Payment method recommendation processing method, device, equipment and system

Abstract

This specification provides a payment method recommendation processing method, apparatus, device, and system. Before a user approaches a payment device, the system identifies whether a user intends to use the payment device by identifying images of the device's surroundings. After determining that a user is approaching the payment device, the system then identifies the user's intended payment method by performing motion recognition on the user's pre-payment motion image. The system then recommends the target payment method to the user. This eliminates the need for users to select their own payment method, meets the payment needs of different users, reduces payment time, and improves payment efficiency.

Description

Technical Field

[0001] This specification belongs to the field of computer technology, and in particular relates to a payment method recommendation processing method, device, equipment and system. Background Art

[0002] With the development of computer and internet technology, online payment methods are becoming increasingly common, such as facial recognition, QR code scanning, and card payment. As technology advances, devices capable of making and receiving payments are gradually emerging. As payment methods increase, the number of payment methods supported by these devices is also gradually expanding. When a device supports two or more payment methods, users may need to manually select a payment method, which is cumbersome, affects payment efficiency, and increases user interaction costs. Summary of the Invention

[0003] The purpose of the embodiments of this specification is to provide a payment method recommendation processing method, device, equipment and system to improve payment efficiency.

[0004] In one aspect, an embodiment of this specification provides a method for processing payment method recommendations, the method comprising:

[0005] identifying whether a payment object is approaching the payment device based on image information of the surrounding environment of the payment device;

[0006] After determining that a payment object is approaching the payment device, obtaining motion image information of the payment object;

[0007] Matching the action image information with pre-set key actions corresponding to different payment methods to determine the target payment method corresponding to the payment object;

[0008] The target payment method is displayed to the payment object so that the payment object can perform a payment operation.

[0009] In another aspect, this specification provides a payment method recommendation processing device, the device comprising:

[0010] An approach detection module, configured to identify whether a payment object is approaching the payment device based on image information of the surrounding environment of the payment device;

[0011] a motion image acquisition module, configured to acquire motion image information of a payment object after determining that the payment object is approaching the payment device;

[0012] An action detection module is used to match the action image information with pre-set key actions corresponding to different payment methods to determine the target payment method corresponding to the payment object;

[0013] The payment method recommendation module is used to present the target payment method to the payment object so that the payment object can perform a payment operation.

[0014] On the other hand, an embodiment of the present specification provides a payment method recommendation processing device, including at least one processor and a memory for storing processor-executable instructions, and the processor implements the above-mentioned payment method recommendation processing method when executing the instructions.

[0015] In another aspect, an embodiment of the present specification provides a payment method recommendation processing system, the system comprising: a payment device and a payment server, wherein:

[0016] The payment device is provided with an image acquisition unit and a display screen, wherein the image acquisition unit is used to acquire image information of the surrounding environment and image information of the movement of the payment object;

[0017] The payment server includes at least one processor and a memory for storing processor-executable instructions. When the processor executes the instructions, the payment method recommendation processing method is implemented, which is used to identify whether a payment object is approaching the payment device based on the surrounding environment image information collected by the payment device. After determining that a payment object is approaching the payment device, the payment object's action image information is obtained, and the action image information is matched with pre-set key actions corresponding to different payment methods to determine the target payment method corresponding to the payment object, and the target payment method is returned to the payment device.

[0018] The payment device displays the target payment method to the payment object on a display screen according to the target payment method returned by the payment server, so that the payment object can perform a payment operation.

[0019] The payment method recommendation processing method, apparatus, device, and system provided in this specification identify users who need to use the payment device by identifying images of the payment device's surroundings before the user approaches the payment device. After determining that a user is approaching the payment device, the system then identifies the user's desired payment method by performing motion recognition on the user's pre-payment motion image information, and recommends the determined target payment method to the user. This eliminates the need for users to select their own payment method, meets the payment needs of different users, reduces payment time, and improves payment efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0021] Figure 1 This is a flowchart of an embodiment of a payment method recommendation processing method provided in an embodiment of this specification;

[0022] Figure 2 This is a flowchart of a payment method recommendation process in another embodiment of this specification;

[0023] Figure 3 This is a schematic diagram of the module structure of an embodiment of the payment method recommendation processing device provided in this specification;

[0024] Figure 4 This is a hardware structure block diagram of a payment method recommendation processing server in one embodiment of this specification. DETAILED DESCRIPTION

[0025] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. All other embodiments derived by those skilled in the art based on the embodiments in this specification without creative effort shall fall within the scope of protection of this specification.

[0026] With technological advancements, the emergence of payment devices has facilitated people's daily shopping needs. Users can make online payments through payment devices, eliminating the need to carry cash. Typically, payment devices may only support QR code scanning and may not support other payment methods, such as facial recognition payment. Such payment devices may not be able to complete payments if the user does not have the client. Alternatively, some payment devices support multiple payment methods but require the user to manually select one. This can easily result in the payment method displayed being different from the one requested, leading to payment failures or extended payment interactions.

[0027] The embodiments of this specification provide a payment method recommendation processing method, which collects images of the environment surrounding the payment device to identify whether a user needs to make a payment. After determining that a user has made a payment, the payment method that the user is most likely to use is determined based on the user's actions before payment, thereby recommending the payment method the user needs, reducing the steps for the user to manually select the payment method, and improving payment efficiency.

[0028] Figure 1 It is a flow chart of an embodiment of the payment method recommendation processing method provided in the embodiment of this specification. Although this specification provides the method operation steps or device structure as shown in the following embodiments or drawings, the method or device may include more or fewer operation steps or module units after partial merger based on routine or no creative labor. In the steps or structures where there is no necessary causal relationship logically, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure shown in the embodiments or drawings of this specification. When the method or module structure is applied to an actual device, server or terminal product, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiment or drawings (for example, a parallel processor or multi-threaded processing environment, or even a distributed processing, server cluster implementation environment).

[0029] The payment method recommendation processing method provided in the embodiments of this specification can be applied to the client or server, such as: it can be applied to the local client of the payment device, or to the server that communicates data with the payment device, or it can also be applied to a client with certain data processing capabilities such as: a smartphone, tablet computer, computer or other terminal that can communicate data with the payment device. The specific method can be determined according to actual needs and is not specifically limited in the embodiments of this specification.

