WO2019153982A1

WO2019153982A1 - Payment processing method and device, computer apparatus, and storage medium

Info

Publication number: WO2019153982A1
Application number: PCT/CN2019/070085
Authority: WO
Inventors: 普璇
Original assignee: 深圳壹账通智能科技有限公司
Priority date: 2018-02-08
Filing date: 2019-01-02
Publication date: 2019-08-15
Also published as: CN108347441B; CN108347441A

Abstract

A payment processing method, comprising: receiving a payment request sent by a terminal, the payment request carrying order data and a password record; acquiring a user identifier corresponding to a first password in the password record; acquiring a first preset authentication question, sending the first preset authentication question to the terminal, and receiving a first answer recording corresponding to the first preset authentication question returned by the terminal; extracting from the order data a first authentication answer corresponding to the first preset authentication question, and searching for a first voiceprint feature corresponding to the user identifier; recognizing a second authentication answer from the first answer recording and extracting a second voiceprint feature; and if the second authentication answer is consistent with the first authentication answer, and the second voiceprint feature successfully matches the first voiceprint feature, searching for a payment account corresponding to the user identifier, and deducting from the payment account a value corresponding to a payment value in the order data.

Description

Payment processing method, device, computer device and storage medium

Cross-reference to related applications

This application claims the priority of the Chinese Patent Application entitled "Payment Processing Method, Apparatus, Computer Equipment, and Storage Media" by the Chinese Patent Office, filed on February 8, 2018, the entire disclosure of which is incorporated by reference. In this application.

Technical field

The present application relates to a payment processing method, apparatus, computer device, and storage medium.

Background technique

With the development of computer technology and various applications with payment functions, the way of making payment is convenient and fast, eliminating the trouble of people taking cash and being accepted and used by more and more people. However, the inventor realized that the current non-current payment method basically relies on other devices, such as bank cards, credit cards, mobile phones, smart wearable devices, etc. to complete the payment, and the payment process is complicated, and usually requires the user to open the device, A series of operations such as unlocking, opening an application, entering a password, etc., the user's payment process is complicated.

Summary of the invention

According to various embodiments disclosed herein, a payment processing method, apparatus, computer device, and storage medium are provided.

A payment processing method comprising:

Receiving a payment request sent by the terminal, where the payment request carries an order data and a password recording;

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

Obtaining a first preset authentication question, sending the first preset authentication question to the terminal, and receiving a first answer recording that is returned by the terminal and corresponding to the first preset authentication question;

Extracting, from the order data, a first authentication answer corresponding to the first preset authentication question, and searching for 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 for a payment account corresponding to the user identifier, from the payment The account number is deducted from the value corresponding to the payment value in the order data.

A payment processing device comprising:

a request receiving module, configured to receive a payment request sent by the terminal, where the payment request carries an order data and a password recording;

An identifier obtaining module, configured to acquire a user identifier corresponding to the first password in the password recording;

The answer recording acquisition module is configured to obtain the first preset authentication question, send the first preset authentication question to the terminal, and receive the first corresponding to the first preset authentication question returned by the terminal Answer recording

a feature search module, configured to extract a first authentication answer corresponding to the first preset authentication question from the order data, and search for a first voiceprint feature corresponding to the user identifier;

An answer recording identification module, configured to identify a second authentication answer from the first answer recording and extract a second voiceprint feature; and

a first payment module, configured to: when the second authentication answer is consistent with the first authentication answer, and the second voiceprint feature matches the first voiceprint feature, searching for the user identifier The payment account is deducted from the payment account with a value consistent with the payment value in the order data.

A computer device comprising a memory and one or more processors having stored therein computer readable instructions, the computer readable instructions being executable by the processor to cause the one or more processors to execute The following steps:

One or more non-transitory computer readable storage mediums storing computer readable instructions, when executed by one or more processors, cause one or more processors to perform the steps of:

Details of one or more embodiments of the present application are set forth in the accompanying drawings and description below. Other features and advantages of the present invention will be apparent from the description, drawings and claims.

DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings to be used in the embodiments will be briefly described below. Obviously, the drawings in the following description are only some embodiments of the present application, Those skilled in the art can also obtain other drawings based on these drawings without any creative work.

1 is an application scenario diagram of a payment processing method according to one or more embodiments;

2 is a schematic flow chart of a payment processing method according to one or more embodiments;

3 is a structural block diagram of a payment processing apparatus in accordance with one or more embodiments;

4 is a diagram showing the internal structure of a computer device in accordance with one or more embodiments.

Detailed ways

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

The payment processing method provided by the present application can be applied to an application environment as shown in FIG. 1. The terminal communicates with the server through the network through the network. When the payment is made, the terminal sends a payment request carrying the payment order data and the user's password recording to the server, and after receiving the payment request sent by the terminal, the server obtains the password recording and searches for the user corresponding to the first password in the password recording. The identifier is obtained by the server, and the first preset authentication problem corresponding to the user identifier is sent to the terminal, and the terminal collects the first answer recording corresponding to the first preset authentication question by the user, and collects the first An answer recording is sent to the server, and the server extracts the first authentication answer corresponding to the first preset authentication question from the order data, and searches for the first voiceprint feature corresponding to the user identifier, and the server identifies the first answer from the received first answer recording. Second, the authentication answer and extract the second voiceprint feature from the first answer recording. The server compares the second authentication answer with the first authentication answer, and matches the second voiceprint feature with the first voiceprint feature, when the second authentication answer is consistent with the first authentication answer, and the second voiceprint feature is When the first voiceprint feature is successfully matched, the payment account corresponding to the user identifier is searched, and the value corresponding to the payment value in the order data is deducted from the payment account, thereby completing the payment of the order. The terminal can be, but is not limited to, various personal computers, notebook computers, smart phones, tablets, and portable wearable devices. The server can be implemented by a separate server or a server cluster composed of multiple servers.

