TW201944320A - Payment authentication method, device, equipment and storage medium - Google Patents

Abstract

The embodiment of the invention discloses a payment authentication method, device, equipment and storage medium. The method includes a step of acquiring a to-be-verified payment voice associated witha payment order and identifying identity feature information included in the to-be-verified payment voice, a step of obtaining a standard payment voice of a legal payment user if a condition that theidentified identity feature information is matched with identity feature information of the legal payment user, and a step of performing a payment operation matched with the payment order if a condition that the to-be-verified payment voice is matched with the standard payment voice.

Description

   Payment authentication method, device, equipment and storage medium   

The present invention relates to identity authentication technology, for example, to a payment authentication method, device, device, and storage medium.

With the development of Internet technology, people can make online purchases, purchases, and pay bills without leaving home, and online smart payment has become a common payment method used in people's lives.

However, due to the spread of computer viruses, hackers and spyware or SMS scams, customer passwords are easily stolen on the Internet. In order to realize the security of smart payment, it is usually necessary to verify the identity of the payment user. The verification methods in related technologies include SMS verification, fingerprint verification, password verification, and signature verification. These authentication methods all require users to perform input operations, and the payment efficiency is low. When users cannot perform input operations, the user's identity cannot be verified. At the same time, these authentication methods are easy to be stolen by others, and the security is poor. In addition, the verification method further includes face recognition and voiceprint recognition, but the efficiency of face recognition is low and the requirements for ambient light are high. In the case of voiceprint recognition, voiceprint recognition is still performed when the input voice is significantly different from the target voice, which is inefficient.

The invention provides a payment authentication method, device, device and storage medium, which can optimize the payment authentication method in related technologies, improve the efficiency and security of payment authentication, and greatly increase the convenience of payment authentication.

In a first aspect, the present invention provides a payment authentication method, comprising: acquiring a payment voice to be verified associated with a payment order, and identifying the identity characteristic information contained in the payment voice to be verified; If the identity information of the user matches, the standard payment voice of the legitimate payment user is obtained. If it is determined that the payment voice to be verified matches the standard payment voice, a payment operation matching the payment order is performed.

In a second aspect, the present invention further provides a payment authentication device, including: a payment voice recognition module for obtaining a payment voice to be verified associated with a payment order, and identifying the identity characteristic information contained in the payment voice to be verified; a standard payment voice An obtaining module for obtaining the standard payment voice of the legitimate payment user if it is determined that the identified identity characteristic information matches the identity characteristic information of the legal payment user; a payment operation execution module for determining the aforementioned If the payment voice to be verified matches the standard payment voice, a payment operation matching the payment order is executed.

According to a third aspect, the present invention further provides a device including a memory, a processor, and a computer program stored on the memory and operable on the processor. The processor executes the program as described above. Any of the aforementioned payment authentication methods.

According to a fourth aspect, the present invention further provides a computer-readable storage medium storing a computer program, wherein the program, when executed by a processor, implements any of the foregoing payment authentication methods according to aspects of the present invention.

The invention judges in advance whether the identity characteristic information identified by the payment voice to be verified matches the identity characteristic information of the legitimate payment user, and when the identified identity characteristic information matches the identity characteristic information of the legitimate payment user, it determines whether to wait Verify that the payment voice and standard payment voice match, solve the problem of low payment identity authentication in related technology, ensure the security of payment, and improve the efficiency of payment authentication.

210‧‧‧Payment voice recognition module

220‧‧‧Standard payment voice acquisition module

230‧‧‧ payment operation execution module

240‧‧‧Legal Identity Acquisition Module

250‧‧‧Legal User Image Acquisition Module

260‧‧‧ does not match the payment module

270‧‧‧ Feature information model generation module

301‧‧‧equipment

302‧‧‧processing unit

303‧‧‧System memory

304‧‧‧Bus

305‧‧‧ Random Access Memory

306‧‧‧Cache memory

307‧‧‧Storage System

308‧‧‧Program module

309‧‧‧Programs / Utilities for Program Module 308

310‧‧‧External Equipment

311‧‧‧Display

312‧‧‧input / output (I / O) interface

313‧‧‧Network Interface Card

[Fig. 1] A flowchart of a payment authentication method provided in Embodiment 1; [Fig. 2] A structural diagram of a payment authentication device provided in Embodiment 2; [Fig. 3] A structural diagram of a device provided in Embodiment 3.

