Payment method based on face recognition, apparatus, electronic device and storage medium

HK40073127BActive Publication Date: 2026-08-28TENCENT TECHNOLOGY (SHENZHEN) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
HK42022062166
Authority / Receiving Office
HK · HK
Patent Type
Patents
Current Assignee / Owner
Filing Date
2022-10-14
Publication Date
2026-08-28

AI Technical Summary

Technical Problem

Existing facial recognition payment methods suffer from issues such as large data volumes, user habits, and privacy concerns. Furthermore, payment code methods require multiple steps and are not effectively integrated with facial recognition technology.

Method used

Near-field communication (NFC) is used to quickly transmit billing data, and facial recognition technology is combined to detect facial similarity, reducing the amount of data comparison and enabling fast payment.

Benefits of technology

It improves the efficiency of facial recognition payment, provides a new payment method, reduces user operation steps, and enhances the convenience and security of payment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000000_0000_ABST
    Figure 00000000_0000_ABST
Patent Text Reader

Abstract

Embodiments of the present application disclose a payment method and device based on face recognition, electronic equipment and storage medium; when it is detected that the distance between the target face recognition device meets the preset distance range, the near field communication connection between the target face recognition device is established; the auxiliary payment data is obtained from the target face recognition device through the near field communication connection, the auxiliary payment data includes the bill data and the face data collected by the target face recognition device; the face data is determined as the to-be-detected face data of the current user of the mobile terminal, the reference face data of the current user of the mobile terminal is obtained; the face similarity detection is performed based on the to-be-detected face data and the reference face data; if it is detected that the face corresponding to the to-be-detected face data is the face of the current user, the payment operation is performed based on the bill data. The scheme can quickly transfer the bill data through the near field communication connection, and efficiently perform the payment in combination with the face recognition technology.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of computer technology, and more specifically to a payment method, device, electronic device, and storage medium based on facial recognition. Background Technology

[0002] Facial recognition is a biometric technology that identifies individuals based on their facial features. It involves using cameras or webcams to capture images or video streams containing faces, automatically detecting faces within the images, and then performing facial recognition on the detected faces. This technology is also commonly referred to as portrait recognition, face recognition, or facial identification.

[0003] In the process of researching and practicing related technologies, the inventors of this application discovered that existing facial recognition payment is a common method for realizing payment based on facial recognition. However, the process of facial recognition payment involves a large amount of data comparison, such as comparing the collected facial data with all facial data in the facial database. Furthermore, many users still rarely use facial recognition payment due to habit or privacy concerns. Besides facial recognition payment, the commonly used payment method is through payment codes (such as payment codes, collection codes, etc.). However, because these are not integrated with facial recognition technology, users still need to perform many steps on their mobile devices to complete the payment. Therefore, facial recognition-based payment methods still need further exploration and improvement. Summary of the Invention

[0004] This application provides a payment method, device, electronic device, and storage medium based on facial recognition, which can quickly transmit bill data through near-field communication and efficiently process payment based on the bill data in conjunction with facial recognition technology.

[0005] This application provides a payment method based on facial recognition, including:

[0006] When the distance between the target face recognition device and the target face recognition device is detected to meet the preset distance range, a near-field communication connection is established with the target face recognition device;

[0007] Through the near-field communication connection, auxiliary payment data is obtained from the target face recognition device, wherein the auxiliary payment data includes bill data and facial data collected by the target face recognition device;

[0008] The facial data is determined as the facial data to be detected for the current user of the mobile terminal, and reference facial data for the current user of the mobile terminal is obtained.

[0009] Face similarity detection is performed based on the face data to be detected and the reference face data;

[0010] If the face corresponding to the detected face data is found to be the face of the current user, a payment operation is performed based on the bill data.

[0011] Accordingly, this application also provides another payment method based on facial recognition, including:

[0012] When the distance between the mobile terminal and the mobile terminal is detected to meet the preset distance range, a near-field communication connection is established with the mobile terminal.

[0013] Receive product information for goods to be paid for, and generate bill data to be paid based on the product information;

[0014] Collect facial data from target users;

[0015] Based on the facial data and the billing data, auxiliary payment data is generated;

[0016] The auxiliary payment data is sent to the mobile terminal via the near-field communication connection to trigger a payment operation based on the auxiliary payment data.

[0017] Accordingly, embodiments of this application also provide a payment device based on facial recognition, including:

[0018] The first establishing unit is used to establish a near-field communication connection with the target face recognition device when the distance between the device and the target face recognition device is detected to meet a preset distance range.

[0019] An auxiliary acquisition unit is used to acquire auxiliary payment data from the target face recognition device through the near-field communication connection, wherein the auxiliary payment data includes bill data and facial data collected by the target face recognition device;

[0020] The reference acquisition unit is used to determine the facial data as the facial data to be detected of the current user of the mobile terminal, and to acquire the reference facial data of the current user of the mobile terminal.

[0021] A detection unit is used to perform face similarity detection based on the face data to be detected and the reference face data;

[0022] The payment unit is used to perform a payment operation based on the billing data if the face corresponding to the face data to be detected is the face of the current user.

[0023] In one embodiment, the payment unit includes:

[0024] The first generation subunit is used to generate a payment request based on the bill data and the user identification information of the current user if the face corresponding to the face data to be detected is detected as the face of the current user.

[0025] The first determining subunit is used to determine the target payment user of the billing data from the associated users of the current user;

[0026] The first sending subunit is used to send the payment request to the terminal of the target payment user to trigger the target payment user to pay the bill data.

[0027] In one embodiment, the first determining subunit is configured to:

[0028] The process involves determining the associated payment groups to which the current user belongs, wherein each associated payment group includes at least one associated user of the current user, and each associated payment group is configured with a paying user, who is a user who makes payments for the billing data of the associated users in the associated payment group; parsing the billing data to determine the transaction attributes corresponding to the billing data; and, based on a preset mapping relationship between associated payment groups and transaction attributes, determining the target associated payment group corresponding to the transaction attributes of the billing data, and identifying the paying user of the target associated payment group as the target paying user of the billing data.

[0029] In one embodiment, the face data to be detected includes a face image to be detected; the detection unit includes:

[0030] The recognition subunit is used to perform face detection on the face image to be detected in order to determine at least one candidate face region in the face image to be detected, wherein one candidate face region corresponds to one candidate user;

[0031] The first calculation subunit is used to calculate the priority of the candidate face region based on the geometric features of the candidate face region, wherein the priority is the priority of the candidate face region for face similarity detection;

[0032] The first detection subunit is used to perform face similarity detection on the candidate face region and the reference face data according to the priority.

[0033] In one embodiment, the detection unit further includes:

[0034] The second determining subunit is used to determine the current user's payment proxy user group if the face similarity detection between the candidate face region and the reference face data fails, wherein the payment proxy user group includes at least one payment proxy user of the current user;

[0035] The third determining subunit is used to determine the target payment user selected by the current user from the payment user group and to obtain the user identification information of the target payment user.

[0036] The second generation subunit is used to generate a payment request based on the bill data and the user identification information of the target payment user;

[0037] The second sending subunit is used to send the payment request to the terminal of the target payment user to trigger the target payment user to pay the bill data.

[0038] In one embodiment, the detection unit further includes:

[0039] The second detection subunit is used to perform face similarity detection based on the candidate face region and the face data of each paying user in the current user's paying user group if the face similarity detection between the candidate face region and the reference face data fails, so as to identify the user corresponding to the candidate face region.

[0040] The third generation subunit is used to generate a list of payment agents for the current user to select based on the recognition result, wherein the list of payment agents includes at least one payment agent corresponding to a candidate facial region with successful identity recognition.

[0041] The first acquisition subunit is used to acquire the target payment user selected by the current user from the payment user list;

[0042] The fourth generation subunit is used to generate a payment request for the target payment user based on the bill data and the user identification information of the target payment user, and send the payment request to the terminal of the target payment user to trigger the target payment user to pay the bill data.

[0043] In one embodiment, the reference facial data includes the facial features of the current user, and the candidate facial region includes channel data from at least one image channel; the first detection subunit is configured to:

[0044] The facial features of the candidate face region are generated using the channel data; the facial features of the candidate face region are compared with the facial features of the current user to obtain a comparison result; based on the comparison result, the facial similarity detection result between the candidate face region and the reference face data is determined.

[0045] In one embodiment, the face recognition-based payment device further includes:

[0046] The calling unit is used to, if it is detected that the face corresponding to the face data to be detected is not the face of the current user, collect the face data to be compared by calling the image acquisition module; perform face similarity detection based on the face data to be compared and the reference face data; and perform payment operation based on the detection result and the bill data.

[0047] Accordingly, embodiments of this application also provide a payment device based on facial recognition, including:

[0048] The second establishment unit is used to establish a near-field communication connection with the mobile terminal when the distance between the mobile terminal is detected to meet the preset distance range.

[0049] The bill generation unit is used to receive product information of goods to be paid and generate bill data to be paid based on the product information;

[0050] The acquisition unit is used to collect facial data from the target user.

[0051] An auxiliary generation unit is used to generate auxiliary payment data based on the facial data and the billing data;

[0052] The sending unit is used to send the auxiliary payment data to the mobile terminal through the near-field communication connection to trigger a payment operation based on the auxiliary payment data.

