A face payment prompting method, device and equipment
By using facial recognition payment devices to detect users' facial images and distance in real time, and automatically prompting users to make facial recognition payments, the problem of users' lack of awareness of new payment methods is solved, and the effects of reducing labor costs and improving user experience are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ADVANCED NEW TECHNOLOGIES CO LTD
- Filing Date
- 2019-04-15
- Publication Date
- 2026-06-12
Smart Images
Figure CN116051115B_ABST
Abstract
Description
[0001] This application is a divisional application of the invention entitled "A method, device and equipment for facial recognition payment prompts", filed on April 15, 2019, with application number 2019103013078. Technical Field
[0002] This specification relates to the field of facial recognition technology, and in particular to a method, device and equipment for prompting facial recognition payment. Background Technology
[0003] Facial recognition is a biometric identification technology that authenticates identity based on facial features. With its development, facial recognition technology has been applied to various fields. Face-scanning payment is a new payment method in offline scenarios. Because it's still relatively new to users, most people tend to ignore the existing face-scanning payment devices at supermarket and convenience store checkouts, remaining unaware of this new product. Therefore, cashiers often need to actively recommend or inquire about these devices to attract customers' attention. Therefore, by having the face-scanning device proactively greet users when they approach, prompting them to use face-scanning payment, not only can labor costs be saved, but the user experience can also be improved. Summary of the Invention
[0004] Based on this, this specification provides a method, device, and equipment for prompting facial recognition payment.
[0005] According to a first aspect of the embodiments of this specification, a facial recognition payment prompt method is provided, applicable to facial recognition payment devices, comprising:
[0006] When a user's face image is detected in the captured video image, it is determined whether the user is the target user based on the face image. The target user meets the following conditions: the face image is a face image in a specified state, and the distance between the user and the face-scanning payment device is less than a preset distance.
[0007] If so, the target user will be prompted to make a facial recognition payment.
[0008] According to a second aspect of the embodiments of this specification, a facial recognition payment device is provided, suitable for facial recognition payment equipment, comprising:
[0009] The judgment module is used to determine whether the user is a target user based on the face image when a user's face image is detected in the captured video image. The target user meets the following conditions: the face image is a face image in a specified state, and the distance between the user and the face-scanning payment device is less than a preset distance.
[0010] The prompting module is used to prompt the target user to make a face-scanning payment if the user is the target user.
[0011] According to a third aspect of the embodiments of this specification, a facial recognition payment device is provided, including a memory, a processor, and a video acquisition device. The memory stores a computer program that can run on the processor, and the processor executes the program to implement the method described in any of the embodiments.
[0012] Applying the embodiments of this specification, the facial recognition payment device captures real-time video images of the surrounding environment through a video capture device. When a user's face image is detected in the captured video images, the device determines whether the face image is in a specified state and calculates the distance between the user and the facial recognition payment device based on the face image. It then determines whether the distance is less than a preset distance. If the above conditions are met, the device prompts the target user to make a facial recognition payment. By determining whether the user is a target user with payment intention through the captured user's face image, and then proactively prompting the user to make a facial recognition payment instead of the cashier, the device interacts with the user, thus improving the user experience.
[0013] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this specification. Attached Figure Description
[0014] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this specification and, together with the description, serve to explain the principles of this specification.
[0015] Figure 1 This is a flowchart of a facial recognition payment prompt method according to one embodiment of this specification;
[0016] Figure 2 This is a flowchart illustrating a facial recognition payment prompt method according to one embodiment of this specification.
[0017] Figure 3 This is a schematic diagram of the logical structure of a facial recognition payment prompt device according to one embodiment of this specification;
[0018] Figure 4 This is a schematic diagram of the logical structure of a facial recognition payment device according to one embodiment of this specification. Detailed Implementation
[0019] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this specification. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this specification as detailed in the appended claims.
[0020] The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of this specification. The singular forms “a,” “the,” and “the” as used in this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.
[0021] It should be understood that although the terms first, second, third, etc., may be used in this specification to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this specification, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."
