the account and a voiceprint model in a voiceprint library; or after the current voiceprint of the user is obtained, whether the corresponding historical voiceprint exists in the target account or not can be judged according to the corresponding relation between the account and the voiceprint model in the voiceprint library.

And if the corresponding historical voiceprint exists in the target account, determining the operation authority of the user on the target account based on the matching state of the current voiceprint of the user and the historical voiceprint corresponding to the target account. And if the target account does not have the corresponding historical voiceprint, performing a traditional identity verification process.

Optionally, if the target account has the corresponding historical voiceprint, it may be determined that the user has the authority to operate the target account when the current voiceprint of the user matches the historical voiceprint corresponding to the target account; and when the current voiceprint of the user is not matched with the historical voiceprint corresponding to the target account, determining that the user does not have the authority of operating the target account.

In the embodiment of the specification, comparing the current voiceprint of the user with the historical voiceprint corresponding to the target account to obtain a comparison score; and comparing the comparison score with a preset threshold, if the comparison result is greater than the preset threshold, indicating that the current voiceprint of the user is matched with the historical voiceprint corresponding to the target account, and if the comparison result is not greater than the preset threshold, indicating that the current voiceprint of the user is not matched with the historical voiceprint corresponding to the target account.

In this embodiment, the operation authority may include: and carrying out loss reporting authority on the account.

In this embodiment of the present specification, when the current voiceprint of the user does not match the historical voiceprint corresponding to the target account, it is prompted that an operation needs to be performed by the holder of the target account.

The embodiment can be seen in that the voiceprint recognition technology is adopted to carry out identity verification on the user in the account operation process of the user through the customer service system, and the voiceprint is the unique biological feature of the person, namely, the voiceprint cannot be stolen, so that the security is high, and the loss caused by the fact that the information of the user is leaked and the fake recognizer carries out related operation on the account can be avoided.

In order to prevent the impostor from impersonating the account holder to operate on the account through a pre-recorded recording, in another embodiment provided in the present specification, the embodiment may be based on the embodiment shown in fig. 1, and the method further includes the following steps:

when the current voiceprint of the user is matched with the historical voiceprint corresponding to the target account, indicating the user to pronounce according to first designated content;

and when the content actually pronounced by the user is matched with the first specified content, determining that the user has the authority to operate the target account.

In the embodiment of the specification, after receiving a voice of a user for an actual pronunciation of first designated content, recognizing the voice as a text, comparing the text with the text corresponding to the first designated content, and if the two are the same, indicating that the actual pronunciation of the user is matched with the first designated content, that is, indicating that the user is a target account holder; if the two are different, the content indicating the actual pronunciation of the user does not match the first specified content, i.e. indicating that the user is not the target account holder.

In this embodiment of the present specification, the first designated content is a random content, such as a string of random numbers, or a string of random letters, and since the random content cannot be spoofed by a pre-recorded voice, a loss caused by a spoofer spoofing an account holder operating the account through a pre-recorded recording can be avoided.

In order to facilitate understanding of the technical solution, the technical solution is described below with reference to specific application scenarios.

Fig. 2 is a flowchart of an authentication method according to another embodiment of the present disclosure, which is applied to a telephone customer service system, and as shown in fig. 2, the method may include the following steps:

in S202, when the user accesses through the telephone, the target account to which the user requests the operation is determined.

In the embodiment of the specification, the telephone customer service system can provide remote service for users, and the customer service in the telephone customer service system can be an intelligent customer service robot or an artificial customer service.

When the user needs to operate the account, the user service telephone of the telephone service system can be dialed through the mobile phone or the landline phone, and at the moment, the intelligent service robot or the manual service can provide service for the user.

In order to improve the security of the account, a user usually binds a phone number with the account, i.e. establishes a correspondence between the phone number of an account holder and the account. In the embodiment of the present specification, when it is detected that a user accesses a telephone customer service system through a telephone, an account corresponding to an incoming call number of the user may be determined according to a correspondence between the incoming call number of the user and a telephone number of an account holder and the account.

Optionally, in an embodiment, the account corresponding to the determined incoming call number of the user may be directly determined as the target account.

Optionally, in another embodiment, whether the user agrees to use the account corresponding to the incoming call number of the user as the target account may be prompted, and when the user agrees, the account corresponding to the incoming call number of the user is determined as the target account.

Optionally, in another embodiment, considering that one phone number may bind to multiple accounts at some time, at this time, whether the user agrees to use a specific account of the accounts corresponding to the incoming phone number of the user as the target account may be prompted, and the specific account agreed by the user may be determined as the target account.

