HK1258035B - Payment processing method and device, computer equipment and storage medium - Google Patents

Description

Payment processing method and device, computer equipment and storage medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to a payment processing method and apparatus, a computer device, and a storage medium.

Background

With the development of computer technology and the operation of various application programs with payment functions, the payment-free mode is convenient and quick, the trouble of people to get cash is eliminated, and the payment-free mode is accepted and used by more and more people. However, the existing ubiquitous payment mode basically needs to rely on other devices, such as a bank card, a credit card, a mobile phone, an intelligent wearable device and the like, to complete payment, and the payment process is complex, and usually a user needs to perform a series of operations such as opening a device, unlocking, opening an application program, inputting a password and the like, and the operation process of user payment is complex.

Disclosure of Invention

In view of the above, it is necessary to provide a payment processing method, an apparatus, a computer device and a storage medium capable of simplifying a user payment operation flow in order to solve the above technical problems.

A payment processing method, the method comprising:

receiving a payment request sent by a terminal, wherein the payment request carries order data and password record;

acquiring a user identifier corresponding to a first password in the password recording;

acquiring a first preset authentication problem, sending the first preset authentication problem to the terminal, and receiving a first answer record corresponding to the first preset authentication problem and returned by the terminal;

extracting a first authentication answer corresponding to the first preset authentication question from the order data, and searching a first voiceprint feature corresponding to the user identifier;

identifying a second authentication answer from the first answer recording and extracting a second voiceprint feature;

and when the second authentication answer is consistent with the first authentication answer and the second voiceprint feature is successfully matched with the first voiceprint feature, searching a payment account corresponding to the user identifier, and deducting a value consistent with the payment value in the order data from the payment account.

In one embodiment, the method further comprises the following steps:

when the user identification corresponding to the first password in the password record is not obtained, generating an authentication failure notice and sending the authentication failure notice to the terminal;

after receiving the record retransmitted by the terminal, taking the retransmitted record as a password record and continuously and circularly executing the step of acquiring the user identifier corresponding to the first password in the password record;

and when the number of times of generating the authentication failure notice exceeds a preset authentication number threshold, generating a payment locking notice and sending the payment locking notice to the terminal.

In one embodiment, before the step of receiving the payment request sent by the terminal, the method further includes:

receiving a user registration request, wherein the user registration request carries registration password recording and a payment account;

generating a user identifier according to the user registration request;

identifying a second password from the registration password record, generating a registration confirmation instruction carrying the second password and a user identifier, and sending the registration confirmation instruction to the terminal;

and after receiving a registration confirmation notification returned by the terminal, extracting a third voiceprint feature from the registration password record, taking the second password as a new user password, and performing associated storage on the user identification, the new user password and the third voiceprint feature.

In one embodiment, the method further comprises the following steps:

when the second authentication answer is inconsistent with the first authentication answer, generating a payment refusing notice;

and returning the payment refusal notice to the terminal.

In one embodiment, the method further comprises the following steps:

when the second authentication answer is consistent with the first authentication answer and the second voiceprint feature is unsuccessfully matched with the first voiceprint feature, searching a first auxiliary voiceprint feature and a preset auxiliary authentication problem corresponding to the user identifier;

sending the auxiliary authentication problem to the terminal; after receiving an auxiliary answer recording corresponding to the auxiliary authentication question returned by the terminal, extracting a second auxiliary voiceprint feature from the auxiliary answer recording;

and when the second auxiliary voiceprint feature is successfully matched with the first auxiliary voiceprint feature, searching a payment account corresponding to the user identifier, and deducting a value consistent with the payment value in the order data from the payment account.

In one embodiment, the method further comprises the following steps:

when the first auxiliary voiceprint feature corresponding to the user identification cannot be found, acquiring a second preset authentication problem, and sending the second preset authentication problem to the terminal;

receiving a second answer record returned by the terminal, and extracting a fourth voiceprint feature from the second answer record;

and when the fourth voiceprint feature is unsuccessfully matched with the first voiceprint feature, generating a payment refusing notice and returning the payment refusing notice to the terminal.

In one embodiment, the step of obtaining the first preset authentication question includes:

acquiring a commodity code from the order data;

searching a preset problem pool corresponding to the commodity code, wherein the preset problem pool comprises a plurality of preset authentication problems;

and randomly extracting a first preset authentication problem from the preset problem pool.

A payment processing apparatus, the apparatus comprising:

the request receiving module is used for receiving a payment request sent by a terminal, and the payment request carries order data and password record;

the identification acquisition module is used for acquiring a user identification corresponding to a first password in the password records;

the answer record acquisition module is used for acquiring a first preset authentication question, sending the first preset authentication question to the terminal and receiving a first answer record which is returned by the terminal and corresponds to the first preset authentication question;

the characteristic searching module is used for extracting a first authentication answer corresponding to the first preset authentication question from the order data and searching a first voiceprint characteristic corresponding to the user identification;

the answer record identification module is used for identifying a second authentication answer from the first answer record and extracting a second sound print characteristic;

and the first payment module is used for searching a payment account corresponding to the user identification and deducting a value consistent with the payment value in the order data from the payment account when the second authentication answer is consistent with the first authentication answer and the second voiceprint feature is successfully matched with the first voiceprint feature.

A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the above method when executing the computer program.

A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method.

According to the payment processing method, the payment processing device, the computer equipment and the storage medium, when payment is carried out, a user only needs to enter the password record and answer the preset authentication question, the password content in the password record is successfully verified, and after the answer content of the answer record answered by the user and the voiceprint feature of the user are successfully verified, the payment operation can be completed, the user does not need to carry out other operation processes, the payment process is convenient and fast, and the payment operation experience of the user can be improved.

