WO2020024398A1

WO2020024398A1 - Biometrics-assisted payment method and apparatus, and computer device and storage medium

Info

Publication number: WO2020024398A1
Application number: PCT/CN2018/106431
Authority: WO
Inventors: 赵琳
Original assignee: 平安科技（深圳）有限公司
Priority date: 2018-08-02
Filing date: 2018-09-19
Publication date: 2020-02-06
Also published as: CN108846676B; CN108846676A

Abstract

A biometrics-assisted payment method and apparatus, and a computer device and a storage medium. The method comprises: receiving a payment instruction sent by a payment user, and acquiring a first face image of the current payer, wherein the payment instruction includes a unique identifier associated with the payment user and order information (S10); retrieving, from a database, a second face image of the payment user according to the unique identifier (S20); when it is confirmed that the first face image matches the second face image, retrieving, from the database, voiceprint information of the payment user according to the unique identifier, wherein the voiceprint information includes a payment password text preset by the user, an audio entered by the payment user and corresponding to the payment password text, and a first voiceprint feature extracted from the audio (S30); acquiring a second voiceprint feature entered by the current payer according to the preset payment password text, and when the similarity between the first voiceprint feature and the second voiceprint feature exceeds a preset voiceprint similarity threshold value, confirming that the verification, i.e. authentication of the current payer is passed (S40); and displaying the order information and carrying out payment according to order amount (S50). By means of a duplication check, i.e. face recognition and voiceprint recognition, the security of biometrics recognition-based payment is improved and the property security of a user during payment is fully protected.

Description

Biometric auxiliary payment method, device, computer equipment and storage medium

This application is based on a Chinese invention patent application filed on August 2, 2018 with the application number 201810869072.8 and entitled "Biometric Auxiliary Payment Method, Device, Computer Equipment, and Storage Medium", and claims its priority.

Technical field

The present application relates to the field of payment technology, and in particular, to a method, a device, a computer device, and a storage medium for assisted payment of biometrics.

Background technique

With the development of science and technology, biometric verification has been widely used in various payment tools, for example, unmanned supermarkets use face recognition to pay. However, the current biometric verification method is generally a single verification, that is, only one biometric is verified. At this time, in the face of people who intentionally undermine payment security and infringe on the property of others, they will use technical means to simulate the user's biometric Verification, if only a single biometric is verified, it is easy to simulate the user's biometrics through technical means to pass the verification, reducing the security of biometric identification payment.

Summary of the invention

Based on this, it is necessary to provide a biometric assisted payment method, device, computer equipment and storage medium in response to the above technical problems, to improve the security of biometric payment, and to prevent a third person from easily passing a single biometric verification. The technical means simulates the biological characteristics of the user, and the payment can be made without the user's own operation, thereby fully protecting the user's payment and property security.

A biometric auxiliary payment method includes:

Receiving a payment instruction sent by a payment user, and obtaining a first face image of a current payer; the payment instruction includes a unique identifier and order information associated with the payment user;

Retrieve a second face image of the payment user from the database according to the unique identifier;

When it is confirmed that the first face image matches the second face image, the voiceprint information of the payment user is retrieved from the database according to the unique identifier, and the voiceprint information includes a user preset A payment password text, audio corresponding to the payment password text entered by the payment user, and a first voiceprint feature extracted from the audio;

Obtain the second voiceprint feature extracted from the audio input by the current payer according to the preset payment password text, and the similarity between the first voiceprint feature and the second voiceprint feature exceeds the preset voiceprint When the texture similarity threshold is confirmed, the current payer is verified to pass;

Display the order information and pay according to the order information.

A biometric auxiliary payment device includes:

A receiving module, configured to receive a payment instruction sent by a payment user, and obtain a first face image of a current payer; the payment instruction includes a unique identifier and order information associated with the payment user;

An image retrieval module, configured to retrieve a second face image of the payment user from the database according to the unique identifier;

A voiceprint retrieval module, configured to retrieve voiceprint information of the payment user from the database according to the unique identifier when confirming that the first face image matches the second face image; The voiceprint information includes a payment password text preset by the user, audio corresponding to the payment password text entered by the payment user, and a first voiceprint feature extracted from the audio;

A voiceprint detection module, configured to obtain a second voiceprint feature extracted from the audio input by the current payer based on the text of the preset payment password, and compare the first voiceprint feature with the second voiceprint feature When the similarity exceeds a preset voiceprint similarity threshold, confirm that the current payer is verified;

A payment module is configured to display the order information and pay according to the order information.