In addition, after accessing the telephone customer service system, the user may also send a voice to the customer service system through the telephone, an account to be operated is described in the voice, the customer service system may determine the account described in the voice as a target account, and in practical applications, the information for describing the account may include at least one of the following information: the account number, the identification number associated with the account, the mobile phone number associated with the account, and the mailbox associated with the account.

In S204, it is determined whether the target account has a corresponding historical voiceprint, if so, S206 is performed, otherwise, a conventional authentication procedure is performed.

In the embodiment of the present specification, whether the target account has the corresponding historical fingerprint may be determined according to the voiceprint library, the correspondence between the voiceprint model and the account in the voiceprint library, and the target account. And if the voiceprint library has the voiceprint model corresponding to the target account, indicating that the corresponding historical voiceprint exists in the target account. And if the voiceprint library does not have the voiceprint model corresponding to the target account, the corresponding historical voiceprint does not exist in the target account.

It should be noted that the voiceprint library may be pre-established by the telephone customer service system, or may be acquired from other devices (for example, a server), and the voiceprint library stores voiceprint models of a plurality of account holders, and records a correspondence between an account and a voiceprint model in the voiceprint library.

Preferably, when the voiceprint library is established, the pronunciation content of the user may not be specified, and the voiceprint model of each user is established according to the random pronunciation content of the user.

In S206, the current voiceprint of the user is acquired.

When voiceprint recognition is performed using a voiceprint library generated based on a user's random utterance, the user may randomly vocalize, for example, a voice describing what to do with the account, receive speech generated from the user's random utterance, extract acoustic features from the speech, and extract a voiceprint from the acoustic features that uniquely characterizes the user's identity.

In addition, in order to improve the accuracy of feature extraction, it is necessary to determine whether the speech generated by the user utterance satisfies some specified conditions, for example, the duration of the speech reaches a duration threshold, the noise of the speech is lower than a noise threshold, the volume of the speech reaches a volume threshold, and the number of conversation people in the speech is 1.

In this embodiment of the present specification, when there is no corresponding history voiceprint in the target account, a conventional authentication process is performed, where the conventional authentication process refers to verifying an identity through a customer service question and answer, specifically, the customer service may present a series of related questions to the user, and determine whether the user is an account holder by verifying whether an answer given by the user is correct, where the questions may include: 8 digits after the account holder's identification number, the phone number, four digits after the bound bank card number, and so on. In addition, in a telephone customer service system, a user is prompted to input a query password for verification, which is common in customer service of a bank or a communication operator.

In S208, when the current voiceprint of the user matches the historical voiceprint corresponding to the target account, it is determined that the user has the right to operate the target account; and when the current voiceprint of the user is not matched with the historical voiceprint corresponding to the target account, determining that the user does not have the authority of operating the target account.

In the embodiment of the specification, comparing the current voiceprint of the user with the historical voiceprint corresponding to the target account to obtain a comparison score; and comparing the comparison score with a preset threshold, if the comparison result is greater than the preset threshold, indicating that the current voiceprint of the user is matched with the historical voiceprint corresponding to the target account, namely if the comparison result is not greater than the preset threshold, indicating that the current voiceprint of the user is not matched with the historical voiceprint corresponding to the target account.

In an alternative application scenario, the intelligent customer service robot in the telephone customer service system provides services for the user, as shown in fig. 3, the application scenario includes: when the user 30 needs to perform a loss report operation on an account (for example, a bank account), the user 30 dials a service phone "XXXX" in the telephone service system through the mobile phone 31, when the smart service robot 32 receives a call that the user 30 calls through the mobile phone 31, the user 30 may describe the account that needs to be operated by voice to the smart service robot 32 through the mobile phone 31, the smart service robot 32 may determine a target account that the user 30 requests to operate according to a mobile phone number of the mobile phone 31 or a voice that the user 30 transmits through the mobile phone 31, and replace the target account with the account a for subsequent convenience of description, and the smart service robot 32 determines whether the account a has a corresponding history voiceprint according to an identifier of the account a, that is, determines whether a voiceprint of a holder of the account a exists. When the voiceprint of the account a holder exists, the intelligent customer service robot 32 may prompt the user 30 to describe an operation that needs to be performed on the account a, at this time, the user 30 may describe, by using the mobile phone 31, which operations need to be performed on the account a to the intelligent customer service robot 32 in a voice mode, after receiving the voice of the user 31, the intelligent customer service robot 32 extracts the current voiceprint of the user 30 from the voice, compares the current voiceprint of the user 30 with the voiceprint of the account a holder, and if the current voiceprint of the user 30 and the voiceprint of the account a holder are matched, the intelligent customer service robot 32 performs an operation on the account a according to an instruction of the user 30, for example, performs a loss reporting operation.