[0053] In one embodiment, the acquisition unit includes:

[0054] A data acquisition subunit is used to acquire raw facial data of a target user, wherein the raw facial data includes at least one candidate facial image;

[0055] The second calculation subunit is used to calculate the image quality of the candidate face image in at least one quality evaluation dimension;

[0056] An image selection subunit is used to select a target face image from the candidate face images based on the image quality of the candidate face images;

[0057] The image processing subunit is used to perform image processing on the target face image to obtain processed face data as the face data of the target user.

[0058] Accordingly, this application also provides a storage medium storing a computer program thereon, wherein the computer program, when executed by a processor, implements the steps of the face recognition-based payment method shown in this application embodiment.

[0059] Accordingly, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the face recognition-based payment method shown in this application embodiment.

[0060] This application embodiment can establish a near-field communication connection with the target face recognition device when the distance between the device and the target face recognition device meets a preset distance range; through the near-field communication connection, auxiliary payment data is obtained from the target face recognition device, wherein the auxiliary payment data includes bill data and facial data collected by the target face recognition device; the facial data is determined as the face data to be detected of the current user of the mobile terminal, and reference facial data of the current user of the mobile terminal is obtained; face similarity detection is performed based on the face data to be detected and the reference facial data; if the face corresponding to the face data to be detected is detected to be the face of the current user, a payment operation is performed based on the bill data.

[0061] This solution collects facial data using a target facial recognition device and leverages the near-field communication (NFC) capability, which allows for connection establishment within a predetermined distance. The collected facial data is then transmitted to a mobile terminal. The mobile terminal uses this data as the target facial data for the current user and performs facial similarity detection against reference facial data to determine if the target facial data matches the reference facial data. This verifies whether the facial recognition result of the target facial data matches the current user's identity, allowing for payment processing based on the result. This solution eliminates the need to compare the target facial data with all facial data in a server or local terminal facial database; it only requires comparing the target facial data with reference facial data to determine if the target facial data meets the identity verification requirements for payment. In this way, the solution reduces the amount of data required for facial recognition and can quickly transmit billing data to mobile terminals for payment via near-field communication. Therefore, this solution not only provides users with a new payment method in existing facial recognition payment and payment code payment scenarios, but also improves facial recognition-based payment efficiency. Attached Figure Description

[0062] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0063] Figure 1 This is a schematic diagram illustrating a scenario of the face recognition-based payment method provided in an embodiment of this application.

[0064] Figure 2 This is a flowchart of a face recognition-based payment method provided in an embodiment of this application;

[0065] Figure 3 This is a payment illustration of the face recognition-based payment method provided in this application embodiment;

[0066] Figure 4 This is another payment illustration of the face recognition-based payment method provided in the embodiments of this application;

[0067] Figure 5 This is another schematic diagram of the payment method based on facial recognition provided in the embodiments of this application;

[0068] Figure 6 This is a schematic diagram of a device for a face recognition-based payment method provided in an embodiment of this application;

[0069] Figure 7 This is a schematic diagram of the architecture of the face recognition-based payment method provided in the embodiments of this application;

[0070] Figure 8 This is a schematic diagram of the structure of a face recognition-based payment device provided in an embodiment of this application;

[0071] Figure 9 This is another structural schematic diagram of the face recognition-based payment device provided in the embodiments of this application;

[0072] Figure 10 This is another structural schematic diagram of the face recognition-based payment device provided in the embodiments of this application;

[0073] Figure 11 This is another structural schematic diagram of the face recognition-based payment device provided in the embodiments of this application;

[0074] Figure 12 This is another structural schematic diagram of the face recognition-based payment device provided in the embodiments of this application;

[0075] Figure 13 This is another structural schematic diagram of the face recognition-based payment device provided in the embodiments of this application;

[0076] Figure 14 This is another structural schematic diagram of the face recognition-based payment device provided in the embodiments of this application;

[0077] Figure 15 This is another structural schematic diagram of the face recognition-based payment device provided in the embodiments of this application;

[0078] Figure 16 This is a schematic diagram of the structure of the computer device provided in the embodiments of this application. Detailed Implementation

[0079] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0080] This application provides a payment method, apparatus, electronic device, and storage medium based on facial recognition. Specifically, this application provides a facial recognition-based payment device (which may be referred to as a first payment device for distinction) suitable for a first computer device, and a facial recognition-based payment device (which may be referred to as a second payment device for distinction) suitable for a second computer device. The first payment device and the second payment device can be terminal devices. Specifically, the terminal can be a smartphone, tablet computer, laptop computer, desktop computer, smart speaker, smartwatch, etc., but is not limited to these. In particular, the terminal can be a facial recognition device with facial recognition functionality, such as a facial payment device.

[0081] For example, the first payment device can be integrated into a mobile terminal, and the second payment device can be integrated into a facial recognition device.

[0082] This application embodiment will take the first payment device as a mobile terminal and the second payment device as a facial recognition device as an example to introduce a payment method based on facial recognition.

[0083] refer to Figure 1 This application provides a face recognition-based payment system including a mobile terminal 10 and a face recognition device 20, wherein a first payment device can be integrated into the mobile terminal, for example, in the form of a client; and a second payment device can be integrated into the face recognition device, for example, in the form of a client.

[0084] The mobile terminal 10 can establish a near-field communication connection with the target facial recognition device when it detects that the distance between it and the target facial recognition device meets a preset distance range. Similarly, the facial recognition device 20 can also establish a near-field communication connection with the mobile terminal when it detects that the distance between it and the mobile terminal meets a preset distance range. Furthermore, the facial recognition device 20 can receive product information of the goods to be paid for, generate bill data to be paid based on the product information; collect the facial data of the target user; generate auxiliary payment data based on the facial data and the bill data; and send the auxiliary payment data to the mobile terminal through the near-field communication connection to trigger a payment operation based on the auxiliary payment data.

[0085] Mobile terminal 10 can acquire auxiliary payment data from the target face recognition device via the near-field communication connection. The auxiliary payment data includes billing data and facial data collected by the target face recognition device. The facial data is identified as the face data to be detected for the current user of the mobile terminal, and reference facial data for the current user of the mobile terminal is acquired. Face similarity detection is performed based on the face data to be detected and the reference facial data. If the face corresponding to the face data to be detected is detected to be the face of the current user, a payment operation is performed based on the billing data.

[0086] The following sections provide detailed descriptions of each example. It should be noted that the order in which the embodiments are described is not intended to limit the preferred order of the embodiments.

[0087] This application provides a payment method based on facial recognition, which can be executed by the processor of a terminal, such as... Figure 2 The specific process of this facial recognition-based payment method can be described as follows:

[0088] 101. When the distance between the target face recognition device and the target face recognition device is detected to meet the preset distance range, a near-field communication connection is established between the target face recognition device and the target face recognition device.

[0089] Facial recognition refers to the technology of identifying faces using computer analysis and comparison techniques. Facial recognition technology belongs to biometric identification technology, which distinguishes individuals based on the biological characteristics of an organism (generally referring to humans).

[0090] Accordingly, a facial recognition device is a device with facial recognition functionality. For example, it can be a facial payment device, or it can be a device that only provides facial recognition without providing payment functionality, and so on. A facial recognition device can run a facial application (APP), and the facial recognition function can be provided through the facial application. For example, a facial recognition APP can be used to perform facial recognition-related steps, such as facial capture and facial selection.

[0091] Facial recognition devices may include the means to collect facial data, such as facial recognition cameras. There are various types of facial recognition cameras, such as 2D (two-dimensional) cameras and 3D (three-dimensional) cameras; among them, 2D cameras may include color cameras, infrared cameras, etc., and 3D cameras may include structure depth cameras, time-of-flight cameras, etc.

[0092] In addition to facial recognition, facial recognition devices can also acquire related functions through Near Field Communication (NFC) technology. NFC is an emerging technology that allows devices (such as mobile terminals and facial recognition devices) to exchange data when they are close to each other. It evolved from contactless radio frequency identification (RFID) and interconnection technologies, integrating inductive card readers, inductive cards, and point-to-point communication functions onto a single chip. This enables applications such as mobile payment, electronic ticketing, access control, mobile identity verification, and anti-counterfeiting using mobile terminals.

[0093] The target facial recognition device is the facial recognition device used when applying the facial recognition-based payment method described in this application. For example, in an offline payment scenario, a shop may have a facial recognition device. When the facial recognition device is used to implement the facial recognition-based payment method described in this application, the facial recognition device is the target facial recognition device.

[0094] In one embodiment, the target facial recognition device can be an Internet of Things (IoT) facial recognition device. To enhance the security of user facial recognition, a 3D camera is used on the IoT facial recognition device. In addition to red, green, and blue (RGB) images, the camera outputs data including a depth map and other relevant information. Analogous to traditional cameras, the 3D camera adds liveness-related hardware and software, including a depth camera and an infrared camera, which helps ensure information security. Furthermore, the target facial recognition device may also include an NFC module and a facial recognition app, which can be used to quickly establish connections with other NFC-enabled devices, transmit data, and handle facial recognition steps.

[0095] Near Field Communication (NFC) connections are established using near-field communication technology, enabling rapid data transmission. For example, devices can perform contactless point-to-point data transmission via NFC. Compared to other short-range wireless communication technologies such as Bluetooth and infrared, NFC offers advantages such as high security and lower cost.

[0096] The preset distance range is the communication distance range of near-field communication. The traditional communication distance range is mostly 0-20cm, but with the development of technology, there is a trend to extend the communication distance range to 20cm-3m. Therefore, in this application, the preset distance range is not limited. The preset distance range is the communication distance range that can realize near-field communication, and its specific value can be adjusted according to the actual application.