Drawings

FIG. 1 is a diagram of an application scenario of a payment processing method in one embodiment;

FIG. 2 is a schematic flow diagram of a payment processing method in one embodiment;

FIG. 3 is a block diagram of the structure of a payment processing apparatus in one embodiment;

FIG. 4 is a diagram illustrating an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

Before describing in detail embodiments that are in accordance with the present invention, it should be observed that the embodiments reside primarily in combinations of steps and system components related to payment processing methods, apparatus, computer devices, and storage media. Accordingly, the system components and method steps have been represented where appropriate by conventional symbols in the drawings, showing only those details that are pertinent to understanding the embodiments of the present invention so as not to obscure the disclosure with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.

In this document, relational terms such as left and right, top and bottom, front and back, first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. 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.

The payment processing method provided by the application can be applied to the application environment shown in fig. 1. Wherein, the terminal communicates with the server through the network. When payment is carried out, a terminal sends a payment request carrying payment order data and a password record of a user to a server, the server receives the payment request sent by the terminal, acquires the password record from the payment request and searches for a user identifier corresponding to a first password in the password record, the server acquires a first preset authentication question corresponding to the user identifier and sends the first preset authentication question to the terminal, the terminal acquires a first answer record corresponding to the first preset authentication question from the user and sends the acquired first answer record to the server, the server extracts a first authentication answer corresponding to the first preset authentication question from the order data and searches for a first voiceprint feature corresponding to the user identifier, and the server identifies a second authentication answer from the received first answer record and extracts a second voiceprint feature from the first answer record. And the server compares the second authentication answer with the first authentication answer, matches the second voiceprint feature with the first voiceprint feature, searches the payment account corresponding to the user identification when the second authentication answer is consistent with the first authentication answer and the second voiceprint feature is successfully matched with the first voiceprint feature, and deducts a value consistent with the payment value in the order data from the payment account so as to finish the payment of the order.

The terminal can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices, and the server can be implemented by an independent server or a server cluster formed by a plurality of servers.

In one embodiment, as shown in fig. 2, a payment processing method is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:

and step 210, receiving a payment request sent by the terminal, wherein the payment request carries order data and password record.

The payment processing method in the embodiment can be applied to various payment scenes, a user can place an order to pay through a mobile phone, a computer and other terminals used by the user, the user can also place the order to purchase commodities in an online store, and a clerk can pay the order through the store terminal.

After the commodity order is generated through payment, the terminal can send a prompt for reading the prestored payment password to the user, and the terminal can prompt the user or a shop assistant in a text or voice mode. Wherein the pre-stored payment password is set when the user registers in advance. After receiving the prompt, the user reads the pre-stored payment password set by the user, the terminal collects the record of the pre-stored payment password read by the user through a microphone and other devices, and when the terminal sends the collected record of the password read by the user to the server together with the order data of the product purchased by the user.

The pre-stored payment password may be a mobile phone number and an identification number selected by a user, or a string of preset random numbers, a segment of characters, and the like, and may be in other forms. The order data sent by the terminal to the server may include information of purchased goods, such as a goods code, and may also include data of a payment value, an order number, an order generation time, user information, and the like.

Step 220, a user identifier corresponding to the first password in the password recording is obtained.

And after receiving the payment request sent by the terminal, the server acquires order data and password record in the payment request. The server identifies the first password from the password recording, acquires a user information table, searches whether a pre-stored payment password matched with the first password exists in the user information table, indicates that the user is a registered user when the pre-stored payment password matched with the first password is found, and searches the user identification corresponding to the matched pre-stored payment password from the user information table.

The server stores the user information of all registered users in a user information table in advance, and the user information table correspondingly stores information such as user identification, prestored payment passwords, payment account numbers of the users and the like. Wherein the user identification is used for uniquely identifying the user identity.

Step 230, obtaining a first preset authentication question, sending the first preset authentication question to the terminal, and receiving a first answer record corresponding to the first preset authentication question returned by the terminal.

The server obtains a first preset authentication problem. Specifically, the first preset authentication question is related to a commodity purchased by the user, and the first preset authentication question may be set according to data included in a commodity order. Taking the commodity as an insurance product as an example for explanation, the first preset authentication problem may be: what the name of the insured life is, what the name of the insurer is, how long the product is in effect for the insured life, etc. The number of the first preset authentication questions corresponding to the same commodity may be multiple. The server can read the commodity code from the order data, search for a first preset authentication problem corresponding to the commodity code, and send the searched preset authentication problem to the terminal.

And after the terminal receives the first preset authentication problem sent by the server, the first preset authentication problem is displayed to the user. The terminal can display the first preset authentication question on a terminal interface in a text mode and prompt the user to answer the question, and the terminal can play the first preset authentication question to the user in a voice prompt mode. After receiving the question prompt, the user needs to answer the first preset authentication question in a voice mode. The terminal can collect first answer records answered by the user through a microphone and other devices, and the terminal returns the collected first answer records of the user to the server. And the server receives the first answer record returned by the terminal.

Step 240, extracting a first authentication answer corresponding to the first preset authentication question from the order data, and searching for a first voiceprint feature corresponding to the user identifier.

After the server acquires the first preset authentication question, a first authentication answer corresponding to the acquired first preset authentication question is extracted from order data.