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

Step 210: Receive a payment request sent by the terminal, where the payment request carries the order data and the password recording.

The payment processing method in this embodiment can be applied to a plurality of payment scenarios, and the user can make an order by using a mobile phone, a computer, or the like, which is used by the user, and the user can also purchase the product online at the store, and the clerk uses the order after the store terminal orders. Make a payment.

After the payment is generated to generate the commodity order, the terminal may issue a reminder to the user to read the pre-stored payment password, and the terminal may remind the user or the clerk by text or voice. The pre-stored payment password is set when the user registers in advance. After receiving the reminder, the user reads the pre-stored payment password set by the user, and the terminal collects the recording of the pre-stored payment password read by the user through a device such as a microphone, and the terminal records the collected password read by the user together with the order data of the product purchased by the user. Sent to the server.

The pre-stored payment password may be a mobile phone number selected by the user, an ID number, or a string of random numbers set in advance, a piece of text, etc., and the pre-stored payment password may also be in other forms. The order data sent by the terminal to the server may include information of the purchased product, such as an item code, and may also include data such as a payment value, an order number, an order generation time, and user information.

Step 220: Acquire a user identifier corresponding to the first password in the password recording.

After receiving the payment request sent by the terminal, the server acquires the order data and the password recording in the payment request. The server identifies the first password from the password recording, and obtains a user information table, and searches the user information table for whether there is a pre-stored payment password matching the first password, and when the pre-stored payment password matching the first password is found, , indicating that the user is a registered user, and the server searches the user information table for the user identifier corresponding to the matching pre-stored payment password.

The server pre-stores the user information of all registered users in the user information table, and stores information such as the user identifier, the pre-stored payment password, and the user's payment account in the user information table. The user identifier is used to uniquely identify the user identity.

Step 230: Acquire a first preset authentication question, send the first preset authentication question to the terminal, and receive a first answer recording corresponding to the first preset authentication question returned by the terminal.

The server obtains the first preset authentication question. Specifically, the first preset authentication question is related to the item purchased by the user, and the first preset authentication question may be set according to data included in the item order. Taking the commodity as an insurance product as an example, the first default authentication question may be: what is the name of the insured, what is the name of the insured, how long the insured product is valid, and so on. The number of the first preset authentication questions corresponding to the same item may be plural. The server can read the commodity code from the order data, find the first preset authentication problem corresponding to the commodity code, and send the found preset authentication problem to the terminal.

After receiving the first preset authentication question sent by the server, the terminal presents the first preset authentication question to the user. The terminal may display the first preset authentication question in the form of a text on the terminal interface, and prompt the user to answer the question, and the terminal may play the first preset authentication question to the user by using a voice prompt. After receiving the problem prompt, the user needs to answer the first preset authentication question by voice. The terminal can collect the first answer recording of the user's answer through a device such as a microphone, and the terminal returns the collected first answer of the user to the server. The server receives the first answer recording returned by the terminal.

Step 240: Extract a first authentication answer corresponding to the first preset authentication question from the order data, and find a first voiceprint feature corresponding to the user identifier.

After obtaining the first preset authentication question, the server extracts, from the order data, a first authentication answer corresponding to the obtained first preset authentication question.

Specifically, each of the first preset authentication questions has its corresponding key field, for example, the keyword segment of “what is the name of the insured person” is the “name of the insured person”, and the keyword of the “insurance period of the insured product” The paragraph is “insurance validity period”. 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" from the order data according to the "insured name field" as the first authentication answer.

The server searches for the first voiceprint feature corresponding to the user identifier, and when the user registers the voice payment function, the user needs to provide the recording of the pre-stored payment password, and the server extracts the first voiceprint feature of the user from the recording of the pre-stored payment password, and The extracted first voiceprint feature is stored in association with the user identity.

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

After receiving the first answer recording, the server recognizes the textual meaning content of the recording, that is, the second authentication answer, from the first answer recording, and extracts the voiceprint feature from the first answer recording to extract the second voiceprint. feature.

Step 260: When the second authentication answer is consistent with the first authentication answer, and the second voiceprint feature and the first voiceprint feature are successfully matched, the payment account corresponding to the user identifier is searched, and the payment value in the order data is deducted from the payment account. Consistent values.

The server compares the second authentication answer answered by the user with the first authentication answer extracted from the order data to determine whether the two are consistent. The server matches the second voiceprint feature with the pre-stored first voiceprint feature to determine whether the two can be successfully matched. After the server determines that the second authentication answer is consistent with the first authentication answer, and determines that the second voiceprint feature and the second voiceprint feature are successfully matched, the server successfully authenticates the user, and may perform a payment operation. The server searches for the payment account corresponding to the user identifier from the user information table, and extracts the payment value of the order from the order data. The server deducts the value corresponding to the payment value from the user's payment account, and completes the payment operation. Among them, the payment account is reserved in advance by the user. The payment account can be a user's bank card account, Alipay account, WeChat account, and other financial accounts that can be paid.

In this embodiment, when the user pays for the product order, only the password recording is read and the default authentication question is answered, and the server successfully checks the password content in the password recording, and the answer content of the answer to the user answer is recorded. After the user voiceprint feature verification is successful, the corresponding value can be deducted from the user's payment account, and the payment operation is completed, and the user does not need to perform other operation processes. The payment process is convenient and fast, and the user's payment operation experience can be improved. In addition, by requiring the user to answer the first preset authentication question, the user's answer recording is subjected to secondary matching authentication, and the double verification can improve the security of the voice payment.

In one embodiment, the step of acquiring the first preset authentication question includes: obtaining an item code from the order data; searching for a preset problem pool corresponding to the item code, where the preset problem pool includes a plurality of preset authentication questions; The first preset authentication problem is randomly extracted from the preset problem pool.