For ease of description, the drawings only show some but not all of the content related to the present invention. Before discussing the exemplary embodiments in more detail, it should be mentioned that some of the exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart describes multiple operations (or steps) as a sequential process, many of these operations can be performed in parallel, concurrently, or simultaneously. In addition, the order of multiple operations can be rearranged. The foregoing processing may be terminated when the operation is completed, but further may have additional steps not included in the drawings. The foregoing processing may correspond to a method, a function, a computer program, a subroutine or a subroutine, and the like.

Example one

FIG. 1 is a flowchart of a payment authentication method provided in Embodiment 1. This embodiment is applicable to a case where payment authentication is performed by inputting a payment voice. The method may be performed by a payment authenticator device provided in this embodiment. The device It can be implemented in at least one of software and hardware, and can generally be integrated into terminal devices used by payment users, such as PCs, tablets, and mobile phones. It includes the following steps:

S110: Obtain a payment voice to be verified associated with a payment order, and identify the identity characteristic information contained in the payment voice to be verified.

In this embodiment, the to-be-verified payment voice associated with the payment order can be the voice input device of the user after the voiceprint payment is turned on when the user needs to perform a payment operation; the identity characteristic message can be a message that can indicate the identity of the user . In an embodiment, the payment voice to be verified may be a voice issued by the user according to the setting content displayed on the display screen of the device, or an arbitrary voice issued by the user; the identity characteristic message may include at least one of gender and age Among them, the gender includes male and female; the age can be an age range, for example, it can be 10-18 years, 19-30 years, 31-40 years, 41-50 years, or 51-70 years.

In an embodiment, in order to ensure the security of the payment operation, the identity characteristic message may further include: an answer to a setting question. Optionally, the answer may be an answer given by the user to the setting question, and is input in a voice form. Correspondingly, the payment voice to be verified may be an answer voice issued for a setting question displayed on the display screen of the device. By setting the setting question and the corresponding answer, a targeted identity characteristic message can be set to improve the security of the payment operation. In order to ensure the security of the payment operation, the aforementioned setting questions and corresponding answers may be updated once within a set time interval (for example, within half a year, within a month, or within a week).

In this embodiment, selectively identifying the identity feature information contained in the payment voice to be verified includes: extracting the acoustic features of the payment voice to be verified according to the payment voice to be verified; and combining the foregoing acoustic feature with pre-training Compare at least two feature information models of the, to determine a feature information model that matches the aforementioned acoustic feature, and use the feature information corresponding to the matched feature information model as the identity feature message.

Alternatively, the acoustic characteristics may be pitch parameters, short-term energy, short-time zero-crossing rate, speech endpoints (such as the occurrence point and end point of effective speech), linear prediction cepstrum parameters, or Mel frequency cepstrum parameters. The model can be a support vector machine model or a Gaussian mixture model. There can be multiple feature information models, a feature information model set can be generated, and a feature information model set contains at least two feature information models of one type of feature information. The method of determining the feature information model for acoustic feature matching can evaluate the degree of matching between the acoustic feature and the feature information model by using a log-likelihood ratio. The larger the ratio, the higher the degree of matching between the acoustic feature and the feature information model. The feature information model with the highest feature matching degree is used as the feature information model that matches the acoustic feature.

The pre-trained feature information model is used to determine the identity feature information contained in the payment voice to be verified, which can quickly obtain the identity feature information contained in the to-be-verified payment voice, thereby quickly filtering out those that are significantly different from the legitimate payment user identity feature information Pay for voice to increase the efficiency of payment authentication.

In one embodiment, the feature information model is set as a gender feature information model, and the feature information model with a male gender and the feature information model with a female gender are pre-trained. The acoustic features in the payment voice to be verified are extracted and compared with the feature information model of gender male and the feature information model of female gender. If the model with the highest similarity is the feature information model of male gender, determine the to be verified The gender in the identity feature message of the payment voice is male.

The acoustic characteristics and the content of the model can be selected according to actual needs or implementation effects.

In another optional embodiment, before acquiring the payment voice to be verified associated with the payment order, the method may further include: acquiring at least two standard payment voices, selecting any one of the standard payment voices, and extracting the acoustic characteristics of the aforementioned standard payment voices ; Generating at least two feature information models based on the identity characteristic information of the user corresponding to the aforementioned standard payment voice and the acoustic characteristics of the aforementioned standard payment voice.

