Method, device, electronic device and storage medium for processing biometric payment features

Abstract

The present application provides a method, device, electronic device and storage medium for processing biometric payment features; the method includes: receiving a verification request sent by a terminal, the verification request is used to request verification of whether there is an incorrect binding of the biometric payment feature; fusing multiple first facial features of the expenditure object to obtain a fused feature, the multiple first facial features are facial features obtained at different stages of the biometric payment registration stage of the expenditure object; comparing the fused feature with the second facial feature of the expenditure object to obtain a comparison result, the second facial feature is a facial feature obtained during the facial service registration stage of the expenditure object; generating a binding recognition result of the biometric payment feature based on the comparison result. Through this application, the accuracy and security of the use of biometric payment features can be improved.

Description

Technical Field

[0001] The present application relates to artificial intelligence technology, and in particular to a method, device, electronic device and storage medium for processing biometric payment features. Background Art

[0002] Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. Computer vision technology and speech technology are important technologies of artificial intelligence.

[0003] With the development and progress of smart terminal technology, people are increasingly accustomed to paying through biometric features (such as facial features, fingerprint features, palm print features, etc.). When users open biometric payment services, there is a risk of binding other users' biometric features, resulting in the theft of payment accounts, which reduces the security of payment. There is currently no good solution to determine whether a biometric feature is the user's own biometric feature. Summary of the invention

[0004] The embodiments of the present application provide a method, device, electronic device, computer-readable storage medium, and computer program product for processing biometric payment features, which can improve the accuracy and security of the biometric payment features during use.

[0005] The technical solution of the embodiment of the present application is implemented as follows:

[0006] The embodiment of the present application provides a method for processing a biometric payment feature, wherein the biometric payment feature is a biometric feature other than a facial feature, including:

[0007] A verification request sent by a receiving terminal is used to request verification of whether there is an incorrect binding of the biometric payment feature;

[0008] fusing a plurality of first facial features of the expenditure object to obtain a fused feature, wherein the plurality of first facial features are facial features obtained at different stages of the biometric payment registration phase of the expenditure object;

[0009] Comparing the fused feature with a second facial feature of the expenditure object to obtain a comparison result, wherein the second facial feature is a facial feature obtained during the facial service registration phase of the expenditure object;

[0010] A binding identification result of the biometric payment feature is generated based on the comparison result.

[0011] The embodiment of the present application provides a device for processing a biometric payment feature, wherein the biometric payment feature is a biometric feature other than a facial feature, and the device includes:

[0012] A request receiving module, used for receiving a verification request sent by a terminal, wherein the verification request is used for requesting verification of whether there is an incorrect binding situation of the biometric payment feature;

[0013] A feature fusion module, used for fusing multiple first facial features of the expenditure object to obtain a fusion feature, wherein the multiple first facial features are facial features obtained at different stages of the biometric payment registration stage of the expenditure object;

[0014] A feature comparison module, used for comparing the fused feature with a second facial feature of the expenditure object to obtain a comparison result, wherein the second facial feature is a facial feature obtained during the facial service registration phase of the expenditure object;

[0015] A result generating module is used to generate a binding recognition result of the biological payment feature based on the comparison result.

[0016] In some embodiments, the result generation module is used to determine that the fusion feature and the second facial feature belong to the same expenditure object when the comparison result indicates that the fusion feature matches the second facial feature, and generate a binding recognition result indicating that there is no incorrect binding of the biometric payment feature.

[0017] In some embodiments, the result generation module is used to query the face service database based on the fused feature when the comparison result indicates that the fused feature does not match the second face feature, wherein the face service database includes the following two types of parameters of the registered object of the face service: the object identifier of the registered object, and the registered face feature of the registered object;

[0018] When the registered face feature matching the fused feature is queried in the face service database, it is determined that the expenditure object has registered for the face service, and the object identifier of the registered face feature matching the fused feature is compared with the object identifier of the expenditure object;

[0019] When a consistent identification comparison result is obtained, it is determined that the fused feature and the second facial feature belong to the same expenditure object, and a binding recognition result is generated indicating that there is no incorrect binding of the biometric payment feature.

[0020] In some embodiments, the result generation module is used to call the manual customer service terminal to perform the following processing: prompting that there is no incorrect binding of the biometric payment feature, and guiding the expenditure object to verify the payment record of the electronic payment based on the biometric payment feature.

[0021] In some embodiments, the result generation module is used to query a face service database based on the fused feature when the comparison result indicates that the fused feature does not match the second face feature, wherein the face service database includes the following two types of parameters of the registered object: the object identifier of the registered object, and the registered face feature of the registered object;

[0022] When the registered face feature matching the fused feature is queried in the face service database, it is determined that the expenditure object has registered for the face service, and the object identifier of the registered face feature matching the fused feature is compared with the object identifier of the expenditure object;

[0023] When an inconsistent identification comparison result is obtained, it is determined that the fused feature and the second facial feature belong to different expenditure objects, and a binding recognition result is generated indicating that an erroneous binding situation exists in the biometric payment feature.

[0024] In some embodiments, the result generation module is used to call the manual customer service terminal to perform the following processing: prompting that there is an incorrect binding of the biometric payment feature, and guiding the spender to close the biometric payment service.

[0025] In some embodiments, a feature comparison module is used to obtain an object identifier of the expenditure object based on the verification request before comparing the fused feature with the second facial feature of the expenditure object;

[0026] Based on the identifier of the expenditure object, the face service database is queried, wherein the face service database includes the following two types of parameters of the registered object of the face service: the object identifier of the registered object, and the registered face feature of the registered object;

[0027] When the registered facial feature matching the second facial feature is found in the facial service database, the process proceeds to executing the process of comparing the fused feature with the second facial feature of the expenditure object.

[0028] In some embodiments, the feature comparison module is used to call the manual customer service terminal to perform the following processing when the registered facial feature that matches the second facial feature is not found in the facial service database: prompt the spender that the spender has not registered for the facial service, and guide the spender to register for the facial service and biometric payment service.

[0029] In some embodiments, the verification request carries an identity of the expenditure object in the mini-program, different identities are used to represent different expenditure objects in the mini-program, and the mini-program runs in the client of the terminal;

[0030] A feature comparison module, configured to query an identification database based on the identity identification, and use the object identification associated with the identity identification obtained through the query as the object identification of the expenditure object;

[0031] The identification database includes the following two types of parameters of the registered object: the identity identification of the registered object in the applet, and the object identification of the registered object in the client.

[0032] In some embodiments, the request receiving module is used to receive the biometric sent by the biometric payment device during the biometric registration phase before the verification request sent by the receiving terminal, wherein the biometric is obtained by collecting the biometric of the expenditure object and is collected by the biometric payment device when detecting the expenditure object;

[0033] Receive the object identifier of the payment object and the multiple first facial features sent by the biometric payment device, wherein the multiple first facial features are obtained by the biometric payment device from multiple facial images taken in the first link and the second link, and the multiple facial images are taken by the biometric payment device controlling the shooting device, the first link is a period of time after the biometric payment device first obtains the biometric feature, and the second link is a period of time after the biometric payment device starts to verify the payment object;

[0034] Storing the mapping relationship between the identifier of the payment object and the biometric feature in a biometric feature database, wherein the biometric feature database is used to verify the biometric payment feature of the payment object;

[0035] The multiple first facial features are stored in a facial feature database, wherein the facial feature database is used to store facial features of different expenditure objects in the biometric payment registration stage.

[0036] In some embodiments, the photographing device enters the first link after receiving a first photographing instruction sent by the biometric payment device. The first photographing instruction is sent by the biometric payment device when the biometric is first acquired, and is used to instruct the photographing device to perform periodic photographing in the first link and send at least two of the facial images obtained by photographing to the biometric payment device.

[0037] In some embodiments, a request receiving module is configured to query the biometric database based on the biometric when receiving the biometric sent by the biometric payment device, wherein the biometric database includes the biometric payment features of registered objects of the biometric payment service;

[0038] When the biometric feature of the expenditure object is not queried, it is determined that the expenditure object has not registered for the biometric payment service, and a graphic code for activating the biometric payment service is sent to the biometric payment device so that the biometric payment device displays the graphic code.

[0039] In some embodiments, the request receiving module is used to receive a verification notification sent by the terminal before receiving the object identifier of the payment object and the plurality of first facial features sent by the biometric payment device, wherein the verification notification indicates that the terminal has opened the biometric payment function interface by scanning the graphic code;

[0040] The verification notification is sent to the biometric payment device so that the biometric payment device sends a second shooting instruction to the shooting device, wherein the second shooting instruction is used to trigger the shooting device to enter the second link to perform periodic shooting, and send at least two facial images obtained by shooting to the biometric payment device.

[0041] In some embodiments, the request receiving module is used to receive the verification information sent by the terminal after the terminal opens the biometric payment function interface by scanning the graphic code;

[0042] When the verification information matches the verification information preset by the expenditure object, it is determined that the identity authentication of the expenditure object is passed, and an activation notification is sent to the terminal, wherein the activation notification indicates that the biometric payment function of the expenditure object has been activated.