The server reads the item code from the order data, and the item code is used to uniquely identify the item purchased by the user. Each item or each type of item has a preset problem pool corresponding thereto, and the preset question pool includes a plurality of preset authentication questions, and the preset problem pool is associated and stored with the commodity code of the corresponding item. The server randomly extracts a preset authentication question from the preset problem pool as the first preset authentication question, thereby ensuring that the preset authentication problem extracted by each payment is random and unpredictable.

In other embodiments, the server may also encode multiple preset authentication questions in the preset problem pool. Each time the first preset authentication problem is obtained, one pre-emptive extraction is performed from the preset problem pool according to the coding sequence. Set certification issues.

Since the user pre-stored payment password is fixed, if the user's identity is authenticated only by the pre-stored payment password, it is likely that someone else will record and copy the user's read-aloud payment password, and copy the recording to impersonate the user's identity for payment. . In this embodiment, after the user successfully authenticates the password, the user also needs to answer the randomly extracted authentication question. Since the authentication problem is randomly selected, others cannot steal the payment by copying the recording, thereby greatly improving the voice payment. Security.

In one embodiment, the method further includes: when the user identifier corresponding to the first password in the password recording is not acquired, generating an authentication failure notification and transmitting the notification to the terminal; after receiving the recording resent by the terminal, Recording the resent recording as a password and continuing to loop to perform the step of acquiring the user identifier corresponding to the first password in the password recording; when the number of times the authentication failure notification is generated exceeds the preset authentication number threshold, a payment lock notification is generated and sent to terminal.

When the server recognizes the first password from the password recording, and does not find the pre-stored payment password corresponding to the first password from the user information table, and fails to acquire the user identifier with the first password, the server generates an authentication failure notification and authenticates A failure notification is sent to the terminal. Since the user's reading password is easily affected by ambient noise, a semantic recognition error may occur. After receiving the authentication failure notification, the terminal may prompt the user to re-read the password recording prompt, and the terminal collects the recording re-read by the user through a sound collection device such as a microphone, and retransmits the collected recording to the server. After receiving the re-sent recording of the terminal, the server records the received recording as a password, and continues to loop the step of acquiring the user identifier corresponding to the first password in the password recording, that is, the server cyclically executes the first identification from the password recording. The password is a step of searching from the user information table for whether there is a pre-stored payment password matching the first password, and then searching for the user identifier corresponding to the matching pre-stored payment password from the user information table. When the server cannot find the pre-stored payment password matching the first password and cannot obtain the user identifier corresponding to the first password in the password recording, the authentication failure notification is continuously generated and sent to the terminal.

The server records the number of times the authentication failure notification is sent to the terminal, and the server finds the pre-stored authentication number threshold. When the number of times the server records the number of times exceeds the preset number of authentication times, the server generates a payment lock notification and sends a payment lock notification to the server. terminal. The server performs a payment lock record for the user. In one of the embodiments, the server can set the payment lockout time and release the payment lock for the user when the payment lockout time is reached. During the payment lockout period, the user cannot perform any payment operation by voice payment. After the payment lock is released, the voice payment operation can be continued.

After receiving the payment lock notification, the terminal presents the user with a payment lock notification prompt, in which the time of the payment lock can be declared. For example, the terminal can display a payment lock notification such as "Payment password authentication failure, voice payment function is locked within 3 hours" by text or voice.

In this embodiment, after failing to authenticate the payment password recording for the user for the first time, the server sends an authentication failure notification to the terminal, and allows the user to continue uploading the re-reading recording until the number of authentication failures exceeds a preset value. A notification of the payment lock is issued again, thereby avoiding the influence of environmental sound interference on the voice authentication process.

In one of the embodiments, within the preset number of authentication thresholds, when the server extracts the first password from the received resent recording and can find the user identifier corresponding to the first password, the server reads the user The payment password authentication is successful, and the server continues to perform the step of obtaining the first preset authentication question.

In one embodiment, before receiving the payment request sent by the terminal, the method further includes: receiving a user registration request, the user registration request carrying the registration password recording and the payment account; generating the user identifier according to the user registration request; Identifying the second password, generating a registration confirmation command carrying the second password and the user identifier, and transmitting the registration confirmation command to the terminal; and receiving the registration confirmation notification returned by the terminal, extracting the third voiceprint feature from the registration password recording, The second password is used as a new user password, and the user identifier, the newly added user password, and the third voiceprint feature are associated and stored.

The user needs to register the user identity information before using the voice payment function. When registering identity information, the user can record the registration password through the terminal and enter the payment account used for payment. After the user completes the above operation and confirms, the terminal generates a user registration request according to the collected registration password and the payment account, and sends the user registration request to the server. After receiving the user registration request, the server generates a unique user identifier. The user identifier can be in the form of a user number. The server can generate a user identifier according to the user number of the last registered user, or generate a user identifier by other methods.

The server obtains the registration password recording and payment account from the user registration request. The server recognizes the recorded content, that is, the second password, from the registered password recording according to the semantic recognition method of the voice. The "second" here is for the "first" in the first password used in the payment in the above embodiment. The distinction does not have other special meanings. The server generates a registration confirmation command according to the generated user identifier and the identified second password, and sends a registration confirmation command to the terminal. After receiving the registration confirmation command, the terminal reads the user identifier and the second password and presents the user, and shows the user whether the second password is used as a prompt for the payment password. After the user confirms the second password through the terminal, the terminal generates a registration confirmation notification and returns it to the server.

After receiving the registration confirmation notification returned by the terminal, the server extracts the third voiceprint feature from the registration password recording, and stores the user identifier, the second password, the payment account, and the third voiceprint feature in association, and stores the information as new user information. In one of these embodiments, the server may add the above information of the registered user to the user information table.