A computer device includes a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor. When the processor executes the computer-readable instructions, the following steps are implemented:

Display the order information and pay according to the order information.

One or more non-volatile readable storage media storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to perform the following steps:

Display the order information and pay according to the order information.

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

BRIEF DESCRIPTION OF THE DRAWINGS

In order to explain the technical solution of the embodiments of the present application more clearly, the drawings used in the description of the embodiments of the application will be briefly introduced below. Obviously, the drawings in the following description are just some embodiments of the application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without paying creative labor.

FIG. 1 is a schematic diagram of an application environment of a biometric auxiliary payment method according to an embodiment of the present application; FIG.

FIG. 2 is a flowchart of a biometric assisted payment method according to an embodiment of the present application; FIG.

FIG. 3 is a flowchart of step S30 of the biometric assisted payment method in an embodiment of the present application;

FIG. 4 is a flowchart of step S30 of the biometric assisted payment method in another embodiment of the present application;

FIG. 5 is a flowchart of step S40 of the biometric-assisted payment method according to an embodiment of the present application;

6 is a schematic diagram of a biometric auxiliary payment device according to an embodiment of the present application;

FIG. 7 is a schematic diagram of a computer device according to an embodiment of the present application.

detailed description

In the following, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

The biometric-assisted payment method provided in this application may be applied in the application environment shown in FIG. 1, where a client (computer device / terminal device) communicates with a server (server) through a network. The payment user sends a payment instruction to the server through the client. The server obtains the first face image of the current payer and the second face image uniquely associated with the payment user, and sends the first face image and the second person. The face image is compared. When the comparison is successful, the second voiceprint information of the current payer and the first voiceprint information uniquely associated with the payment user are obtained, and the first voiceprint feature and the second voiceprint feature are compared. And prompt whether the comparison is successful or not. If successful, payment is made according to the order amount. The second face image and the first voiceprint information uniquely associated with the payment user are stored in the server-side database in advance. The client (computer device / terminal device) includes, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server can be implemented by an independent server or a server cluster composed of multiple servers.

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

S10. Receive a payment instruction sent by a payment user, and obtain a first face image of a current payer; the payment instruction includes a unique identifier and order information associated with the payment user;

The payment user is a user account registered in the server that is currently logged in by the payer; the current payer is the payer who logs in to the payment user on the client; the first face image is the current payment process The face image of the current payer collected in the Internet; the payment instruction is sent by the current payer to the server by clicking a preset button on the client; the unique identifier associated with the payment user is the server identifying the payment User identification, the unique identification includes, but is not limited to, a user name, a mobile phone number, a login account, or a mailbox bound to the payment user, etc., as long as it is unique and can distinguish different payment users; understandable In the management system of an unmanned supermarket, the order information includes, but is not limited to, an order name, a list of product names, each product price, an order amount, each product quantity, and each product discount information.

S20. Retrieve a second face image of the payment user from the database according to the unique identifier;

The second face image is a face image corresponding to the payment user and stored in a database by the user in advance. The second human face image is stored in the database in association with the unique identifier, so the second human face image can be accurately retrieved according to the unique identifier; understandably, the returned stored in association with the unique identifier is also Including other information of the payment user, such as identity information, bank account information and voiceprint information. The second face image is a face image uniquely corresponding to the payment user and stored in the database in advance by the user. The retrieved second face image is used for comparison with the first face image of the current payer to determine whether the biometrics of the current payer and the biometrics uniquely associated with the payment user match.

S30. When it is confirmed that the first face image matches the second face image, the voiceprint information of the payment user is retrieved from the database according to the unique identifier, and the voiceprint information includes the user A preset payment password text, audio corresponding to the payment password text input by the payment user, and a first voiceprint feature extracted from the audio.

That is, when confirming that the first face image of the current payer matches the second face image of the payment user, the server retrieves the first voiceprint of the payment user from the database according to the unique identifier. Feature for comparison with the second voiceprint feature of the current payer to verify whether the voiceprint information of the current payer and the payment user match.

S40. Obtain a second voiceprint feature extracted from the audio input by the current payer based on the preset payment password text, and the similarity between the first voiceprint feature and the second voiceprint feature exceeds a preset When the voiceprint similarity threshold is reached, it is confirmed that the current payer is verified.

The current payer according to the payment password text displayed in the voiceprint recognition interface, records audio in real-time in the recording device of the necklace with the client, and transmits the audio to the server, which then extracts the The second voiceprint feature in the audio. The second voiceprint feature is used for comparison with the first voiceprint feature, so as to further determine whether the current payer matches the payment user, that is, whether the current payer is the actual owner of the payment user.