[0043] In some embodiments, the graphic code carries at least one of the following parameters: a first timestamp and a first device identification of the biometric payment device, wherein the first timestamp corresponds to the time when the graphic code is generated;

[0044] a request receiving module, configured to receive a verification notification sent by the terminal based on the graphic code after the graphic code for activating the biometric payment service is sent to the biometric payment device so that the biometric payment device displays the graphic code, wherein the verification notification includes: a first device identifier of the biometric payment device and a second timestamp corresponding to the moment when the terminal scans the graphic code;

[0045] Obtaining the time interval between the first timestamp and the second timestamp, and comparing the first device identifier with the second device identifier, wherein the second device identifier is a pre-stored identifier of the biometric payment device;

[0046] In response to satisfying the verification condition, a biometric payment function interface is sent to the terminal so that the terminal displays the biometric payment function interface, wherein the verification condition is: the time interval is less than a set duration, and the first device identifier is the same as the second device identifier.

[0047] In some embodiments, the feature fusion module is used to obtain the weight value corresponding to each link in the biometric payment registration stage;

[0048] A weighted summation process is performed based on each of the first facial features and the weight value of the corresponding link to obtain a fusion feature.

[0049] An embodiment of the present application provides an electronic device, including:

[0050] A memory for storing computer executable instructions;

[0051] The processor is used to implement the method for processing the biometric payment features provided in the embodiment of the present application when executing the computer executable instructions stored in the memory.

[0052] An embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions for causing a processor to execute and implement the method for processing biometric payment features provided in the embodiment of the present application.

[0053] An embodiment of the present application provides a computer program product, including a computer program or computer executable instructions, which, when executed by a processor, can implement the method for processing biometric payment features provided in the embodiment of the present application.

[0054] The embodiments of the present application have the following beneficial effects:

[0055] The facial features of the payment object obtained at different stages of the biometric payment registration phase are fused to obtain fused features, which are compared with the second facial features that the payment object has registered, and the binding result of the biometric payment feature is determined based on the comparison result. By fusing the facial features obtained at different stages of the biometric payment registration phase, the accuracy of obtaining facial features is improved. By comparing the fused features with the second facial features, the accuracy and security of the use of biometric payment features can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a schematic diagram of an application mode of the method for processing biological payment features provided in an embodiment of the present application;

[0057] Figure 2 is a schematic diagram of the structure of the server 200 provided in an embodiment of the present application;

[0058] FIG. 3A to FIG. 3J It is a flowchart of a method for processing a biometric payment feature provided in an embodiment of the present application;

[0059] Figure 4A It is a schematic diagram of the process of opening a biometric payment service provided in an embodiment of the present application;

[0060] Figure 4B is a schematic diagram of an activation interface provided in an embodiment of the present application;

[0061] Figure 4C is a schematic diagram of a biometric payment device provided in an embodiment of the present application;

[0062] FIG. 5A to FIG. 5C It is an optional flow chart of the method for processing biometric payment features provided in the embodiment of the present application. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0064] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0065] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0066] It should be pointed out that in the embodiments of the present application, related data such as user information and user feedback data are involved. When the embodiments of the present application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0067] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0068] Before further describing the embodiments of the present application in detail, the nouns and terms involved in the embodiments of the present application are explained. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations.

[0069] 1) Palm scanning, the process of identifying identity information through palm print recognition technology, can identify the identity information of different users based on the image of the palm print area.

[0070] 2) User information (UIN) represents the unique identity ID of the user using the instant messaging client. If the user has registered for the instant messaging client face service, then based on the user's facial feature data, the corresponding UIN can be queried in the server background corresponding to the instant messaging client, and the user's identity can be confirmed based on the UIN.

[0071] 3) Open Identity (OpenId) is the identity of an object (e.g., a user) for a mini program or public account. The same object has different identities when using different mini programs (e.g., user A uses mini programs 1 and 2, has open identity ID1 for mini program 1, and open identity ID2 for mini program 2; user B uses mini program 1 and has open identity ID3). The object using the mini program can be identified through the open identity.

[0072] The embodiments of the present application provide a method for processing biometric payment features, a device for processing biometric payment features, an electronic device, a computer-readable storage medium, and a computer program product, which can improve the accuracy and security of the biometric payment features during use.

[0073] The following describes an exemplary application of the electronic device provided by the embodiment of the present application. The electronic device provided by the embodiment of the present application can be implemented as various types of user terminals such as a laptop computer, a tablet computer, a desktop computer, a set-top box, a mobile device (for example, a mobile phone, a portable music player, a personal digital assistant, a dedicated messaging device, a portable gaming device), and a vehicle-mounted terminal, and can also be implemented as a server. The following describes an exemplary application when the device is implemented as a server.

[0074] refer to Figure 1 , Figure 11 is a schematic diagram of an application mode of a method for processing a biometric payment feature provided in an embodiment of the present application; it is applied to a terminal device 400-1, a terminal device 400-2, and a server 200. The server 200 communicates with the terminal devices 400-1 and 400-2 through a network 300.

[0075] For example, the server 200 is a server of a payment platform, the terminal device 400-1 is a mobile phone used by a user, the terminal device 400-1 is a biometric payment device, and the biometric feature may be an iris feature, a fingerprint feature, or a palm print feature. For example, the terminal device 400-1 is a palm payment device, and the biometric feature is a palm print feature. The above examples are used for explanation in the embodiments of the present application.

[0076] For example, the user can scan the graphic code (graphic code for opening the biometric payment service) displayed on the palm payment device through the terminal device 400-1, and the terminal device 400-1 sends an activation request to the server 200 based on the graphic code, and the activation request includes the user's identity. The user shows the palm and face to the terminal device 400-2, and the terminal device 400-2 takes the palm image and multiple face images, and sends the face image and palm image to the server 200 through the network 300. The server 200 extracts the palm print feature from the palm image. Based on the user's identity, the server 200 obtains the second face feature collected when the user registers for the payment service on the payment platform, and extracts multiple first face features from the multiple face images, and fuses the multiple first face features to obtain a fused feature. The fused feature and the second face feature are compared to obtain a comparison result, and the binding recognition result of the palm print feature is determined based on the comparison result. When the fused feature does not match the second face feature, it means that the palm print feature is not the palm print feature of the user who registered the payment service, and the user is prompted that the binding is wrong. Through the above method, the accuracy of binding biometric payment features is improved, and the security of payment through biometric features is improved.

[0077] The embodiment of the present application can be implemented through blockchain technology. The binding identification result of the embodiment of the present application can be used as the test result, and the test result can be uploaded to the blockchain for storage, and the reliability of the test result can be guaranteed by the consensus algorithm. Blockchain is a new application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods, each of which contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, the platform product service layer, and the application service layer.

[0078] The embodiments of the present application can be implemented through database technology. In short, a database can be regarded as an electronic file cabinet where electronic files are stored. Users can add, query, update, delete, etc. data in the files. The so-called "database" is a collection of data that is stored together in a certain way, can be shared with multiple users, has as little redundancy as possible, and is independent of the application program.

[0079] A database management system (DBMS) is a computer software system designed for managing databases, and generally has basic functions such as storage, retrieval, security, and backup. A database management system can be classified according to the database model it supports, such as relational, XML (Extensible Markup Language); or according to the type of computer it supports, such as server clusters, mobile phones; or according to the query language used, such as Structured Query Language (SQL), XQuery; or according to performance impulse focus, such as maximum scale, maximum operating speed; or other classification methods. In some embodiments, regardless of which classification method is used as exemplified above, the database management system is able to manage databases across categories, for example, supporting multiple query languages ​​at the same time.

[0080] In some embodiments, the server may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal device may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a car terminal, etc., but is not limited thereto. The terminal device and the server may be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiments of the present application.

[0081] The embodiments of the present application can also be implemented through cloud technology. Cloud technology is a general term for network technology, information technology, integration technology, management platform technology, application technology, etc. based on the cloud computing business model application. It can form a resource pool, which is used on demand and is flexible and convenient. Cloud computing technology will become an important support. The background services of the technical network system require a large amount of computing and storage resources, such as video websites, picture websites and more portal websites. With the high development and application of the Internet industry, as well as the promotion of search services, social networks, mobile commerce and open collaboration, each item may have its own hash code identification mark in the future, and all need to be transmitted to the background system for logical processing. Data of different levels will be processed separately, and all kinds of industry data require strong system backing support, which can only be achieved through cloud computing.

[0082] refer to Figure 2 , Figure 2 is a schematic diagram of the structure of the server 200 provided in an embodiment of the present application, Figure 2 The server 200 shown includes: at least one processor 410, a memory 450, and at least one network interface 420. The various components in the terminal device 400 are coupled together through a bus system 440. It can be understood that the bus system 440 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 440 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, Figure 2 Various buses are labeled as bus system 440 .

[0083] Processor 410 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., where the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0084] The memory 450 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard disk drives, optical disk drives, etc. The memory 450 may optionally include one or more storage devices that are physically remote from the processor 410.

[0085] The memory 450 includes a volatile memory or a non-volatile memory, and may also include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), and the volatile memory may be a random access memory (RAM). The memory 450 described in the embodiments of the present application is intended to include any suitable type of memory.

[0086] In some embodiments, memory 450 can store data to support various operations, examples of which include programs, modules, and data structures, or a subset or superset thereof, as exemplarily described below.

[0087] Operating system 451, including system programs for processing various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks;

[0088] A network communication module 452, used to reach other electronic devices via one or more (wired or wireless) network interfaces, exemplary network interfaces include: Bluetooth, Wireless Compatibility Authentication (WiFi), and Universal Serial Bus (USB), etc.;

[0089] In some embodiments, the virtual scene dialogue processing device provided in the embodiments of the present application can be implemented in a software manner. Figure 2 The dialog processing device 455 of the virtual scene stored in the memory 450 is shown, which can be software in the form of a program and a plug-in, etc., including the following software modules: a dialog generation module 4551 and a quality detection module 4552. These modules are logical, so they can be arbitrarily combined or further split according to the functions implemented. The functions of each module will be explained below.