In this embodiment, the user only needs to register the password by voice and provide a payment account to complete the registration of the voice payment function, which is convenient and quick.

In one embodiment, the method further comprises: generating a chargeback notification when the second authentication answer is inconsistent with the first authentication answer; returning the chargeback notification to the terminal.

After the server compares the second authentication answer with the first authentication answer, and determines that the second authentication answer is inconsistent with the first authentication answer, the user identity seriously fails and directly generates whether the second voiceprint feature matches the first voiceprint feature. The chargeback notice returns the chargeback notice to the terminal, and the terminal displays the chargeback prompt to the user after receiving the notice.

In this embodiment, when the content of the answer answered by the user is incorrect, a chargeback notification is directly generated to prevent the user from stealing the copy recording for payment.

In one embodiment, the method may further include the steps of: when the second authentication answer is consistent with the first authentication answer, and the second voiceprint feature fails to match the first voiceprint feature, searching for the corresponding number of the user identifier An auxiliary voiceprint feature and a preset auxiliary authentication problem; the auxiliary authentication problem is sent to the terminal; and after receiving the auxiliary answer recording corresponding to the auxiliary authentication problem returned by the terminal, the second auxiliary voiceprint feature is extracted from the auxiliary answer recording; When the second auxiliary voiceprint feature is successfully matched with the first auxiliary voiceprint feature, the payment account corresponding to the user identifier is searched, and the value corresponding to the payment value in the order data is deducted from the payment account.

When the server determines that the answer content of the user's answer is consistent with the authentication answer extracted from the order, but the second voiceprint feature fails to match the first voiceprint feature, the voiceprint feature is related to the state of the person's breath, pronunciation, etc., the user It may happen that the occasional pronunciation changes cause the recorded voiceprint to fail to match the pre-stored voiceprint. In order to avoid the above situation, the server initiates the auxiliary authentication process of the user identity.

The server searches for the first auxiliary voiceprint feature corresponding to the user identifier. When the first auxiliary voiceprint is searched, the preset auxiliary authentication problem is obtained, and the secondary authentication problem is sent to the terminal to enable the user to answer. Many users, besides their native language, are also proficient in using a second language, such as a foreign language, a dialect, etc., when the user registers, uploads a recording in the second language to the server, and the server receives the second language recording from the second. The corresponding voiceprint feature is extracted from the language recording to assist the voiceprint feature, and the auxiliary voiceprint feature is associated with the user identifier for storage. Take Chinese users as an example. Putting Putonghua as the standard language used for all users to register, in addition to uploading standard payment passwords for Mandarin, users can also choose a second language such as English and French according to their own language ability. Cantonese as a supplementary payment password.

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

After receiving the auxiliary authentication problem, the terminal prompts the user to answer the auxiliary authentication question in the second language, collects the auxiliary answer recording answered by the user, returns the auxiliary answer recording to the server, and the server extracts the second auxiliary after receiving the auxiliary answer recording. a voiceprint feature, and matching the second auxiliary voiceprint feature with the pre-stored first auxiliary voiceprint feature. When the second auxiliary voiceprint feature and the first auxiliary voiceprint feature are successfully matched, the server searches for a payment account corresponding to the user identifier. And the payment value is read from the order data, and the value corresponding to the payment value is deducted from the payment account, thereby completing the payment of the commodity order. When the matching of the second auxiliary voiceprint feature and the first auxiliary voiceprint feature fails, the server generates a chargeback notification and returns to the terminal, and the terminal performs identity authentication failure and the display of the chargeback notification.

In this embodiment, by using the auxiliary voiceprint feature such as the second language, the dialect, and the like to authenticate the user identity, the secondary authentication may be performed when the second voiceprint feature fails to match the first voiceprint feature due to the user's unclear pronunciation. Thereby reducing the probability of identity authentication errors, improving the accuracy of identity authentication, and improving the user experience.

In one embodiment, the method may further include: when the first auxiliary voiceprint feature corresponding to the user identifier is not found, acquiring the second preset authentication problem, and sending the second preset authentication problem to the terminal; The second answer recording returned by the terminal extracts the fourth voiceprint feature from the second answer recording; when the fourth voiceprint feature fails to match the first voiceprint feature, a chargeback notification is generated and the chargeback notification is returned to the terminal.

When the server determines that the second authentication answer is consistent with the first authentication answer, the second voiceprint feature fails to match the first voiceprint feature, and the server does not find the first auxiliary voiceprint feature corresponding to the user identifier, indicating that the user There is no reserved secondary voice recording for the second language. The server searches for a preset problem pool corresponding to the commodity code, and extracts a second preset authentication problem different from the first preset authentication problem from the preset problem pool, and the server may randomly extract or may be based on the preset authentication question number. Take the extraction. The server sends the second preset authentication question to the terminal, and the terminal collects the second answer recording of the second preset authentication question by the user, and sends the second answer recording to the terminal.

The server receives the second answer recording returned by the terminal, and extracts the fourth voiceprint feature from the second answer recording, and the server matches the extracted fourth voiceprint feature with the pre-stored first voiceprint feature, and the fourth sound When the matching of the texture feature and the first voiceprint feature fails, the server generates a chargeback notification and returns it to the terminal, and the terminal performs identity authentication failure and the display of the chargeback notification. When the fourth voiceprint feature matches the first voiceprint feature, the server searches for the payment account corresponding to the user identifier, and reads the payment value from the order data, and deducts the value corresponding to the payment value from the payment account, thereby completing the product. Payment for the order.