[0022] Facial recognition-based payment is a new payment method in offline scenarios. Currently, supermarkets, convenience stores, and shopping malls are all using facial recognition payment devices. Because facial recognition payment is still a relatively new method for users, most people tend to ignore these devices and are unaware of this new product. Therefore, cashiers often need to actively recommend or remind customers to use it. Therefore, having the facial recognition payment device proactively greet and remind users when they approach, instead of a cashier, not only saves labor costs but also improves the user experience.
[0023] Based on this, embodiments of this specification provide a facial recognition payment prompt method. This method is applicable to facial recognition payment devices. The facial recognition payment device can continuously collect video images. When a facial image is detected in the video image, it can determine whether the user is a target user intending to make a payment based on the facial image, and then prompt the user to perform facial recognition payment. Figure 1 As shown, the method may include:
[0024] S102. When a user's face image is detected in the acquired video image, determine whether the user is the target user based on the face image, wherein the target user meets the following conditions: the face image is a face image in a specified state, and the distance between the user and the face-scanning payment device is less than a preset distance.
[0025] S104. If so, prompt the target user to make a face-scanning payment.
[0026] Typically, facial recognition payment devices are placed at checkout counters. These devices include video capture units that continuously collect video images of the area around the device, monitoring the surrounding environment. When a user approaches the device, the video capture unit will include the user's face. The device continuously detects whether a face is present in the captured video images. This detection can be based on existing face detection algorithms, which are now quite mature. Examples include using Haar or HOG features combined with SVM or AdaBoost classification algorithms, or using deep learning algorithms like Fast R-CNN. Using Haar features combined with SVM or AdaBoost is a relatively traditional face detection method. This method assumes a sub-window continuously moves within the video image window during face detection. At each position, the sub-window calculates the features for that region, which are then filtered by an SVM classifier. If a feature passes the classifier's filter, the region is identified as a face. However, this method is less effective and inefficient. The most commonly used face detection algorithm is the Fast R-CNN algorithm based on deep learning. Fast R-CNN is an optimization of R-CNN. R-CNN (Region with CNN feature) applies convolutional neural networks to the face detection problem. CNN has good feature extraction and classification performance. The RegionProposal method for object detection mainly includes the following three steps: (1) Candidate region selection. (2) CNN feature extraction. (3) Classification and boundary regression. The RCNN algorithm overlaps with a large number of candidate frames in the image, resulting in a lot of redundancy in the feature extraction operation. Fast R-CNN solves this problem well, and the training speed is improved.
[0027] If a facial image is detected in the video image, the system further determines whether the user is a target user based on the captured facial image. A target user is someone who may intend to pay. When a user wants to pay, they often walk towards the cashier. At this time, the facial recognition payment device at the cashier is directly facing the user, thus capturing a frontal image of the user's face. In other words, the user's face is directly facing the facial recognition device, resulting in a relatively small angle between the face and the screen. Furthermore, the distance between the user needing to pay and the facial recognition device at the cashier is also relatively small. Therefore, users meeting the following conditions can be identified as target users with payment intentions: the captured facial image is a facial image in a specified state, and the distance between the user and the facial recognition device is less than a preset distance. A facial image in a specified state refers to an image that meets pre-set conditions, such as a frontal facial image, and the tilt or yaw angle of the facial image being within a preset range. Specific conditions can be flexibly set according to actual conditions. Additionally, the distance between the target user and the facial recognition payment device can be calculated using the captured facial image and pre-calibrated intrinsic and extrinsic parameters of the video capture device. The distance between the target user and the facial recognition payment device can be calculated using a binocular vision algorithm. Since the video capture device projects the three-dimensional spatial coordinates of the target object onto two-dimensional spatial coordinates, after calibrating the camera's intrinsic and extrinsic parameters, the three-dimensional coordinates of the face in three-dimensional space, and the distance between the face (target user) and the video capture device (facial recognition payment device), can be calculated using these parameters and the two-dimensional position coordinates of the captured facial image. A distance threshold can be preset, for example, to 80cm. If the distance between the user and the facial recognition device calculated from the captured facial image is less than 80cm, the user is considered to meet the criteria.
[0028] Once a user is identified as a target user, it is assumed that the user intends to make a payment. At this point, the facial recognition payment device can prompt the user to use the device to make a facial recognition payment.