[0030] like Figure 1 As shown, the method may include the following steps:

[0031] Step 102: Identify whether a payment object is approaching the payment device based on the image information of the surrounding environment of the payment device.

[0032] In the specific implementation process, the payment device can be understood as a terminal with online payment collection capabilities, and the user can complete the payment by scanning a code or using facial recognition on the payment device. The payment device in the embodiments of this specification can be equipped with an image acquisition module such as a camera, etc., and can also be equipped with a display screen that can display information such as the payment amount and payment method. The camera in the payment device can collect image information of the surrounding environment of the payment device, and based on the surrounding image information, it can identify whether there is a payment object, such as a user approaching the payment device. For example, it can identify whether there is a person in the surrounding image information. If there is a person, it is considered that there is a payment object approaching the payment device. Among them, the payment object can be understood as a user who needs to use the payment device to make a payment.

[0033] It should be noted that, referring to the description of the above embodiments, it can be understood that the payment method recommendation method in the embodiments of this specification can be applied to a local terminal of a payment device or to a server. If applied to a local terminal of a payment device, the camera in the payment device can capture image information of the surrounding environment of the payment device and send it to the processor of the payment device, which then processes the image. If applied to a server, the camera in the payment device can capture image information of the surrounding environment of the payment device and send it to the server, which then processes the image.

[0034] Step 104: After determining that a payment object is approaching the payment device, obtain motion image information of the payment object.

[0035] In a specific implementation, the payment device can continuously collect image information of its surroundings during idle time, identify the collected image information, and determine whether a payee is approaching the payment device. Once a payee is determined to be approaching the payment device, the payment method can be determined and recommended to the payee. Specifically, the payment device's surrounding images are monitored to detect whether a user is approaching the payment device. After identifying a payee approaching the payment device through the payment device's surrounding image information, image information of the payee before payment, i.e., motion image information of the payee, can be obtained by continuing to capture it through the payment device's camera. It should be noted that the motion image information of the payee can include the surrounding image information used to identify the payee approaching the payment device, and can also include image information of the payee collected after identifying the payee approaching the payment device. In other words, the motion image information can include multiple images, and both the surrounding image information identifying the payee approaching the payment device and the image information of the payee before payment can be used as the motion image information of the payee. The specific configuration can be based on actual needs and is not specifically limited in the embodiments of this specification.

[0036] Step 106: Match the action image information with pre-set key actions corresponding to different payment methods to determine the target payment method corresponding to the payment object.

[0037] In the specific implementation process, the key actions of users when using different payment methods can be obtained based on historical data. Key actions can be understood as the habitual actions of most users when using different payment methods. For example, if a general user uses face-swiping payment, he may need to take off his mask, hat, glasses, look at the camera, etc. If the user uses code scanning payment, he may look down at the phone, raise the phone, take the phone out of his pocket, etc. The key actions corresponding to different payment methods can be obtained based on the analysis of the action data of users when using different payment methods. The specific content of the key actions at the time of different payments can be set based on actual application needs, and the embodiments of this specification do not make specific limitations. After obtaining the action image information of the payment object, the action image information of the payment object can be subjected to action recognition, the action of the payment object in the image can be identified, and the identified action can be matched with the key actions corresponding to the pre-set different payment methods to determine whether there is a key action that conforms to a certain payment method in the action image information of the payment object. If so, the target payment method to be used by the payment object can be determined.

[0038] In some embodiments of this specification, matching the action image information with pre-set key actions corresponding to different payment methods to determine the target payment method corresponding to the payment object includes:

[0039] Inputting the action image information into an action detection model, and using the action detection model to obtain the probability that the payment object hits the key actions of different payment methods; wherein the action detection model is trained based on historical action image information of historical payment objects, wherein the historical action image information includes the key actions corresponding to different payment methods;

[0040] The target payment method is determined according to the probability of the payment object hitting key actions of different payment methods.

[0041] During the specific implementation process, some embodiments of this specification can pre-train and construct an action detection model. The action detection model can be trained based on the historical action image information of historical payment objects. The historical action image information includes key actions corresponding to different payment methods. The historical action image information of historical users using different payment methods can be used to obtain the key actions of users when using different payment methods, perform model training, and obtain an action detection model.

[0042] In some embodiments of this specification, the training method of the action detection model includes:

[0043] Collect historical action image information of multiple payment objects using different payment methods, and configure key action sets corresponding to different payment methods;

[0044] marking the historical action image information according to the key action set, marking the key actions in each historical action image information;

[0045] The action detection model is trained using the annotated historical action image information until the action detection model reaches a preset accuracy or the number of training times reaches a preset number.

[0046] During implementation, key action sets corresponding to different payment methods can be defined based on analysis of user actions when using different payment methods. For example, the key action set corresponding to face-scanning payment is {remove mask, hat, glasses}, the key action set corresponding to QR code payment is {look down at phone, raise phone, take phone from pocket}, and the key action set corresponding to self-selected payment method is {no obvious action}. Then, historical action images of multiple payment subjects using different payment methods are collected. These images are annotated based on the defined key action sets corresponding to different payment methods, identifying the key actions within each historical action image. For example, actions such as removing mask, hat, and glasses are annotated within the image. The input of the model can be set as historical action image information, and the output can be set as the probability distribution of different key actions. For example, if the key actions include taking off the mask, taking off the hat, taking off the glasses, looking down at the phone, raising the phone, taking the phone from the pocket, and {no obvious action 7 in the above examples, then the output probability distribution P = [p0, p1, p2, ..., p6], which respectively represent the probability of hitting the 7 actions, and the sum of the seven probabilities is 1. Based on the set model input and output, the action detection model is trained using the annotated historical action image information until the action detection model reaches a preset accuracy or the number of training times reaches a preset number. In addition, the image information in the embodiments of this specification can include two types, one is an RGB image, i.e., a color image, and the other is a 3D image, i.e., a depth image. The two images can be aligned according to the acquisition time sequence of the two images and used as the input of the model.