In one embodiment, the server may identify the user's password recording by using a text-independent voiceprint recognition method. When the user performs user registration, the terminal may collect the user's registration password recording, and input the registration password training recording into the model for training. A pre-trained voiceprint recognition model is generated, and a standard voiceprint discrimination vector is extracted, and the standard voiceprint discrimination vector is stored as the first voiceprint feature. Among them, the pre-training voiceprint recognition model can adopt a general Gaussian mixture model or a Gaussian mixture model-general background model.

After the user performs the payment upload password recording, the server obtains the password recording, inputs the pre-trained voiceprint recognition model and constructs the single money voiceprint discrimination vector as the second voiceprint feature, and calculates the vector of the first voiceprint feature and the second voiceprint feature. The spatial distance determines whether the first voiceprint feature matches 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, and obtains a preset distance threshold. When the calculated cosine distance is compared with a preset distance threshold, when the cosine distance is less than or equal to the pre-predetermined When the distance threshold is set, it is determined that the first voiceprint feature and the second voiceprint feature are successfully matched. When the cosine distance is greater than the preset distance threshold, it is determined that the first voiceprint feature and the second voiceprint feature fail to match.

It should be understood that although the various steps in the flowchart of FIG. 2 are sequentially displayed as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Except as explicitly stated herein, the execution of these steps is not strictly limited, and the steps may be performed in other orders. Moreover, at least some of the steps in FIG. 2 may include a plurality of sub-steps or stages, which are not necessarily performed at the same time, but may be executed at different times, the execution of these sub-steps or stages The order is also not necessarily sequential, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of the other steps.

In one embodiment, as shown in FIG. 3, a payment processing apparatus is provided, including: a request receiving module 310, an identifier obtaining module 320, an answer recording obtaining module 330, a feature finding module 340, an answer recording identifying module 350, and The first payment module 360, wherein:

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

The identifier obtaining module 320 is configured to acquire a user identifier corresponding to the first password in the password recording.

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

The feature search module 340 is configured to extract a first authentication answer corresponding to the 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 the second authentication answer from the first answer recording and extract the 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, look up the payment account corresponding to the user identifier, and deduct from the payment account. The value in the order data is the same as the value paid.

In one embodiment, the apparatus further includes:

The failure notification module is configured to generate an authentication failure notification and send the notification to the terminal when the user identifier corresponding to the first password in the password recording is not acquired.

The search execution module is configured to, after receiving the re-sent of the terminal, record the re-transmitted recording as a password and continue to loop to perform the step of acquiring the user identifier corresponding to the first password in the password recording.

The lock notification module is configured to generate a payment lock notification and send the notification to the terminal when the number of times the authentication failure notification is generated exceeds the preset authentication number threshold.

In one embodiment, the apparatus further includes:

The registration request module is configured to receive a user registration request, and the user registration request carries a registration password recording and a payment account.

A request response module is configured to generate a user identifier according to a user registration request.

The registration confirmation module is configured to identify the second password from the registration password recording, generate a registration confirmation instruction carrying the second password and the user identifier, and send the registration confirmation instruction to the terminal.

The information adding module is configured to: after receiving the registration confirmation notification returned by the terminal, extract the third voiceprint feature from the registration password recording, use the second password as the new user password, and add the user identifier, the newly added user password, and the third The voiceprint features are stored in association.

In one embodiment, the apparatus further includes:

The chargeback notification generating module is configured to generate a chargeback notice when the second authentication answer is inconsistent with the first authentication answer.

The chargeback notification sending module is configured to return the chargeback notice to the terminal.

In one embodiment, the apparatus further includes:

The auxiliary authentication search module is configured to: when the second authentication answer is consistent with the first authentication answer, and the second voiceprint feature fails to match the first voiceprint feature, the first auxiliary voiceprint feature corresponding to the user identifier and the preset assistance are searched for Certification issue.

The auxiliary feature extraction module is configured to send the auxiliary authentication problem to the terminal; and after receiving the auxiliary answer recording corresponding to the auxiliary authentication problem returned by the terminal, extracting the second auxiliary voiceprint feature from the auxiliary answer recording.

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

In one embodiment, the apparatus further includes:

The second problem sending module is configured to obtain a second preset authentication problem when the first auxiliary voiceprint feature corresponding to the user identifier is not found, and send the second preset authentication problem to the terminal.

The fourth voiceprint extraction module is configured to receive a second answer recording returned by the terminal, and extract a fourth voiceprint feature from the second answer recording.

The chargeback notification returning module is configured to generate a chargeback notice and return the chargeback notice to the terminal when the fourth voiceprint feature fails to match the first voiceprint feature.

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

A code acquisition module for obtaining an item code from the order data.

The problem pool search module is configured to find a preset problem pool corresponding to the commodity code, and the preset problem pool includes multiple preset authentication questions.

The problem extraction module is configured to randomly extract the first preset authentication problem from the preset problem pool.

For the specific definition of the payment processing device, reference may be made to the above definition of the payment processing method, and details are not described herein again. Each of the above-described payment processing devices may be implemented in whole or in part by software, hardware, and combinations thereof. Each of the above modules may be embedded in or independent of the processor in the computer device, or may be stored in a memory in the computer device in a software form, so that the processor invokes the operations corresponding to the above modules.

In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in FIG. The computer device includes a processor, memory, network interface, and database connected by a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium, an internal memory. The non-volatile storage medium stores an operating system, computer readable instructions, and a database. The internal memory provides an environment for operation of an operating system and computer readable instructions in a non-volatile storage medium. The database of the computer device is used to store data such as user identification, preset authentication questions, voiceprint features, and the like. The network interface of the computer device is used to communicate with an external terminal via a network connection. The computer readable instructions are executed by a processor to implement a payment processing method.