[0097] Because NFC does not require a pairing process like Bluetooth, but can identify devices within range, establish a connection, and transmit data, a step can be included before establishing a near-field communication connection to enable the terminal's NFC function, allowing permission to transfer data via NFC.

[0098] In one embodiment, the target facial recognition device can be a facial recognition terminal in an offline store. This terminal may include a 3D camera for collecting facial data, a merchant app, an NFC module, and a facial recognition app for facial recognition. The merchant app's core components may include a network module, a list module, and an order module. The list module allows users to add information about items to be paid for to generate a shopping list. The order module generates a payment invoice based on the shopping list and requests an order from the backend, assigning a unique transaction document (ID) `trade_id` to each transaction. Furthermore, after order identification, the order module can transmit the generated payment invoice to the facial recognition app. In this embodiment, the user's mobile terminal in the offline store can have NFC enabled, and when the distance between the user and the target facial recognition device meets a preset distance range, a near-field communication connection is established.

[0099] 102. Obtain auxiliary payment data from the target facial recognition device via near-field communication connection, wherein the auxiliary payment data includes bill data and facial data collected by the target facial recognition device.

[0100] The billing data can include information about the goods to be paid for, such as illustrations, names, unit prices, discounts, and quantities; merchant information, such as illustrations, names, locations, and promotional information; a trade_id to uniquely identify the order; and other billing information, such as member login information, total price, additional charges (e.g., shipping fees, packaging fees), additional discounts (e.g., member discounts, promotional discounts), and billing generation time.

[0101] There are several ways to generate billing data. For example, billing data can be generated through the merchant's app on the target facial recognition device. For instance, the target facial recognition device may provide a store selection module, a barcode reading module, etc., to assist users in generating billing data.

[0102] The facial data refers to the facial information of the target user collected by the target facial recognition device, where the target user is the user within the camera's field of view. For example, the facial data may include optimized facial images collected by the target facial recognition device for facial recognition of the target user. "Optimized" here means selecting the most suitable facial image for facial recognition through a comprehensive evaluation of factors such as face size, face angle, image contrast, image brightness, and sharpness.

[0103] The auxiliary payment data refers to the data that assists the mobile terminal in making payments based on the bill data. In this embodiment, the auxiliary payment data acquired by the mobile terminal includes the bill data and the facial data collected by the target facial recognition device.

[0104] In one embodiment, in an offline store scenario, the current user of the mobile terminal can generate bill data through the merchant's APP of the target face recognition device. After acquiring raw face data including RGB image stream, depth image stream, infrared image stream, etc. through the 3D camera of the target face recognition device, the most suitable face data for face recognition is selected, and auxiliary payment data including bill data and the selected face data is obtained from the target face recognition device through near-field communication connection.

[0105] 103. Identify the facial data as the facial data to be detected for the current user of the mobile terminal, and obtain the reference facial data of the current user of the mobile terminal.

[0106] Among them, the reference facial data is the real facial data of the current user of the mobile terminal. That is, by referring to the reference facial data, it can be determined whether the user identity corresponding to the facial data to be detected is the current user.

[0107] The format of reference face data can be varied. For example, reference face data can be a real image including the current user's facial region; or it can be facial information features further extracted from the real image, such as features representing the current user's facial information, like geometric features representing the geometric relationships between facial features such as eyes, nose, and mouth, such as distance, area, and angle; or it can be global or local features extracted through some algorithms, such as the feature vector of the real image; and so on.

[0108] In this embodiment, the facial data in the auxiliary payment data obtained through near-field communication (NFC) is a optimized facial image collected by the target facial recognition device for facial recognition of the target user, and the target user is the user within the camera range of the target facial recognition device. Furthermore, since NFC can efficiently transmit data at close range, this facial data can be identified as the facial data to be detected for the current user of the mobile terminal. It can be directly used to determine whether the user corresponding to the facial data to be detected is the current user, without needing to compare the facial data to be detected with facial data of known identities in a cloud or local facial database to determine whether the user corresponding to the facial data to be detected is the current user.

[0109] There are several ways to obtain the reference facial data of the current user of the mobile terminal. For example, the mobile terminal can store the reference facial data of the current user locally, so it only needs to be retrieved from the mobile terminal; or the mobile terminal can request the reference facial data of the current user from other terminals or servers; and so on.

[0110] 104. Perform face similarity detection based on the face data to be detected and the reference face data.

[0111] In this embodiment, face similarity detection is used to determine the similarity between the face data to be detected and the reference face data. For the current user of the mobile terminal, the face data to be detected is the face data collected by the target face recognition device, while the reference face data is the real face data that can be used to determine the identity of the current user. Therefore, face similarity detection can be performed based on the face data to be detected and the reference face data to determine whether the face corresponding to the face data to be detected is the face of the current user, that is, to determine whether the user identity reflected by the face data to be detected is the current user.

[0112] In one embodiment, the face data to be detected may include a face image to be detected. Specifically, the step "performing face similarity detection based on the face data to be detected and reference face data" may include:

[0113] Face detection is performed on the face image to be detected to determine at least one candidate face region in the face image to be detected, wherein a candidate face region corresponds to a candidate user;

[0114] Based on the geometric features of the candidate face regions, the priority of the candidate face regions is calculated, where the priority is the priority of the candidate face regions for face similarity detection.

[0115] Based on priority, face similarity detection is performed on candidate face regions and reference face data.

[0116] Face detection is used to determine the face regions in the face image to be detected. Since the face image to be detected may include not only the face region of the current user, but also the face regions of other users, face detection can determine at least one candidate face region in the face image to be detected, wherein one candidate face region corresponds to one candidate user.

[0117] There are various methods for face detection, including detection based on prior knowledge and detection based on statistical methods.

[0118] Among them, knowledge-based detection mainly utilizes prior knowledge to treat the face as a combination of organ features, detecting faces based on the characteristics of organs such as eyes, eyebrows, mouth, and nose, as well as their geometrical relationships. Knowledge-based face detection methods include: contour rule method, organ distribution method, skin texture method, template matching method, etc.

[0119] Among them, statistical method-based detection treats face detection as a "binary classification problem." It involves training a classifier using a large number of face and non-face samples, and then detecting faces by classifying all possible regions in an image into a statistical pattern recognition problem. Statistical method-based detection includes: feature space methods, probabilistic model methods, support vector machine methods, AdaBoost methods, and neural network methods.

[0120] In one embodiment, the detected candidate face regions can be marked with face bounding boxes so that the geometric features of each candidate face region can be determined based on the face bounding boxes of each candidate face region.

[0121] The geometric features of the candidate face region refer to its position, size, and other geometric information within the image to be detected. Optionally, if the image to be detected is acquired by a 3D camera, the geometric features of the candidate face region may also include the mean depth of the face center region in the depth map, as well as the angle of the face orientation in the depth map.

[0122] In one embodiment, the priority of each candidate face region in the image to be detected can be calculated based on the geometric features of each candidate face region, wherein the priority is the priority of the candidate face region for face similarity detection.

[0123] There are several ways to calculate priority. For example, different weights can be assigned to the geometric features of the candidate face regions, and the weighted values ​​of the geometric features of each candidate face region can be calculated so that the priority of each candidate face region can be determined by comparing the weighted values ​​of the geometric features, and so on.

[0124] After determining the priority of each candidate face region, face similarity detection can be performed on the candidate face regions and reference face data according to the priority. For example, a high-priority candidate face region can be selected for face similarity detection with the reference face data. If the detection passes, face similarity detection is not performed on other candidate face regions. If the detection fails, face similarity detection is performed on other candidate face regions one by one or in batches according to priority. Alternatively, face similarity detection can be performed only on the highest-priority candidate face region, or on candidate face regions with high priority rankings (such as the top two, top three, etc.). If the detection passes, face similarity detection is not performed on other candidate face regions.

[0125] There are various methods for performing face similarity detection on candidate face regions and reference face data. In one embodiment, the reference face data includes the facial features of the current user. The facial features are features that characterize the facial information of the current user. For example, geometric features that characterize the geometric relationship between facial features such as eyes, nose and mouth, such as distance, area and angle; or facial features can be global or local features extracted by some algorithms, such as the feature vector of the current user's real face image; and so on.

[0126] Furthermore, the candidate face region can include channel data from at least one image channel. The image can include at least one image channel, and each image channel can have corresponding channel data. For example, in RGB mode, the image can include three image channels: Red (R), Green (G), and Blue (B). Each pixel in the image can have a corresponding pixel value in the R, G, and B channels, and the pixel value can take various forms, such as between 0 and 255 or between 0 and 1. As another example, if the face image to be detected is acquired by a 3D camera, in addition to the R, G, and B channels, the face image to be detected can also include a depth (D) channel. The channel data of the face image to be detected in the D channel is the depth data acquired by the 3D structured light camera.

[0127] In this embodiment, the step "performing face similarity detection on candidate face regions and reference face data" may include:

[0128] Facial features of candidate facial regions are generated using channel data;

[0129] The facial features of the candidate facial region are compared with the facial features of the current user to obtain the comparison results;

[0130] Based on the comparison results, the facial similarity detection results of the candidate facial regions and the reference facial data are determined.

[0131] In one embodiment, a feature extraction model can be trained to extract corresponding facial features, such as feature vectors, from a face image. Therefore, facial features can be generated using channel data of candidate face regions, and the channel data of the candidate face regions can be used as input data to trigger the feature extraction model to generate the facial features corresponding to the candidate face regions.