Specifically, each first preset authentication question has its corresponding key field, for example, the key field of "what is the name of the insured person" is "the name of the insured person", and the key field of "the guarantee period of validity of the insured product" is "the guarantee period of validity". The server acquires a key field corresponding to the first preset authentication question, and extracts a first authentication answer corresponding to the key field from the order data. For example, the server extracts "zhang san" as the first authentication answer from the order data according to the "insured name field".

The server searches for a first voiceprint feature corresponding to the user identifier, when the user registers the voice payment function, the user needs to provide a record of a pre-stored payment password, the server extracts the first voiceprint feature of the user from the record of the pre-stored payment password, and the extracted first voiceprint feature and the user identifier are stored in an associated mode.

Step 250, identifying a second authentication answer from the first answer record and extracting a second voiceprint feature.

After receiving the first answer recording, the server identifies the semantic content of the recording, namely the second authentication answer, from the first answer recording through a voice identification method, extracts the voiceprint features of the first answer recording, and extracts the second voiceprint features.

And step 260, when the second authentication answer is consistent with the first authentication answer and the second voiceprint feature is successfully matched with the first voiceprint feature, searching the payment account corresponding to the user identifier, and deducting a value consistent with the payment value in the order data from the payment account.

And the server compares the second authentication answer answered by the user with the first authentication answer extracted from the order data and judges whether the second authentication answer is consistent with the first authentication answer. And the server matches the second voiceprint characteristic with a pre-stored first voiceprint characteristic and judges whether the second voiceprint characteristic and the pre-stored first voiceprint characteristic can be successfully matched. And when the server judges that the second authentication answer is consistent with the first authentication answer and judges that the second voiceprint feature is successfully matched with the second voiceprint feature, the server successfully authenticates the identity of the user and can perform payment operation. And the server searches the payment account corresponding to the user identification from the user information table and extracts the payment value of the order from the order data. And the server deducts the value consistent with the payment value from the payment account number of the user to finish the payment operation. Wherein the payment account is reserved in advance for the user. The payment account can be a bank card account, a payment account, a WeChat account and other financial accounts capable of making payment.

In this embodiment, when the user pays for a commodity order, only the password record needs to be read aloud and the preset authentication problem needs to be answered, the server successfully verifies the password content in the obtained password record, and after the answer content of the answer record answered by the user and the voiceprint feature of the user are successfully verified, the corresponding numerical value can be deducted from the payment account number of the user, the payment operation is completed, the user does not need to perform other operation flows, the payment process is convenient and fast, and the payment operation experience of the user can be improved. In addition, the user is required to answer the first preset authentication question, secondary matching authentication is carried out on answer records of the user, and the safety of voice payment can be improved through double verification.

In one embodiment, the step of obtaining the first preset authentication question comprises: acquiring a commodity code from the order data; searching a preset problem pool corresponding to the commodity code, wherein the preset problem pool comprises a plurality of preset authentication problems; and randomly extracting a first preset authentication problem from the preset problem pool.

The server reads a commodity code from the order data, the commodity code being used to uniquely identify the commodity purchased by the user. Each commodity or each type of commodity has a preset problem pool corresponding to the commodity or each type of commodity, the preset problem pool comprises a plurality of preset authentication problems, and the preset problem pool and the commodity code of the corresponding commodity are stored in an associated mode. The server randomly extracts a preset authentication problem from the preset problem pool as a first preset authentication problem, so that the preset authentication problem extracted every time of payment is random and unpredictable.

In other embodiments, the server may also encode a plurality of preset authentication problems in the preset problem pool, and each time the first preset authentication problem is obtained, one preset authentication problem is extracted from the preset problem pool one by one according to the encoding sequence.

Because the payment password pre-stored by the user is fixed, if the identity of the user is authenticated only by pre-storing the payment password, the condition that others record and copy the payment password read by the user and pay by copying the record and pretending to be the identity of the user is likely to occur. In the embodiment, after the authentication of the user payment password is successful, the user also needs to answer the randomly extracted authentication problem, and because the authentication problem is randomly extracted, other people cannot embezzle the payment in a way of copying the record, so that the safety of voice payment is greatly improved.

In one embodiment, the method further comprises: when the user identification corresponding to the first password in the password recording is not obtained, generating an authentication failure notice and sending the authentication failure notice to the terminal; after receiving the record retransmitted by the terminal, taking the retransmitted record as a password record and continuously and circularly executing the step of acquiring the user identifier corresponding to the first password in the password record; and when the number of times of generating the authentication failure notice exceeds a preset authentication number threshold, generating a payment locking notice and sending the payment locking notice to the terminal.

And when the server identifies the first password from the password record, does not find the pre-stored payment password corresponding to the first password from the user information table, and cannot acquire the user identification of the first password, the server generates an authentication failure notice and sends the authentication failure notice to the terminal. Since the user reading the password is easily affected by the noise of the surrounding environment, a literal recognition error may occur. After receiving the authentication failure notification, the terminal can prompt the user to read the password recording again, and the terminal collects the recording read again by the user through sound collection equipment such as a microphone and sends the collected recording to the server again. And after receiving the record retransmitted by the terminal, the server takes the received record as a password record, and continues to circularly execute the step of acquiring the user identification corresponding to the first password in the password record, namely, the server circularly executes the step of identifying the first password from the password record, searching whether a prestored payment password matched with the first password exists in the user information table, and then searching the user identification corresponding to the matched prestored payment password in the user information table. And when the server cannot find the prestored payment password matched with the first password and cannot acquire the user identification corresponding to the first password in the password record, continuously generating an authentication failure notice and sending the authentication failure notice to the terminal.