[0029] This embodiment of the specification uses a facial recognition payment device to collect video images of the surrounding environment in real time. When a user's face is detected in the video image, it determines whether the face image is a face image in a specified state, and calculates the distance between the user and the facial recognition payment device based on the collected face image. It then determines whether this distance is less than a preset distance. If both conditions are met, the user is considered a target user with payment intention, and the facial recognition payment device will prompt the user to use it for facial recognition payment. In this way, the facial recognition payment device can replace the cashier in prompting users to pay, and it increases the interaction between the facial recognition payment device and the user, improving the user experience.
[0030] Since customers typically approach the checkout counter facing the cashier, the captured facial images are usually frontal, not profile shots. Therefore, it can be assumed that a frontal facial image indicates a higher probability of the customer intending to pay. Thus, in some embodiments, a specific facial image can be set to a frontal view. When a facial image is detected in a video image, a pre-defined algorithm is first used to determine if it is a frontal view. Only if it is is the user considered to meet the criteria. Currently, the technology for determining whether a facial image is frontal is relatively mature, and pre-trained classification models can be used to determine whether a facial image is frontal.
[0031] In some embodiments, determining whether a captured face image is a frontal face image can be achieved using the following method: First, multiple key feature points are extracted from the captured 2D face image, and the coordinates of these key feature points in the 2D image are determined. Then, the 3D coordinates corresponding to the key feature points are calculated based on the pre-calibrated intrinsic and extrinsic parameters of the video capture device, and a 3D face model is established. Next, the user's face deflection angle is determined based on the standard frontal 3D face model and the 3D face model established from the captured face image. Assuming the standard frontal face is parallel to the screen, the angle between the user's face and the screen can be obtained based on the face deflection angle, and it is determined whether this angle is within a preset range, such as less than 15°. If so, the face image is determined to be a frontal face image. Determining whether a face image is a frontal face image by calculating the angle between the face and the screen is more accurate than using a classification model.
[0032] After identifying a user as the target user, the facial recognition payment device can prompt the user and recommend using the device for payment. The method of prompting the user to use the facial recognition payment device can be set according to actual needs. For example, in some embodiments, a voice announcement can be used to prompt the user to use the device for facial recognition payment. In some embodiments, a prompt message can also be displayed on the screen of the facial recognition payment device to prompt the user to make a facial recognition payment. The prompt message can consist of images, text, etc., such as "Welcome to use this device for facial recognition payment." Of course, both voice announcements and text prompts can be used simultaneously; this specification does not impose any limitations. In some embodiments, the prompt message can include a cartoon character, such as a cartoon person or animal. To increase engagement, the cartoon character can perform specific actions to interact with the user, such as waving, greeting, or smiling.
[0033] After informing users that they can use facial recognition payment devices, cartoon avatars can interact with them to increase the fun of the payment process and allow users to warm up to the device before making a payment. For example, in some embodiments, the user's facial movements can be detected, and the cartoon avatar can be controlled to perform corresponding actions, increasing interaction between the two. For instance, if the user blinks, the cartoon avatar blinks; if the user shakes their head, the cartoon avatar shakes their head; if the user smiles, the cartoon avatar smiles; if the user is angry, the cartoon avatar makes an angry face. Through these interactions, the payment process becomes more fun, and users develop a positive impression of the facial recognition device. Facial movement detection can be achieved using mature facial pose algorithms, which analyze facial movements and then control the cartoon avatar to perform corresponding actions.
[0034] Normally, when no target user is detected, the facial recognition payment device can remain in standby mode. Only after a target user is detected will it enter an interface containing prompts for facial recognition payment. Often, the detected target user may not intend to use facial recognition payment, in which case it can return to the standby screen. For example, after prompting the user to make a facial recognition payment, a timer can be started. If the timer exceeds a preset duration, it can then check if a facial recognition payment command has been detected. This command can be entered by the user clicking the facial recognition payment button on the screen. If no command is detected, it returns to the standby screen.