In this embodiment, a characteristic message model can be established by obtaining a standard payment voice preset by a legitimate user, and corresponding identity characteristic information of the standard payment voice, and determining the payment voice to be verified using multiple characteristic message models. Identity information. Optionally, the voice samples and the identity characteristic information corresponding to the voice samples can be further obtained through the network. By establishing the feature message model, the identity feature information corresponding to the payment voice can be accurately identified, and the accuracy of the payment voice discrimination can be improved.

S120. If it is determined that the identified identity characteristic information matches the identity characteristic information of the legitimate payment user, obtain the standard payment voice of the aforementioned legitimate payment user.

In this embodiment, the legal payment user may be a user associated with the payment order; the standard payment voice may be a voice segment input by the legal payment user in advance. Alternatively, the standard payment voice may be set by the legal payment user in accordance with the setting. The voices made by the content can also be any voices made by legitimate payment users. When it is determined that the identity characteristic information contained in the voice to be verified matches the identity characteristic information of the legal payment user, that is, the user currently performing the payment operation matches the legal payment user in at least one of gender and age.

Optionally, the standard payment voice may be a payment voice selected from the payment voice library of a legitimate payment user, and the standard payment voice may be selected by the user. Alternatively, each payment voice may correspond to a voice state. The user can query the corresponding payment voice in the payment voice database according to the voice status as the standard payment voice.

In one embodiment, a user inputs a keyword whose voice status is a cold, and the device queries a corresponding payment voice from a payment voice database according to the cold keyword, and determines the payment voice as a standard payment voice.

Among them, the identity information of the legitimate payment user and the standard payment voice are pre-entered data.

S130. If it is determined that the payment voice to be verified matches the standard payment voice, perform a payment operation matching the payment order.

In this embodiment, by comparing the voiceprint of the payment voice to be verified with the voiceprint of the standard payment voice, the acoustic feature parameters of the payment voice to be verified and the acoustic characteristic parameters of the standard payment voice can be selectively extracted and corresponding. Generate two feature vectors, calculate the distance between the two feature vectors, and use this distance as the similarity between the payment voice to be verified and the standard payment voice. When the similarity value is greater than a set threshold, determine the payment voice to be verified and the standard payment voice Matching, that is, the user currently performing the payment operation is a legitimate payment user. With payment authentication, the payment operation can be performed.

The method of judging whether the payment voice to be verified matches the standard payment voice can be selected according to actual needs or implementation effects.

In another optional implementation of this embodiment, before acquiring the payment voice to be verified associated with the payment order, the method may further include: when a voiceprint payment opening request is detected, providing an identity information registration interface, and by The aforementioned identity information registration interface obtains the identity characteristic information of the aforementioned legitimate payment user; or when detecting the voiceprint payment opening request, extracts the identity characteristic information of the aforementioned legitimate payment user contained in the pre-registered user file.

Optionally, to obtain the identity characteristic information of a legitimate payment user, a standard payment voice matching the identity characteristic information may be obtained according to the identity characteristic information, and based on the identity characteristic information of the legitimate payment user, and matched with the identity characteristic information Standard payment voice to determine whether the user currently performing the payment operation is a legitimate payment user. By obtaining the identity information of the user in advance when the voiceprint payment opening request is detected, the identity information of the user associated with the payment order can be quickly determined, and based on the identity information, whether the identity characteristic information corresponding to the payment voice is consistent Identification information of legitimate users, so as to efficiently screen for unqualified payment voices, reduce the data volume of subsequent voiceprint verification, and improve the efficiency of payment authentication.

In another optional implementation of this embodiment, before obtaining the payment voice to be verified associated with the payment order, the method may further include: when a voiceprint payment opening request is detected, obtaining a pre-registered face for performing face recognition. The identified standard user image; extracting the identity characteristic information of the aforementioned legitimate payment user contained in the aforementioned standard user image.

Alternatively, the way to obtain the identity characteristic information may further be to obtain the user's face image, and optionally, to train the feature information model of the face image to determine the user's identity characteristic information. Use the face recognition method to obtain the user's identity information, without the user's manual input, directly obtain the user's face image and perform face recognition, quickly and intelligently extract the identity information of the payment user, and improve user input Convenience of identity characteristics messages to improve user experience.

In another optional implementation of this embodiment, after identifying the identity characteristic information included in the payment voice to be verified, it may further include: if it is determined that the identified identity characteristic information and the identity characteristic of a legitimate payment user are determined If the information does not match, a password payment method input interface is provided to enable the user to complete the payment operation matching the payment order by entering the payment password; and / or if the identified identity information and the identity of the legitimate payment user are determined If the feature information does not match, a face image to be identified is collected, and when the aforementioned face image to be identified matches a pre-registered standard user image for face recognition, the payment is performed with the aforementioned payment. Order matching payment operation.