The server records the times of sending the authentication failure notification to the terminal, finds the pre-stored authentication time threshold value, and generates a payment locking notification and sends the payment locking notification to the terminal when the sending times recorded by the server exceed the preset authentication time threshold value. The server records the payment lock for the user. In one embodiment, the server may set a payment lock time and, upon reaching the payment lock time, unlock the payment lock for the user. During the payment locking period, the user cannot perform any payment operation through a voice payment mode. After the payment lock is released, the voice payment operation can be continued.

And after receiving the payment locking notification, the terminal displays a payment locking notification prompt to the user, and the time of the payment locking can be declared in the prompt. For example, the terminal may display a payment locking notification, such as "the payment password authentication fails, the voice payment function is locked within 3 hours" in a text or voice manner.

In this embodiment, after the authentication of the first payment password recorded by the user fails, the server sends an authentication failure notification to the terminal, and allows the user to continue uploading the recorded records read again until the number of authentication failures exceeds a preset value, and then sends out a notification of payment locking, thereby avoiding the influence of environmental sound interference on the voice authentication process.

In one embodiment, within the preset authentication frequency threshold, when the server extracts the first password from the received re-sent recording and can find the user identifier corresponding to the first password, the server successfully authenticates the payment password read by the user, and the server continues to perform the step of acquiring the first preset authentication problem.

In one embodiment, before the step of receiving the payment request sent by the terminal, the method further includes: receiving a user registration request, wherein the user registration request carries registration password recording and a payment account; generating a user identifier according to the user registration request; identifying a second password from the registration password record, generating a registration confirmation instruction carrying the second password and the user identification, and sending the registration confirmation instruction to the terminal; and after receiving a registration confirmation notification returned by the terminal, extracting a third voiceprint feature from the registration password record, taking the second password as a newly-added user password, and performing associated storage on the user identification, the newly-added user password and the third voiceprint feature.

Before the user uses the voice payment function, the user needs to register the user identity information. When identity information is registered, a user can enter a registration password record through a terminal and input a payment account number for payment. And after the user completes the operation and confirms, the terminal generates a user registration request according to the acquired registration password and the payment account, and sends the user registration request to the server. The server generates a unique user identifier after receiving the user registration request, the user identifier can be in the form of a user number and the like, and the server can generate the user identifier according to the user number sequence code of the last registered user or generate the user identifier by adopting other methods.

The server acquires the registration password record and the payment account from the user registration request. The server identifies the recorded content, i.e. the second password, from the recording of the registration passwords according to the speech meaning identification method, wherein the second password is used for distinguishing from the first password used in the payment in the above embodiment, and has no other special meaning. And the server generates a registration confirmation instruction according to the generated user identification and the identified second password, and sends the registration confirmation instruction to the terminal. And after receiving the registration confirmation instruction, the terminal reads the user identification and the second password and displays the user, and simultaneously displays a prompt for judging whether the second password is used as a payment password or not to the user. And after the user confirms the second password through the terminal, the terminal generates a registration confirmation notice and returns the registration confirmation notice to the server.

And after receiving a registration confirmation notification returned by the terminal, the server extracts a third voiceprint feature from the registration password record, and stores the user identification, the second password, the payment account and the third voiceprint feature in a correlation manner as the information of the newly added user. In one embodiment, the server may add the above information of the registered user to the user information table.

In this embodiment, the user can complete the registration of the voice payment function only by inputting the registration password and providing the payment account number through voice, which is convenient and fast.

In one embodiment, the method further comprises: when the second authentication answer is inconsistent with the first authentication answer, generating a payment refusing notice; and returning the payment refusal notice to the terminal.

And after the server compares the second authentication answer with the first authentication answer, when the second authentication answer is judged to be inconsistent with the first authentication answer, whether the second voiceprint feature is matched with the first voiceprint feature or not and the identity authentication of the user fails, directly generating a refusal payment notification, returning the refusal payment notification to the terminal, and displaying a refusal payment prompt to the user after the terminal receives the notification.

In the embodiment, when the answer content answered by the user is incorrect, the refusal payment notice is directly generated, so that the condition that the user steals the copy record to pay is prevented.

In one embodiment, the method may further comprise the steps of: when the second authentication answer is consistent with the first authentication answer and the second voiceprint feature is unsuccessfully matched with the first voiceprint feature, searching a first auxiliary voiceprint feature and a preset auxiliary authentication question corresponding to the user identifier; sending the auxiliary authentication problem to the terminal; after receiving an auxiliary answer recording corresponding to the auxiliary authentication question returned by the terminal, extracting a second auxiliary voiceprint feature from the auxiliary answer recording; and when the second auxiliary voiceprint characteristic is successfully matched with the first auxiliary voiceprint characteristic, searching a payment account corresponding to the user identification, and deducting a value consistent with the payment value in the order data from the payment account.

When the server judges that the answer content answered by the user is consistent with the authentication answer extracted from the order, but the second voiceprint feature is unsuccessfully matched with the first voiceprint feature, the voiceprint feature is related to the state of human breath, pronunciation and the like, the user may occasionally pronounce and the matching of the recorded voiceprint with the prestored voiceprint fails, and in order to avoid the above situation, the server starts an auxiliary authentication process of the user identity.

The server searches whether a first auxiliary voiceprint characteristic corresponding to the user identification exists or not, acquires a preset auxiliary authentication problem when the first auxiliary voiceprint characteristic is searched, and sends the auxiliary authentication problem to the terminal so that the user can answer the problem. Many users can skillfully use a second language, such as foreign language, dialect and the like, besides the native language of the users, the users upload the recordings in the second language to the server during registration, and after receiving the recordings in the second language, the server extracts corresponding voiceprint features from the recordings in the second language to serve as auxiliary voiceprint features and stores the auxiliary voiceprint features and user identification in an associated manner. The user in china is taken as an example for explanation, mandarin is taken as a standard language used when all users register, and the user can select a second language such as english, french, cantonese and the like as an auxiliary payment password according to the language capability of the user in addition to uploading the standard payment password of mandarin.