S50: Display the order information and pay according to the order information.

After the current payer and the payment user are successfully authenticated, the server deducts the amount in the bank savings account, credit card, or third-party payment account bound to the payment user according to the order amount to complete the payment. In one embodiment, after the payment is completed, the payment success information and the order information are popped up through the display interface.

The biometric assisted payment method of this embodiment improves the security of biometric recognition payment by performing double verification of face recognition and voiceprint recognition, and prevents a third person from simulating through technical means due to single biometric verification. The user's biometrics can be paid without the user's own operation, which fully protects the user's payment and property security.

In an embodiment, the step S10 includes:

After receiving a payment instruction, a face acquisition instruction is sent to the client; the payment instruction includes a unique identifier and order information associated with the payment user; and the order information includes an order name and an order amount. The payment instruction is sent by the current payer to the server by clicking a preset button on the client. After receiving the payment instruction, the server sends a face acquisition instruction to the client, and the client photographs the current through its shooting device. Pay the person's face video or image and send the face image or video to the server. The server processes the face image or video according to a preset rule to obtain a first face image of a current payer.

Receiving a face image or video of the current payer collected by the client, and generating the first face image from the face image or video according to a preprocessing rule. That is, after the face collection instruction is sent to the client, a face recognition window pops up on the display interface of the client, and the face recognition window is connected to the client's shooting device, which can be When the recognition window pops up, the face video or image of the current payer is captured in real time, and the captured face video or image is transmitted to the server, and the server intercepts the face image of the current payer according to the preprocessing rule. As the first face image; understandably, the first face image may be displayed in the face recognition window, so that a user previews the first face image and verifies the first face image Pass the time, adjust the next shooting state according to the preview situation in the face recognition window. After acquiring the first face image, it may be stored in a database or a cache in association with the unique identification. After the server obtains the first face image, it compares with the second face image stored in the database in advance and is associated with the payment user, so that the first biometric feature of the current payer (that is, in this application) Face image), to determine whether to verify the second biological feature (that is, the voiceprint feature in this application).

In an embodiment, before step S10, the method further includes: receiving a viewing instruction including target information, fetching the target information and displaying it on a display interface.

The viewing instruction is sent by the user to the server after the client scans a preset two-dimensional code (or triggers a preset viewing button), and after receiving the viewing instruction, the server according to the target information contained in the viewing instruction (i.e. The target information corresponding to the two-dimensional code scanned by the user or the target information linked by the view button), the target information is retrieved from the database and sent to the client for viewing and selection by the user. In the unmanned supermarket management system, the target information is the product information that the user wants to view. For example, when a consumer wants to purchase a certain product, he can scan the corresponding QR code to obtain the target information. The target information includes But it is not limited to commodity price, commodity production date and shelf life, commodity name, commodity origin, commodity type or other special marked information; in this case, the target information is stored in the database of the unmanned supermarket management system.

In an embodiment, before step S20, the method further includes: storing a second face image of the payment user into a database.

When the user registers the payment user on the client, the server sends a collection instruction to the client. After the client receives the collection instruction, a face recognition window pops up, and the client's shooting device captures the user's face video in real time. Or image, and transmits it to the server, the server intercepts the face image in the face video or image as a second face image according to a preprocessing rule, and uses the second face image and the second face image The unique identifier is stored in the database in association with other user information entered by the user during registration, which facilitates the retrieval of the second face image and other user information from the database according to the unique identifier.

In an embodiment, as shown in FIG. 3, before step S30, the method further includes steps:

S301. Detect whether the similarity between the first face image and the second face image exceeds a preset image similarity threshold; understandably, the preset image similarity threshold may be performed in advance according to actual conditions. set up.

Detecting whether the similarity between the first face image and the second face image exceeds a preset image similarity threshold may be performed on the entirety of the first face image and the second face image The comparison may also compare only some of the facial features of the two.

In an embodiment, the facial contours of the first facial image and the second facial image are first compared; the facial contours of the first facial image and the second facial image do not exceed a preset ratio ( When the preset ratio can be set according to requirements, for example, 0.6-0.8), it is directly determined that the first face image of the current payer does not match the second face image of the payment user, and a prompt is displayed at this time. The match failed.