[0035] The facial recognition payment device in the embodiments of this specification may include one or more video capture devices. In some embodiments, the facial recognition payment device may include one video capture device that can switch between two-dimensional and three-dimensional perspectives. It can use a two-dimensional perspective to capture video images of the area surrounding the facial recognition payment device in real time. When a target user is detected, a facial recognition payment prompt is issued. Upon receiving a facial recognition command input by the user, the two-dimensional perspective of the video capture is switched to a three-dimensional perspective to capture a three-dimensional face image. This three-dimensional face image is then recognized to complete the facial recognition payment. Since face detection has lower requirements for the captured image, a two-dimensional face image can be used. However, face recognition has higher requirements for the image, requiring the extraction of more feature information to avoid false recognition; therefore, a three-dimensional face image can be used. After the facial recognition payment is completed, the video capture device will switch from a three-dimensional perspective mode to a two-dimensional perspective mode. At this time, since the user has not yet left, the user's face can still be captured, and the user will still be identified as the target user based on the captured face image, prompting a prompt. To avoid this situation, a certain delay can be set after the facial recognition payment is completed before re-executing the facial recognition payment prompt process.
[0036] To further explain the facial recognition payment prompt method provided in the embodiments of this specification, a detailed embodiment will be described below.
[0037] Facial recognition payment is a new payment method that is already in use in major shopping malls and supermarkets. However, as it is a new payment method, many users are currently unaware of the facial recognition payment devices at the checkout counter. To enable facial recognition payment devices to proactively prompt users to use facial recognition payment, increase interaction between the device and the user, and enhance the payment process, a facial recognition payment prompt method is provided. This facial recognition payment prompt method is applied to facial recognition payment devices. Figure 2 This is a schematic diagram illustrating the specific facial recognition payment method. The facial recognition payment device includes a video capture device that can switch between two-dimensional and three-dimensional perspectives, capturing both 2D and 3D video images. The 2D mode is used to monitor the surroundings of the facial recognition payment device in real time, capturing video images of the area. When a captured video image includes a user's face, it determines whether the face is a frontal view and calculates the distance between the user and the device based on the face image and pre-calibrated intrinsic and extrinsic parameters of the video capture device. It then checks if this distance is less than a preset distance. If the conditions are met, the user is identified as the target user, and a voice prompt prompts them to proceed with facial recognition payment. The screen transitions from standby to a welcome screen, displaying a text message prompting the user to make the payment. This message includes a cartoon character that interacts with the user, performing actions such as nodding, blinking, smiling, or shaking their head upon detecting facial movement, to enhance the payment process. After prompting the user for facial recognition payment, a timer begins. If the preset time expires and no facial recognition payment command is detected by the user clicking the on-screen facial recognition payment button, the screen returns to the standby interface. If a facial recognition payment command is detected, the video capture device switches from 2D mode to 3D mode, captures the user's 3D facial image, recognizes the 3D facial image, and completes the facial recognition payment. The various technical features in the above embodiments can be combined arbitrarily, as long as there is no conflict or contradiction between the combinations of features. However, due to space limitations, not all combinations are described individually. Therefore, any combination of the various technical features in the above embodiments falls within the scope of this specification.
[0038] like Figure 3 The image shown is an embodiment of a facial recognition payment prompt device according to this specification. The device may include:
[0039] The judgment module 31 is used to determine whether the user is a target user based on the face image when a user's face image is detected in the acquired video image, wherein the target user meets the following conditions: the face image is a face image in a specified state, and the distance between the user and the face-scanning payment device is less than a preset distance;
[0040] The prompting module 32 is used to prompt the target user to make a face-scanning payment if the user is the target user.
[0041] In one embodiment, the face image of the specified state includes:
[0042] The facial image is a frontal image.
[0043] In one embodiment, the process of determining that the face image is a frontal face image includes:
[0044] Based on the facial image, determine whether the angle between the user's face and the screen of the facial recognition payment device is less than a preset angle;
[0045] If the value is smaller than the specified value, the face image is determined to be a frontal face image.
[0046] In one embodiment, prompting the target user to make a facial recognition payment includes:
[0047] The user is prompted to make a facial recognition payment via voice prompt; or,
[0048] The screen of the facial recognition payment device displays a prompt message reminding the user to make a facial recognition payment.
[0049] In one embodiment, the prompt text includes a cartoon image that performs a specified action to interact with the user.
[0050] In one embodiment, after prompting the target user to make a facial recognition payment, the method further includes:
[0051] Detect the user's facial movements;
[0052] The cartoon character is controlled to perform corresponding actions based on the facial movements.