The preset auxiliary authentication problem may be the same as the preset authentication problem or different from the preset authentication problem. Similarly, the preset auxiliary authentication question is also set according to the commodity purchased by the user, and can be further adaptively set according to the language characteristics of the second language. The server acquires a second language identification corresponding to the user identification, searches a corresponding preset auxiliary problem pool according to the commodity code and the second language identification, and can randomly extract an auxiliary authentication problem from the preset auxiliary problem pool and send the auxiliary authentication problem to the terminal.

The method comprises the steps that after a terminal receives an auxiliary authentication question, the terminal prompts a user to answer the auxiliary authentication question by using a second language, auxiliary answer records answered by the user are collected, the auxiliary answer records are returned to a server, after the server receives the auxiliary answer records, a second auxiliary voiceprint feature is extracted from the auxiliary answer records and matched with a pre-stored first auxiliary voiceprint feature, when the second auxiliary voiceprint feature is successfully matched with the first auxiliary voiceprint feature, the server searches a payment account corresponding to a user identification, reads a payment value from order data, deducts a value consistent with the payment value from the payment account, and accordingly payment of a commodity order is completed. And when the second auxiliary voiceprint feature is failed to be matched with the first auxiliary voiceprint feature, the server generates a payment refusal notice and returns the payment refusal notice to the terminal, and the terminal displays the identity authentication failure and the payment refusal notice of the user.

In this embodiment, through adopting supplementary vocal print characteristics such as second language, dialect to authenticate user's identity, can assist the authentication when failing because user's pronunciation leads to second vocal print characteristic and first vocal print characteristic matching to reduce the wrong probability of authentication, improve authentication's rate of accuracy, improve user experience.

In one embodiment, the method may further comprise: when the first auxiliary voiceprint characteristic corresponding to the user identification cannot be found, a second preset authentication problem is obtained, and the second preset authentication problem is sent to the terminal; receiving a second answer record returned by the terminal, and extracting a fourth voiceprint feature from the second answer record; and when the fourth voiceprint feature is failed to be matched with the first voiceprint feature, generating a payment refusing notice and returning the payment refusing notice to the terminal.

And when the server judges that the second authentication answer is consistent with the first authentication answer, the second voiceprint feature is unsuccessfully matched with the first voiceprint feature, and the server cannot search the first auxiliary voiceprint feature corresponding to the user identifier, the server indicates that the user does not reserve the auxiliary password record of the second language. The server searches a preset problem pool corresponding to the commodity code, extracts a second preset authentication problem different from the first preset authentication problem from the preset problem pool, and can extract randomly or according to a preset authentication problem number. The server sends the extracted second preset authentication question to the terminal, the terminal collects a second answer record of the user to the second preset authentication question, and the second answer record is sent to the terminal.

The server receives a second answer record returned by the terminal, extracts a fourth voiceprint feature from the second answer record, matches the extracted fourth voiceprint feature with the prestored first voiceprint feature, generates a payment refusal notice and returns the notice to the terminal when the fourth voiceprint feature is unsuccessfully matched with the first voiceprint feature, and the terminal displays the user with the failure of identity authentication and the payment refusal notice. When the fourth voiceprint feature is matched with the first voiceprint feature, the server searches a payment account corresponding to the user identifier, reads a payment value from the order data, and deducts a value consistent with the payment value from the payment account, so that the payment of the commodity order is completed.

In one embodiment, the server may recognize the user's password recording by a text-independent voiceprint recognition method, and when the user registers, the terminal may collect the user's registration password recording, input the registration password training recording into the model for training, generate a pre-training voiceprint recognition model, extract a standard voiceprint discrimination vector, and store the standard voiceprint discrimination vector as the first voiceprint feature. The pre-training voiceprint recognition model can adopt a general Gaussian mixture model or a Gaussian mixture model-general background model and the like.

After the user pays and uploads the password record, the server acquires the password record, inputs a pre-training voiceprint recognition model and constructs a single-money voiceprint identification vector as a second voiceprint feature, calculates the vector space distance between the first voiceprint feature and the second voiceprint feature, and judges whether the first voiceprint feature is matched with the second voiceprint feature according to the vector space distance. Specifically, the server calculates a cosine distance between the first voiceprint feature and the second voiceprint feature, obtains a preset distance threshold, compares the calculated cosine distance with the preset distance threshold, judges that the first voiceprint feature is successfully matched with the second voiceprint feature when the cosine distance is smaller than or equal to the preset distance threshold, and judges that the first voiceprint feature is unsuccessfully matched with the second voiceprint feature when the calculated cosine distance is larger than the preset distance threshold.

It should be understood that, although the steps in the flowchart of fig. 2 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 2 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

In one embodiment, as shown in fig. 3, there is provided a payment processing apparatus comprising: a request receiving module 310, an identification obtaining module 320, an answer recording obtaining module 330, a feature searching module 340, an answer recording identifying module 350, and a first payment module 360, wherein:

the request receiving module 310 is configured to receive a payment request sent by a terminal, where the payment request carries order data and password record.

An identification obtaining module 320, configured to obtain a user identification corresponding to a first password in the password records.