[0090] The method for processing biometric payment features provided in the embodiment of the present application will be explained in combination with the exemplary application and implementation of the terminal device provided in the embodiment of the present application.

[0091] refer to Figure 3A , Figure 3A This is a flow chart of the method for processing the biometric payment feature provided in the embodiment of the present application. The following is a server as the execution subject. Figure 3A The steps shown are explained.

[0092] For example, the biometric payment feature is a biometric feature other than a facial feature. The biometric feature may be a palm print feature, a fingerprint feature, or an iris feature. In the embodiment of the present application, the palm print feature is taken as an example for explanation.

[0093] In step 301, a verification request sent by a terminal is received.

[0094] For example, the verification request is used to request verification of whether there is an incorrect binding of the biometric payment feature, that is, whether there is a binding relationship between the biometric payment feature and the object identifier (UIN) of other expenditure objects that are not bound to the biometric feature. For example: Account B belongs to user B, and user A binds palm print A to account B through a palm swiping device. Palm print A does not belong to the account holder user B, and the binding is wrong. Then, it can be determined through verification whether the user binds the palm print to the payment account belonging to the user.

[0095] Combination Figure 1 To illustrate, the terminal device 400-1 sends a verification request. The terminal device 400-1 may be a mobile phone, and the user may log in to the instant messaging client through the mobile phone and send a verification request through the swiping payment applet or the official account in the client.

[0096] For example, in the application stage, the spending user may be a real user; in the stage of testing the biometric payment service, the spending user may be a virtual object, such as a user simulation program.

[0097] In some embodiments, reference Figure 3B , Figure 3B It is a flow chart of the method for processing biometric payment features provided in an embodiment of the present application. In the biometric registration stage before step 301, the mapping relationship between the identifier of the payment object and the biometric feature is stored through the following steps 3011 to 3014, which are described in detail below.

[0098] In step 3011, a biometric characteristic sent by a biometric payment device is received.

[0099] Combination Figure 1 For illustration, the biometric payment device is terminal device 400-2, which has a built-in camera for collecting images corresponding to the biometrics, such as a palm swiping device. At the same time, terminal device 400-2 is also provided with a camera (built-in or external) for collecting facial images.

[0100] For example, the biometric feature is obtained by collecting the biometric feature of the payment object, and is collected by the biometric payment device when the payment object is detected. For example: when the biometric payment device detects the payment object, it collects an image and extracts the biometric feature from the collected image. Figure 4A , Figure 4AThis is a schematic diagram of the process of opening a biometric payment service provided by an embodiment of the present application. When the user shows his palm (with the palm facing the biometric payment device), the biometric payment device 401A records the palm (collects a palm image), and performs palm print recognition on the collected palm image to obtain a palm print recognition result (for example: extracting an image corresponding to a specific palm print pattern from the palm image as a palm print recognition result).

[0101] In some embodiments, reference Figure 3C , Figure 3C It is a flow chart of the method for processing biometric payment features provided in an embodiment of the present application. When executing step 3011, the graphic code for activating the biometric payment service can be displayed through the following steps 3021 to 3022, which are described in detail below.

[0102] In step 3021, a biometric database is queried based on the biometrics.

[0103] Here, the biometric database includes the biometric payment features of the registered objects of the biometric payment service. The registered objects refer to the objects that have opened the biometric payment service.

[0104] In step 3022, when the biometric characteristics of the expenditure object are not queried, it is determined that the expenditure object has not registered for the biometric payment service, and a graphic code for activating the biometric payment service is sent to the biometric payment device so that the biometric payment device displays the graphic code.

[0105] For example, graphic codes such as QR codes, continue to refer to Figure 4A , the activation code 402A is displayed in the human-machine interaction interface 403A of the biometric payment device 401A. The user can scan the activation code through the instant messaging client in the terminal device, open the palm-swiping applet, and activate the biometric payment service.

[0106] In some embodiments, the graphic code carries at least one of the following parameters: a first timestamp and a first device identifier of a biometric payment device, wherein the first timestamp corresponds to the time when the graphic code is generated. Figure 3D , Figure 3D It is a flow chart of the method for processing biometric payment features provided in an embodiment of the present application. After step 3022, an interface for activating the biometric payment function is displayed to the terminal through steps 3023 to 3025, which is described in detail below.

[0107] In step 3023, the receiving terminal sends a verification notification based on the graphic code.

[0108] For example, the verification notification includes: a first device identification of the biometric payment device, and a second timestamp corresponding to the time when the terminal scans the graphic code. Figure 1 To illustrate, the user scans the graphic code displayed in the terminal device 400-2 through the instant messaging client of the terminal device 400-1, and the terminal device 400-1 generates a verification notification based on the graphic code and sends the verification notification to the server 200. The verification notification carries a second timestamp when the verification notification is sent, and the second timestamp corresponds to the time when the terminal device 400-1 scans the graphic code.

[0109] In step 3024, the time interval between the first timestamp and the second timestamp is obtained, and the first device identifier is compared with the second device identifier.

[0110] For example, the second device identifier is a pre-stored identifier of a biometric payment device. When the first device identifier is the same as the second device identifier, it is determined that the user has activated the biometric payment service by scanning the activation code displayed by the biometric payment device.

[0111] In step 3025, in response to the verification condition being met, a biometric payment function interface is sent to the terminal so that the terminal displays the biometric payment function interface.

[0112] For example, the verification condition is: the time interval is less than the set time length, and the first device identifier is the same as the second device identifier. The set time length is, for example, 30 seconds.

[0113] For example, if the user does not scan the graphic code within the set time, the graphic code will automatically expire, and the user cannot open the biometric payment function interface by scanning the same graphic code again. The user can obtain a new graphic code by refreshing the graphic code of the biometric payment device and scan the new graphic code to enter the biometric payment function interface. Figure 4B , Figure 4B 4 is a schematic diagram of an activation interface provided by an embodiment of the present application; a user logs in to the mini program using a terminal device, and a confirmation option 403B is displayed in the activation interface 401B of the mini program, and the user confirms whether to agree to the corresponding agreement of the payment server and whether to activate the biometric payment service. After the user confirms to activate the biometric payment service, a second confirmation option 402B is displayed to allow the user to confirm again that the palm (biometric feature) belongs to the real-name identity. After the user confirms the second time, a prompt message "Already activated" is displayed.

[0114] Continue to refer Figure 3B In step 3012, an object identifier of a payment object and a plurality of first facial features sent by a biometric payment device are received.

[0115] For example, the multiple first facial features are obtained by the biometric payment device from multiple facial images periodically taken in the first link and the second link, and the multiple facial images are taken by the biometric payment device controlling the shooting device.

[0116] In some embodiments, reference Figure 3E , Figure 3E It is a flow chart of the method for processing biometric payment features provided in an embodiment of the present application. Before step 3012, multiple first facial features are obtained through the following steps 30121 to 30122.

[0117] In step 30121, a verification notification is received from the terminal.

[0118] For example, the verification notification indicates that the terminal has opened the biometric payment function interface (for example, a small program with a biometric payment function) by scanning a graphic code.

[0119] In some embodiments, after the terminal opens the biometric payment function interface by scanning a graphic code, the terminal receives verification information (e.g., payment password, query password, etc.) sent by the terminal; when the verification information matches the verification information pre-set by the expenditure object, it is determined that the identity authentication of the expenditure object is passed, and an activation notification is sent to the terminal (e.g., a small program in the terminal's client), wherein the activation notification indicates that the biometric payment function of the expenditure object has been activated. Figure 1 To explain, the terminal device 400-1 sends the payment password to the server 200, and the server 200 verifies whether the password is correct. If the verification is successful, the server 200 sends a prompt message indicating that the verification is successful to the terminal device 400-1, and the small program of the terminal device 400-1 displays the verification success.

[0120] In step 30122, a verification notification is sent to the biometric payment device so that the biometric payment device sends a second shooting instruction to the shooting device.

[0121] Here, the second shooting instruction is used to trigger the shooting device to enter the second stage to perform periodic shooting, and send at least two facial images obtained by the shooting to the biometric payment device.

[0122] For example, the first stage is a period of time after the biometric payment device first obtains the biometric feature, and the second stage is a period of time after the biometric payment device begins to verify the payment object (verification method, such as payment password verification). Periodic shooting, for example, taking a picture every 1 second to obtain a face image.

[0123] refer to Figure 4CWhen the user successfully scans through the terminal device 403C, the biometric payment device 401C sends a second shooting instruction to the face camera 402C, and the biometric payment device 401C shoots the user's face 406C through the face camera 402C.

[0124] Continue to refer Figure 3B In step 3013, the mapping relationship between the payment object's identifier and the biometric feature is stored in the biometric feature database.

[0125] Here, the biometric database is used to verify the biometric payment feature of the expenditure object. The identifier of the payment object can be an open identity identifier, and the same payment object can have different open identity identifiers for different biometric payment applets.

[0126] In step 3014, the plurality of first facial features are stored in a facial feature database.

[0127] For example, the facial feature database is used to store facial features of different payment objects during the biometric payment registration phase. The facial feature database and the biometric feature database can be independent databases or integrated into one database.

[0128] At the same time, after the shooting phase is completed, the biometric payment device sends a shutdown command to the shooting device to save power.