[0132] After obtaining the facial features of the candidate face regions, these features can be compared with the current user's facial features to obtain the comparison result. For example, facial features can be in the form of feature vectors. The feature vectors of the candidate face regions can be compared with the feature vectors of the current user to obtain the comparison result. Furthermore, the face similarity detection result between the candidate face regions and the reference face data can be determined based on the comparison result. For example, if the comparison result is greater than a preset threshold, the face similarity detection result between the candidate face regions and the reference face data is considered a pass, meaning the face corresponding to the candidate face region is the current user's face; if the comparison result is less than the preset threshold, the face similarity detection result is considered a fail, meaning the face corresponding to the candidate face region is not the current user's face.

[0133] It is worth noting that in some scenarios, the current user can set up a payment agent, i.e., a user who pays the bill on behalf of the current user. In this case, if the facial similarity detection of all candidate facial regions and reference facial data in the image to be detected fails due to poor image quality or other factors such as a mask obscuring the face, or a trusted friend or relative holding the mobile device, the payment agent can still pay the current user's bill. Specifically, after the step "perform facial similarity detection on candidate facial regions and reference facial data according to priority", it can also include:

[0134] If the face similarity detection between the candidate face region and the reference face data fails, determine the current user's payment proxy user group, wherein the payment proxy user group includes at least one payment proxy user of the current user;

[0135] Determine the target payer selected by the current user from the payer group, and obtain the user identification information of the target payer.

[0136] A payment request is generated based on the billing data and the user identification information of the target payment user.

[0137] Send a payment request to the target user's terminal to trigger the target user to pay the bill data.

[0138] In this context, a "pay-on-behalf user" refers to a user who pays the bill on behalf of the current user. Therefore, a "pay-on-behalf user group" is a group that includes at least one such user. It's worth noting that in practice, the current user's pay-on-behalf users can be pre-set by the current user. For example, the current user can designate their parents and partner as their pay-on-behalf users, thus creating a "pay-on-behalf user group" for the current user.

[0139] There are several ways to determine the current user's payment group. In one embodiment, it can be determined by password verification. Specifically, if the face similarity detection of each candidate face region and the reference face data in the face image to be detected fails, the mobile terminal can determine the current user's payment group by verifying the payment verification password entered by the current user. The payment verification password can take many forms, such as character password, gesture password, fingerprint password, voice password, etc.

[0140] As an example, see reference Figure 3 If the face similarity detection of each candidate face region and the reference face data in the face image to be detected fails, the mobile terminal can display... Figure 3 On the payment verification selection page shown in 201, if the current user selects to pay the bill through a third-party payment user via the control shown in 202, the mobile terminal can display the payment verification password input page shown in 203. The current user can enter a preset payment verification password in control 204 to determine the current user's third-party payment user group. The controls in this embodiment can be in the form of icons, input boxes, or buttons, etc.

[0141] In this embodiment, different payment verification passwords can be mapped to different payment user groups. Therefore, the mobile terminal can further determine the current user's payment user group by the payment verification password entered by the current user in control 204. As shown in 205, the payment user group may include at least one payment user that the current user can select.

[0142] After determining the current user's payment proxy user group, the mobile terminal can determine the target payment proxy user selected by the current user from the payment proxy user group, for example, referring to... Figure 3 The mobile terminal can determine the target payment user based on the payment user selected by the current user on page 205.

[0143] The current user's user identification information is the relevant information that identifies the current user. For example, the user identification information may include the current user's social application account, ID card number, mobile phone number, email account, etc.

[0144] After identifying the target payer and their user identification information, the mobile terminal can generate a payment request based on the bill data and the target payer's user identification information. This request can then be sent to the target payer's terminal to trigger the target payer to pay the bill data.

[0145] For example, in one embodiment, payment can be made through WeChat Pay bill data. In this case, the user identification information of the target payment user may include the target payment user's WeChat account. The mobile terminal can generate a payment request based on the bill data and the target payment user's WeChat account, and send the payment request to the target payment user's WeChat account to trigger the target payment user to make payment through WeChat Pay bill data.

[0146] In other scenarios, the current user can set up a payment agent, and this payment agent can also have corresponding facial data. In this case, if the facial similarity detection of all candidate facial regions and reference facial data in the image to be detected fails due to poor image quality or other factors such as a mask obscuring the face, or a trusted friend or relative holding the mobile device, the payment agent can still make the payment for the current user's bill. Specifically, after the step "perform facial similarity detection on candidate facial regions and reference facial data according to priority," it can also include:

[0147] If the face similarity detection between the candidate face region and the reference face data fails, face similarity detection is performed based on the candidate face region and the face data of each paying user in the current user's paying user group in order to identify the user corresponding to the candidate face region.

[0148] Based on the recognition results, a list of payment agents is generated for the current user to select. The payment agent list includes payment agents corresponding to at least one candidate facial region with successful identity recognition.

[0149] Retrieve the target payment user selected by the current user from the list of payment payment users;

[0150] Based on the billing data and the user identification information of the target payment user, a payment request for the target payment user is generated and sent to the target payment user's terminal to trigger the target payment user to pay the billing data.

[0151] If the face similarity detection between the candidate face region and the reference face data fails, the mobile terminal can perform face similarity detection between each candidate face region and the face data of each paying user in the current user's paying user group to identify the user corresponding to each candidate face region, thereby determining whether the face image to be detected includes the face corresponding to the current user's paying user.

[0152] Furthermore, the mobile terminal can generate a list of payment-on-behalf users for the current user to select based on the recognition results. This list includes payment-on-behalf users corresponding to at least one candidate facial region with successfully recognized identity. For example, in one embodiment, referring to… Figure 4Based on the recognition results, the mobile terminal identified the users corresponding to the candidate facial regions, including the current user's mother, grandfather, and brother. Furthermore, the mobile terminal can generate data such as... Figure 4 The list of payers available for selection by the current user, shown in section 206, includes at least one payer corresponding to a candidate facial region with successful identity recognition, namely the current user's mother, grandfather, and brother.

[0153] The current user can select a target user from the list of users who can make payments on behalf of others. The mobile terminal can also obtain the target user selected by the current user from the list of users who can make payments on behalf of others, and generate a payment request for the target user based on the bill data and the user identification information of the target user. The payment request is then sent to the terminal of the target user to trigger the target user to pay the bill data.

[0154] For example, in one embodiment, payment can be made through WeChat Pay bill data. In this case, the user identification information of the target payment user may include the target payment user's WeChat account. The mobile terminal can generate a payment request based on the bill data and the target payment user's WeChat account, and send the payment request to the target payment user's WeChat account to trigger the target payment user to make payment through WeChat Pay bill data.

[0155] 105. If the face corresponding to the face data to be detected is the current user's face, the payment operation is performed based on the bill data.

[0156] If the face corresponding to the face data to be detected is the face of the current user, that is, if it is confirmed that the user identity corresponding to the face data to be detected is consistent with the user identity of the current user, the current user's mobile terminal can perform payment operation based on the bill data.

[0157] There are various ways for a terminal to make payments based on billing data. For example, in one embodiment, the mobile terminal can trigger the current user to pay the billing data through a payment platform, such as WeChat Pay. Alternatively, the mobile terminal can trigger the current user's associated users to pay the billing data through a payment platform. The associated users are users who have a relationship with the current user, and this relationship can take many forms, such as a payment on behalf of another user, or a shared payment relationship, etc. Specifically, the step "If the face corresponding to the detected facial data is the current user's face, perform a payment operation based on the billing data" can include:

[0158] If the face corresponding to the face data to be detected is the face of the current user, a payment request is generated based on the bill data and the user identification information of the current user;

[0159] Determine the target payment user for the billing data from the current user's associated users;

[0160] Send a payment request to the target payment user's terminal to trigger the target payment user to pay the bill data.

[0161] Since the payment request is generated based on the current user's billing data and user identification information, it can be used not only to trigger payment for the billing data, but also to indicate the relationship between the billing data and the current user. For example, it can indicate that the billing data was generated by the current user making a purchase.

[0162] In one embodiment, payment can be made via WeChat Pay, where the current user's user identification information can be their WeChat account. When the mobile terminal detects that the face corresponding to the detected facial data belongs to the current user, it can generate a payment request based on the bill data and the current user's WeChat account.

[0163] The mobile terminal can determine the target payment user for the billing data from the current user's associated users, so that the target payment user can be triggered to pay for the billing data by sending a payment request to the target payment user's terminal.

[0164] There are several ways for a mobile terminal to determine the target payment user from the current user's associated users. For example, different associated payment groups can be set up for pending orders with different transaction attributes. In this way, after the mobile terminal obtains the billing data via near-field communication, it can determine the target associated payment group by analyzing the transaction attributes corresponding to the billing data. Specifically, the step "determine the target payment user of the billing data from the current user's associated users" can include:

[0165] Determine the associated payment group to which the current user belongs. An associated payment group includes at least one associated user of the current user. Each associated payment group is set with a payment user, who is the user who makes payments for the billing data of the associated user in the associated payment group.

[0166] Parse the billing data to determine the corresponding transaction attributes;

[0167] Based on the preset mapping relationship between associated payment groups and transaction attributes, the target associated payment group corresponding to the transaction attributes of the bill data is determined, and the payment users of the target associated payment group are determined as the target payment users of the bill data.