[0047] In the embodiments of this specification, the action detection model network structure can be composed of two ResNet18s, one accepting RGB images and the other accepting 3D images. The model loss function can use a Softmax loss function. Training is performed based on the model loss function and labeled data until the model converges, thereby obtaining an action detection model. Based on historical action image information of users using different payment methods, the action detection model is trained on multimodal data, constructing a model capable of identifying the probabilities of different key actions in action images, laying an accurate data foundation for subsequent key action recognition of payment objects.

[0048] When a payment recipient is identified as approaching a payment device and a payment method recommendation is needed, the collected motion image of the payment recipient can be input into the motion detection model trained in the above embodiment. The motion detection model can then identify the probability of the payment recipient hitting the key motions of different payment methods, i.e., the key motions that the payment recipient may have. Furthermore, based on the probability of the payment recipient hitting the key motions of different payment methods, the target payment method that the payment recipient intends to use can be determined. For example, the payment method corresponding to the key motion with the highest payment probability can be selected as the target payment method.

[0049] Based on the payment recipient's actions before payment and the pre-trained action recognition model, the probability of the payment recipient performing each key action is identified. Then, based on the probability of each key action, the payment method that the payment recipient may currently want to use can be characterized, laying the foundation for the subsequent payment method recommendation, realizing accurate payment method recommendation, meeting the user's payment needs, and improving payment efficiency and user experience.

[0050] In some embodiments of this specification, determining the target payment method based on the probability of the payment object hitting key actions of different payment methods includes:

[0051] Using the action detection model, respectively obtaining the probability of the payee hitting the key actions of different payment methods in multiple frames of action image information within a specified time range after the payee approaches the payment device;

[0052] According to the probability of the payment object hitting the key actions of different payment methods in the multi-frame action image information, the target payment method corresponding to the payment object is comprehensively determined.

[0053] During the specific implementation process, there may be a certain amount of time from detecting that the payment object is approaching the payment device to the payment object starting to pay. In the embodiment of this specification, multiple frames of action image information can be collected within a specified time range after detecting that the payment object is approaching the payment device. The multiple frames of action image information may include surrounding environment image information for identifying that the payment object is approaching the payment device. The collected multiple frames of action image information are input into the trained action detection model, and the probabilities of the payment object hitting the key actions of different payment methods in the multiple frames of action image information can be obtained respectively, that is, the probability of the payment object doing each key action in each frame of action image information in the multiple frames of action image information can be obtained. Based on the probabilities of the payment object hitting the key actions of different payment methods in the multiple frames of action image information, a comprehensive analysis is made on which key actions the payment object has taken, and then the target payment method to be used by the payment object is determined.

[0054] By collecting multiple frames of images within a specified time range after the user approaches the payment device, performing motion detection on the multiple frames, and comprehensively analyzing the user's movements, the accuracy of key action recognition is improved, thereby improving the accuracy of payment method recommendations, so that the recommended payment methods can meet the needs of different users, improving payment efficiency and user experience.

[0055] In some embodiments of this specification, comprehensively determining the target payment method corresponding to the payment object based on the probability of the payment object hitting the key actions of different payment methods in multiple frames of action image information includes:

[0056] According to the probability of the payment object corresponding to the multi-frame action image information hitting the key actions of different payment methods, the average or median of the probability of the payment object hitting each key action is calculated, and the payment method corresponding to the key action with the highest average or median is selected as the target payment method.

[0057] During the specific implementation process, when comprehensively analyzing the probability of payment objects corresponding to multiple frames of action image information hitting key actions of different payment methods, the average or median of the probabilities of different key actions can be calculated, and the payment method corresponding to the key action with the highest average or median can be selected as the target payment method. For example, action detection can be continuously performed within 1 second after the user's entry detection. Assuming that N frames of payment object action image information are collected within 1 second, the action detection model can be used to run N action detections, and the N detection results are averaged as the final detection result. That is, the average of the probability values ​​corresponding to each key action in the N detection results is calculated, and the payment method corresponding to the key action with the highest average is selected as the target payment method. This fusion method can reduce the impact of environmental and data noise on the results, improve the accuracy of the results, and thus improve the accuracy of payment method recommendations, meet user needs, and improve payment efficiency.

[0058] Step 108: Display the target payment method to the payment recipient so that the payment recipient can perform a payment operation.

[0059] During the specific implementation process, after determining the target payment method that the payment object wants to use, the target payment method can be displayed to the payment object, and the payment object can then use the target payment method to perform payment operations. When the payment method recommendation processing method in the embodiment of this specification is applied to the local terminal of the payment device, the payment device can display the interactive interface of the target payment method on the display screen for the user to use after determining the target payment method to be used by the payment object. If the payment method recommendation processing method in the embodiment of this specification is applied in the server, the server can return the determined target payment method to the payment device, and the payment device can then display the target payment method on the display screen for the user to use.

[0060] In some embodiments of this specification, there may be multiple payment methods according to the actual application scenario. The payment methods in the embodiments of this specification may include face payment, code scanning payment, and self-selected payment methods. Among them, code scanning payment may include a payment method in which the user client presents a payment code to be scanned by the payment device or the payment device displays a payment code to be scanned by the user's client. Self-selected payment methods can be understood as the user manually or by voice control selecting a payment method. Of course, according to actual needs, there may also be password payment, card payment, etc., which are not specifically limited in the embodiments of this specification. According to the type of payment method determined, the user's habitual actions when using different payment methods can be analyzed to determine the key actions corresponding to different payment methods (such as: when swiping a card to pay, the user needs to take out a bank card or wallet), and then the actions of the payment object are detected and identified, and a satisfactory payment method is recommended to the user. The embodiments of this specification can realize intelligent recommendation of multiple different payment methods, recommend a payment method that satisfies the user, thereby improving payment efficiency and reducing payment interaction time.

[0061] Of course, the payment method may not include the option of self-selection of payment method. If the key action of a valid payment method (such as face recognition payment, code scanning payment) is not matched based on the user's action image information, it can be considered that the user needs to self-select the payment method, and the self-selected payment method is used as the target payment method.