A computer device comprising a memory and one or more processors, the memory storing computer readable instructions, the computer readable instructions being executed by the processor, causing the one or more processors to perform the step of: receiving a payment sent by the terminal The request, the payment request carries the order data and the password recording; obtains the user identifier corresponding to the first password in the password recording; acquires the first preset authentication question, sends the first preset authentication question to the terminal, and receives the return from the terminal a first answer recording corresponding to the first preset authentication question; extracting a first authentication answer corresponding to the first preset authentication question from the order data, and finding a first voiceprint feature corresponding to the user identifier; from the first answer Identifying the second authentication answer in the recording and extracting the 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 for the corresponding user identifier The payment account is deducted from the payment account with a value consistent with the payment value in the order data.

In one embodiment, when the processor executes the computer readable instructions, the following steps are further implemented: when the user identifier corresponding to the first password in the password recording is not acquired, an authentication failure notification is generated and sent to the terminal; when received After the re-sent recording of the terminal, recording the re-transmitted recording as a password and continuing to loop to perform the step of acquiring the user identifier corresponding to the first password in the password recording; when the number of times the authentication failure notification is generated exceeds the preset authentication number threshold, A payment lock notification is generated and sent to the terminal.

In one embodiment, the processor further implements the following steps: receiving a user registration request, carrying a registration password recording and a payment account in the user registration request; generating a user identifier according to the user registration request; and recording from the registration password Identifying the second password, generating a registration confirmation command carrying the second password and the user identifier, and transmitting the registration confirmation command to the terminal; and receiving the registration confirmation notification returned by the terminal, extracting the third voiceprint feature from the registration password recording, The second password is used as a new user password, and the user identifier, the newly added user password, and the third voiceprint feature are associated and stored.

In one of the embodiments, the processor, when executing the computer readable instructions, further implements the step of generating a chargeback notification when the second authentication answer is inconsistent with the first authentication answer; returning the chargeback notification to the terminal.

In one embodiment, the processor, when executing the computer readable instructions, further implements the step of: locating the user when the second authentication answer is consistent with the first authentication answer and the second voiceprint feature fails to match the first voiceprint feature Identifying the corresponding first auxiliary voiceprint feature and the preset auxiliary authentication problem; sending the auxiliary authentication problem to the terminal; and receiving the secondary answer recording corresponding to the auxiliary authentication problem returned by the terminal, extracting the second auxiliary sound from the auxiliary answer recording When the second auxiliary voiceprint feature is successfully matched with the first auxiliary voiceprint feature, the payment account corresponding to the user identifier is searched, and the value corresponding to the payment value in the order data is deducted from the payment account.

In one embodiment, when the processor executes the computer readable instructions, the following steps are further implemented: when the first auxiliary voiceprint feature corresponding to the user identifier is not found, the second preset authentication problem is obtained, and the second preset authentication is obtained. The problem is sent to the terminal; the second answer recording returned by the receiving terminal is used to extract the fourth voiceprint feature from the second answer recording; when the fourth voiceprint feature fails to match the first voiceprint feature, a chargeback notification is generated and rejected The payment notice is returned to the terminal.

In one embodiment, when the processor executes the computer readable instructions, the following steps of obtaining the first preset authentication question are further used to: obtain the commodity code from the order data; and find a preset problem pool corresponding to the commodity code, The problem pool includes multiple preset authentication questions; the first preset authentication problem is randomly extracted from the preset problem pool.

One or more non-transitory computer readable storage mediums storing computer readable instructions, when executed by one or more processors, cause one or more processors to perform the steps of: receiving by a terminal The payment request carries the order data and the password recording; the user identifier corresponding to the first password in the password recording is obtained; the first preset authentication problem is obtained, the first preset authentication problem is sent to the terminal, and the receiving terminal returns a first answer recording corresponding to the first preset authentication question; extracting a first authentication answer corresponding to the first preset authentication question from the order data, and finding a first voiceprint feature corresponding to the user identifier; The second authentication answer is identified in the answer recording and the second voiceprint feature is extracted; when the second authentication answer is consistent with the first authentication answer, and the second voiceprint feature and the first voiceprint feature are successfully matched, the search user identifier is correspondingly The payment account is deducted from the payment account with a value consistent with the payment value in the order data.

In one of the embodiments, when the computer readable instructions are executed by the processor, the step of: generating an authentication failure notification and transmitting to the terminal when the user identification corresponding to the first password in the password recording is not acquired; After the recording is resent to the terminal, the re-transmitted recording is recorded as a password and the looping process is performed to obtain the user identifier corresponding to the first password in the password recording; when the number of times the authentication failure notification is generated exceeds the preset authentication number threshold , generate a payment lock notification and send it to the terminal.

In one embodiment, the computer readable instructions are further executed by the processor to: receive a user registration request, the user registration request carries a registration password recording and a payment account; generate a user identification according to the user registration request; and record from the registration password Identifying the second password, generating a registration confirmation command carrying the second password and the user identifier, and transmitting the registration confirmation command to the terminal; and receiving the registration confirmation notification returned by the terminal, extracting the third voiceprint feature from the registration password recording The second password is used as a new user password, and the user identifier, the newly added user password, and the third voiceprint feature are associated and stored.

In one of the embodiments, the computer readable instructions are further executed by the processor to: when the second authentication answer is inconsistent with the first authentication answer, generate a chargeback notification; return the chargeback notification to the terminal.

In one of the embodiments, the computer readable instructions are further executed by the processor to: when the second authentication answer is consistent with the first authentication answer, and the second voiceprint feature fails to match the first voiceprint feature, The first auxiliary voiceprint feature corresponding to the user identifier and the preset auxiliary authentication problem; the auxiliary authentication problem is sent to the terminal; and after receiving the auxiliary answer recording corresponding to the auxiliary authentication problem returned by the terminal, the second auxiliary is extracted from the auxiliary answer recording The voiceprint feature; when the second auxiliary voiceprint feature is successfully matched with the first auxiliary voiceprint feature, the payment account corresponding to the user identifier is searched, and the value corresponding to the payment value in the order data is deducted from the payment account.

