CN113947400A

CN113947400A - Payment mode recommendation processing method, device, equipment and system

Info

Publication number: CN113947400A
Application number: CN202111091120.3A
Authority: CN
Inventors: 曹佳炯; 丁菁汀
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: AlipayCom Co ltd
Priority date: 2021-09-17
Filing date: 2021-09-17
Publication date: 2022-01-18

Abstract

The specification provides a payment mode recommendation processing method, a payment mode recommendation processing device and a payment mode recommendation processing system. The user does not need to select the payment mode, the payment requirements of different users are met, the time required by payment is shortened, and the payment efficiency is improved.

Description

Payment mode recommendation processing method, device, equipment and system

Technical Field

The specification belongs to the technical field of computers, and particularly relates to a payment mode recommendation processing method, device, equipment and system.

Background

With the development of computer internet technology, online payment methods are more and more, such as: as technologies advance, devices capable of being used for payment or collection of money gradually appear, and as payment methods increase, payment methods which can be supported by the devices also gradually increase. When one device can support 2 or more than 2 payment methods, the user may be required to manually select the payment method, which is tedious to operate, affects the payment efficiency, and increases the interaction cost of the user.

Disclosure of Invention

An object of the embodiments of the present specification is to provide a payment method recommendation processing method, device, apparatus, and system, which improve payment efficiency.

In one aspect, an embodiment of the present specification provides a payment method recommendation processing method, where the method includes:

identifying whether a payment object approaches the payment equipment or not according to the surrounding environment image information of the payment equipment;

after determining that a payment object approaches the payment equipment, acquiring action image information of the payment object;

matching the action image information with key actions corresponding to different preset payment modes to determine a target payment mode corresponding to the payment object;

and displaying the target payment mode to the payment object so as to enable the payment object to carry out payment operation.

In another aspect, the present specification provides a payment means recommendation processing apparatus, including:

the approach detection module is used for identifying whether a payment object approaches the payment equipment or not according to the surrounding environment image information of the payment equipment;

the action image acquisition module is used for acquiring action image information of the payment object after determining that the payment object is close to the payment equipment;

the action detection module is used for matching the action image information with key actions corresponding to different preset payment modes and determining a target payment mode corresponding to the payment object;

and the payment mode recommending module is used for displaying the target payment mode to the payment object so as to enable the payment object to carry out payment operation.

In another aspect, an embodiment of the present specification provides a payment method recommendation processing apparatus, which includes at least one processor and a memory for storing processor-executable instructions, where the processor executes the instructions to implement the above payment method recommendation processing method.

In a further aspect, an embodiment of the present specification provides a payment method recommendation processing system, where the system includes: payment equipment, payment server, wherein:

the payment equipment is provided with an image acquisition unit and a display screen, wherein the image acquisition unit is used for acquiring image information of the surrounding environment and action image information of a payment object;

the payment server comprises at least one processor and a memory for storing an executable instruction of the processor, and when the processor executes the instruction, the payment mode recommendation processing method is realized, and is used for identifying whether a payment object approaches the payment equipment or not according to the image information of the surrounding environment acquired by the payment equipment, acquiring the action image information of the payment object after determining that the payment object approaches the payment equipment, matching the action image information with preset key actions corresponding to different payment modes, determining a target payment mode corresponding to the payment object, and returning the target payment mode to the payment equipment;

and the payment equipment displays the target payment mode to the payment object in a display screen according to the target payment mode returned by the payment server so as to enable the payment object to carry out payment operation.

According to the payment mode recommendation processing method, device, equipment and system provided by the specification, before a user approaches payment equipment, whether the user needs to use the payment equipment is determined by identifying the surrounding environment image of the payment equipment, after the user approaches the payment equipment, the action image information of the user before payment is identified, a target payment mode which the user wants to use is determined, and the determined target payment mode is recommended to the user. The user does not need to select the payment mode, the payment requirements of different users are met, the time required by payment is shortened, and the payment efficiency is improved.

Drawings

In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.

Fig. 1 is a schematic flowchart of an embodiment of a payment method recommendation processing method provided in an embodiment of the present specification;

FIG. 2 is a schematic flow chart of a payment method recommendation process in another embodiment of the present disclosure;

fig. 3 is a schematic block diagram of an embodiment of a payment recommendation processing apparatus provided in the present specification;

fig. 4 is a block diagram of a hardware configuration of a payment means recommendation processing server in one embodiment of the present specification.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present specification, and not all of the embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments in the present specification without any inventive step should fall within the scope of protection of the present specification.