[0129] In some embodiments, the photographing device enters the first stage after receiving the first photographing instruction sent by the biometric payment device. The first photographing instruction is sent when the biometric payment device first obtains the biometric feature, and is used to instruct the photographing device to periodically photograph in the first stage and send the photographed at least two face images to the biometric payment device. For example, refer to Figure 4C , Figure 4C 4 is a schematic diagram of a biometric payment device provided in an embodiment of the present application. When the user successfully records his / her palm, the face camera 402C receives a first shooting instruction, the biometric payment device 401C continuously shoots the user's hand 405C, and the biometric payment device 401C shoots the user's face 406C through the face camera 402C.

[0130] Continue to refer Figure 3A In step 302, multiple first facial features of the expenditure object are fused to obtain a fused feature.

[0131] For example, in the electronic payment scenario after the application is launched on the client, the object can be a real user; in the payment test scenario during the client development process, the expenditure object can be a user simulation program, which can simulate the user's biometric features and simulate the user's operations in the client.

[0132] For example, multiple first facial features are facial features obtained at different stages of the biometric payment registration stage of the expenditure object; the first facial feature and the second facial feature are only used to distinguish different features, and do not specifically refer to a certain feature.

[0133] In some embodiments, reference Figure 3F , Figure 3F It is a flowchart of the method for processing biometric payment features provided in an embodiment of the present application. Step 302 can be implemented through the following steps 3026 and 3027, which are described in detail below.

[0134] In step 3026, the weight values ​​corresponding to each link in the biometric payment registration stage are obtained.

[0135] For example, the weight value corresponding to each link can be determined by any of the following methods:

[0136] Method 1: Allocate the same weight to each link. For example, 10 images are taken, 4 in the first link and 6 in the second link. A first facial feature is extracted from the images in each link, and the weight value corresponding to each first facial feature is 0.1.

[0137] Method 2: Determine the weight according to the degree of change in the position of the face in each link. The link with a greater degree of position change has a smaller weight. For example: obtain each face image of the first link, compare each face image to determine the face position change Z1 of the first link, obtain each face image of the second link, and compare each face image to determine the face position change Z2 of the second link. Based on the size of the facial position change, assign a corresponding weight to the first face feature of each link, and the facial position change is negatively correlated with the weight.

[0138] In step 3027, a weighted sum process is performed based on each first facial feature and the weight value of the corresponding link to obtain a fusion feature.

[0139] For example, multiple first facial features are facial features obtained at different stages in the biological payment registration phase of the expenditure object, including the first stage and the second stage. Based on the weight value corresponding to each stage, each first facial feature is weighted and summed to obtain a fusion feature.

[0140] In an embodiment of the present application, by acquiring facial images of different links in the process of opening a biometric payment service, facial features are extracted based on the facial images, and the facial features are fused, the accuracy of acquiring facial features is improved, and the fused features can be accurately compared with the second facial features to determine the binding result of the biometric features, thereby improving the security of payments based on biometrics.

[0141] Continue to refer Figure 3A In step 303, the fused feature is compared with the second facial feature of the expenditure object to obtain a comparison result.

[0142] Here, the second facial feature is the facial feature obtained during the facial service registration phase of the expenditure object.

[0143] For example, the comparison can be implemented in the following manner to obtain the similarity between the fused feature and the second facial feature: Both the fused feature and the second facial feature can be represented in vector form, and the cosine similarity between the two can be obtained as the comparison result.

[0144] In some embodiments, reference Figure 3G , Figure 3G It is a flowchart of the method for processing biometric payment features provided in an embodiment of the present application. Before step 303, steps 3031 to 3033 are executed, which are described in detail below.

[0145] In step 3031, the object identifier of the expenditure object is obtained based on the verification request.

[0146] In some embodiments, the verification request carries the identity of the expenditure object in the mini-program with biometric payment function, and different identity identifiers are used to represent different expenditure objects in the mini-program, and the mini-program runs in the instant messaging client of the terminal.

[0147] Step 3031 is implemented in the following manner: querying the identification database based on the identity identifier, and using the object identifier associated with the identity identifier obtained by the query as the object identifier of the expenditure object; wherein the identification database includes the following two types of parameters of the registered object: the identity identifier of the registered object in the mini program, for example: the open identity identifier OpenId; the object identifier of the registered object in the client, for example: user information (UIN, User INformation).

[0148] For example, the identification database includes a mapping relationship between an open identity OpenId and user information UIN, and the user information UIN can be obtained based on the open identity OpenId.

[0149] In step 3032, the face service database is queried based on the identifier of the expenditure object.

[0150] For example, the face service database includes the following two types of parameters of the registered objects of the face service: the object identifier of the registered object, and the registered face features of the registered object. The registered face features are the face features obtained during the face service registration phase of the object. Face service registration refers to registering for services that require face recognition, such as face payment services, binding face features to accounts, etc.

[0151] In step 3033, when a registered facial feature matching the second facial feature is found in the facial service database, the process proceeds to step 303.

[0152] In some embodiments, when no registered facial feature matching the second facial feature is found in the facial service database, it indicates that the user has neither activated the facial service nor the biometric payment service, and the manual customer service terminal is called to perform the following processing: prompting the spender that the spender has not registered for the facial service, and guiding the spender to register for the facial service and the biometric payment service.

[0153] In step 304, a binding recognition result of the biometric payment feature is generated based on the comparison result.

[0154] In some embodiments, reference Figure 3H , Figure 3H It is a flowchart of the method for processing biometric payment features provided in an embodiment of the present application. Step 304 can be implemented through step 3041H, which is described in detail below.

[0155] In step 3041H, when the comparison result indicates that the fusion feature matches the second facial feature, it is determined that the fusion feature and the second facial feature belong to the same expenditure object, and a binding identification result is generated indicating that there is no incorrect binding of the biometric payment feature.

[0156] For example, when the similarity between the second facial feature and the fused feature is greater than the similarity threshold, the second facial feature matches the fused feature, and it can be determined that there is no incorrect binding of the biometric payment feature.

[0157] In some embodiments, reference Fig. 3I , Fig. 3I It is a flowchart of the method for processing biometric payment features provided in an embodiment of the present application. Step 304 can be implemented through steps 3041I to 3043I, which are described in detail below.

[0158] In step 3041I, when the comparison result indicates that the fused feature does not match the second facial feature, the facial service database is queried based on the fused feature.

[0159] For example, the face service database includes the following two types of parameters of the registered (face service) objects of the face service: the object identifier of the registered object, and the registered face features of the registered object (the registered face features are the face features obtained during the face service registration phase of the object).

[0160] For example: if the fusion feature corresponding to user A does not match the second facial feature of the facial service activated by the instant messaging client used by user A, further query is conducted in the facial server database based on the fusion feature to determine whether the fusion feature belongs to other objects that have registered for the facial service.

[0161] In step 3042I, when a registered facial feature matching the fused feature is queried in the facial service database, it is determined that the expenditure object has registered for the facial service, and the object identifier of the registered facial feature matching the fused feature is compared with the object identifier of the expenditure object.

[0162] For example, continuing with the above example, when the fusion feature of user A matches the registered facial feature, it is determined that user A has registered for the facial service, and the object identifier UIN of user A and the object identifier UIN associated with the registered facial feature are compared.

[0163] In step 3043I, when a consistent identification comparison result is obtained, it is determined that the fused feature and the second facial feature belong to the same expenditure object, and a binding recognition result is generated indicating that there is no incorrect binding of the biometric payment feature.

[0164] For example, we continue to explain based on the above example. When the two UINs are the same, it means that the fused feature and the second facial feature belong to the same expenditure object. There is no binding recognition result of the biometric payment feature with incorrect binding. In actual applications, there may be a situation where a user has registered for facial services on mini-programs on different terminals at the same time. When the fused feature does not match the second facial feature, the accuracy of the comparison result is improved by comparing the registered facial features of the registered user and the UIN, thereby improving the accuracy of determining the binding result.

[0165] In some embodiments, a manual customer service terminal may be called to perform the following processing: prompting that there is no incorrect binding of the biometric payment feature, and guiding the expenditure object to verify the payment record of the electronic payment based on the biometric payment feature.

[0166] For example, when there is no incorrect binding of the biometric payment feature, the manual customer service terminal can guide the user to query the payment record to determine the security of the electronic payment.

[0167] In some embodiments, reference Figure 3J , Figure 3J It is a flowchart of the method for processing biometric payment features provided in an embodiment of the present application. Step 304 can be implemented through steps 3041J to 3043J, which are described in detail below.

[0168] In step 3041J, when the comparison result indicates that the fused feature does not match the second facial feature, the facial service database is queried based on the fused feature.

[0169] For example, the face service database includes the following two types of parameters of the registered (face service) object: the object identifier of the registered object, and the registered face features of the registered object. The registered face features are the face features obtained during the face service registration phase of the object. The execution of step 3041J is the same as step 3041I, and will not be repeated here.

[0170] In step 3042J, when a registered facial feature matching the fused feature is queried in the facial service database, it is determined that the expenditure object has registered for the facial service, and the object identifier of the registered facial feature matching the fused feature is compared with the object identifier of the expenditure object.

[0171] For example, the execution of step 3042J is the same as step 3042I, which will not be repeated here.

[0172] In step 3043J, when an inconsistent identification comparison result is obtained, it is determined that the fused feature and the second facial feature belong to different expenditure objects, and a binding recognition result is generated indicating that an incorrect binding situation exists in the biometric payment feature.

[0173] For example, when the UIN comparison result is inconsistent, it means that the fused feature does not belong to the registered user, nor to the binding recognition result based on the user who has opened the face server based on the terminal device, and there is an incorrect binding situation.