Optionally, the way to determine whether the face image to be recognized matches the pre-registered standard user image for face recognition may be to calculate the face image to be recognized and the standard user image. To determine the similarity of the image, it can be further judged by model-based methods (such as Hidden Markov Model, Active Shape Model or Active Appearance Model, etc.). When the identity information of the legitimate payment user does not match, the password payment or face recognition verification payment can be used to avoid the voiceprint recognition failure of the legitimate payment user and the payment operation cannot be performed to improve the accuracy of payment verification. .

In this embodiment, it is determined in advance whether the identity characteristic information identified by the payment voice to be verified matches the identity characteristic information of a legitimate payment user, and when the identified identity characteristic information matches the identity characteristic information of a legitimate payment user, it is judged again It is to be verified whether the payment voice and the standard payment voice match, to solve the problem of low payment identity authentication in related technologies, to ensure the security of payment, and to improve the efficiency of payment authentication.

Example two

FIG. 2 is a schematic structural diagram of a payment authentication device according to a second embodiment. As shown in FIG. 2, the aforementioned device includes: a payment voice recognition module 210 configured to acquire a payment voice to be verified associated with a payment order, and identify the identity characteristic information contained in the payment voice to be verified; a standard payment voice acquisition module 220, configured to obtain the standard payment voice of the legitimate payment user if it is determined that the identified identity characteristic information matches the identity characteristic information of the legitimate payment user; and the payment operation execution module 230 is configured to determine the aforementioned If the payment voice to be verified matches the standard payment voice, a payment operation matching the payment order is executed.

In this embodiment, it is determined in advance whether the identity characteristic information identified by the payment voice to be verified matches the identity characteristic information of a legitimate payment user, and when the identified identity characteristic information matches the identity characteristic information of a legitimate payment user, it is judged again It is to be verified whether the payment voice and the standard payment voice match, to solve the problem of low payment identity authentication in related technologies, to ensure the security of payment, and to improve the efficiency of payment authentication.

In one embodiment, the aforementioned payment speech recognition module 210 further includes: the aforementioned identity characteristic information includes at least one of gender and age.

In one embodiment, the payment voice recognition module 210 is further configured to: extract the acoustic characteristics of the payment voice to be verified according to the payment voice to be verified; perform the acoustic feature and at least two feature information models trained in advance By comparison, a feature information model matching the aforementioned acoustic feature is determined, and the feature information corresponding to the matched feature information model is used as the identity feature information.

In one embodiment, the aforementioned device further includes: a legal identity feature obtaining module 240 configured to provide an identity information registration interface when a voiceprint payment opening request is detected, and obtain the aforementioned legal payment through the identity information registration interface. The identity information of the user; or when the voiceprint payment opening request is detected, the identity information of the aforementioned legitimate payment user contained in the pre-registered user file is extracted.

In an embodiment, the aforementioned device further includes: a legitimate user image acquisition module 250 configured to acquire a pre-registered standard user image for face recognition when a voiceprint payment open request is detected. ; Extracting the identity characteristic information of the aforementioned legitimate payment user contained in the aforementioned standard user image.

In one embodiment, the aforementioned device further includes a mismatch payment module 260 configured to provide a password payment method input interface if it is determined that the identified identity characteristic information does not match the identity characteristic information of a legitimate payment user. To enable the user to complete the payment operation matching the payment order by entering a payment password; and / or if it is determined that the identified identity characteristic information does not match the identity characteristic information of a legitimate payment user, collect the person to be identified A face image, and when the aforementioned face image to be identified matches a pre-registered standard user image for performing face recognition, a payment operation matching the aforementioned payment order is performed.

In one embodiment, the aforementioned device further includes: a feature information model generation module 270 configured to obtain at least two standard payment voices, select any one of the standard payment voices, and extract the acoustic characteristics of the aforementioned standard payment voices; The identity information of the user corresponding to the payment voice and the acoustic characteristics of the aforementioned standard payment voice generate at least two feature information models.

The payment authentication device provided in this embodiment can execute the payment authentication method provided in any embodiment of the present invention, and has the corresponding function modules and functions for executing the payment authentication method.

Example three

FIG. 3 is a schematic structural diagram of a device according to a third embodiment. FIG. 3 shows a block diagram of an exemplary device 301 suitable for use in implementing embodiments of the present invention. The device 301 shown in FIG. 3 is only an example, and should not impose any limitation on the functions and scope of use of this embodiment.