In one embodiment, when the computer readable instructions are executed by the processor, the following steps are further implemented: when the first auxiliary voiceprint feature corresponding to the user identifier is not found, the second preset authentication problem is obtained, and the second preset is obtained. The authentication problem is sent to the terminal; the second answer recording returned by the receiving terminal is used to extract the fourth voiceprint feature from the second answer recording; when the fourth voiceprint feature fails to match the first voiceprint feature, a chargeback notification is generated and The chargeback notice is returned to the terminal.

In one embodiment, when the computer readable instructions are executed by the processor to implement the following steps of obtaining the first preset authentication question, the method further comprises: obtaining an item code from the order data; and searching for a preset problem pool corresponding to the item code, The preset question pool includes multiple preset authentication questions; the first preset authentication question is randomly extracted from the preset question pool.

One of ordinary skill in the art can understand that all or part of the process of implementing the above embodiments can be completed by computer readable instructions, which can be stored in a non-volatile computer. The readable storage medium, which when executed, may include the flow of an embodiment of the methods as described above. Any reference to a memory, storage, database or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. 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 formats, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronization chain. Synchlink DRAM (SLDRAM), Memory Bus (Rambus) Direct RAM (RDRAM), Direct Memory Bus Dynamic RAM (DRDRAM), and Memory Bus Dynamic RAM (RDRAM).

The technical features of the above embodiments may be arbitrarily combined. For the sake of brevity of description, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, It is considered to be the range described in this specification.

The above-mentioned embodiments are merely illustrative of several embodiments of the present application, and the description thereof is more specific and detailed, but is not to be construed as limiting the scope of the invention. It should be noted that a number of variations and modifications may be made by those skilled in the art without departing from the spirit and scope of the present application. Therefore, the scope of the invention should be determined by the appended claims.

Claims

A payment processing method comprising:

Receiving a payment request sent by the terminal, where the payment request carries an order data and a password recording;

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

Obtaining a first preset authentication question, sending the first preset authentication question to the terminal, and receiving a first answer recording that is returned by the terminal and corresponding to the first preset authentication question;

Extracting, from the order data, a first authentication answer corresponding to the first preset authentication question, and searching for 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 for a payment account corresponding to the user identifier, from the payment The account number is deducted from the value corresponding to the payment value in the order data.
The method of claim 1 further comprising:

When the user identifier corresponding to the first password in the password recording is not obtained, an authentication failure notification is generated and sent to the terminal;

After receiving the retransmission of the recording by the terminal, recording the retransmitted recording as a password and continuing to loop to perform the step of acquiring a user identifier corresponding to the first password in the password recording; and

When the number of times the authentication failure notification is generated exceeds the preset authentication number threshold, a payment lock notification is generated and sent to the terminal.
The method according to claim 1, wherein before the step of receiving the payment request sent by the terminal, the method further comprises:

Receiving a user registration request, where the user registration request carries a 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 command carrying the second password and the user identifier, and transmitting the registration confirmation command to the terminal; and

After receiving the registration confirmation notification returned by the terminal, extracting a third voiceprint feature from the registration password recording, using the second password as a new user password, and adding the user identifier to the new user The password and the third voiceprint feature are stored in association.
The method of claim 1 further comprising:

Generating a chargeback notification when the second authentication answer is inconsistent with the first authentication answer; and

Returning the chargeback notification to the terminal.
The method of claim 1 further comprising:

When the second authentication answer is consistent with the first authentication answer, and the second voiceprint feature fails to match the first voiceprint feature, searching for the first auxiliary voiceprint feature corresponding to the user identifier and Preset auxiliary authentication issues;

Sending the auxiliary authentication question to the terminal; and receiving the auxiliary answer recording corresponding to the auxiliary authentication question returned by the terminal, extracting the second auxiliary voiceprint feature from the auxiliary answer recording;

When the second auxiliary voiceprint feature is successfully matched with the first auxiliary voiceprint feature, searching for 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. .
The method of claim 5, wherein the method further comprises:

When the first auxiliary voiceprint feature corresponding to the user identifier is not found, obtaining a second preset authentication problem, and sending the second preset authentication problem to the terminal;

Receiving a second answer recording returned by the terminal, and extracting a fourth voiceprint feature from the second answer recording; and

When the fourth voiceprint feature fails to match the first voiceprint feature, a chargeback notification is generated and the chargeback notification is returned to the terminal.
The method according to any one of claims 1 to 6, wherein the step of acquiring the first preset authentication question comprises:

Obtaining an item code from the order data;

Searching for a preset problem pool corresponding to the commodity code, where the preset problem pool includes multiple preset authentication issues; and

The first preset authentication problem is randomly extracted from the preset problem pool.
A payment processing device comprising:

a request receiving module, configured to receive a payment request sent by the terminal, where the payment request carries an order data and a password recording;

An identifier obtaining module, configured to acquire a user identifier corresponding to the first password in the password recording;

The answer recording acquisition module is configured to obtain the first preset authentication question, send the first preset authentication question to the terminal, and receive the first corresponding to the first preset authentication question returned by the terminal Answer recording

a feature search module, configured to extract a first authentication answer corresponding to the first preset authentication question from the order data, and search for a first voiceprint feature corresponding to the user identifier;

An answer recording identification module, configured to identify a second authentication answer from the first answer recording and extract a second voiceprint feature;

a first payment module, configured to: when the second authentication answer is consistent with the first authentication answer, and the second voiceprint feature matches the first voiceprint feature, searching for the user identifier The payment account is deducted from the payment account with a value consistent with the payment value in the order data.
The device according to claim 8, further comprising:

a failure notification module, configured to generate an authentication failure notification and send the notification to the terminal when the user identifier corresponding to the first password in the password recording is not obtained;

a search execution module, configured to: after receiving the retransmission of the recording by the terminal, recording the retransmitted recording as a password and continuing to loop to perform a step of acquiring a user identifier corresponding to the first password in the password recording; and