In another optional application scenario, the user is served by a human customer service in a telephone customer service system, as shown in fig. 4, the application scenario includes: user 40, mobile phone 41, terminal device 42 and manual customer service 43. When a user 40 needs to perform a loss-reporting operation on an account (for example, a bank account), a customer service telephone "XXXX" in a telephone customer service system is dialed by a mobile phone 41, when an artificial customer service 43 receives a call which is incoming by the user 40 through the mobile phone 41, the user 40 may describe an account which needs to be operated by a voice to the artificial customer service 43 through the mobile phone 41, the artificial customer service 43 may input a mobile phone number of the mobile phone 41 or a voice which is transmitted by the user 40 through the mobile phone 41 into an inquiry terminal device 42, the terminal device 42 determines a target account which the user 40 requests to operate, and for subsequent convenience of description, the target account is replaced by the account B, and the terminal device 42 determines whether the account B has a corresponding history voiceprint according to an identifier of the account B, that is, whether the voiceprint of a holder of the account B exists is determined. When the terminal device 42 determines that there is a voiceprint of the account B holder, the artificial customer service 43 may prompt the user 40 to describe an operation that needs to be performed on the account B, at this time, the user 40 may describe, by a mobile phone 41, which operations need to be performed on the account B to the artificial customer service 43 by voice, the artificial customer service 43 inputs the voice of the user 40 into the terminal device 42, the terminal device 42 extracts the current voiceprint of the user 40 from the voice, and compares the current voiceprint of the user 40 with the voiceprint of the account B holder, if the two are matched, the artificial customer service 43 performs the operation on the account B according to an instruction of the user 40, for example, performs a loss removal operation.

The embodiment can be seen in that a voice print recognition biological characteristic recognition means is adopted to carry out identity verification on the incoming call user in the process of carrying out account operation such as hang-up, hang-down and other related operations through the telephone by the user, so that the security is high, and the loss caused by the fact that the false recognizers carry out the related operations on the account due to user information leakage can be avoided. In addition, the voice is unchangeable by the user of the incoming call, and in the process of communication, the voice is the only biological feature which can be obtained, so that the user does not sense in the whole verification process, a series of problems do not need to be answered, the time waste of the user and the customer service is caused, the working efficiency of the customer service is improved to a great extent, and the user experience is improved.

Fig. 5 is a flowchart of an authentication method according to another embodiment of the present disclosure, which is applied in a network customer service system, and as shown in fig. 5, the method may include the following steps:

in S502, when the user accesses through the network, the target account to which the user requests the operation is determined.

In the embodiment of the specification, the network customer service system can provide remote service for users, and the customer service in the network customer service system can be an intelligent customer service robot or an artificial customer service.

When a user needs to operate an account, the user can use terminal equipment (such as a computer, a smart phone and the like) to contact customer service in a network customer service system through a network, and at the moment, the user can be provided with services by an intelligent customer service robot or artificial customer service.

In order to improve the security of the account, the user usually binds the terminal device with the account, i.e. establishes a corresponding relationship between the hardware identifier of the terminal device and the account. In this embodiment of the present specification, when it is detected that a user accesses a network customer service system through a network, an account corresponding to a hardware identifier of a terminal device currently used by the user may be determined according to the hardware identifier of the terminal device and a correspondence between the hardware identifier of the terminal device and the account, and the account corresponding to the hardware identifier may be used as a target account for an operation requested by the user.

In addition, after accessing the network customer service system, the user may also send a segment of voice to the customer service system through the network, where an account to be operated is described in the voice, and the customer service system may determine the account described in the voice as a target account, where in actual applications, the information for describing the account may include at least one of the following information: the account number, the identification number associated with the account, the mobile phone number associated with the account, and the mailbox associated with the account.

In S504, it is determined whether the target account has a corresponding historical voiceprint, if so, S506 is performed, otherwise, a conventional authentication procedure is performed.

In this implementation, the historical voiceprint corresponding to the target account may include: a voiceprint model of a target account holder.

In S506, the current voiceprint of the user is acquired.