[0174] In some embodiments, the manual customer service terminal is called to perform the following processing: prompting that there is an error in binding the biometric payment feature, and guiding the payee to close the biometric payment service. Since there is a binding error, the user is guided to close the biometric payment service, and the user can re-bind the biometric feature after closing the biometric payment service.

[0175] The embodiment of the present application fuses the facial features obtained by the payment object at different stages in the biometric payment registration stage to obtain a fused feature, compares the fused feature with the second facial feature that the payment object has registered, and determines the binding result of the biometric payment feature based on the comparison result. By fusing the facial features obtained at different stages in the biometric payment registration stage, the accuracy of obtaining the facial features is improved, and by comparing the fused feature with the second facial feature, the accuracy of binding the biometric payment feature is improved, thereby improving the security of the payment object using the biometric payment feature for payment.

[0176] Below, an exemplary application of the method for processing biometric payment features provided in an embodiment of the present application in an actual application scenario will be described.

[0177] Biometric payment is becoming increasingly popular. Users can pay by swiping their palms, faces, fingerprints, etc. In the process of activating the biometric payment service, for example: User A identifies the biometrics on the biometric payment device. After the biometrics are successfully identified, User A can scan the graphic code displayed on the screen of the biometric payment device through the terminal device, and complete the biometric payment registration by punching in the mini program in the terminal device.

[0178] In some cases, user A who performs registration for biometric payment service may not be the user who logs into the payment account in the terminal device. For example, user A steals user B's terminal device to scan the graphic code and binds his own biometric feature; or, when queuing to register for biometric payment service, user B accidentally scans the activation code, and the biometric payment device recognizes user A's biometric feature, resulting in a binding error. User A swiped his palm to make a purchase on a certain payment device, but the money of user B was deducted. In the related art, the accuracy of binding biometric payment features is not high, which affects the security of payment through biometric features. The method for processing biometric payment features provided in the embodiment of the present application can use face recognition to compare the fusion features of the facial features (the first facial features above) obtained in different links in the biometric payment registration stage with the facial features (the second facial features above) obtained in the face service registration stage to determine the binding recognition result of the biometric payment feature, thereby improving the accuracy of binding the biometric payment feature.

[0179] For example, the biometric feature may be a palm print feature, an iris feature, a fingerprint feature, etc., and the palm print feature is used as an example for explanation in the implementation of this application. The biometric payment device may be a palm swiping device, which includes a built-in camera and an external face camera, wherein the built-in camera is used to capture a palm image, and the face camera is used to capture a face image.

[0180] During the palm print recognition process, the face camera is used to shoot the user facing the palm swiping user to obtain a face image. Based on the face image, the facial features of the user who has completed the palm swiping can be identified. After the user completes the registration and activation process, the palm swiping device immediately transmits the face image obtained by the face camera to the server. The server compares the facial features of the retrieved registered user and the facial features extracted from the face image. In this way, the device user in the palm swiping registration scenario can be effectively identified through the face, confirming that the user operating the palm swiping device is the same user as the user who registered for the palm swiping payment service, which can solve the problem of incorrect binding of user identity information.

[0181] refer to Figure 5A , Figure 5A53A is an optional flow chart of the method for processing biometric payment features provided in the embodiment of the present application, involving a palm-swiping device 531A, a face camera 532A, a server 533A, and a palm-swiping applet 534A (corresponding to a terminal device). The server 533A may be a server of an instant messaging payment platform. The server 533A is Figure 2 A specific implementation of the server 200.

[0182] The user shows his palm to the palm scanning device 531A, and the palm scanning device 531A executes step 501A and sends an opening instruction to turn on the face camera to prepare for collection. The palm scanning device 531A includes a built-in camera for photographing the palm print area of ​​the palm.

[0183] For example, for the palm scanning device 531A, the face camera 532A is an external camera. This is because the face camera shoots the face, while the palm scanning device shoots the palm, and there is a difference in the shooting positions of the two. In order to facilitate facial shooting, the face camera is set outside the palm scanning device.

[0184] In some embodiments, for an iris feature payment device, the face camera may be disposed inside the iris feature payment device. For a fingerprint feature payment device, the face camera may be disposed outside the fingerprint feature payment device.

[0185] The palm scanning device 531A executes step 502A, continues to perform palm print recognition, and obtains a palm print recognition result.

[0186] For example, the palm scanning device 531A obtains the palm image through the built-in camera, referring to Figure 4A , Figure 4A The biometric payment device 401A inputs the palm (collects the palm image), and performs palm print recognition on the collected palm image to obtain the palm print recognition result.

[0187] The palm scanning device 531A executes step 503A and plays a prompt tone indicating successful palm print recognition.

[0188] The palm scanning device 531A executes step 504A to extract palm print features from the palm print recognition result.

[0189] The palm-swiping device 531A executes step 505A and sends a first shooting instruction to enable the facial camera to obtain a first facial image.

[0190] For example, the first and second are only used to distinguish the names. The facial camera 532A may acquire the first facial image by acquiring 5 frames of images within 5 seconds before receiving the first shooting instruction, and acquiring 1 frame every 1 second. For the acquired first facial image, facial features are extracted based on the facial recognition algorithm, and the facial features are uploaded to the server 533A.

[0191] refer to Figure 4C , Figure 4C 401C is a schematic diagram of a biometric payment device provided in an embodiment of the present application. When the user successfully records his / her palm, the biometric payment device 401C continuously photographs the user's hand 405C, and the biometric payment device 401C photographs the user's face 406C through the face camera 402C.

[0192] The palm scanning device 531A executes step 506A to submit the palm print features to the server.

[0193] For example, steps 505A to 506A may be performed simultaneously.

[0194] The facial camera 532A executes step 507A and sends the collected first facial image to the palm scanning device 531A.

[0195] The server 533A executes step 508A to continue palm print feature recognition.

[0196] The server 533A executes step 509A, and returns an activation code if the palm print feature has not been activated for the palm scanning service. The activation code is returned to the palm scanning device 531A.

[0197] The palm-swiping device 531A executes step 510A and displays the activation code.

[0198] For example, the activation code carries security information such as the device serial number and timestamp. The user can scan the activation code through the instant messaging client. The terminal device sends the user's UIN to the server 533A based on the activation code to verify the pass of the current palm-swiping registration process. The verification can be achieved in the following way: the first timestamp carried by the activation code has a pre-set specified time, and the second timestamp of the scanning moment when the user scans the activation code through the terminal device is obtained, and the time length between the first timestamp and the second timestamp is obtained. Based on the time length, it is determined whether the scanning is successful within the specified time. If the scanning is successful, the palm-swiping device information is identified according to the device serial number (the unique identifier of each palm-swiping device). When the palm-swiping device information is the same as the device information stored in the palm-swiping service backend of the instant messaging client, it is determined that the verification is passed.

[0199] Continue to refer Figure 4A, the activation code 402A is displayed in the human-machine interaction interface 403A of the biometric payment device 401A. The user can scan the activation code through the instant messaging client in the terminal device to open the palm-swiping applet 534A.

[0200] If the code is scanned successfully, the Shua Palm mini program 534A executes step 511A to inform the server (server 200) that the user has successfully opened the mini program.

[0201] Server 533A executes step 512A to inform the device (palm-swiping device 531A) that the user has successfully opened the mini-program.

[0202] The palm-swiping device 531A executes step 513A and sends a second shooting instruction to enable the facial camera to obtain a second facial image.

[0203] refer to Figure 4C When the user successfully scans through the terminal device 403C, the biometric payment device 401C captures the user's face 406C through the face camera 402C.

[0204] For example, steps 511A to 513A may be performed simultaneously.

[0205] The facial camera 532A executes step 514A and sends the captured second facial image.

[0206] The user can enter the payment password in the ShuaPal applet 534A and confirm that it is his or her real-name information. The user enters his or her payment password and confirms whether it is his or her real-name information. The ShuaPal applet confirms that the person operating the ShuaPal applet is himself or herself based on the payment password, and submits an activation request to the server (the activation request includes the user's UIN information, device serial number, and timestamp). The user needs to enter his or her payment password in the ShuaPal applet. After the input is completed, the ShuaPal applet will send a request to activate the ShuaPal backend. The information carried mainly includes the device serial number, the user's UIN, etc. Based on the user's UIN information, the server stores the user's corresponding palm print features, palm images, and facial images according to the UIN.

[0207] Example, reference Figure 4B , Figure 4B 4 is a schematic diagram of an activation interface provided by an embodiment of the present application; a user logs in to the mini program using a terminal device, and a confirmation option 403B is displayed in the activation interface 401B of the mini program, and the user confirms whether to agree to the corresponding agreement of the payment server and whether to activate the payment service. After the user confirms to activate the payment service, a second confirmation option 402B is displayed to allow the user to confirm again that the palm belongs to the real-name identity. After the user confirms twice, a prompt message "Already activated" is displayed.

[0208] Continue to refer Figure 5A , the shuazhang applet 534A executes step 515A and submits an activation request to the server.

[0209] For example, after the user confirms, the palm-swiping applet will send a request to the server 533A to activate palm-swiping payment. The information carried in the request includes: the terminal device serial number and the user's OpenId.

[0210] Server 533A executes step 516A to notify the mini program that the palm-swipe payment service has been successfully activated, and simultaneously executes step 517A to inform the palm-swipe device that the user has successfully activated the palm-swipe payment service.

[0211] The palm-swiping applet 534A executes step 518A and displays the result of successful activation.

[0212] The palm-swiping device 531A executes step 519A to extract facial features from the first facial image and the second facial image.