[0168] The associated payment group is a group that includes at least one associated user of the current user. Each associated payment group has a designated payment user, who is the user who makes payments based on the billing data of the associated user within that group. It is worth noting that the payment user designated for an associated payment group can include various scenarios. For example, the number of payment users can be one or more; the payment user can be an associated user within the associated payment group, or a user outside the associated payment group; and so on.

[0169] The transaction attributes of bill data can include various scenarios. For example, the transaction attributes can be determined based on the transaction scenario, such as online shopping or offline consumption; or based on the purchased goods, such as food and beverage, clothing and accessories, home furnishings and decoration, or digital appliances; or based on the amount spent, such as total spending less than 10,000 yuan, total spending between 10,000 and 100,000 yuan, or total spending more than 100,000 yuan; and so on.

[0170] In this embodiment, different associated payment groups can be set for different transaction attributes, that is, a mapping relationship between transaction attributes and associated payment groups can be established. This allows the mobile terminal to determine the target associated payment group by analyzing the transaction attributes of the bill data after obtaining the bill data via near-field communication. Furthermore, since each associated payment group has a corresponding payment user, the mobile terminal can determine the payment user of the target associated payment group as the target payment user of the bill data.

[0171] For example, different associated payment groups can be set up for bill data corresponding to different transaction scenarios. For instance, associated payment group A can be set up for online consumption expenditures, and associated payment group B can be set up for offline consumption expenditures. Or, different associated payment groups can be set up for different consumption amounts in the bill data. For instance, if the total consumption amount of the bill data is less than 10,000 yuan, associated payment group C can be set up; if the total consumption amount is between 10,000 yuan and 100,000 yuan, associated payment group D can be set up; if the total consumption amount is more than 100,000 yuan, associated payment group E can be set up; and so on.

[0172] Furthermore, in other embodiments, if the face to be detected is not the current user's face due to poor image quality or other factors such as a mask obscuring the face, or a trusted relative or friend holding the mobile terminal, the mobile terminal can also collect the current user's face data by calling the image acquisition module, and determine whether the current user's identity is legitimate for payment by performing face similarity detection between the collected face data and reference face data. Specifically, the face recognition-based payment method may further include:

[0173] If the face corresponding to the face data to be detected is not the current user's face, the face data to be compared is collected by calling the image acquisition module;

[0174] Face similarity detection is performed based on the face data to be compared and the reference face data;

[0175] Payment is processed based on the test results and billing data.

[0176] In one embodiment, the image acquisition module can be the camera of the mobile terminal. Therefore, the mobile terminal can collect the current user's facial data by calling the camera to obtain the facial data to be compared. Further, the mobile terminal can perform facial similarity detection based on the facial data to be compared and the reference facial data to determine whether the current user's identity is a legitimate identity for payment. Specifically, if the detection result is successful, the mobile terminal can generate a payment request based on the bill data and the current user's user identification information to trigger payment for the bill data. For example, the payment request can trigger the WeChat Pay backend to execute a payment operation based on the payment request. If the detection result is unsuccessful, the mobile terminal may not generate a payment request.

[0177] As can be seen from the above, this embodiment can establish a near-field communication connection with the target face recognition device when the distance between the device and the target face recognition device meets a preset distance range; through the near-field communication connection, auxiliary payment data is obtained from the target face recognition device, wherein the auxiliary payment data includes bill data and face data collected by the target face recognition device; the face data is determined as the face data to be detected of the current user of the mobile terminal, and reference face data of the current user of the mobile terminal is obtained; face similarity detection is performed based on the face data to be detected and the reference face data; if the face corresponding to the face data to be detected is detected to be the face of the current user, a payment operation is performed based on the bill data.

[0178] This solution collects facial data using a target facial recognition device and leverages the near-field communication (NFC) capability, which allows for connection establishment within a predetermined distance. The collected facial data is then transmitted to a mobile terminal. The mobile terminal uses this data as the target facial data for the current user and performs facial similarity detection against reference facial data to determine if the target facial data matches the reference facial data. This verifies whether the facial recognition result of the target facial data matches the current user's identity, allowing for payment processing based on the result. This solution eliminates the need to compare the target facial data with all facial data in a server or local terminal facial database; it only requires comparing the target facial data with reference facial data to determine if the target facial data meets the identity verification requirements for payment. In this way, the solution reduces the amount of data required for facial recognition and can quickly transmit billing data to mobile terminals for payment via near-field communication. Therefore, this solution not only provides users with a new payment method in existing facial recognition payment and payment code payment scenarios, but also improves facial recognition-based payment efficiency.

[0179] Based on the method described in the above embodiments, the following examples will provide further detailed explanations.

[0180] In this embodiment, the first payment device is specifically integrated into a mobile terminal and the second payment device is specifically integrated into a facial recognition device, as an example for explanation.

[0181] like Figure 5 As shown, a payment method based on facial recognition follows this process:

[0182] 301. When the distance between the face recognition device and the mobile terminal is detected to meet the preset distance range, the face recognition device establishes a near-field communication connection with the mobile terminal.

[0183] In one embodiment, the facial recognition device can be as follows: Figure 6 As shown, it includes a camera, such as a 3D camera, required to capture facial data. Furthermore, the facial recognition device can... Figure 7 The IoT face recognition terminal device shown may include a 3D camera, a face recognition app, and a merchant app at its core.

[0184] In this embodiment, to enhance the security of user facial recognition, a 3D camera can be used on the IoT facial recognition terminal. In addition to RGB images, the data output by the 3D camera also includes depth maps and other relevant information.

[0185] In addition, refer to Figure 7 The facial recognition device may also include an NFC module, which is used to establish a near-field communication connection with the mobile terminal when the distance between the device and the mobile terminal meets a preset distance range.

[0186] Similarly, when the distance between the mobile terminal and the target facial recognition device is detected to meet the preset distance range, the mobile terminal can also establish a near-field communication connection with the target facial recognition device.

[0187] 302. The facial recognition device receives the product information of the goods to be paid for and generates the bill data to be paid based on the product information.

[0188] In one embodiment, reference Figure 7 The merchant app on the facial recognition device can receive product information for items to be paid for and generate a bill based on that information. Specifically, the core of the merchant app includes a network module, a list module, and an order module. The list module allows users to add information about items to be paid for, generating a shopping list. The order module generates a payment bill based on the shopping list, requests an order from the backend, and assigns a unique transaction document (ID), `trade_id`, to each transaction to identify it. Furthermore, after order identification, the order module can transmit the generated payment bill to the facial recognition app.

[0189] 303. Facial recognition devices collect facial data of target users.

[0190] In one embodiment, reference Figure 7 The facial recognition app on the device can collect the facial data of the target user. The core of the facial recognition app can include facial capture and facial selection. Facial capture can be performed using a 3D camera to acquire RGB image streams, depth image streams, infrared image streams, etc. Facial selection can be used to comprehensively evaluate and select the optimal facial image based on factors such as face size, face angle, image contrast, image brightness, and sharpness. Specifically, the step "collecting the target user's facial data" can include:

[0191] Collect raw facial data of the target user, wherein the raw facial data includes at least one candidate facial image;

[0192] Calculate the image quality of candidate face images in at least one quality evaluation dimension;

[0193] Select the target face image from the candidate face images based on the image quality of the candidate face images;

[0194] Image processing is performed on the target face image to obtain the processed face data, which is then used as the target user's face data.

[0195] The facial recognition device can collect raw facial data of a target user through a camera. This raw facial data includes at least one candidate facial image. For example, the raw facial data may include a video clip collected by the facial recognition device for facial recognition of the target user, which may contain data of the target user's facial image; or, the raw facial data may include multiple candidate images collected by the facial recognition device for facial recognition of the target user, which may contain regions corresponding to the target user's facial image; and so on.

[0196] The quality assessment dimension is a dimension used to evaluate the image quality of candidate face images. For example, the quality assessment dimension may include the region size or face angle of the face area in the candidate face image. Optionally, the quality assessment dimension may also include the image contrast, brightness, and sharpness of the candidate face image.

[0197] In one embodiment, the image quality of candidate face images can be calculated in at least one quality evaluation dimension, and a target face image can be selected from the candidate face images based on the image quality of the candidate face images. For example, the candidate face image with the highest image quality can be determined as the target face image.

[0198] Furthermore, the facial recognition device can perform image processing on the target facial image. For example, the facial recognition device can perform image processing steps such as image enhancement, image cropping, and image compression on the target facial image to obtain the processed facial data as the target user's facial data.

[0199] 304. Facial recognition devices generate auxiliary payment data based on facial data and billing data.

[0200] 305. The facial recognition device sends auxiliary payment data to the mobile terminal via near-field communication to trigger the mobile terminal to perform a payment operation based on the auxiliary payment data.

[0201] In one embodiment, reference Figure 7 Facial recognition devices can use NFC modules to send auxiliary payment data to mobile terminals via near-field communication connections.

[0202] 306. The mobile terminal obtains auxiliary payment data from the target facial recognition device through near-field communication connection. The auxiliary payment data includes bill data and facial data collected by the target facial recognition device.

[0203] In one embodiment, reference Figure 7 Mobile terminals can use NFC modules to achieve near-field communication connections and obtain auxiliary payment data from target facial recognition devices.

[0204] 307. The mobile terminal identifies the facial data as the facial data to be detected for the current user of the mobile terminal, and obtains the reference facial data of the current user of the mobile terminal.

[0205] In one embodiment, reference Figure 7 Payment can be made through WeChat Pay. Furthermore, the mobile terminal can request the current user's reference facial data from the WeChat backend facial database via the network module to obtain the current user's reference facial data for the mobile terminal.