In S508, when the current voiceprint of the user matches the historical voiceprint corresponding to the target account, it is determined that the user has the authority to operate the target account; and when the current voiceprint of the user is not matched with the historical voiceprint corresponding to the target account, determining that the user does not have the authority of operating the target account.

In an optional application scenario, the intelligent customer service robot in the network customer service system provides services for the user, as shown in fig. 6, the application scenario includes: the method comprises the steps that a user 60, a terminal device 61, an intelligent customer service robot 62 and a network 63 are used, when the user 60 needs to perform loss report operation on an account (such as a bank account), the terminal device 61 is used for contacting customer service in a network customer service system through the network 63, after the intelligent customer service robot 62 establishes network connection with the terminal device 61, the user 60 can describe the account needing to be operated to the intelligent customer service robot 62 through the terminal device 61 in a voice mode, the intelligent customer service robot 62 can determine a target account which the user 60 requests to operate according to a hardware identifier of the terminal device 61 or the voice transmitted by the user 60 through the terminal device 61, for the purpose of subsequent convenience in description, the target account is replaced by the account C, and the intelligent customer service robot 62 determines whether the account C has a corresponding historical voiceprint according to the identifier of the account C, namely whether the voiceprint of a holder of the account C exists or not. When there is a voiceprint of the account C holder, the intelligent customer service robot 62 may prompt the user 60 to describe an operation that needs to be performed on the account C, at this time, the user 60 may describe, by a voice to the intelligent customer service robot 62 through the terminal device 61, which operations need to be performed on the account C, after receiving the voice of the user 61, the intelligent customer service robot 62 extracts the current voiceprint of the user 60 from the voice, and compares the current voiceprint of the user 60 with the voiceprint of the account C holder, and if the two are matched, the intelligent customer service robot 62 performs an operation on the account C according to an instruction of the user 60, for example, performs a loss reporting operation.

In another optional application scenario, as shown in fig. 7, the user is served by a human customer service in the network customer service system, and the application scenario includes: user 70, terminal device 71, terminal device 72, human customer service 73, and network 74. When the user 70 needs to perform a loss-removing operation on an account (e.g., a bank account), the terminal device 71 is used to contact customer service in the network customer service system through the network 74, after the terminal device 72 establishes a network connection with the terminal device 71, the user 70 may describe an account to be operated to the manual customer service 73 by voice through the terminal device 71, the terminal device 72 may determine a target account requested to be operated by the user 70 according to a hardware identifier of the terminal device 71 or voice transmitted by the user 70 through the terminal device 71, for convenience of description, the account D is used instead, and the terminal device 72 determines whether a corresponding history voiceprint exists in the account D according to an identifier of the account D, that is, whether a voiceprint of a holder of the account D exists is determined. When the voiceprint of the account D holder exists, the artificial customer service 73 may prompt the user 70 to describe an operation that needs to be performed on the account D, at this time, the user 70 may describe, by the terminal device 71, which operations need to be performed on the account D to the artificial customer service 73 in a voice, after receiving the voice of the user 71, the terminal device 72 extracts the current voiceprint of the user 70 from the voice, compares the current voiceprint of the user 70 with the voiceprint of the account D holder, and if the two are matched, the artificial customer service 73 operates the account D according to an instruction of the user 70, for example, performs a loss removal operation.

The embodiment can be seen in that the user can be authenticated by adopting a voiceprint recognition biological characteristic recognition means in the process of performing account operation such as hang-off and other related operations through a network, and the security is high, so that the loss caused by the fact that a false recognizer performs related operations on the account due to user information leakage can be avoided. In addition, the voice is unchangeable by the user of the incoming call, and in the process of network communication, the voice is the only biological feature which can be obtained, so that the user does not sense in the whole verification process and does not need to answer a series of questions, the time waste of the user and the customer service is caused, the working efficiency of the customer service is improved to a great extent, and the user experience is improved.

Fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present specification. Referring to fig. 8, at a hardware level, the electronic device includes a processor, and optionally further includes an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory, such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.

The processor, the network interface, and the memory may be connected to each other via an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 8, but that does not indicate only one bus or one type of bus.

And the memory is used for storing programs. In particular, the program may include program code comprising computer operating instructions. The memory may include both memory and non-volatile storage and provides instructions and data to the processor.

The processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to form the authentication device on the logic level. The processor is used for executing the program stored in the memory and is specifically used for executing the following operations:

determining a target account requested to be operated by a user;

acquiring the current voiceprint of the user;

The method performed by the authentication device according to the embodiment shown in fig. 8 of the present specification can be applied to or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present specification may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present specification may be embodied directly in a hardware decoding processor, or in a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.