The answer record obtaining module 330 is configured to obtain a first preset authentication question, send the first preset authentication question to the terminal, and receive a first answer record corresponding to the first preset authentication question and returned by the terminal.

The feature searching module 340 is configured to extract a first authentication answer corresponding to a first preset authentication question from the order data, and search for a first voiceprint feature corresponding to the user identifier.

The answer recording identification module 350 is configured to identify a second authentication answer from the first answer recording and extract a second voiceprint feature.

The first payment module 360 is configured to, when the second authentication answer is consistent with the first authentication answer and the second voiceprint feature is successfully matched with the first voiceprint feature, search for a payment account corresponding to the user identifier, and deduct a value consistent with the payment value in the order data from the payment account.

In one embodiment, the apparatus further comprises:

and the failure notification module is used for generating an authentication failure notification and sending the authentication failure notification to the terminal when the user identifier corresponding to the first password in the password record is not acquired.

And the searching execution module is used for taking the record retransmitted by the terminal as the password record and continuously and circularly executing the step of acquiring the user identifier corresponding to the first password in the password record after receiving the record retransmitted by the terminal.

And the locking notification module is used for generating a payment locking notification and sending the payment locking notification to the terminal when the number of times of generating the authentication failure notification exceeds a preset authentication number threshold.

In one embodiment, the apparatus further comprises:

and the registration request module is used for receiving a user registration request, and the user registration request carries registration password recording and a payment account.

And the request response module is used for generating a user identifier according to the user registration request.

And the registration confirmation module is used for identifying the second password from the registration password record, generating a registration confirmation instruction carrying the second password and the user identifier, and sending the registration confirmation instruction to the terminal.

And the information adding module is used for extracting a third voiceprint feature from the registration password record after receiving the registration confirmation notification returned by the terminal, taking the second password as a newly-added user password, and performing associated storage on the user identification, the newly-added user password and the third voiceprint feature.

In one embodiment, the apparatus further comprises:

and the refusal payment notification generation module is used for generating a refusal payment notification when the second authentication answer is inconsistent with the first authentication answer.

And the refusal payment notification sending module is used for returning the refusal payment notification to the terminal.

In one embodiment, the apparatus further comprises:

and the auxiliary authentication searching module is used for searching a first auxiliary voiceprint characteristic corresponding to the user identifier and a preset auxiliary authentication problem when the second authentication answer is consistent with the first authentication answer and the second voiceprint characteristic fails to be matched with the first voiceprint characteristic.

The auxiliary characteristic extraction module is used for sending an auxiliary authentication problem to the terminal; and after receiving an auxiliary answer recording corresponding to the auxiliary authentication question returned by the terminal, extracting a second auxiliary voiceprint feature from the auxiliary answer recording.

And the second payment module is used for searching the payment account corresponding to the user identifier and deducting a value consistent with the payment value in the order data from the payment account when the second auxiliary voiceprint feature is successfully matched with the first auxiliary voiceprint feature.

In one embodiment, the apparatus further comprises:

and the second problem sending module is used for acquiring a second preset authentication problem when the first auxiliary voiceprint characteristic corresponding to the user identifier cannot be found, and sending the second preset authentication problem to the terminal.

And the fourth voiceprint extraction module is used for receiving the second answer record returned by the terminal and extracting the fourth voiceprint characteristics from the second answer record.

And the payment refusal notification returning module is used for generating a payment refusal notification and returning the payment refusal notification to the terminal when the fourth voiceprint feature is unsuccessfully matched with the first voiceprint feature.

In one embodiment, the answer recording obtaining module 330 further includes:

and the code acquisition module is used for acquiring the commodity codes from the order data.

And the problem pool searching module is used for searching a preset problem pool corresponding to the commodity code, and the preset problem pool comprises a plurality of preset authentication problems.

And the problem extraction module is used for randomly extracting a first preset authentication problem from the preset problem pool.

For specific limitations of the payment processing apparatus, reference may be made to the above limitations of the payment processing method, which are not described herein again. The various modules in the payment processing apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 4. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing data such as user identification, preset authentication problems, voiceprint characteristics and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a payment processing method.

In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program: receiving a payment request sent by a terminal, wherein the payment request carries order data and password record; acquiring a user identifier corresponding to a first password in the password recording; acquiring a first preset authentication problem, sending the first preset authentication problem to a terminal, and receiving a first answer record corresponding to the first preset authentication problem and returned by the terminal; extracting a first authentication answer corresponding to a first preset authentication problem from order data, and searching a first voiceprint feature corresponding to a user identifier; identifying a second authentication answer from the first answer record and extracting a second voiceprint feature; and when the second authentication answer is consistent with the first authentication answer and the second voiceprint feature is successfully matched with the first voiceprint feature, searching the payment account corresponding to the user identifier, and deducting a value consistent with the payment value in the order data from the payment account.

In one embodiment, the processor, when executing the computer program, further performs the steps of: when the user identification corresponding to the first password in the password recording is not obtained, generating an authentication failure notice and sending the authentication failure notice to the terminal; after receiving the record retransmitted by the terminal, taking the retransmitted record as a password record and continuously and circularly executing the step of acquiring the user identifier corresponding to the first password in the password record; and when the number of times of generating the authentication failure notice exceeds a preset authentication number threshold, generating a payment locking notice and sending the payment locking notice to the terminal.

In one embodiment, the processor, when executing the computer program, further performs the steps of: receiving a user registration request, wherein the user registration request carries registration password recording and a payment account; generating a user identifier according to the user registration request; identifying a second password from the registration password record, generating a registration confirmation instruction carrying the second password and the user identification, and sending the registration confirmation instruction to the terminal; and after receiving a registration confirmation notification returned by the terminal, extracting a third voiceprint feature from the registration password record, taking the second password as a newly-added user password, and performing associated storage on the user identification, the newly-added user password and the third voiceprint feature.