[0206] In another embodiment, the mobile terminal may store reference facial data of the current user, so the reference facial data of the current user can be obtained simply by searching on the mobile terminal.

[0207] 308. The mobile terminal performs face similarity detection based on the face data to be detected and the reference face data.

[0208] In one embodiment, reference Figure 7 A face similarity detection module can be set up on the mobile terminal. Therefore, face similarity detection can be performed based on the face data to be detected and the reference face data through this module.

[0209] 309. If the face corresponding to the face data to be detected is the current user's face, the mobile terminal will perform a payment operation based on the bill data.

[0210] In one embodiment, reference Figure 7 Payment can be made through WeChat Pay. Mobile terminals can use the network module to call the basic payment service provided by the WeChat backend service to complete the payment operation of the bill data.

[0211] As can be seen from the above, this embodiment of the application can collect facial data through a target facial recognition device and, combined with the characteristic of near-field communication that a connection can be established within a predetermined distance, transmit the collected facial data to a mobile terminal. The mobile terminal can then use this data as the facial data to be detected for the current user and perform facial similarity detection between this data and the current user's reference facial data to determine whether the face corresponding to the facial data to be detected is the same as the face corresponding to the reference facial data. In other words, it determines whether the facial recognition result of the facial data to be detected matches the current user's identity, so that payment can be made based on this result. This embodiment of the application does not require comparing the facial data to be detected with all facial data in the server or the terminal's local facial database; it only needs to compare the facial data to be detected with the reference facial data to determine whether the facial data to be detected meets the identity verification requirements for the current user to make a payment. In this way, the embodiments of this application reduce the amount of data required for facial recognition, and can quickly transmit bill data to the mobile terminal for payment via near-field communication. Therefore, the embodiments of this application not only provide users with new payment methods in existing facial recognition payment and payment code payment scenarios, but also improve facial recognition payment and payment code payment, thereby improving the efficiency of facial recognition-based payment.

[0212] To better implement the above methods, this application also provides a face recognition-based payment device (i.e., a first payment device), which can be integrated into a terminal. This terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc., but is not limited to these.

[0213] For example, such as Figure 8 As shown, the face recognition-based payment device may include a first establishment unit 401, an auxiliary acquisition unit 402, a reference acquisition unit 403, a detection unit 404, and a payment unit 405, as follows:

[0214] The first establishment unit 401 is used to establish a near-field communication connection with the target face recognition device when the distance between the device and the target face recognition device is detected to meet a preset distance range.

[0215] The auxiliary acquisition unit 402 is used to acquire auxiliary payment data from the target face recognition device through the near-field communication connection, wherein the auxiliary payment data includes bill data and facial data collected by the target face recognition device;

[0216] The reference acquisition unit 403 is used to determine the face data as the face data to be detected of the current user of the mobile terminal, and to acquire the reference face data of the current user of the mobile terminal.

[0217] The detection unit 404 is used to perform face similarity detection based on the face data to be detected and the reference face data;

[0218] Payment unit 405 is used to perform a payment operation based on the bill data if the face corresponding to the face data to be detected is the face of the current user.

[0219] In one embodiment, reference Figure 9 The payment unit 405 may include:

[0220] The first generation subunit 4051 can be used to generate a payment request based on the bill data and the user identification information of the current user if the face corresponding to the face data to be detected is detected as the face of the current user.

[0221] The first determining subunit 4052 can be used to determine the target payment user of the bill data from the associated users of the current user;

[0222] The first sending subunit 4053 can be used to send the payment request to the terminal of the target payment user to trigger the target payment user to pay the bill data.

[0223] In one embodiment, the first determining subunit 4052 can be used to:

[0224] The process involves determining the associated payment groups to which the current user belongs, wherein each associated payment group includes at least one associated user of the current user, and each associated payment group is configured with a paying user, who is a user who makes payments for the billing data of the associated users in the associated payment group; parsing the billing data to determine the transaction attributes corresponding to the billing data; and, based on a preset mapping relationship between associated payment groups and transaction attributes, determining the target associated payment group corresponding to the transaction attributes of the billing data, and identifying the paying user of the target associated payment group as the target paying user of the billing data.

[0225] In one embodiment, reference Figure 10 The face data to be detected includes a face image to be detected; the detection unit 404 may include:

[0226] The identification subunit 4041 can be used to perform face detection on the face image to be detected, so as to determine at least one candidate face region in the face image to be detected, wherein one candidate face region corresponds to one candidate user;

[0227] The first calculation subunit 4042 can be used to calculate the priority of the candidate face region based on the geometric features of the candidate face region, wherein the priority is the priority of the candidate face region for face similarity detection;

[0228] The first detection subunit 4043 can be used to perform face similarity detection on the candidate face region and the reference face data according to the priority.

[0229] In one embodiment, reference Figure 11 The detection unit 404 may further include:

[0230] The second determining subunit 4044 can be used to determine the current user's payment proxy user group if the face similarity detection between the candidate face region and the reference face data fails, wherein the payment proxy user group includes at least one payment proxy user of the current user;

[0231] The third determining subunit 4045 can be used to determine the target paying user selected by the current user from the paying user group and obtain the user identification information of the target paying user.

[0232] The second generation subunit 4046 can be used to generate a payment request based on the bill data and the user identification information of the target payment user;

[0233] The second sending subunit 4047 can be used to send the payment request to the terminal of the target payment user to trigger the target payment user to pay the bill data.

[0234] In one embodiment, reference Figure 12 The detection unit may further include:

[0235] The second detection subunit 4048 can be used to perform face similarity detection based on the candidate face region and the face data of each paying user in the current user's paying user group if the face similarity detection between the candidate face region and the reference face data fails, so as to identify the user corresponding to the candidate face region.

[0236] The third generation subunit 4049 can be used to generate a list of payment-on-behalf users for the current user to select based on the recognition result, wherein the list of payment-on-behalf users includes at least one payment-on-behalf user corresponding to a candidate facial region with successful identity recognition.

[0237] The first acquisition subunit 40410 can be used to acquire the target payment user selected by the current user from the payment user list;

[0238] The fourth generation subunit 40411 can be used to generate a payment request for the target payment user based on the bill data and the user identification information of the target payment user, and send the payment request to the terminal of the target payment user to trigger the target payment user to pay the bill data.

[0239] In one embodiment, the reference facial data includes the facial features of the current user, and the candidate facial region includes channel data from at least one image channel; the first detection subunit 4043 can be used to:

[0240] The facial features of the candidate face region are generated using the channel data; the facial features of the candidate face region are compared with the facial features of the current user to obtain a comparison result; based on the comparison result, the facial similarity detection result between the candidate face region and the reference face data is determined.

[0241] In one embodiment, reference Figure 13 The facial recognition-based payment device may further include:

[0242] The calling unit 406 can be used to collect face data to be compared by calling the image acquisition module if it is detected that the face corresponding to the face data to be detected is not the face of the current user; perform face similarity detection based on the face data to be compared and the reference face data; and perform payment operation based on the detection result and the bill data.

[0243] In practice, each of the above units can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units, please refer to the previous method embodiments, which will not be repeated here.

[0244] As can be seen from the above, in the face recognition-based payment device of this embodiment, when the first establishment unit 401 detects that the distance between itself and the target face recognition device meets a preset distance range, it establishes a near-field communication connection with the target face recognition device; the auxiliary acquisition unit 402 acquires auxiliary payment data from the target face recognition device through the near-field communication connection, wherein the auxiliary payment data includes bill data and face data collected by the target face recognition device; the reference acquisition unit 403 determines the face data as the face data to be detected of the current user of the mobile terminal and acquires the reference face data of the current user of the mobile terminal; the detection unit 404 performs face similarity detection based on the face data to be detected and the reference face data; and the payment unit 405 performs a payment operation based on the bill data if it detects that the face corresponding to the face data to be detected is the face of the current user.

[0245] This solution collects facial data using a target facial recognition device and leverages the near-field communication (NFC) capability, which allows for connection establishment within a predetermined distance. The collected facial data is then transmitted to a mobile terminal. The mobile terminal uses this data as the target facial data for the current user and performs facial similarity detection against reference facial data to determine if the target facial data matches the reference facial data. This verifies whether the facial recognition result of the target facial data matches the current user's identity, allowing for payment processing based on the result. This solution eliminates the need to compare the target facial data with all facial data in a server or local terminal facial database; it only requires comparing the target facial data with reference facial data to determine if the target facial data meets the identity verification requirements for payment. In this way, the solution reduces the amount of data required for facial recognition and can quickly transmit billing data to mobile terminals for payment via near-field communication. Therefore, this solution not only provides users with a new payment method in existing facial recognition payment and payment code payment scenarios, but also improves facial recognition-based payment efficiency.

[0246] To better implement the above methods, this embodiment of the invention also provides a face recognition-based payment device (i.e., a second payment device), which can be integrated into a terminal. The terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc. Furthermore, the terminal can also be a face recognition device with face recognition functionality, such as a face payment device, but is not limited to these.

[0247] For example, such as Figure 14 As shown, the payment device may include a second establishment unit 501, a bill generation unit 502, a collection unit 503, an auxiliary generation unit 504, and a sending unit 505, as follows:

[0248] The second establishment unit 501 is used to establish a near-field communication connection with the mobile terminal when the distance between the mobile terminal is detected to meet a preset distance range.