The electronic device may also execute the method of fig. 1 and implement the functions of the authentication apparatus in the embodiment shown in fig. 1, which are not described herein again in this specification.

Of course, besides the software implementation, the electronic device in this specification does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may also be hardware or logic devices.

Embodiments of the present specification also propose a computer-readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a portable electronic device comprising a plurality of application programs, are capable of causing the portable electronic device to perform the method of the embodiment shown in fig. 1, and in particular for performing the method of:

determining a target account requested to be operated by a user;

acquiring the current voiceprint of the user;

Fig. 9 is a schematic structural diagram of an authentication device according to an embodiment of the present disclosure. Referring to fig. 9, in a software implementation, the authentication apparatus 900 may include: a determining unit 901, an obtaining unit 902 and an authenticating unit 903, wherein,

a determining unit 901, configured to determine a target account that a user requests to operate;

an obtaining unit 902, configured to obtain a current voiceprint of the user;

an authentication unit 903, configured to determine, when the corresponding historical voiceprint exists in the target account, an operation permission of the user for the target account based on a matching state of the current voiceprint of the user and the historical voiceprint corresponding to the target account.

Optionally, as an embodiment, the authentication unit 903 may include:

the first permission determining subunit is configured to determine that the user has permission to operate the target account when the current voiceprint of the user matches the historical voiceprint corresponding to the target account;

and the second permission determining subunit is configured to determine that the user does not have permission to operate the target account when the current voiceprint of the user does not match the historical voiceprint corresponding to the target account.

Optionally, as an embodiment, the authentication unit 903 may further include:

the first indication subunit is used for indicating the user to pronounce according to first specified content when the current voiceprint of the user is matched with the historical voiceprint corresponding to the target account;

the first permission determining subunit is specifically configured to determine that the user has permission to operate the target account when the content actually pronounced by the user matches the first specified content.

Optionally, as an embodiment, the determining unit 901 may include:

the first account determining subunit is used for determining the target account which is requested to be operated by the user under the condition that the user accesses through the telephone.

Optionally, as an embodiment, the first account determining subunit may include:

the system comprises a relation table acquisition subunit, a relation table acquisition subunit and a relation table processing unit, wherein the relation table acquisition subunit is used for acquiring a relation table under the condition that a user accesses through a telephone, and the relation table records the corresponding relation between an account and a telephone number;

the second account determining subunit is used for determining an account corresponding to the incoming call number of the user according to the relation table;

and the third account determining subunit is used for determining the account corresponding to the incoming call number of the user as the target account.

Optionally, as an embodiment, the first account determining subunit may further include:

the prompting subunit is used for prompting whether the account corresponding to the incoming call number of the user is used as a target account;

the third account determination subunit is specifically configured to determine, when it is determined that the user agrees, an account corresponding to the incoming call number of the user as a target account.

Optionally, as an embodiment, the determining unit 901 may include:

and the fourth account determining subunit is used for determining the target account which is requested to be operated by the user under the condition that the user accesses through the network.

Optionally, as an embodiment, the determining unit 901 may include:

the first voice acquiring subunit is used for acquiring a first voice of a user, wherein the first voice comprises a voice segment used for describing an account;

and the fifth account determining subunit is used for determining the account described by the voice fragment as the target account.

Optionally, as an embodiment, the obtaining unit 902 may include:

the second voice acquiring subunit is used for acquiring a second voice of the user;

a feature extraction subunit, configured to extract an acoustic feature from the second speech;

and the voiceprint acquisition subunit is used for extracting the voiceprint used for representing the identity of the user from the acoustic features.

Optionally, as an embodiment, the second speech acquiring subunit may include:

a second indicating subunit, configured to indicate the user to pronounce according to a second specified content;

and the voice receiving subunit is used for receiving the voice obtained by the user according to the pronunciation of the second specified content.

Optionally, as an embodiment, the second speech acquiring subunit is specifically configured to acquire speech obtained by the random utterance of the user.

Optionally, as an embodiment, the feature extraction subunit may include:

an acoustic feature extraction subunit, configured to extract an acoustic feature from the second voice when the second voice satisfies a set condition;

the setting condition includes at least one of the following: the duration of the second voice reaches a duration threshold, the noise of the second voice is lower than a noise threshold, the volume of the second voice reaches a volume threshold, and the number of conversation people in the second voice is 1.