[0062] In some embodiments of this specification, presenting the target payment method to the payment recipient includes:

[0063] The target payment method is displayed on the display screen of the payment device, and a text and / or voice prompt is used to indicate that the current payment method of the payment object is the target payment method.

[0064] In a specific implementation, after obtaining the target payment method to be used by the payee, the payment device can display the target payment method on the display screen of the payment device and use text and / or voice prompts to remind the payee that the current payment method is the target payment method, thereby avoiding payment failures caused by incorrect recommendations. After determining the target payment method that the payee wants to use, the payment method is automatically switched for the user to use, and the user is reminded of the payment method to be used by voice and / or text prompts, thereby avoiding payment failures caused by the recommended payment method not being what the user wants but the user is unaware of it.

[0065] For example, if, based on the motion detection results in the above embodiment, the highest probability of hitting one of the key actions is {taking off a mask, taking off a hat, taking off glasses}, it can be determined that the user is likely to want to pay by face recognition. The payment device can automatically switch to the face recognition payment interactive page and highlight the user with the text "Face recognition payment is in use." If, based on the motion detection results in the above embodiment, the highest probability of hitting one of the key actions is {looking down at the phone, raising the phone, taking the phone out of the pocket}, it can be determined that the user is likely to want to pay by code scanning. The payment device can automatically switch to the code scanning payment interactive page and highlight the text "Scan code payment is in use." If, based on the motion detection results in the above embodiment, the key action hits {no obvious action}, it means that the motion detection model cannot clearly determine whether the user wants to pay by face recognition or code scanning. In this case, the payment device switches to the user-selected mode, highlights the text "Please select a payment method," and reinforces the user's perception through voice announcement.

[0066] The payment method recommendation processing method provided in the embodiments of this specification determines whether a user needs to use the payment device by identifying images of the payment device's surroundings before the user approaches the payment device. After determining that a user is approaching the payment device, the method determines the user's desired payment method by identifying the user's pre-payment motion image information and recommends the determined target payment method to the user. This eliminates the need for users to select their own payment methods, meets the payment needs of different users, reduces payment time, and improves payment efficiency.

[0067] In some embodiments of this specification, identifying whether a payment object is approaching the payment device based on image information of the surrounding environment of the payment device includes:

[0068] Performing face recognition on the surrounding environment image information, if face information is recognized in the surrounding environment image information, determining that a payment object is approaching the payment device; otherwise, determining that no payment object is approaching the payment device.

[0069] In a specific implementation, when detecting a user's entry, a facial recognition algorithm can be used to perform facial recognition on the image information of the payment device's surroundings captured by the payment device's camera. If facial information is recognized in the surrounding image information, it is determined that the user and the payment object are approaching the payment device. Otherwise, it can be determined that no payment object is approaching the payment device. The method of performing facial recognition on the surrounding image information is not specifically limited in the embodiments of this specification, and commonly used facial recognition algorithms or visual recognition algorithms can be used.

[0070] As described in the above embodiment, the image information collected by the payment device in the embodiment of this specification may include two types: RGB image and 3D image. When performing face recognition, the RGB image can be used for face recognition detection.

[0071] By performing facial recognition on the image information of the surrounding environment of the payment device, it is possible to accurately identify whether there is a user approaching the payment device, and then accurately identify whether there is a user who needs to use the payment device, and make timely recommendations on payment methods.

[0072] In some embodiments of this specification, identifying whether a payment object is approaching the payment device based on image information of the surrounding environment of the payment device includes:

[0073] extracting a designated central area image of the peripheral image information;

[0074] An average depth of the designated central area image is calculated. If the average depth is greater than zero and less than a preset depth threshold, it is determined that a payment object is approaching the payment device; otherwise, it is determined that no payment object is approaching the payment device.

[0075] In a specific implementation, when detecting a user's approach, a depth-based approach detection algorithm can be used to calculate the depth of the collected image information of the payment device's surroundings. A designated area, such as the central area, can be pre-circumscribed within the surrounding image information. An image of the designated central area of ​​the surrounding image information can be obtained, and the average depth of the designated central area of ​​the surrounding image information can be calculated. If the calculated average depth is not zero and less than a preset depth threshold (i.e., greater than zero and less than the preset depth threshold), it can be determined that a payment object is approaching the payment device. Otherwise, it can be assumed that no payment object is approaching the payment device. A smaller depth value indicates closer proximity to the payment device's camera. By setting a preset depth threshold, it is possible to detect whether an object has reached a certain distance from the payment device's camera. Generally, if no object is approaching the payment device and the collected surrounding image information only shows the background, the depth is 0. The value of the preset depth threshold can be set based on actual scenario requirements. This can be accomplished by placing an object or a user at a specified distance from the payment device's camera, capturing the payment device's surrounding image information at that time, and calculating the average depth of the current surrounding image information. This average depth value is then used as the preset depth threshold. Of course, other methods may also be used to determine the value of the preset depth threshold, which is not specifically limited in the embodiments of this specification.

[0076] The average depth can be calculated using a monocular depth estimation method or a binocular depth estimation method. For example, the average depth can be calculated using a depth estimation method based on image content understanding, which primarily classifies each scene block in the image and then estimates the depth information of each scene category using a method applicable to each category. Alternatively, other image depth calculation methods can be used as needed, which are not specifically limited in this specification.

[0077] In addition, referring to the description of the above embodiment, the image information collected by the payment device in the embodiment of this specification may include two types: RGB image and 3D image. When performing depth calculation, the 3D image can be used for face recognition detection.

[0078] By calculating the average depth of the image information of the surrounding environment of the payment device, it is determined whether a user is close to the payment device. The data processing speed is fast, and it can quickly determine whether a user is close to the payment device, thereby improving the data processing efficiency of payment method recommendations.

[0079] In some other embodiments of this specification, identifying whether a payment object is approaching the payment device based on the image information of the surrounding environment of the payment device includes:

[0080] extracting a designated central area image of the peripheral image information;

[0081] Calculate the average depth of the designated central area image; if the average depth is greater than zero and less than a preset depth threshold, perform facial recognition on the surrounding environment image information; if facial information is recognized in the surrounding environment image information, determine that a payment object is approaching the payment device.