[0213] The palm-swiping device 531A executes step 520A and submits the corresponding facial features to the server.

[0214] For example, after the facial features collected during the palm-swiping registration stage are submitted to the server, the server can obtain the facial features of the user collected during the password payment service registration stage based on the user's identity identifier, and compare the facial features of the two stages. If the facial feature comparison result is a different face, it means that the binding is incorrect.

[0215] The palm scanning device 531A executes step 521A and sends a close instruction to turn off the face camera.

[0216] In some embodiments, steps 519 to 520A may be executed after step 514A and before the user enters the payment password. Server 533A compares facial features at different stages to determine whether the binding is incorrect, and sends palm prints or user error prompts in advance to prevent users from binding incorrect palm print features.

[0217] refer to Figure 5B , Figure 5B This is an optional flow chart of the method for processing biometric payment features provided in the embodiment of the present application. In the user registration stage, steps 501B to 503B are executed. Steps 501B to 503B can be obtained by Figure 5A The steps in are implemented and will not be repeated here.

[0218] Step 501B, collecting the facial image of the registered user through the facial camera.

[0219] Step 502B, extracting registered facial features.

[0220] Step 503B, saving the facial image and registered facial features to the server.

[0221] At the stage where customer complaints regarding incorrect binding of personal information on the ShuaPal account occur, that is, at the stage where complaints are received from customers (ie, users) regarding incorrect binding of personal information on the ShuaPal account, execute steps 504B to 511B.

[0222] Step 504B, query the identity of the customer complainant.

[0223] For example, users (customer complainants) can make complaint feedback through official accounts, mini-programs and other channels. The feedback information includes the open identity (OpenId) of the customer's instant messaging client, and the UIN of the instant messaging client is determined based on the open identity.

[0224] Step 505B, determine whether the user has registered for the face service. If the judgment result of step 505B is no, execute step 508B to send the on-site photo to the manual customer service terminal. If the judgment result of step 505B is yes, execute step 506B to compare the registered face features with the on-site face features (face features extracted based on the on-site photo).

[0225] For example, in the above step 508B, the on-site photo is sent to the manual customer service terminal so that the manual customer service can perform manual identification processing based on the on-site photo (the face image mentioned above). A payment platform can correspond to multiple manual customer service terminals, and the manual customer service terminal that receives the on-site photo can be determined in the following way: obtain the number of tasks to be processed by each manual customer service terminal, and send the on-site photo to the manual customer service terminal with the least number of tasks to be processed.

[0226] For example, the instant messaging-based client UIN queries the server to see if the facial service has been registered. Facial services include facial payment services and account binding facial features. If the user has registered for the facial service, the facial fusion features collected when the user registered for the palm swiping service are compared with the facial features of the user registered for the facial service to confirm whether they are the same person. If they are the same person, it means that the information is not misbound and there is no palm swiping payment error. The manual customer service staff intervenes through the manual customer service terminal to guide the user to confirm again (for example: confirm payment of the bill, etc.).

[0227] For example, the facial service has been explained above. The facial service can be a facial feature payment service (face recognition service), an account binding facial feature, etc. For example, a user may activate the face recognition service before registering by swiping his palm, and the facial feature data matching the current user's UIN will be stored in the server's database.

[0228] If the comparison result of step 506B is the same person, step 511B is executed to confirm that it is not a mistaken binding, and a prompt message is sent to the manual customer service terminal. If the comparison result of step 506B is not the same person, step 507B is executed to determine whether the facial features of the person on site are the features of a registered user.

[0229] For example, in the above step 511B, the prompt information of non-mis-binding is sent to the manual customer service terminal, the manual customer service terminal displays the prompt information, and the manual customer service using the manual customer service terminal can follow up and handle it.

[0230] When the result of step 507B is that the user is not registered, step 508B is executed to send the on-site photo to the manual customer service terminal. Step 508B has been explained above and will not be repeated here. When the result of step 507B is that the user is registered, step 509B is executed to determine whether the user UINs corresponding to the two features are the same.

[0231] For example, if the feature comparison result shows that they are not the same person, the facial fusion features obtained when the user registered by swiping his palm are used to search the facial database of registered users to determine whether the user has registered for the facial service. If not, it means that the server has no way to determine whether the person swiping his palm is the user who complained based on the user's facial information. At this time, manual customer service intervention is required.

[0232] When the judgment result of step 509B is that the UIN is inconsistent, step 510B is executed to confirm that it is an erroneous binding and display a prompt message. The prompt message is used to guide the user to close the erroneously activated palm-swiping service. When the judgment result of step 509B is that the UIN is consistent, step 511B is executed to confirm that it is not an erroneous binding and send a prompt message to the manual customer service terminal. Step 511B has been explained above and will not be repeated here.

[0233] For example, if the comparison result is that the face service has been registered, the UIN corresponding to the face feature is compared with the UIN of the user's own instant messaging client to see if they are consistent. If the UINs are consistent, it means that the user's non-personal information is mistakenly bound, and there is no wrong money deducted from the palm payment. At this time, the manual customer service intervenes to guide the user to confirm again (pay the bill, etc.). If the UIN comparison is inconsistent, it means that the user has indeed bound the wrong information, and the customer service system can directly prompt and guide the user to close the palm payment service that was mistakenly activated.

[0234] Through the above-mentioned scheme, the embodiment of the present application can effectively identify the situation where the user’s palm-swiping service is incorrectly bound, saving the process required to handle the incorrect binding, and thus can improve the security of users using biometrics for payment.

[0235] In some embodiments, reference Figure 5C , Figure 5CIt is an optional flow chart of the method for processing biometric payment features provided in the embodiment of the present application. Figure 5C Expressed through interactive flow charts Figure 5B Steps 504B to 511B in the embodiment involve a user terminal 531C, an instant messaging server 532C, a face matching server 533C, and a manual customer service terminal 534C. Figure 5A The server 533A in the embodiment includes an instant messaging server 532C and a face matching server 533C. The user terminal 531C is Figure 1 The terminal device 400-1 in.

[0236] The user terminal 531C executes step 501C and initiates a wrong binding customer complaint request.

[0237] The instant messaging server 532C executes step 502C to determine the UIN according to the user identity.

[0238] The instant messaging server 532C executes step 503C and sends the UIN to the face comparison server 533C.

[0239] The face comparison server 533C executes step 504C to determine whether the user has registered for the face service.

[0240] The face comparison server 533C executes step 505C to determine that the user has not registered for the face service, and synchronizes the information to the manual service terminal 534C.

[0241] The face comparison server 533C executes step 506C to fuse the facial features corresponding to the on-site photo to obtain facial fusion features.

[0242] The face comparison server 533C executes step 507C to compare the registered face features with the face features of the person on site.

[0243] The face comparison server 533C executes step 508C, and the comparison result is the same, so it is determined that it is not a mistaken binding.

[0244] The face comparison server 533C executes step 509C to determine whether the face fusion features corresponding to the scene photo have been registered for the face service.

[0245] In some embodiments, the user may register two accounts with face service enabled. The face feature-UIN database is queried based on the face fusion features corresponding to the on-site photo. If there is a matching face feature, it is determined that the face feature corresponding to the on-site photo has registered the face service. Step 509C can avoid the situation where the user registers two instant messaging client accounts and misbinds.

[0246] For example, a user receives a payment notification in the instant messaging client A, but believes that he has not made a palm print payment on the instant messaging client A. The reason for the customer complaint is that he has never made a palm print payment on the instant messaging client A.

[0247] Through step 509C, the UIN corresponding to the facial fusion feature corresponding to the user's on-site photo is compared with the UIN corresponding to the facial feature of the customer complaint user registered for the facial service. The result is that the UINs are inconsistent, which means that the user actually has two instant messaging client numbers A and B, and both have activated palm payment. That is, when the user bound the palm print payment, he mistakenly bound the palm print service of the instant messaging client number B to the instant messaging client number A, resulting in the instant messaging client number A receiving the payment notification after the user used the instant messaging client number B to make a payment.

[0248] The face comparison server 533C executes step 510C, and sends the on-site photo to the manual customer service terminal 534C without registration. The principle of step 510C is the same as that of step 508B above, and will not be repeated here.

[0249] The face comparison server 533C executes step 512C to determine whether the user UINs of the two features are the same.

[0250] The face comparison server 533C executes step 513C, and if the UINs are consistent, a prompt message is sent to the manual customer service terminal 534C. The principle of step 513C is the same as that of step 511B, and will not be repeated here.

[0251] The face comparison server 533C executes step 514C, and if the UINs are inconsistent, a prompt message is sent to the user terminal 531C. The user terminal 531C displays the received prompt message, which is used to guide the user to close the mistakenly activated palm scanning service.

[0252] For example, the face comparison server sends a prompt message to the terminal device, guiding the user to close the palm-scanning service that was mistakenly activated. The public account of the instant messaging client or the customer service system corresponding to the customer service will actively guide the user to close the palm-scanning service that was mistakenly activated.

[0253] The embodiments of the present application collect and compare facial features to effectively identify device users in the palm-swiping registration scenario, confirming that the person who operates and activates the palm-swiping device is the same user who completes the subsequent registration and activation process on the mobile phone. This can more smoothly solve the problem of incorrect binding of user identity information, improve the efficiency of repairing customer complaints, and thereby improve the security of biometric payment.