[0249] The bill generation unit 502 is used to receive product information of goods to be paid and generate bill data to be paid based on the product information;

[0250] The acquisition unit 503 is used to acquire facial data of the target user;

[0251] The auxiliary generation unit 504 is used to generate auxiliary payment data based on the facial data and the billing data;

[0252] The sending unit 505 is used to send the auxiliary payment data to the mobile terminal through the near-field communication connection to trigger a payment operation based on the auxiliary payment data.

[0253] In one embodiment, reference Figure 15 The acquisition unit 503 may include:

[0254] The data acquisition subunit 5031 can be used to acquire the original facial data of the target user, wherein the original facial data includes at least one candidate facial image;

[0255] The second calculation subunit 5032 can be used to calculate the image quality of the candidate face image in at least one quality evaluation dimension;

[0256] The image selection subunit 5033 can be used to select a target face image from the candidate face images based on the image quality of the candidate face images;

[0257] The image processing subunit 5034 can be used to perform image processing on the target face image to obtain processed face data as the face data of the target user.

[0258] The facial recognition-based payment device provided in this application embodiment can quickly transmit bill data through near-field communication connection and efficiently process payment based on the bill data in combination with facial recognition technology.

[0259] Furthermore, this application also provides an electronic device, which can be a computer device, or a terminal device, such as a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc., but is not limited to these. The terminal can also be a facial recognition device with facial recognition functionality, such as a facial payment device. Figure 16 As shown, it illustrates a structural schematic diagram of the computer device involved in the embodiments of this application, specifically:

[0260] The computer device may include radio frequency (RF) circuitry 601, a memory 602 including one or more computer-readable storage media, a sensor 603, a wireless Fidelity (WiFi) module 604, a processor 605 including one or more processing cores, and a power supply 606, among other components. Those skilled in the art will understand that... Figure 16 The computer device structure shown does not constitute a limitation on the computer device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0261] The RF circuit 601 can be used for receiving and transmitting signals during information transmission or calls. Specifically, it receives downlink information from the base station and hands it over to one or more processors 605 for processing; additionally, it transmits uplink data to the base station. Typically, the RF circuit 601 includes, but is not limited to, an antenna, at least one amplifier, a tuner, one or more oscillators, a Subscriber Identity Module (SIM) card, a transceiver, a coupler, a low-noise amplifier (LNA), a duplexer, etc. Furthermore, the RF circuit 601 can also communicate wirelessly with networks and other devices. This wireless communication can use any communication standard or protocol, including but not limited to GSM, GPRS, CDMA, WCDMA, LTE, email, and SMS.

[0262] The memory 602 can be used to store software programs and modules. The processor 605 executes various functional applications and data processing by running the software programs and modules stored in the memory 602. The memory 602 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device (such as audio data, telephone directory, etc.). In addition, the memory 602 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 602 may also include a memory controller to provide access to the memory 602 for the processor 605 and the input unit 603.

[0263] The computer device may also include at least one sensor 603, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor can adjust the brightness of the display panel according to the ambient light level, and the proximity sensor can turn off the display panel and / or backlight when the computer device is moved to the ear. As a type of motion sensor, a gravity acceleration sensor can detect the magnitude of acceleration in various directions (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that recognize the phone's posture (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc. Other sensors that may be configured in the computer device, such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, will not be described in detail here.

[0264] WiFi is a short-range wireless transmission technology. Computer devices using a WiFi module 604 can help users send and receive emails, browse web pages, and access streaming media, providing users with wireless broadband internet access. Although Figure 16 WiFi module 604 is shown, but it is understood that it is not an essential component of computer equipment and can be omitted as needed without changing the nature of the invention.

[0265] The processor 605 is the control center of the computer device, connecting various parts of the mobile phone through various interfaces and lines. It performs various functions of the computer device and processes data by running or executing software programs and / or modules stored in the memory 602, and by calling data stored in the memory 602, thereby performing overall detection of the mobile phone. Optionally, the processor 605 may include one or more processing cores; preferably, the processor 605 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the aforementioned modem processor may also not be integrated into the processor 605.

[0266] The computer device also includes a power supply 606 (such as a battery) that supplies power to various components. Preferably, the power supply can be logically connected to the processor 605 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 606 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0267] Although not shown, the computer device may also include a camera, Bluetooth module, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 605 in the computer device loads the executable files corresponding to the processes of one or more applications into the memory 602 according to the following instructions, and the processor 605 runs the applications stored in the memory 602 to realize various functions, as follows:

[0268] When the distance between the target facial recognition device and the target facial recognition device is detected to meet a preset distance range, a near-field communication connection is established with the target facial recognition device. Through this near-field communication connection, auxiliary payment data is obtained from the target facial recognition device, including billing data and facial data collected by the target facial recognition device. The facial data is identified as the face data to be detected for the current user of the mobile terminal, and reference facial data for the current user of the mobile terminal is obtained. Facial similarity detection is performed based on the face data to be detected and the reference facial data. If the face corresponding to the face data to be detected is detected to be the face of the current user, a payment operation is performed based on the billing data.

[0269] or

[0270] When the distance between the device and the mobile terminal is detected to meet a preset distance range, a near-field communication connection is established with the mobile terminal; product information of the goods to be paid is received, and bill data to be paid is generated based on the product information; facial data of the target user is collected; auxiliary payment data is generated based on the facial data and the bill data; and the auxiliary payment data is sent to the mobile terminal through the near-field communication connection to trigger a payment operation based on the auxiliary payment data.

[0271] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0272] As described above, the computer device in this embodiment can collect facial data through a target facial recognition device. Leveraging the near-field communication (NFC) feature, which allows for connection establishment within a predetermined distance, the collected facial data is transmitted to a mobile terminal. The mobile terminal can then use this data as the facial data to be detected for the current user. It performs facial similarity detection between this data and the user's reference facial data to determine if the face corresponding to the detected data matches the face corresponding to the reference data. In other words, it determines whether the facial recognition result of the detected data matches the current user's identity, allowing for further payment based on the result. The computer device in this embodiment does not need to compare the detected facial data with all facial data in the server or the terminal's local facial database; it only needs to compare the detected facial data with the reference facial data to determine whether the detected facial data meets the identity verification requirements for the current user to make a payment. In this way, the computer device of this embodiment reduces the amount of data required for facial recognition, and can quickly transmit bill data to the mobile terminal for payment via near-field communication. Therefore, the computer device of this embodiment not only provides users with new payment methods in existing facial recognition payment and payment code payment scenarios, but also improves facial recognition payment and payment code payment, thereby increasing the efficiency of facial recognition-based payment.

[0273] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0274] To this end, embodiments of this application provide a storage medium storing a plurality of instructions that can be loaded by a processor to execute steps in any of the face recognition-based payment methods provided in embodiments of this application. For example, the instructions can execute the following steps:

[0275] When the distance between the target facial recognition device and the target facial recognition device is detected to meet a preset distance range, a near-field communication connection is established with the target facial recognition device. Through this near-field communication connection, auxiliary payment data is obtained from the target facial recognition device, including billing data and facial data collected by the target facial recognition device. The facial data is identified as the face data to be detected for the current user of the mobile terminal, and reference facial data for the current user of the mobile terminal is obtained. Facial similarity detection is performed based on the face data to be detected and the reference facial data. If the face corresponding to the face data to be detected is detected to be the face of the current user, a payment operation is performed based on the billing data.

[0276] or

[0277] When the distance between the device and the mobile terminal is detected to meet a preset distance range, a near-field communication connection is established with the mobile terminal; product information of the goods to be paid is received, and bill data to be paid is generated based on the product information; facial data of the target user is collected; auxiliary payment data is generated based on the facial data and the bill data; and the auxiliary payment data is sent to the mobile terminal through the near-field communication connection to trigger a payment operation based on the auxiliary payment data.

[0278] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0279] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0280] Since the instructions stored in the storage medium can execute the steps of any of the face recognition-based payment methods provided in the embodiments of this application, the beneficial effects that any of the face recognition-based payment methods provided in the embodiments of this application can achieve can be realized, as detailed in the preceding embodiments, and will not be repeated here.

[0281] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various alternative implementations of the facial recognition-based payment aspect described above.