The lock notification module is configured to generate a payment lock notification and send the notification to the terminal when the number of times the authentication failure notification is generated exceeds the preset authentication number threshold.
A computer device comprising a memory and one or more processors having stored therein computer readable instructions, the computer readable instructions being executed by the one or more processors to cause the one or more The processors perform the following steps:

Receiving a payment request sent by the terminal, where the payment request carries an order data and a password recording;

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

Obtaining a first preset authentication question, sending the first preset authentication question to the terminal, and receiving a first answer recording that is returned by the terminal and corresponding to the first preset authentication question;

Extracting, from the order data, a first authentication answer corresponding to the first preset authentication question, and searching for 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 for a payment account corresponding to the user identifier, from the payment The account number is deducted from the value corresponding to the payment value in the order data.
The computer apparatus according to claim 10, wherein said processor further performs the following steps when said computer readable instructions are executed:

When the user identifier corresponding to the first password in the password recording is not obtained, an authentication failure notification is generated and sent to the terminal;

After receiving the retransmission of the recording by the terminal, recording the retransmitted recording as a password and continuing to loop to perform the step of acquiring a user identifier corresponding to the first password in the password recording; and

When the number of times the authentication failure notification is generated exceeds the preset authentication number threshold, a payment lock notification is generated and sent to the terminal.
The computer apparatus according to claim 10, wherein said processor further performs the following steps when said computer readable instructions are executed:

Receiving a user registration request, where the user registration request carries a 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 command carrying the second password and the user identifier, and transmitting the registration confirmation command to the terminal; and

After receiving the registration confirmation notification returned by the terminal, extracting a third voiceprint feature from the registration password recording, using the second password as a new user password, and adding the user identifier to the new user The password and the third voiceprint feature are stored in association.
The computer apparatus according to claim 10, wherein said processor further performs the following steps when said computer readable instructions are executed:

Generating a chargeback notification when the second authentication answer is inconsistent with the first authentication answer; and

Returning the chargeback notification to the terminal.
The computer apparatus according to claim 10, wherein said processor further performs the following steps when said computer readable instructions are executed:

When the second authentication answer is consistent with the first authentication answer, and the second voiceprint feature fails to match the first voiceprint feature, searching for the first auxiliary voiceprint feature corresponding to the user identifier and Preset auxiliary authentication issues;

Sending the auxiliary authentication question to the terminal; and receiving the auxiliary answer recording corresponding to the auxiliary authentication question returned by the terminal, extracting the second auxiliary voiceprint feature from the auxiliary answer recording;

When the second auxiliary voiceprint feature is successfully matched with the first auxiliary voiceprint feature, searching for 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. .
The computer apparatus according to claim 10, wherein said processor further performs the following steps when said computer readable instructions are executed:

When the first auxiliary voiceprint feature corresponding to the user identifier is not found, obtaining a second preset authentication problem, and sending the second preset authentication problem to the terminal;

Receiving a second answer recording returned by the terminal, and extracting a fourth voiceprint feature from the second answer recording; and

When the fourth voiceprint feature fails to match the first voiceprint feature, a chargeback notification is generated and the chargeback notification is returned to the terminal.
One or more non-transitory computer readable storage mediums storing computer readable instructions, when executed by one or more processors, cause the one or more processors to perform the following steps:

Receiving a payment request sent by the terminal, where the payment request carries an order data and a password recording;

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

Obtaining a first preset authentication question, sending the first preset authentication question to the terminal, and receiving a first answer recording that is returned by the terminal and corresponding to the first preset authentication question;

Extracting, from the order data, a first authentication answer corresponding to the first preset authentication question, and searching for 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 for a payment account corresponding to the user identifier, from the payment The account number is deducted from the value corresponding to the payment value in the order data.
The storage medium of claim 16 wherein said computer readable instructions are further executed by said processor to perform the following steps:

When the user identifier corresponding to the first password in the password recording is not obtained, an authentication failure notification is generated and sent to the terminal;

After receiving the retransmission of the recording by the terminal, recording the retransmitted recording as a password and continuing to loop to perform the step of acquiring a user identifier corresponding to the first password in the password recording; and

When the number of times the authentication failure notification is generated exceeds the preset authentication number threshold, a payment lock notification is generated and sent to the terminal.
The storage medium of claim 16 wherein said computer readable instructions are further executed by said processor to perform the following steps:

Receiving a user registration request, where the user registration request carries a 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 command carrying the second password and the user identifier, and transmitting the registration confirmation command to the terminal; and

After receiving the registration confirmation notification returned by the terminal, extracting a third voiceprint feature from the registration password recording, using the second password as a new user password, and adding the user identifier to the new user The password and the third voiceprint feature are stored in association.
The storage medium of claim 16 wherein said computer readable instructions are further executed by said processor to perform the following steps:

Generating a chargeback notification when the second authentication answer is inconsistent with the first authentication answer; and

Returning the chargeback notification to the terminal.
The storage medium of claim 16 wherein said computer readable instructions are further executed by said processor to perform the following steps:

When the second authentication answer is consistent with the first authentication answer, and the second voiceprint feature fails to match the first voiceprint feature, searching for the first auxiliary voiceprint feature corresponding to the user identifier and Preset auxiliary authentication issues;

Sending the auxiliary authentication question to the terminal; and receiving the auxiliary answer recording corresponding to the auxiliary authentication question returned by the terminal, extracting the second auxiliary voiceprint feature from the auxiliary answer recording;

When the second auxiliary voiceprint feature is successfully matched with the first auxiliary voiceprint feature, searching for 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. .