[0254] The following is a description of an exemplary structure of a software module implemented as a processing device 455 for biometric payment features provided in an embodiment of the present application. In some embodiments, for example, Figure 2 As shown, the software modules in the biometric payment feature processing device 455 stored in the memory 450 may include: a request receiving module 4551, used to receive a verification request sent by the terminal, wherein the verification request is used to request verification of whether there is an incorrect binding situation of the biometric payment feature; a feature fusion module 4552, used to fuse multiple first facial features of the expenditure object to obtain a fused feature, wherein the multiple first facial features are facial features obtained at different links in the biometric payment registration stage of the expenditure object; a feature comparison module 4553, used to compare the fused feature with the second facial feature of the expenditure object to obtain a comparison result, wherein the second facial feature is a facial feature obtained in the facial service registration stage of the expenditure object; a result generation module 4554, used to generate a binding recognition result of the biometric payment feature based on the comparison result.

[0255] In some embodiments, the result generation module 4554 is used to determine that the fused feature and the second facial feature belong to the same expenditure object when the comparison result indicates that the fused feature matches the second facial feature, and to generate a binding recognition result indicating that there is no incorrect binding of the biometric payment feature.

[0256] In some embodiments, the result generation module 4554 is used to query the face service database based on the fused feature when the comparison result indicates that the fused feature does not match the second facial feature, wherein the face service database includes the following two types of parameters of the registered objects of the face service: the object identifier of the registered object and the registered facial feature of the registered object; when a registered facial feature matching the fused feature is queried in the face service database, it is determined that the expenditure object has registered for the face service, and the object identifier of the registered facial feature matching the fused feature is compared with the object identifier of the expenditure object; when a consistent identifier comparison result is obtained, it is determined that the fused feature and the second facial feature belong to the same expenditure object, and a binding recognition result is generated indicating that there is no incorrect binding of the biometric payment feature.

[0257] In some embodiments, the result generation module 4554 is used to call the manual customer service terminal to perform the following processing: prompt that there is no incorrect binding of the biometric payment feature, and guide the expenditure object to verify the payment record of the electronic payment based on the biometric payment feature.

[0258] In some embodiments, the result generation module 4554 is used to query the face service database based on the fused feature when the comparison result indicates that the fused feature does not match the second facial feature, wherein the face service database includes the following two types of parameters of the registered object: the object identifier of the registered object and the registered facial feature of the registered object; when a registered facial feature matching the fused feature is queried in the face service database, it is determined that the expenditure object has registered for the facial service, and the object identifier of the registered facial feature matching the fused feature is compared with the object identifier of the expenditure object; when an inconsistent identifier comparison result is obtained, it is determined that the fused feature and the second facial feature belong to different expenditure objects, and a binding recognition result is generated indicating that there is an incorrect binding situation of the biometric payment feature.

[0259] In some embodiments, the result generation module 4554 is used to call the manual customer service terminal to perform the following processing: prompt that there is an incorrect binding of the biometric payment feature, and guide the payee to close the biometric payment service.

[0260] In some embodiments, the feature comparison module 4553 is used to obtain the object identification of the expenditure object based on the verification request before comparing the fused feature with the second facial feature of the expenditure object; query the face service database based on the identification of the expenditure object, wherein the face service database includes the following two types of parameters of the registered objects of the face service: the object identification of the registered object, and the registered facial feature of the registered object; when a registered facial feature matching the second facial feature is queried in the face service database, it proceeds to execute the processing of comparing the fused feature with the second facial feature.

[0261] In some embodiments, the feature comparison module 4553 is used to call the manual customer service terminal to perform the following processing when no registered facial feature matching the second facial feature is found in the facial service database: prompting the payee that the payee has not registered for the facial service, and guiding the payee to register for the facial service and the biometric payment service.

[0262] In some embodiments, the verification request carries the identity of the expenditure object in the mini program, and different identity identifiers are used to represent different expenditure objects in the mini program, and the mini program runs in the client of the terminal; the feature comparison module 4553 is used to query the identification database based on the identity identifier, and use the object identifier associated with the identity identifier obtained by the query as the object identifier of the expenditure object; wherein, the identification database includes the following two types of parameters of the registered object: the identity identifier of the registered object in the mini program, and the object identifier of the registered object in the client.

[0263] In some embodiments, the request receiving module 4551 is used to receive the biometric characteristics sent by the biometric payment device in the biometric registration stage before the verification request sent by the receiving terminal, wherein the biometric characteristics are obtained by collecting the biometric characteristics of the expenditure object and the expenditure object, and are collected by the biometric payment device when the expenditure object is detected; receive the object identification of the payment object sent by the biometric payment device and multiple first facial features, wherein the multiple first facial features are obtained by the biometric payment device from multiple facial images taken in the first link and the second link, and the multiple facial images are taken by the biometric payment device controlling the shooting device, the first link is a period of time after the biometric payment device first obtains the biometric characteristics, and the second link is a period of time after the biometric payment device starts to verify the expenditure object; store the mapping relationship between the identification of the payment object and the biometric characteristics in the biometric database, wherein the biometric database is used to verify the biometric payment characteristics of the expenditure object; store the multiple first facial features in the facial feature database, wherein the facial feature database is used to store the facial features of different expenditure objects in the biometric payment registration stage.

[0264] In some embodiments, the photographing device enters the first stage after receiving a first photographing instruction sent by a biometric payment device. The first photographing instruction is sent when the biometric payment device obtains the biometric for the first time, and is used to instruct the photographing device to take periodic photos in the first stage and send at least two facial images taken to the biometric payment device.

[0265] In some embodiments, the request receiving module 4551 is used to query the biometric database based on the biometric when receiving the biometric sent by the biometric payment device, wherein the biometric database includes the biometric payment characteristics of the registered objects of the biometric payment service; when the biometric characteristics of the expenditure object are not queried, it is determined that the expenditure object has not yet registered for the biometric payment service, and a graphic code for activating the biometric payment service is sent to the biometric payment device, so that the biometric payment device displays the graphic code.

[0266] In some embodiments, the request receiving module 4551 is used to receive a verification notification sent by the terminal before receiving the object identifier of the payment object and multiple first facial features sent by the biometric payment device, wherein the verification notification indicates that the terminal has opened the biometric payment function interface by scanning a graphic code; and send a verification notification to the biometric payment device so that the biometric payment device sends a second shooting instruction to the shooting device, wherein the second shooting instruction is used to trigger the shooting device to enter the second stage for periodic shooting, and send at least two facial images captured to the biometric payment device.

[0267] In some embodiments, the request receiving module 4551 is used to receive verification information sent by the terminal after the terminal opens the biometric payment function interface by scanning a graphic code; when the verification information matches the verification information pre-set by the expenditure object, it is determined that the identity authentication of the expenditure object is passed, and an activation notification is sent to the terminal, wherein the activation notification indicates that the biometric payment function of the expenditure object has been activated.

[0268] In some embodiments, the graphic code carries at least one of the following parameters: a first timestamp and a first device identifier of a biometric payment device, wherein the first timestamp corresponds to the time when the graphic code is generated; a request receiving module 4551 is used to receive a verification notification sent by the terminal based on the graphic code after sending a graphic code for activating a biometric payment service to the biometric payment device so that the biometric payment device displays the graphic code, wherein the verification notification includes: the first device identifier of the biometric payment device, and a second timestamp corresponding to the time when the terminal scans the graphic code; obtaining the time interval between the first timestamp and the second timestamp, and comparing the first device identifier with the second device identifier, wherein the second device identifier is a pre-stored identifier of a biometric payment device; in response to satisfying the verification condition, sending a biometric payment function interface to the terminal so that the terminal displays the biometric payment function interface, wherein the verification condition is: the time interval is less than the set duration, and the first device identifier is the same as the second device identifier.

[0269] In some embodiments, the feature fusion module 4552 is used to obtain the weight values ​​corresponding to each link in the biometric payment registration stage; and perform weighted summation processing based on each first facial feature and the weight value of the corresponding link to obtain a fused feature.

[0270] The embodiment of the present application provides a computer program product, which includes a computer program or a computer executable instruction, and the computer program or the computer executable instruction is stored in a computer readable storage medium. The processor of the computer device reads the computer executable instruction from the computer readable storage medium, and the processor executes the computer executable instruction, so that the computer device executes the above-mentioned method for processing the biometric payment feature in the embodiment of the present application.

[0271] The present application embodiment provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the processor will execute the method for processing the biometric payment feature provided in the present application embodiment, for example, Figure 3A A method for processing a biometric payment feature is shown.

[0272] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface storage, optical disk, or CD-ROM; or it may be various devices including one or any combination of the above memories.

[0273] In some embodiments, computer executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0274] As an example, computer-executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file storing other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0275] As an example, computer executable instructions may be deployed to be executed on one electronic device, or on multiple electronic devices located at one site, or on multiple electronic devices distributed at multiple sites and interconnected by a communication network.

[0276] In summary, through the embodiment of the present application, the facial features obtained by the payment object at different stages in the biometric payment registration stage are fused to obtain fused features, and the fused features are compared with the second facial features that the payment object has registered, and the binding result of the biometric payment feature is determined based on the comparison result. By fusing the facial features obtained at different stages in the biometric payment registration stage, the accuracy of obtaining facial features is improved, and by comparing the fused features with the second facial features, the accuracy of binding the biometric payment feature is improved, thereby improving the security of the payment object using the biometric payment feature for payment.

[0277] The above is only an embodiment of the present application and is not intended to limit the protection scope of the present application. Any modifications, equivalent substitutions and improvements made within the spirit and scope of the present application are included in the protection scope of the present application.