As shown in FIG. 3, the device 301 is expressed in the form of a general-purpose computer device. The components of the device 301 may include, but are not limited to, one or more processors or processing units 302, a system memory 303, and a bus 304 connecting different system components (including the system memory 303 and the processing unit 302).

The bus 304 represents one or more of several types of bus structures, including a memory bus or a memory controller, a peripheral bus, a graphics acceleration port, a processor, or an area using any of a variety of bus structures. Bus. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MCA) bus, the enhanced ISA bus, and the Video Electronics Standards Association (Video) Electronics Standards Association (VESA) regional bus and Peripheral Component Interconnect (PCI) bus.

The device 301 contains various computer system-readable media. These media can be any available media that can be connected by the device 301, including volatile and non-volatile media, removable and non-removable media.

The system memory 303 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 305 and / or cache memory 306. The device 301 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 307 can be used to read and write non-removable, non-volatile magnetic media (not shown in FIG. 3 and is commonly referred to as a "hard drive"). Although not shown in Figure 3, disk drives are available for reading and writing to removable non-volatile disks (such as "floppy disks"), and removable non-volatile disks (such as CD-ROM) (Compact Disc Read-Only Memory (CD-ROM), Digital Video Disc-Read Only Memory (DVD-ROM) or other optical media). In these cases, each drive may be connected to the bus 304 through one or more data medium interfaces. The memory 303 may include at least one program product. The program product has a set (for example, at least one) of program modules, and the program modules are configured to perform functions of the embodiments of the present invention.

A program / utility tool 309 having a set (at least one) of program modules 308 may be stored in, for example, the memory 303. Such a program module 308 includes an operating system, one or more application programs, other program modules, and programs Data, each or some combination of these examples may include an implementation of the network environment. The program module 308 generally performs functions and / or methods in the embodiments described in the present invention.

The device 301 may also communicate with one or more external devices 310 (such as a keyboard, a sensing device, a display 311, etc.), and may further communicate with one or more devices that enable a user to interact with the device 301, and / or with Any device (such as a network card, modem, etc.) that enables the device 301 to communicate with one or more other computer devices. This communication can be performed through an input / output (I / O) interface 312. In addition, the device 301 can further use the network interface card 313 and one or more networks (such as a Local Area Network (LAN), a Wide Area Network (WAN), and / or a public network, such as Internet) communication. As shown in the figure, the network interface card 313 communicates with other modules of the device 301 through the bus 304. It should be understood that although not shown in FIG. 3, other hardware and / or software modules may be used in conjunction with the device 301, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, independent Redundant Arrays of Inexpensive Disks (RAID) systems, tape drives, and data backup storage systems.

The processing unit 302 executes various functional applications and data processing by running programs stored in the system memory 303, such as implementing a payment authentication method provided in this embodiment.

That is, when the foregoing processing unit executes the foregoing program, it realizes: acquiring the payment voice to be verified associated with the payment order, and identifying the identity characteristic information contained in the payment voice to be verified; if it is determined that the identified identity characteristic information is used for legitimate payment If the identity information of the user matches, the standard payment voice of the legitimate payment user is obtained. If it is determined that the payment voice to be verified matches the standard payment voice, a payment operation matching the payment order is performed.

Embodiment 4

This fourth embodiment further provides a computer-readable storage medium that stores a computer program that, when executed by a processor, implements a payment authentication method as provided by all embodiments of the present invention: obtaining a payment voice to be verified associated with a payment order, And identify the identity feature information contained in the aforementioned to-be-verified payment voice; if it is determined that the identified identity feature information matches the identity feature information of the legitimate payment user, then obtain the standard payment voice of the aforementioned legitimate payment user; If the payment voice to be verified matches the standard payment voice, a payment operation matching the payment order is executed.

The computer storage medium of this embodiment may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: electrical connections with one or more wires, portable computer diskettes, hard drives, RAM, read-only memory (Read Only Memory, ROM), Erasable Programmable Read Only Memory (EPROM), flash memory, optical fiber, portable CD-ROM, optical storage device, magnetic storage device, or any suitable device described above The combination. In this specification, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in combination with an instruction execution system, device, or device.