[0053] In one embodiment, after prompting the target user to make a facial recognition payment, the method further includes:
[0054] Start the timer;
[0055] When the timeout period exceeds the predetermined time, determine whether the user's input of a facial recognition payment command has been detected;
[0056] If not detected, the system will return to the standby screen.
[0057] In one embodiment, the video image is a two-dimensional video image, and after prompting the target user to perform facial recognition payment, the method further includes:
[0058] Receive the facial recognition payment instruction input by the target user;
[0059] The three-dimensional image acquisition device is invoked to acquire a three-dimensional facial image of the target user;
[0060] The system identifies the 3D facial image and completes facial recognition payment.
[0061] For details on the implementation process of the functions and roles of each module in the above device, please refer to the implementation process of the corresponding steps in the above method, which will not be repeated here.
[0062] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of the solution in this specification according to actual needs. Those skilled in the art can understand and implement this without creative effort.
[0063] The embodiments of the device described in this specification can be applied to computer devices, such as servers or smart terminals. The device embodiments can be implemented through software, hardware, or a combination of both. Taking software implementation as an example, as a logical device, it is formed by a processor that handles file processing reading the corresponding computer program instructions from non-volatile memory into memory for execution. From a hardware perspective, such as... Figure 4 The diagram shown is a hardware structure diagram of a facial recognition payment device, in which the device described in this manual is located. (Except for...) Figure 4 In addition to the processor 402, memory 404, network interface 406, and non-volatile memory 408 shown, and the video acquisition device 4010, the server or electronic device in which the device is located in the embodiment may also include other hardware depending on the actual function of the computer device, which will not be described in detail here.
[0064] Accordingly, embodiments of this specification also provide a computer storage medium storing a program that, when executed by a processor, implements the method in any of the above embodiments.
[0065] Accordingly, embodiments of this specification also provide a facial recognition payment device, including a memory, a processor, a video capture device, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method in any of the above embodiments.
[0066] This application may take the form of a computer program product implemented on one or more storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing program code. Computer storage media include permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information may be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to: phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.
[0067] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the description disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.
[0068] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.
[0069] The above description is merely a preferred embodiment of this disclosure and is not intended to limit this disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.
Claims
1. A facial recognition payment device, wherein the facial recognition payment device is an integrated device, the integrated device comprising at least a video acquisition device, a display screen, a processor, and a memory, wherein the memory stores a computer program executable by the processor, and the processor executes the computer program to perform the following steps: Acquire video images of the environment surrounding the facial recognition payment device captured by the video acquisition device; If a target user with payment intent is detected around the facial recognition payment device based on the video image, the display page of the screen is switched from the standby page to the facial recognition payment prompt page. The cartoon character on the facial recognition payment prompt page interacts with the target user to prompt the target user to use the facial recognition payment device for facial recognition payment. Upon detecting a facial recognition payment instruction, the display screen is switched from the facial recognition payment prompt page to the facial recognition payment page, and the facial image of the target user is captured through the facial recognition payment page for payment verification.
2. The facial recognition payment device according to claim 1, wherein the video acquisition device includes a two-dimensional view mode and a three-dimensional view mode; in the two-dimensional view mode, the image acquired by the video acquisition device is a two-dimensional image, and in the three-dimensional view mode, the image acquired by the video acquisition device is a three-dimensional image, and the video image of the surrounding environment of the facial recognition payment device is a two-dimensional image. After switching the display page of the screen from the facial recognition payment prompt page to the facial recognition payment page, the processor is further configured to: The video capture device is switched from the two-dimensional view mode to the three-dimensional view mode to capture the three-dimensional facial image of the target user for payment verification.
3. In the facial recognition payment device according to claim 1, after switching the display page of the screen from the standby page to the facial recognition payment prompt page, the processor is further configured to: If no facial recognition payment instruction is detected after a preset time period, the display screen will return to the standby page.
4. The facial recognition payment device according to any one of claims 1-3, wherein the facial recognition payment prompt page includes a facial recognition payment control, and the target user can trigger the facial recognition payment instruction by touching the facial recognition payment control.