Claims

1. A method for processing biometric payment features, characterized in that: The biometric payment feature is a biometric feature other than a facial feature, and the method includes: A verification request sent by a receiving terminal is used to request verification of whether there is an incorrect binding of the biometric payment feature; Obtaining a weight value corresponding to each link in the biometric payment registration stage, wherein the weight value of each link is determined according to the degree of change in the position of the face in the face image of each link, and the degree of position change is negatively correlated with the weight; Performing weighted sum processing based on each first facial feature and the weight value of the corresponding link to obtain a fusion feature, wherein the multiple first facial features are facial features obtained at different links in the biological payment registration stage of the expenditure object; Comparing the fused feature with a second facial feature of the expenditure object to obtain a comparison result, wherein the second facial feature is a facial feature obtained during the facial service registration phase of the expenditure object; A binding identification result of the biometric payment feature is generated based on the comparison result.

2. The method according to claim 1, characterized in that The generating the binding recognition result of the biometric payment feature based on the comparison result includes: When the comparison result indicates that the fusion feature matches the second facial feature, it is determined that the fusion feature and the second facial feature belong to the same expenditure object, and a binding recognition result is generated indicating that there is no incorrect binding of the biometric payment feature.

3. The method according to claim 1, characterized in that The generating the binding recognition result of the biometric payment feature based on the comparison result includes: When the comparison result indicates that the fused feature does not match the second facial feature, querying a facial service database based on the fused feature, wherein the facial service database includes the following two types of parameters of a registered object of facial service: an object identifier of the registered object, and a registered facial feature of the registered object; When the registered face feature matching the fused feature is queried in the face service database, it is determined that the expenditure object has registered for the face service, and the object identifier of the registered face feature matching the fused feature is compared with the object identifier of the expenditure object; When a consistent identification comparison result is obtained, it is determined that the fused feature and the second facial feature belong to the same expenditure object, and a binding recognition result is generated indicating that there is no incorrect binding of the biometric payment feature.

4. The method according to claim 2 or 3, characterized in that: The method further comprises: The manual customer service terminal is called to perform the following processing: prompting that there is no incorrect binding of the biometric payment feature, and guiding the expenditure object to verify the payment record of the electronic payment based on the biometric payment feature.

5. The method according to claim 1, characterized in that The generating the binding recognition result of the biometric payment feature based on the comparison result includes: When the comparison result indicates that the fused feature does not match the second facial feature, querying a facial service database based on the fused feature, wherein the facial service database includes the following two types of parameters of the registered object: an object identifier of the registered object, and a registered facial feature of the registered object; When the registered face feature matching the fused feature is queried in the face service database, it is determined that the expenditure object has registered for the face service, and the object identifier of the registered face feature matching the fused feature is compared with the object identifier of the expenditure object; When an inconsistent identification comparison result is obtained, it is determined that the fused feature and the second facial feature belong to different expenditure objects, and a binding recognition result is generated indicating that an erroneous binding situation exists in the biometric payment feature.

6. The method according to claim 5, characterized in that The method further comprises: The manual customer service terminal is called to perform the following processing: prompting that there is an incorrect binding of the biometric payment feature, and guiding the spender to close the biometric payment service.

7. The method according to claim 1, characterized in that Before comparing the fused feature with the second facial feature of the expenditure object, the method further includes: Obtaining an object identifier of the expenditure object based on the verification request; Based on the identifier of the expenditure object, the face service database is queried, wherein the face service database includes the following two types of parameters of the registered object of the face service: the object identifier of the registered object, and the registered face feature of the registered object; When the registered facial feature matching the second facial feature is found in the facial service database, the process proceeds to executing the process of comparing the fused feature with the second facial feature of the expenditure object.

8. The method according to claim 7, characterized in that When the registered facial feature matching the second facial feature is not found in the facial service database, the method further includes: Call the manual customer service terminal to perform the following processing: prompt the spender that the spender has not registered for the facial service, and guide the spender to register for the facial service and biometric payment service.

9. The method according to claim 7, characterized in that: The verification request carries the identity of the expenditure object in the mini-program, and different identity identifiers are used to represent different expenditure objects in the mini-program, and the mini-program runs in the client of the terminal; The obtaining the object identifier of the expenditure object based on the verification request includes: Based on the identity identifier, the identification database is queried and the object identifier associated with the identity identifier is used as the object identifier of the expenditure object; wherein the identification database includes the following two types of parameters of the registered object: the identity identifier of the registered object in the mini program, and the object identifier of the registered object in the client.

10. The method according to claim 1, characterized in that In the biometric registration phase before the verification request sent by the receiving terminal, the method further includes: Receiving the biometric characteristic sent by the biometric characteristic payment device, wherein the biometric characteristic is obtained by collecting the biometric characteristic of the expenditure object and is collected by the biometric characteristic payment device when detecting the expenditure object; Receive the object identifier of the payment object and the multiple first facial features sent by the biometric payment device, wherein the multiple first facial features are obtained by the biometric payment device from multiple facial images taken in the first link and the second link, and the multiple facial images are taken by the biometric payment device controlling the shooting device, the first link is a period of time after the biometric payment device first obtains the biometric feature, and the second link is a period of time after the biometric payment device starts to verify the payment object; Storing the mapping relationship between the identifier of the payment object and the biometric feature in a biometric feature database, wherein the biometric feature database is used to verify the biometric payment feature of the payment object; The multiple first facial features are stored in a facial feature database, wherein the facial feature database is used to store facial features of different expenditure objects in the biometric payment registration stage.

11. The method according to claim 10, characterized in that The shooting device enters the first link after receiving the first shooting instruction sent by the biometric payment device. The first shooting instruction is sent by the biometric payment device when the biometric is first acquired. It is used to instruct the shooting device to take pictures periodically in the first link and send at least two facial images taken to the biometric payment device.

12. The method according to claim 10, characterized in that When receiving the biometric sent by the biometric payment device, the method further includes: querying the biometric database based on the biometric characteristic, wherein the biometric database includes biometric payment characteristics of registered subjects of the biometric payment service; When the biometric feature of the expenditure object is not queried, it is determined that the expenditure object has not registered for the biometric payment service, and a graphic code for activating the biometric payment service is sent to the biometric payment device so that the biometric payment device displays the graphic code.

13. The method according to claim 12, characterized in that Before receiving the object identifier of the payment object and the plurality of first facial features sent by the biometric payment device, the method further includes: Receiving a verification notification sent by the terminal, wherein the verification notification indicates that the terminal has opened a biometric payment function interface by scanning the graphic code; The verification notification is sent to the biometric payment device so that the biometric payment device sends a second shooting instruction to the shooting device, wherein the second shooting instruction is used to trigger the shooting device to enter the second link to perform periodic shooting, and send at least two facial images obtained by shooting to the biometric payment device.

14. The method according to claim 13, characterized in that After the terminal opens the biometric payment function interface by scanning the graphic code, the method further includes: Receiving verification information sent by the terminal; When the verification information matches the verification information preset by the expenditure object, it is determined that the identity authentication of the expenditure object is passed, and an activation notification is sent to the terminal, wherein the activation notification indicates that the biometric payment function of the expenditure object has been activated.

15. The method according to claim 12, characterized in that The graphic code carries at least one of the following parameters: a first timestamp and a first device identification of the biometric payment device, wherein the first timestamp corresponds to the time when the graphic code is generated; After sending the graphic code for opening the biometric payment service to the biometric payment device so that the biometric payment device displays the graphic code, the method further includes: Receiving a verification notification sent by the terminal based on the graphic code, wherein the verification notification includes: a first device identifier of the biometric payment device and a second timestamp corresponding to the moment when the terminal scans the graphic code; Obtaining the time interval between the first timestamp and the second timestamp, and comparing the first device identifier with the second device identifier, wherein the second device identifier is a pre-stored identifier of the biometric payment device; In response to satisfying the verification condition, a biometric payment function interface is sent to the terminal so that the terminal displays the biometric payment function interface, wherein the verification condition is: the time interval is less than a set duration, and the first device identifier is the same as the second device identifier.

16. A device for processing biometric payment features, characterized in that: The biometric payment feature is a biometric feature other than a facial feature, and the device includes: A request receiving module, used for receiving a verification request sent by a terminal, wherein the verification request is used for requesting verification of whether there is an incorrect binding situation of the biometric payment feature; A feature fusion module is used to obtain the weight value corresponding to each link in the biometric payment registration stage, wherein the weight value of each link is determined according to the degree of change of the position of the face in the face image of each link, and the degree of position change is negatively correlated with the weight; based on each first facial feature and the weight value of the corresponding link, a weighted summation process is performed to obtain a fusion feature, wherein the multiple first facial features are facial features obtained at different links in the biometric payment registration stage of the expenditure object; A feature comparison module, used for comparing the fused feature with a second facial feature of the expenditure object to obtain a comparison result, wherein the second facial feature is a facial feature obtained during the facial service registration phase of the expenditure object; A result generating module is used to generate a binding recognition result of the biological payment feature based on the comparison result.

17. An electronic device, characterized in that: The electronic device comprises: A memory for storing computer executable instructions; A processor, configured to implement the method for processing biometric payment features as described in any one of claims 1 to 15 when executing computer executable instructions stored in the memory.

18. A computer-readable storage medium storing computer-executable instructions, characterized in that: When the computer executable instructions are executed by a processor, the method for processing the biometric payment features described in any one of claims 1 to 15 is implemented.

19. A computer program product comprising a computer program or computer executable instructions, characterized in that: When the computer program or computer executable instructions are executed by a processor, the method for processing the biometric payment features described in any one of claims 1 to 15 is implemented.

Images