With the progress of science and technology, the payment requirement of people in daily shopping is facilitated by the payment equipment, and a user can pay online through the payment equipment without carrying cash. Generally, a payment device may only support code-scanning payment, and not support other payment methods such as: without a face-brushing payment entrance, the payment device may not complete payment in a scenario where the user does not carry the client. Or, some payment devices may support multiple payment methods, but require a user to manually select the payment method, which is different from the payment method required by the user, and thus, the problem of payment failure or prolonged payment interaction time may occur.

The embodiment of the specification provides a payment mode recommendation processing method, which includes the steps of identifying whether a user needs to pay or not by collecting images of the surrounding environment of payment equipment, and determining the most probable payment mode used by the user according to the action of the user before payment after the user is determined to pay, so that the required payment mode is recommended for the user, the steps of manually selecting the payment mode by the user are reduced, and the payment efficiency is improved.

Fig. 1 is a schematic flow chart of an embodiment of a payment method recommendation processing method provided in an embodiment of the present specification. Although the present specification provides the method steps or apparatus structures as shown in the following examples or figures, more or less steps or modules may be included in the method or apparatus structures based on conventional or non-inventive efforts. In the case of steps or structures which do not logically have the necessary cause and effect relationship, the execution order of the steps or the block structure of the apparatus is not limited to the execution order or the block structure shown in the embodiments or the drawings of the present specification. When the described method or module structure is applied to a device, a server or an end product in practice, the method or module structure according to the embodiment or the figures may be executed sequentially or in parallel (for example, in a parallel processor or multi-thread processing environment, or even in an implementation environment including distributed processing and server clustering).

The payment method recommendation processing method provided in the embodiments of the present specification may be applied to a client or a server, for example: the method can be applied to a local client of the payment device, or a server side which is in data communication with the payment device, or can also be applied to a client with certain data processing capacity such as: the terminal, such as a smart phone, a tablet computer, or a computer, capable of performing data communication with the payment device may be specifically determined according to actual needs, and embodiments of the present specification are not specifically limited.

As shown in fig. 1, the method may include the steps of:

step 102, identifying whether a payment object approaches the payment device or not according to the surrounding environment image information of the payment device.

In a specific implementation process, the payment device may be understood as a terminal with an online collection capability, and a user may complete payment by scanning a code or swiping a face on the payment device. The payment device in the embodiments of the present description may have an image capturing module such as: the camera and the like can also be provided with a display screen and can display information such as payment amount, payment method and the like. The camera in the payment device can collect the peripheral environment image information of the payment device, and whether a payment object exists can be identified based on the peripheral environment image information, such as: the user approaches the payment device, such as: whether the people exist in the surrounding environment image information can be identified, and if the people exist, the fact that the payment object approaches the payment equipment is considered. Wherein, the payment object can be understood as a user who needs to use the payment device for payment.

It should be noted that, referring to the description of the foregoing embodiment, it can be known that the payment method recommendation method in this embodiment may be applied to a local terminal of a payment device, and may also be applied to a server, and if the method is applied to the local terminal of the payment device, a camera in the payment device may acquire image information of a surrounding environment of the payment device and then send the image information to a processor of the payment device, and the processor of the payment device performs image processing. If the method is applied to the server, the camera in the payment equipment acquires the image information of the surrounding environment of the payment equipment, and then the payment equipment can send the image information of the surrounding environment to the server, and the server processes the image.

And 104, acquiring action image information of the payment object after determining that the payment object is close to the payment device.

In a specific implementation process, the peripheral environment image information of the payment device can be continuously collected during idle time when the payment device is not used by a user, the collected peripheral environment image information is identified, whether a payment object approaches the payment device or not is determined, and after the payment object approaches the payment device is determined, the payment method of the payment object is determined and recommended. Namely, the surrounding environment image of the payment device is monitored to detect whether a user approaches the payment device. After the payment object approaching the payment device is identified through the surrounding environment image information of the payment device, the image information of the payment object before payment, namely the action image information of the payment object, collected by a camera in the payment device can be obtained continuously. It should be noted that the motion image information of the payment object may include ambient environment image information for identifying that the payment object approaches the payment device, and may further include image information of the payment object collected after identifying that the payment object approaches the payment device. That is to say, the motion image information may include a plurality of images, the ambient environment image information identifying that the payment object is close to the payment device and the image information of the payment object before payment may both be used as the motion image information of the payment object, which may be specifically set according to actual needs, and the embodiment of this specification is not specifically limited.