The computer-readable signal medium may include a data signal transmitted in a base band or transmitted as part of a carrier wave, which carries computer-readable code. The transmitted data signals can take many forms, including electromagnetic signals, optical signals, or any suitable combination of the foregoing. The computer-readable signal medium may further be any computer-readable medium other than a computer-readable storage medium, and the computer-readable medium may transmit, propagate, or transmit a program for use by or in connection with an instruction execution system, device, or device. .

The code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical cable, radio frequency (RF), etc., or any suitable combination of the foregoing.

The computer program code for performing the operations of the present invention may be written in one or more programming languages or combinations thereof. The aforementioned programming languages include object-oriented programming languages such as Java, Smalltalk, C ++, and further include conventional programmatic programming. Language, such as "C" or similar programming language. The code can run entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer, partly on a remote computer, or entirely on the remote computer or On the server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a LAN or WAN, or it can be connected to an external computer (such as through an Internet service provider) Internet connection).

[Industrial availability]

The payment authentication method provided by the present invention solves the problem of low efficiency of payment identity authentication in the related technology, ensures payment security, and improves the efficiency of payment authentication.

Claims (10)

    A payment authentication method, comprising: obtaining a payment voice to be verified associated with a payment order, and identifying the identity feature information contained in the payment voice to be verified; if the identified identity feature information is identified with a legitimate payment user If the identity characteristics of the information match, the standard payment voice of the legitimate payment user is obtained; and if it is determined that the payment voice to be verified matches the standard payment voice, a payment operation matching the payment order is performed.         The method described in item 1 of the scope of patent application, wherein the aforementioned identity characteristic information includes at least one of gender and age.         The method as described in item 1 or 2 of the scope of patent application, before obtaining the payment voice to be verified associated with the payment order, further includes: when a voiceprint payment opening request is detected, providing an identity message registration interface and borrowing The identity characteristic information of the legal payment user is obtained from the identity information registration interface; or when the voiceprint payment opening request is detected, the identity characteristic information of the legal payment user included in the pre-registered user file is extracted.         The method as described in item 1 or 2 of the patent application scope, wherein before obtaining the payment voice to be verified associated with the payment order, further comprising: obtaining a pre-registered person for performing the process when a voiceprint payment opening request is detected; Standard user image for face recognition; extracting the identity characteristic information of the aforementioned legitimate payment user contained in the aforementioned standard user image.         The method described in item 1 of the scope of patent application, wherein after identifying the identity characteristic information contained in the aforementioned to-be-verified payment voice, it further includes at least one of the following operations: if it is determined that the aforementioned identity characteristic information is identified and used for legitimate payment If the user ’s identity information does not match, a password payment method input interface is provided to enable the user to complete the payment operation matching the payment order by entering the payment password; and if the identified identity information is determined to be valid for a legitimate payment user If the identity characteristics of the images do not match, the face image to be identified is collected, and when the aforementioned face image to be identified matches a pre-registered standard user image for face recognition, the execution is performed with The aforementioned payment order matches the payment operation.         The method according to item 1 or 2 of the scope of the patent application, wherein the aforementioned identification characteristic information included in the payment voice to be verified includes: extracting the acoustic characteristics of the payment voice to be verified according to the payment voice to be verified; and The aforementioned acoustic feature is compared with at least two feature information models trained in advance, a feature information model matching the aforementioned acoustic feature is determined, and feature information corresponding to the matched feature information model is used as the aforementioned identity feature information.         The method described in item 6 of the scope of patent application, before obtaining the payment voice to be verified associated with the payment order, further comprises: obtaining at least two standard payment voices, selecting any one of the standard payment voices, and extracting the aforementioned standard payment voices And at least two feature information models based on the identity information of the user corresponding to the aforementioned standard payment voice and the acoustic features of the aforementioned standard payment voice.         A payment authentication device, comprising: a payment voice recognition module configured to obtain a payment voice to be verified associated with a payment order, and identify the identity characteristic information contained in the payment voice to be verified; a standard payment voice acquisition module Is configured to obtain the standard payment voice of the legitimate payment user if it is determined that the identified identity characteristic information matches the identity characteristic information of the legitimate payment user; and the payment operation execution module is configured to determine the aforementioned pending verification if it is determined If the payment voice matches the aforementioned standard payment voice, then a payment operation matching the aforementioned payment order is performed.         A device includes a memory, a processor, and a computer program stored on the memory and capable of running on the processor. The processor executes the program as described in any one of claims 1-7 when applying the foregoing program. Documented payment authentication method.         A computer-readable storage medium stores a computer program, wherein the program, when executed by a processor, implements a payment authentication method as described in any one of items 1-7 of the scope of patent application.