5. The facial recognition payment device according to claim 1, wherein when the processor interacts with the target user through the cartoon character on the facial recognition payment prompt page, it is specifically used for: Detect the facial movements of the target user; The cartoon character is controlled to perform corresponding actions based on the facial movements.
6. The facial recognition payment device according to claim 1, wherein when the processor detects a target user with payment intent in the vicinity of the facial recognition payment device based on the video image, it is specifically configured to: If a user's face image is detected in the video image, and the distance between the user and the facial recognition payment device is less than a preset distance, and the face image is a face image in a specified state, then it is determined that there is a target user with payment intent around the facial recognition payment device.
7. The facial recognition payment device according to claim 6, wherein the facial image in the specified state includes: The facial image is a frontal image.
8. The facial recognition payment device according to claim 7, wherein if the angle between the user's face and the display screen is less than a preset angle based on the facial image, the facial image is determined to be a frontal face image.
9. A method for prompting payment via facial recognition, applicable to a facial recognition payment device, wherein the facial recognition payment device is an integrated device, and the integrated device integrates at least a video capture device and a display screen, the method comprising: Acquire video images of the environment surrounding the facial recognition payment device captured by the video acquisition device; If a target user with payment intent is detected around the facial recognition payment device based on the video image, the display page of the screen is switched from the standby page to the facial recognition payment prompt page. The cartoon character on the facial recognition payment prompt page interacts with the target user to prompt the target user to use the facial recognition payment device for facial recognition payment. Upon detecting a facial recognition payment instruction, the display screen is switched from the facial recognition payment prompt page to the facial recognition payment page, and the facial image of the target user is captured through the facial recognition payment page for payment verification.
10. The method according to claim 9, wherein the video acquisition device includes a two-dimensional view mode and a three-dimensional view mode; in the two-dimensional view mode, the image acquired by the video acquisition device is a two-dimensional image, and in the three-dimensional view mode, the image acquired by the video acquisition device is a three-dimensional image, and the video image of the environment surrounding the facial recognition payment device is a two-dimensional image. After switching the display page of the screen from the facial recognition payment prompt page to the facial recognition payment page, the method further includes: The video capture device is switched from the two-dimensional view mode to the three-dimensional view mode to capture the three-dimensional facial image of the target user for payment verification.
11. The method according to claim 9, after switching the display page of the screen from the standby page to the facial recognition payment prompt page, the method further includes: If no facial recognition payment instruction is detected after a preset time period, the display screen will return to the standby page.
12. The method according to any one of claims 9-11, wherein the face recognition payment prompt page includes a face recognition payment control, and the target user can trigger the face recognition payment instruction by touching the face recognition payment control.
13. The method according to claim 9, wherein interacting with the target user through a cartoon character on the facial recognition payment prompt page comprises: Detect the facial movements of the target user; The cartoon character is controlled to perform corresponding actions based on the facial movements.
14. The method according to claim 9, wherein detecting the presence of a target user with payment intent around the facial recognition payment device based on the video image includes: If a user's face image is detected in the video image, and the distance between the user and the facial recognition payment device is less than a preset distance, and the face image is a face image in a specified state, then it is determined that there is a target user with payment intent around the facial recognition payment device.
15. The method according to claim 14, wherein the face image in the specified state comprises: The facial image is a frontal image.
16. The method according to claim 14, wherein if the angle between the user's face and the display screen is less than a preset angle based on the face image, then the face image is determined to be a frontal face image.
17. A facial recognition payment prompt device, applicable to facial recognition payment equipment, wherein the facial recognition payment equipment is an integrated device, and the integrated device integrates at least a video capture device and a display screen, the device comprising: The acquisition module acquires video images of the environment surrounding the facial recognition payment device, captured by the video acquisition device. The prompting module is configured to, when detecting a target user with payment intent around the facial recognition payment device based on the video image, switch the display page of the screen from the standby page to the facial recognition payment prompt page, and interact with the target user through a cartoon character on the facial recognition payment prompt page to prompt the target user to use the facial recognition payment device for facial recognition payment; and when a facial recognition payment instruction is detected, switch the display page of the screen from the facial recognition payment prompt page to the facial recognition payment page, and collect the target user's facial image through the facial recognition payment page for payment verification.