And 106, matching the action image information with preset key actions corresponding to different payment modes, and determining a target payment mode corresponding to the payment object.

In a specific implementation process, key actions of the user when the user uses different payment methods for payment can be obtained according to historical data, and the key actions can be understood as habitual actions of most users when the user uses different payment methods, such as: general users may need to take off a mask, take off a hat, take off glasses, aim at a camera and the like if using face brushing payment, and may look down at a mobile phone, lift the mobile phone, take the mobile phone from a pocket and the like if using code scanning payment. After the action image information of the payment object is acquired, action recognition can be carried out on the action image information of the payment object, the action of the payment object in the image is recognized, the recognized action is matched with key actions corresponding to different preset payment modes, whether the key action meeting a certain payment mode exists in the action image information of the payment object is determined, and if the key action exists, a target payment mode to be used by the payment object can be determined.

In some embodiments of this specification, the matching the motion image information with key motions corresponding to different preset payment methods to determine a target payment method corresponding to the payment object includes:

inputting the motion image information into a motion detection model, and obtaining the probability of hitting key motions of different payment modes on the payment object by using the motion detection model; the action detection model is obtained by training based on historical action image information of a historical payment object, wherein the historical action image information comprises key actions corresponding to different payment modes;

and determining the target payment mode according to the probability of hitting the key actions of different payment modes on the payment object.

In a specific implementation process, in some embodiments of the present description, an action detection model may be trained in advance to be constructed, the action detection model may be obtained by training based on historical action image information of a historical payment object, the historical action image information includes key actions corresponding to different payment methods, and historical action image information of a historical user when paying in different payment methods may be used to obtain key actions of the user when paying in different payment methods, and the action detection model is obtained by performing model training.

In some embodiments of the present description, the training method of the motion detection model includes:

acquiring historical action image information of a plurality of historical payment objects when the plurality of historical payment objects adopt different payment modes for payment, and configuring key action sets corresponding to the different payment modes;

marking the historical action image information according to the key action set, and marking out key actions in the historical action image information;

and performing model training on the motion detection model by using the marked historical motion image information until the motion detection model reaches preset precision or the training times reach preset times.

In a specific implementation process, a key action set corresponding to different payment modes can be defined according to action analysis when a user adopts different payment modes, such as: the key action set corresponding to face brushing payment is { take mask, take hat and take glasses }, the key action set corresponding to code scanning payment is { look down at the mobile phone, lift up the mobile phone and take the mobile phone from a pocket }, and the key action set corresponding to the payment mode is selected autonomously and is { no obvious action }. And then collecting historical action image information when a plurality of historical payment objects adopt different payment modes for payment, labeling the collected historical action image information according to a key action set corresponding to different payment modes, and labeling key actions in each piece of historical action image information, wherein the steps are as follows: and marking actions of removing the mask, removing the hat, removing the glasses and the like in the image. The input of the model can be set as historical motion image information, and the output is probability distribution of different key motions, such as: let the key actions include taking off the mask, taking off the hat, taking off the glasses, looking down at the cell phone, lifting up the cell phone, taking the cell phone from the pocket, and { without obvious action 7, the probability distribution P of the output is [ P0, P1, P2, …, P6], which respectively represents the probability of hitting 7 actions, and the seven probabilities add up to 1. And based on the set model input and output, performing model training on the motion detection model by using the marked historical motion image information until the motion detection model reaches the preset precision or the training times reach the preset times. In addition, the image information in the embodiment of the present specification may include two types, one type is an RGB image, that is, a color image, and the other type is a 3D image, that is, a depth image, and the two types of images may be aligned according to the acquisition time sequence of the two types of images and then used as the input of the model.

In the embodiment of the present disclosure, the network structure of the motion detection model may be formed by two ResNet18, one may input RGB images, and the other may input 3D images, and the loss function of the model may be trained based on the model loss function and labeled data by using a Softmax loss function until the model converges to obtain the motion detection model. According to the action image information of the historical user in different payment modes, the action detection model of the multi-mode data is trained, a model capable of identifying the probability of different key actions in the action image is built, and an accurate data base is laid for the key action identification of a subsequent payment object.