When the facial contours of the first face image and the second face image exceed a preset ratio, comparing the facial features of the first face image with the second face image; determining Whether the facial features of the first face image and the second face image exceed a preset image similarity threshold (the first and second can be set according to requirements, such as 0.55 or more). When the similarity of the facial features between the first face image and the second face image exceeds a preset image similarity threshold value, it is prompted that the matching is successful, and the first face image and the second face image are matched. When the facial feature similarity of the image does not exceed the preset image similarity threshold, a matching failure is prompted. At this time, the matching failure information is sent to the client, prompting that the face matching of the current payer fails.

S302. When the similarity between the first face image and the second face image exceeds a preset image similarity threshold, confirm that the first face image of the current payer and the first The two face images match. At this time, the information of successful matching is sent to the client, prompting that the face matching of the current payer is successful.

S303. When the similarity between the first face image and the second face image does not exceed a preset image similarity threshold, prompting that the matching fails. At this time, the matching failure information is sent to the client, prompting that the face matching of the current payer fails.

In an embodiment, after step S303, the method further includes the following steps:

When the first modification instruction is received, the second face image is modified according to a key pre-stored by the payment user.

That is, after the user performs plastic surgery or changes in facial features of the face due to other reasons, the similarity verification between the first face image and the second face image cannot be verified, that is, whether the current payer and the When the payment user is matched, the second face image may be modified. At this time, the user can click the preset button to modify the face features on the client to send the first modification instruction to the server, and at the same time, a key input window pops up, and the current payer enters the pre-stored key when registering the payment user After that, the second face image may be modified, that is, return to step S201. Understandably, the preset key may be one or more of through-hole identification, one or more fingerprint identification, ID card number, mobile phone number, preset Q & A, and the like.

In an embodiment, as shown in FIG. 4, before step S30, the method further includes steps:

S304. Receive a voiceprint entry instruction and obtain audio input by a user according to a voiceprint rule.

That is, when the payment user is registered on the client, the user clicks a preset entry button on the entry interface to send a voiceprint entry instruction to the server. At this time, the voiceprint entry rules (such as entry duration and number of words) Regulations, language type regulations, speech rate regulations, etc.) can be displayed on the entry interface to prompt users how to enter; users can enter audio that conforms to the voiceprint entry rules according to their needs (that is, pre-plan the payment password that needs to be entered, and Enter the payment password through a recording device connected to the client). Understandably, the audio entered by the user is the audio corresponding to the payment password text, and the audio is stored in the database in association with the unique identification of the payment user.

S305. Identify the payment password text in the audio, extract a first voiceprint feature from the audio, and store the audio, the payment password text, and the first voiceprint feature in association with the unique identifier. To the database.

After acquiring the audio, the server recognizes the text in the audio through voice recognition, that is, the payment password text; at the same time, extracts the first voiceprint feature of the user in the audio from the audio, and records all The first voiceprint feature is described; understandably, after the payment password text is obtained through voice recognition, the payment password text may be displayed on the entry interface for the user to confirm whether the identified payment password text is the user If the text of the payment password is set, the user can click the preset button to confirm. If not, the user can modify or delete the payment password displayed on the input interface, or re-input the audio. When the user has a dialect, etc., the payment password text is modified to meet the user's needs. Understandably, the payment password text, the audio, and the first voiceprint feature are all stored in the database in association with the unique identification of the payment user, so as to be retrieved at any time according to the unique identification.

Understandably, the steps S304 and S305 can be repeated a preset number of times, that is, when the client registers the payment user, the user can input several payment passwords on the entry interface and extract its first voiceprint feature; And multiple of the payment passwords can be marked with their priority. At this time, when the voiceprint information of the payment user is retrieved in step S30, the first voiceprint characteristics of all payment passwords may be retrieved at the same time according to requirements, so that the current payer enters a second voice corresponding to all payment passwords. Multiple comparisons of fingerprint features are performed; the first voiceprint feature of one of the payment passwords may also be called for verification in accordance with the priority; after the first voiceprint feature comparison of the current payment password fails, the next One (or all remaining first voiceprint features) are compared.

In this embodiment, the user randomly enters and recognizes a payment password. The payment password is diverse and has a low degree of coincidence, which improves its security. The payment password is set by the user and is more conducive to user memory.

In an embodiment, as shown in FIG. 5, the step S40 includes the following steps:

S401. Obtain a second voiceprint feature extracted from the audio input by the current payer according to the text of the payment password.