In one embodiment, the processor, when executing the computer program, further performs the steps of: when the second authentication answer is inconsistent with the first authentication answer, generating a payment refusing notice; and returning the payment refusal notice to the terminal.

In one embodiment, the processor, when executing the computer program, further performs the steps of: when the second authentication answer is consistent with the first authentication answer and the second voiceprint feature is unsuccessfully matched with the first voiceprint feature, searching a first auxiliary voiceprint feature and a preset auxiliary authentication question corresponding to the user identifier; sending the auxiliary authentication problem to the terminal; after receiving an auxiliary answer recording corresponding to the auxiliary authentication question returned by the terminal, extracting a second auxiliary voiceprint feature from the auxiliary answer recording; and when the second auxiliary voiceprint characteristic is successfully matched with the first auxiliary voiceprint characteristic, searching a payment account corresponding to the user identification, and deducting a value consistent with the payment value in the order data from the payment account.

In one embodiment, the processor, when executing the computer program, further performs the steps of: when the first auxiliary voiceprint characteristic corresponding to the user identification cannot be found, a second preset authentication problem is obtained, and the second preset authentication problem is sent to the terminal; receiving a second answer record returned by the terminal, and extracting a fourth voiceprint feature from the second answer record; and when the fourth voiceprint feature is failed to be matched with the first voiceprint feature, generating a payment refusing notice and returning the payment refusing notice to the terminal.

In one embodiment, the following steps of obtaining the first predetermined authentication question are further performed when the processor executes the computer program: acquiring a commodity code from the order data; searching a preset problem pool corresponding to the commodity code, wherein the preset problem pool comprises a plurality of preset authentication problems; and randomly extracting a first preset authentication problem from the preset problem pool.

In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: receiving a payment request sent by a terminal, wherein the payment request carries order data and password record; acquiring a user identifier corresponding to a first password in the password recording; acquiring a first preset authentication problem, sending the first preset authentication problem to a terminal, and receiving a first answer record corresponding to the first preset authentication problem and returned by the terminal; extracting a first authentication answer corresponding to a first preset authentication problem from order data, and searching a first voiceprint feature corresponding to a user identifier; identifying a second authentication answer from the first answer record and extracting a second voiceprint feature; and when the second authentication answer is consistent with the first authentication answer and the second voiceprint feature is successfully matched with the first voiceprint feature, searching the payment account corresponding to the user identifier, and deducting a value consistent with the payment value in the order data from the payment account.

In one embodiment, the computer program when executed by the processor further performs the steps of: when the user identification corresponding to the first password in the password recording is not obtained, generating an authentication failure notice and sending the authentication failure notice to the terminal; after receiving the record retransmitted by the terminal, taking the retransmitted record as a password record and continuously and circularly executing the step of acquiring the user identifier corresponding to the first password in the password record; and when the number of times of generating the authentication failure notice exceeds a preset authentication number threshold, generating a payment locking notice and sending the payment locking notice to the terminal.

In one embodiment, the computer program when executed by the processor further performs the steps of: receiving a user registration request, wherein the user registration request carries registration password recording and a payment account; generating a user identifier according to the user registration request; identifying a second password from the registration password record, generating a registration confirmation instruction carrying the second password and the user identification, and sending the registration confirmation instruction to the terminal; and after receiving a registration confirmation notification returned by the terminal, extracting a third voiceprint feature from the registration password record, taking the second password as a newly-added user password, and performing associated storage on the user identification, the newly-added user password and the third voiceprint feature.

In one embodiment, the computer program when executed by the processor further performs the steps of: when the second authentication answer is inconsistent with the first authentication answer, generating a payment refusing notice; and returning the payment refusal notice to the terminal.

In one embodiment, the computer program when executed by the processor further performs the steps of: when the second authentication answer is consistent with the first authentication answer and the second voiceprint feature is unsuccessfully matched with the first voiceprint feature, searching a first auxiliary voiceprint feature and a preset auxiliary authentication question corresponding to the user identifier; sending the auxiliary authentication problem to the terminal; after receiving an auxiliary answer recording corresponding to the auxiliary authentication question returned by the terminal, extracting a second auxiliary voiceprint feature from the auxiliary answer recording; and when the second auxiliary voiceprint characteristic is successfully matched with the first auxiliary voiceprint characteristic, searching a payment account corresponding to the user identification, and deducting a value consistent with the payment value in the order data from the payment account.

In one embodiment, the computer program when executed by the processor further performs the steps of: when the first auxiliary voiceprint characteristic corresponding to the user identification cannot be found, a second preset authentication problem is obtained, and the second preset authentication problem is sent to the terminal; receiving a second answer record returned by the terminal, and extracting a fourth voiceprint feature from the second answer record; and when the fourth voiceprint feature is failed to be matched with the first voiceprint feature, generating a payment refusing notice and returning the payment refusing notice to the terminal.