[0082] In a specific implementation, depth calculation and facial recognition can be combined when detecting and identifying a user's approach. A designated area, such as a central area, can be first identified within the surrounding image information, an image of the designated central area of ​​the surrounding image information can be obtained, and the average depth of the image of the designated central area of ​​the surrounding image information can be calculated. If the calculated average depth is not zero and is less than a preset depth threshold, facial recognition is then performed on the surrounding image information using a facial recognition algorithm. If facial information is recognized in the surrounding image information, it is determined that a user, i.e., the payment recipient, is approaching the payment device. If, after the calculated average depth is not zero and is less than the preset depth threshold, it is determined that no face is present in the surrounding image information, the surrounding image of the payment device is continuously captured and depth calculation is performed. If the calculated average depth is zero or greater than the preset depth threshold, it is directly determined that no user is approaching the payment device, and facial recognition processing is not required. The surrounding image of the payment device is continuously captured and depth calculation is performed until the calculated average depth is greater than zero and less than the preset depth threshold, at which point facial recognition is performed. "Entry detection based on depth data" can be continuously run when the payment device is idle. If "entry detection based on depth data" is hit, "entry detection based on face detection" will be run. If "entry detection based on face detection" is hit, it is determined that a user has entered the payment device.

[0083] As described in the above embodiment, a 3D image can be used when performing depth calculation. If the calculated average depth is not 0 and is less than a preset depth threshold, an RGB image corresponding to the 3D image can be obtained based on the time of image acquisition, and face recognition processing can be performed on the RGB image to determine whether a user is approaching the payment device.

[0084] The embodiments of this specification combine depth computing and facial recognition when detecting user entry. Depth computing can quickly calculate whether there is an object approaching the payment device. After determining that an object is approaching the payment device, facial recognition technology can accurately determine whether the object approaching the payment device is the payment object, thereby ensuring the efficiency of entry detection and improving the accuracy of entry detection.

[0085] In some embodiments of this specification, the method further includes:

[0086] Obtain historical payment data of different payment objects within a specified historical time range at specified intervals, including payment method, payment success rate, and payment interaction time;

[0087] Determine the preferred payment method for different payment recipients based on the payment success rate and payment interaction time trends in their historical payment data;

[0088] When it is determined that there is no matching key action in the action image information of the payment object or it is determined that the target payment method of the payment object is an autonomously selected payment method, the preferred payment method of the payment object is used as the default payment method.

[0089] During implementation, the embodiments of this specification can also adjust the preferred payment method of a payment recipient through regular experience inspections. Specifically, historical payment data for different payment recipients within a specified historical time range can be obtained at specified intervals. The historical payment data includes payment method, payment success rate, and payment interaction time. Payment methods can include facial recognition payment, QR code payment, and self-selected payment methods, as described in the above embodiments. The payment success rate can be understood as the proportion of successful payments made by the user, and the payment interaction time can be understood as the time from the user starting to pay or approaching the payment device to the payment completion. The preferred payment method for each payment recipient can be determined based on the changing trends in the payment success rate and payment interaction time of each payment recipient. Based on the changing trends in the payment success rate and payment interaction time in the payment recipient's historical payment data within a specified historical time range, it can be determined whether the payment method recommended based on approach detection and motion recognition meets the user's needs. For example, based on the results of regular user data inspections, if the user's payment success rate has recently increased and the payment interaction time has decreased, it can indicate that the user experience has been improving. The payment method with the highest probability in the distribution of payment methods in the historical payment data can be selected as the preferred payment method for the payment recipient. Alternatively, the payment success rate and payment interaction time trends for different payment methods can be obtained from the payment recipient's historical payment data, and the payment method with an increased payment success rate and / or decreased payment interaction time can be selected as the preferred payment method. Depending on actual needs, other data processing can also be performed on the payment success rate and payment interaction time to select the payment recipient's preferred payment method.

[0090] When the payment object approaches the payment device and needs to make payment, if, based on the action detection of the payment object, it is determined that there is no matching key action in the action image information of the payment object or it is determined that the target payment method of the payment object is an autonomously selected payment method, the preferred payment method of the payment object determined by regular inspections can be used as the default payment method.

[0091] The embodiments of this specification analyze the historical payment data of each payment object to determine the preferred payment method of each payment object. When the payment object subsequently uses the payment device to make a payment, if the payment method that the user has a clear intention of is not identified, the preferred payment method can be recommended to the payment object, thereby achieving flexible adjustment of the payment method recommendation, meeting the user's payment needs as much as possible, and improving payment efficiency.

[0092] In some embodiments of this specification, setting the preferred payment method of the payment object as the default payment method includes:

[0093] The preferred payment method of the payment object is sorted first in the default payment method list for selection by the payment object.

[0094] In a specific implementation, after determining the preferred payment method of the payment object based on the payment object's historical payment data, if it is determined that there is no matching key action in the payment object's action image information or if it is determined that the payment object's target payment method is a self-selected payment method, a list of all available payment methods can be displayed to the user on the display screen of the payment device, allowing the user to select a payment method. In the list, the preferred payment method of the payment object can be sorted first in the default payment method list so that the user can directly select the payment method to make the payment. For example, if based on the payment success rate and payment interaction time trends in the historical payment data of payment object A, it is determined that the preferred payment method of payment object A is face recognition payment. If payment object A subsequently uses the payment device to make a payment, and the action detection of payment object A does not match the key action corresponding to a valid payment method or it is determined that payment object A has no obvious action, that is, if payment object A's target payment method is a self-selected payment method, face recognition payment will be sorted first in the default payment method list of payment object A so that payment object A can quickly select an appropriate payment method.

[0095] If the payment method recommendation processing method is applied to a payment device, after the payment device determines the preferred payment method of the payment object, it can also be sent to other payment devices through the server, so that other payment devices can set the default payment method list of the payment object based on the preferred payment method when they cannot determine the payment method of the payment object.