When it is recognized that a payment object approaches the payment device and the payment method of the payment object needs to be recommended, the collected motion image of the payment object may be input into the motion detection model trained in the above embodiment, and the probability that the payment object hits the key motion of different payment methods, that is, the key motion that the payment object may have, may be recognized by using the motion detection model. Furthermore, a target payment method that the payment object wants to use can be determined based on the probability that the payment object hits the key actions of different payment methods, such as: the payment method corresponding to the key action with the highest payment probability can be selected as the target payment method.

Based on the action of the payment object before payment and an action recognition model established by pre-training, the probability of implementing each key action by the payment object is recognized, and then based on the probability of each key action, the payment method which the payment object possibly uses at present can be represented, so that a foundation is laid for recommendation of a subsequent payment method, accurate recommendation of the payment method is realized, the payment requirement of a user is met, and the payment efficiency and the user experience are improved.

In some embodiments of the present specification, the determining the target payment method according to the probability of the payment object hitting the key action of different payment methods includes:

respectively obtaining the probability of hitting key actions of different payment modes on the payment object in the multi-frame action image information within a specified time range after the payment object approaches the payment equipment by using the action detection model;

and comprehensively determining a target payment mode corresponding to the payment object according to the probability of hitting the key actions of different payment modes on the payment object in the multi-frame action image information.

In a specific implementation process, a certain time may exist from the time when the payment object is detected to approach the payment device to the time when the payment object starts to pay, in this embodiment of the present specification, multi-frame motion image information may be collected within a specified time range after the payment object is detected to approach the payment device, and the multi-frame motion image information may include ambient environment image information used for identifying that the payment object approaches the payment device. The collected multi-frame action image information is input into a trained action detection model, so that the probability that the payment object in the multi-frame action image information hits the key action of different payment modes can be respectively obtained, namely the probability that the payment object in each frame of action image information in the multi-frame action image information performs each key action can be obtained. And comprehensively analyzing which key actions are taken by the payment object according to the probability of hitting the key actions of different payment modes by the payment object in the multi-frame action image information, and further determining a target payment mode to be used by the payment object.

Through collecting the multiframe images within the appointed time range after the user approaches the payment equipment, the action detection is carried out on the multiframe images, the action of the user is comprehensively analyzed, the accuracy of key action identification is improved, and then the accuracy of payment mode recommendation is improved, so that the recommended payment mode can meet the requirements of different users, and the payment efficiency and the user experience are improved.

In some embodiments of this specification, the comprehensively determining a target payment method corresponding to a payment object according to a probability that the payment object hits a key action of different payment methods in multi-frame action image information includes:

and calculating the average value or the median of the probabilities of the payment objects hitting the key actions of different payment modes according to the probabilities of the payment objects hitting the key actions of different payment modes corresponding to the multi-frame action image information, and selecting the payment mode corresponding to the key action with the highest average value or highest median as the target payment mode.

In a specific implementation process, when the probability that the key actions of different payment modes are hit by the payment object corresponding to the multi-frame action image information is comprehensively analyzed, the average value or the median of the probabilities of the different key actions can be calculated, and the payment mode corresponding to the key action with the highest average value or the highest median is selected as the target payment mode. For example: the motion detection can be continued for 1s after the approach detection of the user. Assuming that N frames of motion image information of the payment object are acquired within 1s, N times of motion detection can be performed by using a motion detection model, the N times of detection results are averaged to serve as a final detection result, that is, an average value of probability values corresponding to each key motion in the N times of detection results is calculated, and a payment mode corresponding to the key motion with the highest average value is selected as a target payment mode. The integration mode can reduce the influence of environment and data noise on the result, improve the accuracy of the result, further improve the accuracy of recommendation of the payment mode, meet the user requirement and improve the payment efficiency.

And 108, displaying the target payment mode to the payment object so that the payment object can carry out payment operation.

In a specific implementation process, after the target payment mode which the payment object wants to use is determined, the target payment mode can be displayed to the payment object, and the payment object can perform payment operation by adopting the target payment mode. When the payment method recommendation processing method in the embodiment of the specification is applied to the local terminal of the payment device, after the payment device determines the target payment method to be used by the payment object, the interactive interface of the target payment method can be displayed in the display screen for the user to use. If the payment mode recommendation processing method in the embodiment of the description is applied to the server, the server may return the determined target payment mode to the payment device, and the payment device displays the target payment mode in the display screen for the user to use.