That is, a voiceprint recognition interface pops up on the client first, and one or more (preset number of) payment password texts are displayed according to the priority of the payment password text on the current voiceprint recognition interface. ; Preferably, when the payment password text is displayed on the voiceprint recognition interface, only part of the text is displayed, and another part of the payment password text is on the voiceprint input interface in a preset form such as "*". Hidden, for example, the payment password text is hidden by 5 words. At this time, the hidden 5 words can be replaced by the omitted form of "***", that is, regardless of the hidden words, "***" is used instead. This solution is more secure; it can also be replaced with "*****", that is, hide a few words and display a few "*". At this time, the user can be prompted to omit the number of words, which improves the user experience; in this embodiment, Because the above payment password text is entered by the user according to his needs, he knows some of the hidden password text, but no one else knows it, which greatly improves the security in the payment process.

Thereafter, the current payer records audio in real time in a recording device connected to the client based on the payment password text displayed on the voiceprint recognition interface, and transmits the audio to the server, the server A second voiceprint feature in the audio is then extracted.

S402: Detect whether the similarity between the first voiceprint feature and the second voiceprint feature exceeds a preset voiceprint similarity threshold.

The preset voiceprint similarity threshold may be set in advance according to an actual situation, for example, the preset voiceprint similarity threshold is above 0.6. Comparing the first voiceprint feature with the second voiceprint feature according to a preset rule, and detecting whether the similarity between the first voiceprint feature and the second voiceprint feature exceeds a preset voiceprint Similarity threshold.

S403. When the similarity between the first voiceprint feature and the second voiceprint feature does not exceed a preset voiceprint similarity threshold, confirm that the current payer has passed verification; after confirming that the current payer has passed verification, The verified information is sent to the client to prompt the current payer.

S404. When the similarity between the first voiceprint feature and the second voiceprint feature does not exceed a preset voiceprint similarity threshold, confirm that the current payer fails to verify; and send the verification failure information to the client. , Prompting that the current payer fails to verify.

In an embodiment, after step S404, the method further includes: when receiving the second modification instruction, modifying the first voiceprint feature according to a pre-stored key.

That is, when a condition occurs in the user's throat, the voice becomes hoarse, or other conditions occur, it is not possible to verify whether the current payer matches the payment user through the similarity between the first voiceprint feature and the second voiceprint feature. At this time, the first voiceprint feature can be modified. At this time, the user can click a preset modification button on the client to send a second modification instruction to the server, and a key input window pops up on the display interface. After the current payer enters the pre-stored key when registering the payment user, the first voiceprint feature can be modified, that is, the process returns to step S304. Understandably, the preset key may be in one or more of the following ways: pupil recognition, one or more fingerprint recognition, ID card number, mobile phone number, preset question answering, and the like.

This application first performs a preliminary verification of the identity of the current payer by using facial features, and further verifies the voiceprint features of the current payer on this basis, only when both face recognition and voiceprint recognition pass Only after confirming that the current payer has successfully verified and paid according to the order information, improves the security of biometric payment, and prevents the third person from simulating the user's biometrics through technical means due to the single biometric verification. Payments can be made without the user's own operation, which fully protects the user's payment and property security.

It should be understood that the size of the sequence numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

In one embodiment, a biometric auxiliary payment device is provided, and the biometric auxiliary payment device corresponds to the biometric auxiliary payment method in the above embodiment in a one-to-one correspondence. As shown in FIG. 6, the biometric auxiliary payment device includes a receiving module 110, an image retrieval module 120, a voiceprint retrieval module 130, a voiceprint detection module 140, and a payment module 150. The detailed description of each function module is as follows:

The receiving module 110 is configured to receive a payment instruction sent by a payment user, and obtain a first face image of a current payer; the payment instruction includes a unique identifier and order information associated with the payment user;

The image retrieval module 120 is configured to retrieve a second face image of the payment user from a database according to the unique identifier;

The voiceprint retrieval module 130 is configured to retrieve the voiceprint of the payment user from the database according to the unique identifier when confirming that the first facial image matches the second facial image. Information; the voiceprint information includes a payment password text preset by a user, audio corresponding to the payment password text entered by the payment user, and a first voiceprint feature extracted from the audio;

The voiceprint detection module 140 is configured to obtain a second voiceprint feature extracted from the audio input by the current payer based on the text of the preset payment password, and compare the first voiceprint feature with the second voiceprint. When the similarity of the texture feature exceeds a preset voiceprint similarity threshold, it is confirmed that the current payer is verified;

The payment module 150 is configured to display the order information and pay according to the order information.

In an embodiment, the device is further configured to detect whether the similarity between the first face image and the second face image exceeds a preset image similarity threshold; between the first face image and the When the similarity of the second face image exceeds a preset image similarity threshold, confirming that the first face image of the current payer matches the second face image of the payment user; in the When the similarity between the first face image and the second face image does not exceed a preset image similarity threshold, it indicates that the matching fails.