[0096] The embodiment of this specification determines the preferred payment method of the payment recipient through regular inspections, and when the payment method of the payment recipient cannot be determined, the preferred payment method is set as the first in the default payment method list so that the payment recipient can quickly select a suitable payment method to improve payment efficiency.

[0097] Figure 2 This is a flowchart of payment method recommendation processing in another embodiment of this specification. Figure 2 As shown, the payment method recommendation processing method provided in the embodiment of this specification mainly includes the following stages:

[0098] 1. Approach detection: The payment device continuously performs approach detection to determine whether a user is approaching the payment device;

[0099] 2. User action detection: Train an action detection and recognition model to detect key actions when the user approaches the device;

[0100] 3. Intelligent payment method switching: intelligent payment method switching based on the results of motion detection;

[0101] 4. Regular experience inspections: Regularly compare experience indicators before and after switching to smart payment methods, and make global adjustments based on the inspection results.

[0102] The embodiments of this specification can determine the payment method that the user is likely to select based on some actions of the user before payment, thereby reducing user experience problems caused by existing devices.

[0103] In this specification, the various embodiments of the above method are described in a progressive manner. The same or similar parts between the various embodiments can be referenced to each other. Each embodiment focuses on the differences from other embodiments. For relevant parts, refer to the partial description of the method embodiment.

[0104] Based on the payment method recommendation processing method described above, one or more embodiments of this specification also provide a device for payment method recommendation processing. The device may include a device (including a distributed system), software (application), module, plug-in, server, client, etc. that uses the method described in the embodiment of this specification and is combined with the necessary implementation hardware. Based on the same innovative concept, the device in one or more embodiments provided in the embodiment of this specification is as described in the following embodiments. Since the implementation scheme and method for solving the problem of the device are similar, the implementation of the specific device in the embodiment of this specification can refer to the implementation of the aforementioned method, and the repetitions will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements predetermined functions. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0105] Specifically, Figure 3 This is a schematic diagram of the module structure of an embodiment of the payment method recommendation processing device provided in this specification. Figure 3 As shown, the device can be applied to the local server of the public transportation vehicle described above. The payment method recommendation processing device provided in this specification may include:

[0106] An approach detection module 31 is configured to identify whether a payment object is approaching the payment device based on image information of the surrounding environment of the payment device;

[0107] The motion image acquisition module 32 is used to acquire motion image information of the payment object after determining that the payment object is close to the payment device;

[0108] An action detection module 33 is used to match the action image information with pre-set key actions corresponding to different payment methods to determine the target payment method corresponding to the payment object;

[0109] The payment method recommendation module 34 is used to present the target payment method to the payment object so that the payment object can perform a payment operation.

[0110] Before a user approaches a payment device, the embodiment of this specification identifies whether a user needs to use the payment device by recognizing images of the payment device's surroundings. Once a user is determined to be approaching the payment device, the embodiment identifies the user's desired payment method by performing motion recognition on the user's pre-payment actions. The determined target payment method is then recommended to the user. This eliminates the need for users to select their own payment methods, meets the payment needs of different users, reduces payment time, and improves payment efficiency.

[0111] It should be noted that the above-mentioned device may also include other implementations according to the description of the corresponding method embodiment. Specific implementations can refer to the description of the corresponding method embodiment above, and will not be described in detail here.

[0112] An embodiment of this specification further provides a payment method recommendation processing device, comprising: at least one processor and a memory for storing processor-executable instructions. When the processor executes the instructions, the payment method recommendation processing method of the above embodiment is implemented. The method includes:

[0113] identifying whether a payment object is approaching the payment device based on image information of the surrounding environment of the payment device;

[0114] After determining that a payment object is approaching the payment device, obtaining motion image information of the payment object;

[0115] Matching the action image information with pre-set key actions corresponding to different payment methods to determine the target payment method corresponding to the payment object;

[0116] The target payment method is displayed to the payment object so that the payment object can perform a payment operation.

[0117] It should be noted that the above-mentioned device or system may also include other implementations according to the description of the method embodiment. Specific implementations can refer to the description of the relevant method embodiment and will not be described in detail here.

[0118] Referring to the above embodiments, when the payment method recommendation method in the embodiments of this specification is applied to the server, the embodiments of this specification provide a payment method recommendation processing system, which includes: a payment device and a payment server, wherein:

[0119] The payment device is provided with an image acquisition unit and a display screen, wherein the image acquisition unit is used to acquire image information of the surrounding environment and image information of the movement of the payment object;

[0120] The payment server includes at least one processor and a memory for storing processor-executable instructions. When the processor executes the instructions, the payment method recommendation method of the above embodiment is implemented, which is used to identify whether a payment object is approaching the payment device based on the surrounding environment image information collected by the payment device. After determining that a payment object is approaching the payment device, the method obtains motion image information of the payment object, matches the motion image information with pre-set key actions corresponding to different payment methods, determines the target payment method corresponding to the payment object, and returns the target payment method to the payment device.

[0121] The payment device displays the target payment method to the payment object on a display screen according to the target payment method returned by the payment server, so that the payment object can perform a payment operation.

[0122] The process of the payment server recommending a payment method may be referred to the description of the above embodiment and will not be described again here.

[0123] The payment method recommendation processing device, equipment and system provided in this specification can also be applied to a variety of data analysis and processing systems. The system or server or terminal or device can be a separate server, or it can include a server cluster, system (including distributed system), software (application), actual operation device, logic gate circuit device, quantum computer, etc. that uses one or more of the methods or one or more embodiments of the system or server or terminal or device of this specification and is combined with a terminal device of necessary implementation hardware. The detection system for checking the difference data may include at least one processor and a memory storing computer-executable instructions, and when the processor executes the instructions, it implements the steps of the method described in any one or more of the above embodiments.