Optionally, as an embodiment, the apparatus may further include:

and the prompting unit is used for prompting that the operation is required to be carried out by the holder of the target account under the condition that the current voiceprint of the user is not matched with the historical voiceprint corresponding to the target account.

The authentication device 900 can also execute the method of the embodiment shown in fig. 1 and implement the functions of the authentication device in the embodiment shown in fig. 9, which are not described herein again in this embodiment of the present disclosure.

In short, the above description is only a preferred embodiment of the present disclosure, and is not intended to limit the scope of the present disclosure. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present specification shall be included in the protection scope of the present specification.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

Claims

1. A method of authentication, the method comprising:

determining a target account requested to be operated by a user, comprising: when a user accesses through a telephone, acquiring a relation table, wherein the relation table records the corresponding relation between an account and a telephone number, determining the account corresponding to the incoming call number of the user according to the relation table, determining the account corresponding to the incoming call number of the user as a target account, and requesting to operate as a loss report operation by the user;

acquiring the current voiceprint of the user;

if the target account has the corresponding historical voiceprint, determining the operation authority of the user on the target account based on the matching state of the current voiceprint of the user and the historical voiceprint corresponding to the target account, wherein the operation authority comprises: and releasing the lost authority of the account.

2. The method of claim 1, wherein the determining the operation authority of the user on the target account based on the matching state of the current voiceprint of the user and the historical voiceprint corresponding to the target account comprises:

when the current voiceprint of the user is matched with the historical voiceprint corresponding to the target account, determining that the user has the authority of operating the target account;

and when the current voiceprint of the user is not matched with the historical voiceprint corresponding to the target account, determining that the user does not have the authority of operating the target account.

3. The method of claim 2, further comprising, prior to the determining that the user has permission to operate on the target account:

instructing the user to pronounce according to a first specified content;

the determining that the user has the right to operate the target account includes:

4. The method of claim 1, before determining the account corresponding to the incoming call number of the user as the target account, further comprising:

prompting whether the account corresponding to the incoming call number of the user is accepted as a target account or not;

the determining the account corresponding to the incoming call number of the user as the target account includes:

and when the user agrees, determining the account corresponding to the incoming call number of the user as a target account.

5. The method of claim 1, the determining a target account for which the user requested an operation, comprising:

and when the user accesses through the network, determining a target account requested to be operated by the user.

6. The method of claim 1, the determining a target account for which the user requested an operation, comprising:

acquiring a first voice of a user, wherein the first voice comprises a voice fragment for describing an account;

and determining the account described by the voice segment as a target account.

7. The method of claim 1, the obtaining the current voiceprint of the user comprising:

acquiring a second voice of the user;

extracting acoustic features from the second speech;

extracting a voiceprint from the acoustic features for characterizing the identity of the user.

8. The method of claim 7, the obtaining the second speech of the user comprising:

instructing the user to pronounce according to a second specified content;

and receiving the voice obtained by the user according to the pronunciation of the second designated content.

9. The method of claim 7, the obtaining the second speech of the user comprising:

and acquiring the voice obtained by the random sound production of the user.

10. The method of claim 7, the extracting acoustic features from the second speech, comprising:

when the second voice meets a set condition, extracting acoustic features from the second voice;

11. The method of claim 2, further comprising:

and when the current voiceprint of the user is not matched with the historical voiceprint corresponding to the target account, prompting that the operation is required to be carried out by a holder of the target account.

12. An authentication apparatus, the apparatus comprising:

the determining unit is used for determining a target account requested to be operated by a user, and comprises the following steps: when a user accesses through a telephone, a relation table is obtained, the corresponding relation between an account and a telephone number is recorded in the relation table, an account corresponding to the incoming call number of the user is determined according to the relation table, the account corresponding to the incoming call number of the user is determined as a target account, and the user request operation comprises the following steps: performing loss releasing operation on the account;

the acquisition unit is used for acquiring the current voiceprint of the user;

an authentication unit, configured to determine, when the target account has a corresponding historical voiceprint, an operation permission of the user for the target account based on a matching state of the current voiceprint of the user and the historical voiceprint corresponding to the target account, where the operation permission of the target account includes: and releasing the lost authority of the account.

13. An electronic device, comprising:

a processor; and

acquiring the current voiceprint of the user;

14. A computer storage medium storing one or more programs that, when executed by an electronic device including a plurality of application programs, cause the electronic device to:

acquiring the current voiceprint of the user;