[0282] The foregoing has provided a detailed description of a face recognition-based payment method, apparatus, electronic device, storage medium, and system. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A face recognition based payment method, characterized by, Applied to a mobile terminal, comprising: When detecting that the distance between the target face recognition device meets the preset distance range, a near field communication connection between the target face recognition device is established; Through the near field communication connection, auxiliary payment data is acquired from the target face recognition device, wherein the auxiliary payment data includes bill data and face data collected by the target face recognition device; The face data is determined as to-be-detected face data of a current user of the mobile terminal, reference face data of the current user of the mobile terminal is acquired, wherein the to-be-detected face data includes to-be-detected face image; Face similarity detection is performed based on the to-be-detected face data and the reference face data, including: face detection is performed on the to-be-detected face image to determine at least one candidate face region in the to-be-detected face image, wherein one candidate face region corresponds to one candidate user; face similarity detection is performed on the candidate face region and the reference face data; if the face similarity detection of the candidate face region and the reference face data fails, face similarity detection is performed based on the candidate face region and face data of each payment user in a payment user group of the current user to identify the user corresponding to the candidate face region; based on the identification result, a payment user list for the current user to select is generated, wherein the payment user list includes at least one payment user corresponding to the candidate face region whose identity recognition succeeds; a target payment user selected by the current user from the payment user list is acquired; based on the bill data and user identification information of the target payment user, a payment request of the target payment user is generated, and the payment request is sent to a terminal of the target payment user to trigger the target payment user to pay the bill data; If it is detected that the face corresponding to the to-be-detected face data is the face of the current user, a payment operation is performed based on the bill data. 2.The face recognition based payment method of claim 1, wherein, If it is detected that the face corresponding to the to-be-detected face data is the face of the current user, a payment operation is performed based on the bill data, including: If it is detected that the face corresponding to the to-be-detected face data is the face of the current user, a payment request is generated based on the bill data and user identification information of the current user; From the associated users of the current user, a target payment user of the bill data is determined; The payment request is sent to a terminal of the target payment user to trigger the target payment user to pay the bill data. 3.The face recognition based payment method of claim 2, wherein, From the associated users of the current user, a target payment user of the bill data is determined, including: An associated payment group to which the current user belongs is determined, wherein one associated payment group includes at least one associated user of the current user, and each associated payment group is provided with a payment user who pays bill data of the associated users in the associated payment group; The bill data is parsed to determine a transaction attribute corresponding to the bill data; Based on a preset mapping relationship between the associated payment group and the transaction attribute, a target associated payment group corresponding to the transaction attribute of the bill data is determined, and a payment user of the target associated payment group is determined as a target payment user of the bill data. 4.The face recognition based payment method of claim 1, wherein, The face similarity detection on the candidate face region and the reference face data includes: Based on the geometric features of the candidate face region, the priority of the candidate face region is calculated, wherein the priority is the priority of the candidate face region for face similarity detection; According to the priority, face similarity detection is performed on the candidate face region and the reference face data.

5. The face recognition based payment method of claim 4, wherein, The method further includes: If the face similarity detection on the candidate face region and the reference face data fails, a payment proxy user group of the current user is determined, wherein the payment proxy user group includes at least one payment proxy user of the current user; A target payment proxy user selected by the current user from the payment proxy user group is determined, and user identification information of the target payment proxy user is obtained; Based on the bill data and the user identification information of the target payment proxy user, a payment request is generated; The payment request is sent to the terminal of the target payment proxy user to trigger the target payment proxy user to pay the bill data. 6.The face recognition based payment method of claim 4, wherein, The reference face data includes face features of the current user, and the candidate face region includes channel data under at least one image channel; The face similarity detection on the candidate face region and the reference face data includes: The face features of the candidate face region are generated through the channel data; The face features of the candidate face region are compared with the face features of the current user to obtain a comparison result; According to the comparison result, the face similarity detection result of the candidate face region and the reference face data is determined. 7.The face recognition based payment method of claim 1, wherein, The method further includes: If it is detected that the face corresponding to the face data to be detected is not the face of the current user, the image acquisition module is called to acquire face data to be compared; Based on the face data to be compared and the reference face data, face similarity detection is performed; Based on the detection result, a payment operation is performed on the bill data.

8. A face recognition based payment method as claimed in any one of claims 1 to 7, wherein, Applied to a face recognition device, including: When it is detected that the distance between the mobile terminal satisfies the preset distance range, the near field communication connection between the mobile terminal is established; Receiving the product information of the product to be paid, generating the bill data to be paid based on the product information; Acquiring the face data of the target user; Based on the face data and the bill data, generating auxiliary payment data; Through the near field communication connection, the auxiliary payment data is sent to the mobile terminal to trigger the payment operation based on the auxiliary payment data. 9.The face recognition based payment method of claim 8, wherein, Acquiring the face data of the target user includes: Acquiring the original face data of the target user, wherein the original face data includes at least one candidate face image; Calculating the image quality of the candidate face image in at least one quality evaluation dimension; According to the image quality of the candidate face image, a target face image is selected from the candidate face image; Perform image processing on the target face image to obtain processed face data as the face data of the target user.

10. A face recognition based payment device, characterized by, Comprise: The first establishment unit is used for establishing a near field communication connection with the target face recognition device when it is detected that the distance between the target face recognition device meets a preset distance range; The auxiliary acquisition unit is used for acquiring auxiliary payment data from the target face recognition device through the near field communication connection, wherein the auxiliary payment data includes bill data and face data collected by the target face recognition device; The reference acquisition unit is used for determining the face data as to-be-detected face data of a current user of the mobile terminal, and acquiring reference face data of the current user of the mobile terminal, wherein the to-be-detected face data includes a to-be-detected face image; The detection unit is used for performing face similarity detection based on the to-be-detected face data and the reference face data, including: performing face detection on the to-be-detected face image to determine at least one candidate face region in the to-be-detected face image, wherein one candidate face region corresponds to one candidate user; performing face similarity detection on the candidate face region and the reference face data; if the face similarity detection of the candidate face region and the reference face data fails, performing face similarity detection based on the candidate face region and face data of each payment user in a payment user group of the current user to identify the identity of the user corresponding to the candidate face region; based on the identification result, generating a payment user list for the current user to select, wherein the payment user list includes at least one payment user corresponding to a candidate face region whose identity recognition is successful; acquiring a target payment user selected by the current user from the payment user list; based on the bill data and user identification information of the target payment user, generating a payment request of the target payment user, and sending the payment request to a terminal of the target payment user to trigger the target payment user to pay the bill data; The payment unit is used for detecting that the face corresponding to the to-be-detected face data is the face of the current user, and performing a payment operation based on the bill data.

11. The face recognition based payment device of claim 10, wherein, The payment unit comprises: The first generation subunit is used for detecting that the face corresponding to the to-be-detected face data is the face of the current user, and generating a payment request based on the bill data and user identification information of the current user; The first determination subunit is used for determining a target payment user of the bill data from associated users of the current user; The first sending subunit is used for sending the payment request to a terminal of the target payment user to trigger the target payment user to pay the bill data.

12. The facial recognition based payment device of claim 11, wherein, The first determination subunit is used for: The process involves determining the associated payment groups to which the current user belongs, wherein each associated payment group includes at least one associated user of the current user, and each associated payment group is configured with a paying user, who is a user who makes payments for the billing data of the associated users in the associated payment group; parsing the billing data to determine the transaction attributes corresponding to the billing data; and, based on a preset mapping relationship between associated payment groups and transaction attributes, determining the target associated payment group corresponding to the transaction attributes of the billing data, and identifying the paying user of the target associated payment group as the target paying user of the billing data.

13. The facial recognition based payment device of claim 10, wherein, The detection unit includes: The first calculation subunit is used to calculate the priority of the candidate face region based on the geometric features of the candidate face region, wherein the priority is the priority of the candidate face region for face similarity detection; The first detection subunit is used to perform face similarity detection on the candidate face region and the reference face data according to the priority.

14. The facial recognition based payment device of claim 13, wherein, The detection unit further includes: The second determining subunit is used to determine the current user's payment-on-behalf user group if the face similarity detection between the candidate face region and the reference face data fails, wherein the payment-on-behalf user group includes at least one payment-on-behalf user of the current user; The third determining subunit is used to determine the target payment user selected by the current user from the payment user group and to obtain the user identification information of the target payment user. The second generation subunit is used to generate a payment request based on the bill data and the user identification information of the target payment user; The second sending subunit is used to send the payment request to the terminal of the target payment user to trigger the target payment user to pay the bill data.

15. The facial recognition based payment device of claim 13, wherein, The reference facial data includes the facial features of the current user, and the candidate facial region includes channel data from at least one image channel; the first detection subunit is configured to: The facial features of the candidate face region are generated using the channel data; the facial features of the candidate face region are compared with the facial features of the current user to obtain a comparison result; based on the comparison result, the facial similarity detection result between the candidate face region and the reference face data is determined.

16. The facial recognition based payment device of claim 10, wherein, The facial recognition-based payment device further includes: The calling unit is used to collect face data to be compared by calling the image acquisition module if it is detected that the face corresponding to the face data to be detected is not the face of the current user; to perform face similarity detection based on the face data to be compared and the reference face data; and to perform payment operation based on the detection result and the bill data.

17. A face recognition based payment device of the apparatus of any one of claims 10 to 16, wherein, include: The second establishment unit is used to establish a near-field communication connection with the mobile terminal when the distance between the mobile terminal is detected to meet the preset distance range. The bill generation unit is used to receive product information of goods to be paid and generate bill data to be paid based on the product information; The acquisition unit is used to collect facial data from the target user. An auxiliary generation unit is configured to generate auxiliary payment data based on the face data and the bill data; A sending unit is configured to send the auxiliary payment data to the mobile terminal through the near field communication connection to trigger a payment operation based on the auxiliary payment data.

18. The facial recognition based payment device of claim 17, wherein, The collection unit comprises: A data collection subunit is configured to collect original face data of a target user, wherein the original face data comprises at least one candidate face image; A second calculation subunit is configured to calculate image quality of the candidate face image in at least one quality evaluation dimension; An image selection subunit is configured to select a target face image from the candidate face images according to the image quality of the candidate face images; An image processing subunit is configured to perform image processing on the target face image to obtain processed face data as the face data of the target user.

19. An electronic device, comprising: The memory stores an application program, and the processor is configured to run the application program in the memory to perform the operations in the face recognition-based payment method of any one of claims 1 to 9.

20. A storage medium, characterized by The storage medium stores a plurality of instructions, and the instructions are adapted to be loaded by the processor to perform the steps in the face recognition-based payment method of any one of claims 1 to 9.

21. A computer program product, characterised in that, The computer program product comprises computer instructions stored in a computer readable storage medium; the processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to enable the computer device to perform the steps in the face recognition-based payment method of any one of claims 1 to 9.