[0124] The method embodiments provided in the embodiments of this specification can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Taking running on a server as an example, Figure 4 This is a hardware block diagram of a payment method recommendation processing server in one embodiment of this specification. The computer terminal may be the payment method recommendation processing server or payment method recommendation processing device in the above embodiment. Figure 4 The server 10 shown may include one or more (only one is shown in the figure) processors 100 (the processor 100 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a non-volatile memory 200 for storing data, and a transmission module 300 for communication functions. It will be understood by those skilled in the art that Figure 4 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 4 More or fewer plug-ins shown in , for example, may also include other processing hardware, such as databases or multi-level caches, GPUs, or have Figure 4 Different configurations shown.

[0125] The non-volatile memory 200 can be used to store software programs and modules of application software, such as the program instructions / modules corresponding to the payment method recommendation processing method in the embodiments of this specification. The processor 100 executes various functional applications and updates resource data by running the software programs and modules stored in the non-volatile memory 200. The non-volatile memory 200 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the non-volatile memory 200 may further include a memory remotely located relative to the processor 100, and these remote memories can be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0126] The transmission module 300 is used to receive or send data via a network. Specific examples of the aforementioned network may include a wireless network provided by a communications provider of a computer terminal. In one embodiment, the transmission module 300 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission module 300 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0127] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0128] The methods or devices described in the above embodiments provided in this specification can implement business logic through computer programs and record them on storage media. The storage media can be read and executed by a computer to achieve the effects of the solutions described in the embodiments of this specification.

[0129] The storage medium may include a physical device for storing information, typically digitizing the information and then storing it in a medium utilizing electrical, magnetic, or optical means. Examples of such storage media include: devices that use electrical energy to store information, such as various types of memory, such as RAM and ROM; devices that use magnetic energy to store information, such as hard disks, floppy disks, magnetic tapes, magnetic core memories, bubble memories, and USB flash drives; and devices that use optical means to store information, such as CDs or DVDs. Of course, there are also other types of readable storage media, such as quantum memories and graphene memories.

[0130] The above-mentioned payment method recommendation processing method or device provided in the embodiments of this specification can be implemented by a processor in a computer executing corresponding program instructions, such as using the C++ language of the Windows operating system on a PC, a Linux system, or other systems such as Android and iOS system programming languages ​​on a smart terminal, as well as processing logic based on a quantum computer.

[0131] The embodiments of this specification are not limited to those that must comply with industry communication standards, standard computer resource data update and data storage rules, or the situations described in one or more embodiments of this specification. Certain industry standards or slightly modified implementation plans based on the implementation described in the embodiments using custom methods or embodiments can also achieve the same, equivalent, or similar implementation effects as the above embodiments, or the expected implementation effects after deformation. The embodiments obtained by applying these modified or deformed data acquisition, storage, judgment, processing methods, etc. can still fall within the scope of the optional implementation plans of the embodiments of this specification.

[0132] In the 1990s, technological improvements could be clearly distinguished as either hardware improvements (for example, improvements to circuit structures like diodes, transistors, and switches) or software improvements (improvements to process flows). However, with the advancement of technology, many process flow improvements today can now be considered direct improvements to hardware circuit structures. Designers almost always create the corresponding hardware circuit structure by programming the improved process flow into the hardware circuit. Therefore, it cannot be said that a process flow improvement cannot be implemented using hardware modules. For example, a programmable logic device (PLD), such as a field programmable gate array (FPGA), is an integrated circuit whose logical function is determined by user programming. Designers can "integrate" a digital system on a PLD through their own programming, without having to hire a chip manufacturer to design and manufacture a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly done using "logic compiler" software. This is similar to the software compiler used when developing programs. Before compilation, the original code must also be written in a specific programming language, called a hardware description language (HDL). There is not just one HDL, but many, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art will also understand that by simply programming the method flow in one of these hardware description languages ​​and then programming it into an integrated circuit, a hardware circuit that implements the logic method flow can be easily obtained.

[0133] The controller can be implemented in any suitable manner. For example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also know that in addition to implementing the controller in a purely computer-readable program code format, the controller can be implemented in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be considered as structures within the hardware component. Or even, the devices for implementing various functions can be considered as both software modules that implement the method and structures within the hardware component.

[0134] For the convenience of description, the above platforms and terminals are described as various modules based on their functions. Of course, when implementing one or more of the present specifications, the functions of each module can be implemented in the same or multiple software and / or hardware, or the module that implements the same function can be implemented by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or plug-ins can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0135] These computer program instructions can also be loaded onto a computer or other programmable resource data updating device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0136] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, since the system embodiments are generally similar to the method embodiments, their description is relatively simple, and relevant parts can be referenced to the partial description of the method embodiments. Throughout this specification, reference to the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of this specification. In this specification, the schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, those skilled in the art may combine and integrate the different embodiments or examples, and features of different embodiments or examples, described in this specification, without conflict.

[0137] The foregoing description is merely an example of one or more embodiments of this specification and is not intended to limit the one or more embodiments of this specification. Those skilled in the art will appreciate that various modifications and variations of one or more embodiments of this specification are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of this specification are intended to be included within the scope of the claims.

Claims

1. A method for processing payment method recommendations, the method comprising: identifying whether a payment object is approaching the payment device based on image information of the surrounding environment of the payment device; The surrounding environment image information is continuously collected during idle time when the payment device is not in use by a user; After determining that a payment object is approaching the payment device, obtaining multiple frames of motion image information of the payment object within a specified time range; wherein one frame of motion image information includes an RGB image and a 3D image of the payment object; Matching each frame of action image information in the multiple frames of action image information with a preset key action corresponding to different payment methods, and determining a target payment method corresponding to the payment object based on the matching results of the multiple frames of action image information; Displaying the target payment method to the payment recipient so that the payment recipient can perform a payment operation; Matching each frame of action image information in the multiple frames of action image information with a preset key action corresponding to different payment methods, and determining a target payment method corresponding to the payment object based on the matching results of the multiple frames of action image information, including: The following operations are performed on each frame of the action image: the RGB image and the 3D image are input into a motion detection model, and the motion detection model is used to obtain the probability that the payment object will hit the key actions of different payment methods; wherein the motion data of users using different payment methods are analyzed in advance, and key action sets corresponding to different payment methods are defined. The key action set corresponding to a payment method is the habitual actions of most users when using that payment method; The probability of the payment object hitting the key actions of different payment methods in the multi-frame action image information is fused and processed, and a payment method is selected as the target payment method according to the fusion processing result.