In some embodiments of the present description, payment manners may be various according to an actual application scenario, and the payment manners in the embodiments of the present description may include face-brushing payment, code-scanning payment, and autonomous selection of a payment manner. The code scanning payment may include a payment mode in which the payment code is displayed by the user client and scanned by the payment device or the payment device displays the collection code and scanned by the user client, and the autonomous selection of the payment mode may be understood as a manual or voice-controlled selection of the payment mode by the user. According to the determined payment mode types, the habit actions of the user when different payment modes are adopted can be analyzed, the key actions corresponding to the different payment modes (such as the fact that the user needs to take out a bank card or a wallet when swiping the card for payment) are determined, the actions of the payment object are detected and identified, and a satisfactory payment mode is recommended for the user. The embodiment of the specification can realize intelligent recommendation of various different payment modes and recommend the payment mode satisfied by the user, thereby improving the payment efficiency and reducing the payment interaction time.

Of course, the payment method may not include the option of selecting the payment method autonomously, and if the image information based on the user's motion does not match the key motion of the effective payment method (e.g., face-brushing payment or code-scanning payment), it may be considered that the user needs to select the payment method autonomously, and the payment method autonomously selected is used as the target payment method.

In some embodiments of the present specification, the presenting the target payment method to the payment object includes:

and displaying the target payment mode in a display screen of the payment equipment, and prompting the current payment mode of the payment object to be the target payment mode by using characters and/or voice.

In a specific implementation process, after the payment device obtains a target payment mode to be adopted by the payment object, the payment device can display the target payment mode in a display screen of the payment device, and prompt the current payment mode of the payment object to be the target payment mode by using characters and/or voice, so that the problem that the payment of a user fails due to recommendation errors is avoided. After the target payment mode which the payment object wants to use is determined, the payment mode is automatically switched to be used by the user, and the payment mode adopted by the user is reminded by using a voice and/or text prompting mode, so that the problem that the recommended payment mode is not needed by the user, but the user does not know the recommended payment mode, and the payment is failed is solved.

For example: if the highest hit probability of the key actions is one of { take mask, take hat and take glasses }, it can be determined that the user wants to pay by swiping face, and the payment device can automatically switch to an interactive page for paying by swiping face, and prompt the user that the user is paying by swiping face with highlight characters. If the highest hit probability of the key actions is one of { looking at the mobile phone down, lifting the mobile phone, fetching the mobile phone from a pocket } based on the action detection result in the above embodiment, it may be determined that the user wants to pay by scanning the code with a high probability, and the payment device may automatically switch to an interactive page for paying by scanning the code, and prompt the user that "payment by scanning the code" is being used with highlight text. If the action detection in the embodiment hits { no obvious action }, the action detection model has no way to definitely judge whether the user wants to pay by swiping the face or pay by scanning the code, at the moment, the mode is switched to the user self-selection mode, the user is prompted to 'please select a payment mode' by highlight characters, and the perception is strengthened through voice broadcast.

In the payment method recommendation processing method provided in the embodiment of the present specification, before a user approaches a payment device, whether the user needs to use the payment device is determined by identifying an image of a surrounding environment of the payment device, after it is determined that the user approaches the payment device, a target payment method that the user wants to use is determined by performing motion identification on motion image information of the user before payment, and the determined target payment method is recommended to the user. The user does not need to select the payment mode, the payment requirements of different users are met, the time required by payment is shortened, and the payment efficiency is improved.

In some embodiments of the present description, the identifying whether a payment object is close to the payment device according to the surrounding environment image information of the payment device includes:

and carrying out face recognition on the surrounding environment image information, if the face information in the surrounding environment image information is recognized, determining that a payment object is close to the payment equipment, and otherwise, determining that no payment object is close to the payment equipment.

In a specific implementation process, when the user is detected to enter the field, the face recognition algorithm can be used for carrying out face recognition on the image information of the surrounding environment of the payment equipment, which is acquired by a camera in the payment equipment, if the face information is recognized in the image information of the surrounding environment, it is determined that the user and the payment object are close to the payment equipment, otherwise, it can be considered that no payment object is close to the payment equipment. The method for performing face recognition on the image information of the surrounding environment is not particularly limited in the embodiments of this specification, and a commonly used face recognition algorithm or visual recognition algorithm may be used.

As described in the above embodiments, the image information collected by the payment device in the embodiments of the present description may include two types: the RGB image and the 3D image can be used for face recognition detection when face recognition is carried out.