In one embodiment, the computer program when executed by the processor further performs the following steps of obtaining a first predetermined authentication question: acquiring a commodity code from the order data; searching a preset problem pool corresponding to the commodity code, wherein the preset problem pool comprises a plurality of preset authentication problems; and randomly extracting a first preset authentication problem from the preset problem pool.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (10)

1. A payment processing method, the method comprising:

receiving a payment request sent by a terminal, wherein the payment request carries order data and password record;

acquiring a user identifier corresponding to a first password in the password recording;

acquiring a first preset authentication problem, sending the first preset authentication problem to the terminal, and receiving a first answer record corresponding to the first preset authentication problem and returned by the terminal;

extracting a first authentication answer corresponding to the first preset authentication question from the order data, and searching a first voiceprint feature corresponding to the user identifier;

identifying a second authentication answer from the first answer recording and extracting a second voiceprint feature;

when the second authentication answer is consistent with the first authentication answer and the second voiceprint feature is successfully matched with the first voiceprint feature, searching a payment account corresponding to the user identifier, and deducting a value consistent with a payment value in the order data from the payment account;

when the second authentication answer is consistent with the first authentication answer and the second voiceprint feature is unsuccessfully matched with the first voiceprint feature, searching a first auxiliary voiceprint feature and a preset auxiliary authentication problem corresponding to the user identifier;

sending the auxiliary authentication problem to the terminal; after receiving an auxiliary answer recording corresponding to the auxiliary authentication question returned by the terminal, extracting a second auxiliary voiceprint feature from the auxiliary answer recording;

and when the second auxiliary voiceprint feature is successfully matched with the first auxiliary voiceprint feature, searching a payment account corresponding to the user identifier, and deducting a value consistent with the payment value in the order data from the payment account.

2. The method of claim 1, further comprising:

when the user identification corresponding to the first password in the password record is not obtained, generating an authentication failure notice and sending the authentication failure notice to the terminal;

after receiving the record retransmitted by the terminal, taking the retransmitted record as a password record and continuously and circularly executing the step of acquiring the user identifier corresponding to the first password in the password record;

and when the number of times of generating the authentication failure notice exceeds a preset authentication number threshold, generating a payment locking notice and sending the payment locking notice to the terminal.

3. The method according to claim 1, wherein before the step of receiving the payment request sent by the terminal, further comprising:

receiving a user registration request, wherein the user registration request carries registration password recording and a payment account;

generating a user identifier according to the user registration request;

identifying a second password from the registration password record, generating a registration confirmation instruction carrying the second password and a user identifier, and sending the registration confirmation instruction to the terminal;

and after receiving a registration confirmation notification returned by the terminal, extracting a third voiceprint feature from the registration password record, taking the second password as a new user password, and performing associated storage on the user identification, the new user password and the third voiceprint feature.

4. The method of claim 1, further comprising:

when the second authentication answer is inconsistent with the first authentication answer, generating a payment refusing notice;

and returning the payment refusal notice to the terminal.

5. The method of claim 1, further comprising:

when the first auxiliary voiceprint feature corresponding to the user identification cannot be found, acquiring a second preset authentication problem, and sending the second preset authentication problem to the terminal;

receiving a second answer record returned by the terminal, and extracting a fourth voiceprint feature from the second answer record;

and when the fourth voiceprint feature is unsuccessfully matched with the first voiceprint feature, generating a payment refusing notice and returning the payment refusing notice to the terminal.

6. The method according to any one of claims 1 to 5, wherein the step of obtaining a first preset authentication question comprises:

acquiring a commodity code from the order data;

searching a preset problem pool corresponding to the commodity code, wherein the preset problem pool comprises a plurality of preset authentication problems;

and randomly extracting a first preset authentication problem from the preset problem pool.

7. A payment processing apparatus, the apparatus comprising:

the request receiving module is used for receiving a payment request sent by a terminal, and the payment request carries order data and password record;

the identification acquisition module is used for acquiring a user identification corresponding to a first password in the password records;

the answer record acquisition module is used for acquiring a first preset authentication question, sending the first preset authentication question to the terminal and receiving a first answer record which is returned by the terminal and corresponds to the first preset authentication question;

the characteristic searching module is used for extracting a first authentication answer corresponding to the first preset authentication question from the order data and searching a first voiceprint characteristic corresponding to the user identification;

the answer record identification module is used for identifying a second authentication answer from the first answer record and extracting a second sound print characteristic;

the first payment module is used for searching a payment account corresponding to the user identification when the second authentication answer is consistent with the first authentication answer and the second voiceprint feature is successfully matched with the first voiceprint feature, and deducting a value consistent with a payment value in the order data from the payment account;

the auxiliary authentication searching module is used for searching a first auxiliary voiceprint characteristic and a preset auxiliary authentication problem corresponding to the user identifier when the second authentication answer is consistent with the first authentication answer and the second voiceprint characteristic fails to be matched with the first voiceprint characteristic;

the auxiliary characteristic extraction module is used for sending the auxiliary authentication problem to the terminal; after receiving an auxiliary answer recording corresponding to the auxiliary authentication question returned by the terminal, extracting a second auxiliary voiceprint feature from the auxiliary answer recording;

and the second payment module is used for searching a payment account corresponding to the user identifier and deducting a value consistent with the payment value in the order data from the payment account when the second auxiliary voiceprint feature is successfully matched with the first auxiliary voiceprint feature.

8. The apparatus of claim 7, further comprising:

the second problem sending module is used for acquiring a second preset authentication problem and sending the second preset authentication problem to the terminal when the first auxiliary voiceprint characteristic corresponding to the user identifier cannot be found;

the fourth voiceprint extraction module is used for receiving a second answer record returned by the terminal and extracting a fourth voiceprint feature from the second answer record;

and the payment refusal notification returning module is used for generating a payment refusal notification and returning the payment refusal notification to the terminal when the fourth voiceprint feature is unsuccessfully matched with the first voiceprint feature.

9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 6 are implemented when the computer program is executed by the processor.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.