2. The method according to claim 1, wherein identifying whether a payment object is approaching the payment device based on image information of the surrounding environment of the payment device comprises: Performing face recognition on the surrounding environment image information, if face information is recognized in the surrounding environment image information, determining that a payment object is approaching the payment device; otherwise, determining that no payment object is approaching the payment device.

3. The method of claim 1, wherein identifying whether a payment object is approaching the payment device based on image information of the surrounding environment of the payment device comprises: extracting a designated central area image of the surrounding environment image information; An average depth of the designated central area image is calculated. If the average depth is greater than zero and less than a preset depth threshold, it is determined that a payment object is approaching the payment device; otherwise, it is determined that no payment object is approaching the payment device.

4. The method of claim 1, wherein identifying whether a payment object is approaching the payment device based on image information of the surrounding environment of the payment device comprises: extracting a designated central area image of the surrounding environment image information; Calculate the average depth of the designated central area image; if the average depth is greater than zero and less than a preset depth threshold, perform facial recognition on the surrounding environment image information; if facial information is recognized in the surrounding environment image information, determine that a payment object is approaching the payment device.

5. The method according to claim 1, wherein the training method of the action detection model comprises: Collect historical action image information of multiple payment objects using different payment methods, and configure key action sets corresponding to different payment methods; marking the historical action image information according to the key action set, marking the key actions in each historical action image information; The action detection model is trained using the annotated historical action image information until the action detection model reaches a preset accuracy or the number of training times reaches a preset number.

6. The method of claim 1, further comprising: Obtain historical payment data of different payment objects within a specified historical time range at specified intervals, including payment method, payment success rate, and payment interaction time; Determine the preferred payment method for different payment recipients based on the payment success rate and payment interaction time trends in their historical payment data; When it is determined that there is no matching key action in the action image information of the payment object or it is determined that the target payment method of the payment object is an autonomously selected payment method, the preferred payment method of the payment object is used as the default payment method.

7. The method according to claim 6, wherein the step of setting the preferred payment method of the payment object as the default payment method comprises: The preferred payment method of the payment object is sorted first in the default payment method list for selection by the payment object.

8. The method according to claim 1, wherein presenting the target payment method to the payment recipient comprises: The target payment method is displayed on the display screen of the payment device, and a text and / or voice prompt is used to indicate that the current payment method of the payment object is the target payment method.

9. The method according to claim 1, wherein the payment method comprises: Pay by face recognition, scan code to pay, and choose the payment method yourself.

10. A payment method recommendation processing device, comprising: An approach detection module is configured to identify whether a payment object is approaching the payment device based on image information of the surrounding environment of the payment device; the image information of the surrounding environment is continuously collected during idle time when the payment device is not in use; A motion image acquisition module, configured to acquire, upon determining that a payment object is approaching the payment device, multiple frames of motion image information of the payment object within a specified time range; wherein one frame of motion image information includes an RGB image and a 3D image of the payment object; an action detection module, configured to match each frame of action image information in the plurality of frames of action image information with a preset key action corresponding to different payment methods, and determine a target payment method corresponding to the payment object based on the matching results of the plurality of frames of action image information; A payment method recommendation module, configured to present the target payment method to the payee so that the payee can perform a payment operation; Matching each frame of action image information in the multiple frames of action image information with a preset key action corresponding to different payment methods, and determining a target payment method corresponding to the payment object based on the matching results of the multiple frames of action image information, including: The following operations are performed on each frame of the action image: the RGB image and the 3D image are input into a motion detection model, and the motion detection model is used to obtain the probability that the payment object will hit the key actions of different payment methods; wherein the motion data of users using different payment methods are analyzed in advance, and key action sets corresponding to different payment methods are defined. The key action set corresponding to a payment method is the habitual actions of most users when using that payment method; The probability of the payment object hitting the key actions of different payment methods in the multi-frame action image information is fused and processed, and a payment method is selected as the target payment method according to the fusion processing result.

11. A payment method recommendation processing device, comprising: At least one processor and a memory for storing processor-executable instructions, wherein when the processor executes the instructions, the method according to any one of claims 1 to 9 is implemented.

12. A payment method recommendation processing system, comprising: Payment device, payment server, including: The payment device is provided with an image acquisition unit and a display screen, wherein the image acquisition unit is used to acquire image information of the surrounding environment and image information of the movement of the payment object; The payment server includes at least one processor and a memory for storing processor-executable instructions, and when the processor executes the instructions, it implements the method according to any one of claims 1 to 9, for identifying whether a payment object is approaching the payment device based on the surrounding environment image information collected by the payment device, wherein the surrounding environment image information is continuously collected during the idle time when the payment device is not used by a user; after determining that a payment object is approaching the payment device, obtaining multiple frames of action image information of the payment object within a specified time range, wherein one frame of action image information includes an RGB image and a 3D image of the payment object; and matching each frame of action image information in the multiple frames of action image information with a pre-set key action corresponding to different payment methods, determining a target payment method corresponding to the payment object based on the matching results of the multiple frames of action image information, and returning the target payment method to the payment device; The payment device displays the target payment method to the payment recipient on a display screen according to the target payment method returned by the payment server, so that the payment recipient can perform a payment operation; Matching each frame of action image information in the multiple frames of action image information with a preset key action corresponding to different payment methods, and determining a target payment method corresponding to the payment object based on the matching results of the multiple frames of action image information, including: The following operations are performed on each frame of the action image: the RGB image and the 3D image are input into a motion detection model, and the motion detection model is used to obtain the probability that the payment object will hit the key actions of different payment methods; wherein the motion data of users using different payment methods are analyzed in advance, and key action sets corresponding to different payment methods are defined. The key action set corresponding to a payment method is the habitual actions of most users when using that payment method; The probability of the payment object hitting the key actions of different payment methods in the multi-frame action image information is fused and processed, and a payment method is selected as the target payment method according to the fusion processing result.

Images