In an embodiment, the voiceprint detection module 140 is further configured to obtain a second voiceprint feature extracted from the audio input by the current payer based on the text of the payment password; and detect the first voiceprint feature and the voiceprint feature. Whether the similarity of the second voiceprint feature exceeds a preset voiceprint similarity threshold; when the similarity between the first voiceprint feature and the second voiceprint feature exceeds a preset voiceprint similarity threshold, confirm The current payer is successfully authenticated; when the similarity between the first voiceprint feature and the second voiceprint feature does not exceed a preset voiceprint similarity threshold, it is confirmed that the current payer authentication fails.

For the specific limitation of the biometric auxiliary payment device, refer to the foregoing limitation on the biometric auxiliary payment method, which will not be repeated here. Each module in the biometric auxiliary payment device can be implemented in whole or in part by software, hardware, and a combination thereof. The above-mentioned modules may be embedded in the hardware form or independent of the processor in the computer device, or may be stored in the memory of the computer device in the form of software, so that the processor calls and performs the operations corresponding to the above modules.

In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. 7. The computer device includes a processor, a memory, a network interface, and a database connected through 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 and an internal memory. The non-volatile storage medium stores an operating system, computer-readable instructions, and a database. The internal memory provides an environment for operating the operating system and computer-readable instructions in a non-volatile storage medium. The database of the computer equipment is used to store the first face image, the second face image, the first voiceprint feature, the second voiceprint feature, the video, image and audio input through the client, preset payment password text target information (For example, in the database of the unmanned supermarket system, the target information is various information about the product, such as price, quantity, name, shelf life and origin, etc.), the user's pre-stored key, and other information about the payment user (such as identity information, Bank credit and debit card information). The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer-readable instructions are executed by a processor to implement the biometric-assisted payment method described above.

In one embodiment, a computer device is provided, including a memory, a processor, and computer-readable instructions stored on the memory and executable on the processor. When the processor executes the computer-readable instructions, the following steps are implemented:

Display the order information and pay according to the order information.

In one embodiment, one or more non-volatile readable storage media storing computer readable instructions are provided, and the non readable storage medium stores computer readable instructions. The computer readable instructions are When executed by one or more processors, the one or more processors implement the following steps:

Display the order information and pay according to the order information.

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

Those skilled in the art can clearly understand that, for the convenience and brevity of the description, only the above-mentioned division of functional units and modules is used as an example. In practical applications, the above functions can be assigned by different functional units, Module completion, that is, dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above.

The above-mentioned embodiments are only used to describe the technical solution of the present application, but are not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still implement the foregoing implementations. The technical solutions described in the examples are modified, or some technical features are equivalently replaced; and these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in Within the scope of this application.

Claims

A biometric-assisted payment method, comprising:

Receiving a payment instruction sent by a payment user, and obtaining a first face image of a current payer; the payment instruction includes a unique identifier and order information associated with the payment user;

Retrieve a second face image of the payment user from the database according to the unique identifier;

When it is confirmed that the first face image matches the second face image, the voiceprint information of the payment user is retrieved from the database according to the unique identifier, and the voiceprint information includes a user preset A payment password text, audio corresponding to the payment password text entered by the payment user, and a first voiceprint feature extracted from the audio;

Obtain the second voiceprint feature extracted from the audio input by the current payer according to the preset payment password text, and the similarity between the first voiceprint feature and the second voiceprint feature exceeds the preset voiceprint When the texture similarity threshold is confirmed, the current payer is verified to pass;

Display the order information and pay according to the order information.
The method according to claim 1, wherein, when confirming that the first face image matches the second face image, adjusting from the database according to the unique identifier is performed. Before obtaining the voiceprint information of the payment user, the method includes:

Detecting whether the similarity between the first face image and the second face image exceeds a preset image similarity threshold;

When the similarity between the first face image and the second face image exceeds a preset image similarity threshold, confirming that the first face image of the current payer and the first Two face image matching;

When the similarity between the first face image and the second face image does not exceed a preset image similarity threshold value, it is prompted that the matching fails.
The method of claim 2, wherein when the similarity between the first face image and the second face image does not exceed a preset image similarity threshold, prompting After the match fails, it also includes:

Receive a first modification instruction, and modify the second face image according to a key pre-stored by the payment user.
The method according to claim 1, wherein, when confirming that the first face image matches the second face image, adjusting from the database according to the unique identifier is performed. Before obtaining the voiceprint information of the payment user, the method includes:

Receive voiceprint entry instructions and obtain audio recorded by the user according to voiceprint entry rules;

Identify the payment password text in the audio, extract a first voiceprint feature from the audio, and store the audio, the payment password text, and the first voiceprint feature in association with the unique identifier to a database .
The method of claim 1, wherein the second voiceprint feature input by the current payer according to the preset payment password text is obtained, and the first voiceprint feature and the When the similarity of the second voiceprint feature exceeds a preset voiceprint similarity threshold, confirming that the current payer has passed verification, including:

Obtaining a second voiceprint feature extracted from audio currently entered by the payer according to the text of the payment password;

Detecting whether the similarity between the first voiceprint feature and the second voiceprint feature exceeds a preset voiceprint similarity threshold;

When the similarity between the first voiceprint feature and the second voiceprint feature exceeds a preset voiceprint similarity threshold, confirming that the current payer is successfully authenticated;

When the similarity between the first voiceprint feature and the second voiceprint feature does not exceed a preset voiceprint similarity threshold, it is confirmed that the current payer authentication fails.
The method of claim 5, wherein when the similarity between the first voiceprint feature and the second voiceprint feature does not exceed a preset voiceprint similarity threshold, After confirming that the current payer authentication fails, it also includes:

Receive a second modification instruction, and modify the first voiceprint feature according to a key pre-stored by the payment user.
The biometric assisted payment method according to claim 1, wherein the receiving a payment instruction sent by a payment user and acquiring a first face image of a current payer comprises:

Receive payment instructions and send face acquisition instructions to the client;

Receiving a face image or video of the current payer collected by the client, and generating the first face image from the face image or video according to a preprocessing rule.
A biometric auxiliary payment device, comprising:

A receiving module, configured to receive a payment instruction sent by a payment user, and obtain a first face image of a current payer; the payment instruction includes a unique identifier and order information associated with the payment user;

An image retrieval module, configured to retrieve a second face image of the payment user from the database according to the unique identifier;

A voiceprint retrieval module, configured to retrieve voiceprint information of the payment user from the database according to the unique identifier when confirming that the first face image matches the second face image; The voiceprint information includes a payment password text preset by the user, audio corresponding to the payment password text entered by the payment user, and a first voiceprint feature extracted from the audio;

A voiceprint detection module, configured to obtain a second voiceprint feature extracted from the audio input by the current payer based on the text of the preset payment password, and compare the first voiceprint feature with the second voiceprint feature When the similarity exceeds a preset voiceprint similarity threshold, confirm that the current payer is verified;

A payment module is configured to display the order information and pay according to the order information.
The biometric auxiliary payment device according to claim 8, wherein the device is further configured to detect whether the similarity between the first face image and the second face image exceeds a preset image similarity Threshold; when the similarity between the first face image and the second face image exceeds a preset image similarity threshold, confirming that the first face image of the current payer and The second face image matching is described; when the similarity between the first face image and the second face image does not exceed a preset image similarity threshold, prompting that the matching fails.
The biometric auxiliary payment device according to claim 8, wherein the voiceprint detection module is further configured to obtain a second voiceprint feature extracted from an audio currently input by the payer based on the payment password text; detecting Whether the similarity between the first voiceprint feature and the second voiceprint feature exceeds a preset voiceprint similarity threshold; when the similarity between the first voiceprint feature and the second voiceprint feature exceeds a predetermined When the voiceprint similarity threshold is set, confirm that the current payer is successfully authenticated; when the similarity between the first voiceprint feature and the second voiceprint feature does not exceed a preset voiceprint similarity threshold, confirm the current payment Person authentication failed.
A computer device includes a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, wherein the processor implements the computer-readable instructions as follows: step:

Receiving a payment instruction sent by a payment user, and obtaining a first face image of a current payer; the payment instruction includes a unique identifier and order information associated with the payment user;

Retrieve a second face image of the payment user from the database according to the unique identifier;

When it is confirmed that the first face image matches the second face image, the voiceprint information of the payment user is retrieved from the database according to the unique identifier, and the voiceprint information includes a user preset A payment password text, audio corresponding to the payment password text entered by the payment user, and a first voiceprint feature extracted from the audio;

Obtain the second voiceprint feature extracted from the audio input by the current payer according to the preset payment password text, and the similarity between the first voiceprint feature and the second voiceprint feature exceeds the preset voiceprint When the texture similarity threshold is confirmed, the current payer is verified to pass;

Display the order information and pay according to the order information.
The computer device of claim 11, wherein the processor further implements the following steps when executing the computer-readable instructions:

Detecting whether the similarity between the first face image and the second face image exceeds a preset image similarity threshold;

When the similarity between the first face image and the second face image exceeds a preset image similarity threshold, confirming that the first face image of the current payer and the first Two face image matching;

When the similarity between the first face image and the second face image does not exceed a preset image similarity threshold value, it is prompted that the matching fails.
The computer device of claim 12, wherein when the processor executes the computer-readable instructions, the following steps are implemented:

Receive a first modification instruction, and modify the second face image according to a key pre-stored by the payment user.
The computer device of claim 11, wherein the processor implements the following steps when executing the computer-readable instructions:

Receive voiceprint entry instructions and obtain audio recorded by the user according to voiceprint entry rules;

Identify the payment password text in the audio, extract a first voiceprint feature from the audio, and store the audio, the payment password text, and the first voiceprint feature in association with the unique identifier to a database .
The computer device according to claim 11, wherein the second voiceprint feature entered by the current payer according to the preset payment password text is obtained, and the first voiceprint feature and the second voiceprint feature When the similarity of voiceprint features exceeds a preset voiceprint similarity threshold, confirm that the current payer has passed verification, including:

Obtaining a second voiceprint feature extracted from audio currently entered by the payer according to the text of the payment password;

Detecting whether the similarity between the first voiceprint feature and the second voiceprint feature exceeds a preset voiceprint similarity threshold;

When the similarity between the first voiceprint feature and the second voiceprint feature exceeds a preset voiceprint similarity threshold, confirming that the current payer is successfully authenticated;

When the similarity between the first voiceprint feature and the second voiceprint feature does not exceed a preset voiceprint similarity threshold, it is confirmed that the current payer authentication fails.
One or more non-volatile readable storage media storing computer-readable instructions, wherein when the computer-readable instructions are executed by one or more processors, the one or more processors execute The following steps:

Receiving a payment instruction sent by a payment user, and obtaining a first face image of a current payer; the payment instruction includes a unique identifier and order information associated with the payment user;

Retrieve a second face image of the payment user from the database according to the unique identifier;

When it is confirmed that the first face image matches the second face image, the voiceprint information of the payment user is retrieved from the database according to the unique identifier, and the voiceprint information includes a user preset A payment password text, audio corresponding to the payment password text entered by the payment user, and a first voiceprint feature extracted from the audio;

Obtain the second voiceprint feature extracted from the audio input by the current payer according to the preset payment password text, and the similarity between the first voiceprint feature and the second voiceprint feature exceeds the preset voiceprint When the texture similarity threshold is confirmed, the current payer is verified to pass;

Display the order information and pay according to the order information.
The computer-readable storage medium of claim 16, wherein when the computer-readable instructions are executed by one or more processors, the one or more processors further perform the following steps:

Detecting whether the similarity between the first face image and the second face image exceeds a preset image similarity threshold;

When the similarity between the first face image and the second face image exceeds a preset image similarity threshold, confirming that the first face image of the current payer and the first Two face image matching;

When the similarity between the first face image and the second face image does not exceed a preset image similarity threshold value, it is prompted that the matching fails.
The computer-readable storage medium of claim 17, wherein when the computer-readable instructions are executed by one or more processors, the one or more processors further perform the following steps:

Receive a first modification instruction, and modify the second face image according to a key pre-stored by the payment user.
The computer-readable storage medium of claim 16, wherein when the computer-readable instructions are executed by one or more processors, the one or more processors further perform the following steps:

Receive voiceprint entry instructions and obtain audio recorded by the user according to voiceprint entry rules;

Identify the payment password text in the audio, extract a first voiceprint feature from the audio, and store the audio, the payment password text, and the first voiceprint feature in association with the unique identifier to a database .
The computer-readable storage medium according to claim 16, wherein the second voiceprint feature entered by the current payer according to the preset payment password text is obtained, and the first voiceprint feature and the When the similarity of the second voiceprint feature exceeds a preset voiceprint similarity threshold, confirming that the current payer has passed verification, including:

Obtaining a second voiceprint feature extracted from audio currently entered by the payer according to the text of the payment password;

Detecting whether the similarity between the first voiceprint feature and the second voiceprint feature exceeds a preset voiceprint similarity threshold;

When the similarity between the first voiceprint feature and the second voiceprint feature exceeds a preset voiceprint similarity threshold, confirming that the current payer is successfully authenticated;

When the similarity between the first voiceprint feature and the second voiceprint feature does not exceed a preset voiceprint similarity threshold, it is confirmed that the current payer authentication fails.