By carrying out face recognition on the image information of the surrounding environment of the payment equipment, whether a user approaches the payment equipment can be accurately recognized, and then the user needs to use the payment equipment is accurately recognized, and the payment mode is timely recommended.

extracting a designated central area image of the peripheral image information;

and calculating the average depth of the appointed central area image, if the average depth is greater than zero and less than a preset depth threshold value, determining that a payment object approaches the payment equipment, and otherwise, determining that no payment object approaches the payment equipment.

In a specific implementation process, when performing approach detection on a user, depth calculation may be performed on acquired image information of a surrounding environment of a payment device by using an approach detection algorithm based on depth data, a specified region such as a central region in the image information of the surrounding environment may be defined in advance, a specified central region image of the image information of the surrounding environment may be obtained, an average depth of the specified central region image of the image information of the surrounding environment is calculated, if the calculated average depth is not 0 and is less than a preset depth threshold, that is, if greater than 0 is less than the preset depth threshold, it may be determined that a payment object is close to the payment device, otherwise, it may be determined that no payment object is close to the payment device. The smaller depth value can indicate that the camera of the payment device is closer, and by setting a preset depth threshold value, whether an object is at a certain distance from the camera of the payment device or not can be detected. Generally, if no object approaches the payment device, the depth is 0 when only the background exists in the collected surrounding environment image information. The value of the preset depth threshold value can be set according to the actual scene requirements, an object can be placed at a position with a specified distance from a camera of the payment device in advance or a user can stand on the payment device, the image information of the current surrounding environment of the payment device is collected, the average depth of the image information of the current surrounding environment is calculated, and the value of the average depth is used as the preset depth threshold value. Of course, other manners may also be used to determine the value of the preset depth threshold, and the embodiments of the present specification are not particularly limited.

Wherein, the average depth may be calculated using a monocular depth estimation method or a binocular depth estimation method, such as: the average depth is calculated by adopting a depth estimation method based on image content understanding in a monocular depth estimation method, wherein the depth estimation method for image content understanding mainly comprises the steps of classifying all scenery blocks in an image and then estimating the depth information of the scenery in each category by using a respectively applicable method. Or, other image depth calculation methods are used according to actual needs, and the embodiments of the present specification are not particularly limited.

In addition, referring to the description of the above embodiments, the image information collected by the payment device in the embodiment of the present specification may include two types: the RGB image and the 3D image can be used for face recognition detection when depth calculation is carried out.

By calculating the average depth of the image information of the surrounding environment of the payment equipment, whether a user is close to the payment equipment or not is determined, the data processing speed is high, whether the user is close to the payment equipment or not can be determined quickly, and the data processing efficiency recommended by the payment mode is improved.

In some other embodiments of the present specification, the identifying whether a payment object is close to the payment device according to the surrounding environment image information of the payment device includes:

extracting a designated central area image of the peripheral image information;

and calculating the average depth of the image of the designated central area, if the average depth is greater than zero and less than a preset depth threshold value, carrying out face recognition on the image information of the surrounding environment, and if the face information in the image information of the surrounding environment is recognized, determining that a payment object is close to the payment equipment.

In a specific implementation process, when performing approach detection and recognition on a user, depth calculation and face recognition may be combined, a specified region, such as a central region, in the peripheral environment image information may be first defined, a specified central region image of the peripheral image information may be obtained, and an average depth of the specified central region image of the peripheral image information may be calculated. If the calculated average depth is not 0 and is smaller than the preset depth threshold, face recognition is performed on the surrounding environment image information by using a face recognition algorithm, and if the face information is recognized in the surrounding environment image information, it is determined that a user, namely a payment object, approaches the payment equipment. If no human face is identified in the surrounding environment image information after the calculated average depth is not 0 and is smaller than the preset depth threshold value, the surrounding environment image of the payment equipment is continuously acquired, and depth calculation is carried out. And if the calculated average depth is 0 or greater than the preset depth threshold, directly determining that no user approaches the payment equipment, continuously acquiring the surrounding environment image of the payment equipment without face recognition processing, performing depth calculation, and performing face recognition until the calculated average depth is greater than 0 and less than the preset depth threshold. The 'approach detection based on depth data' may be continuously run when the payment device is idle, if the 'approach detection based on depth data' hits, the 'approach detection based on face detection' is run, and if the 'approach detection based on face detection' hits, it is determined that there is a user approach.

As described in the above embodiment, a 3D image may be used in the depth calculation, and if the calculated average depth is not 0 and is smaller than the preset depth threshold, an RGB image corresponding to the 3D image may be acquired based on the image capturing time, and face recognition processing may be performed on the RGB image to determine whether a user approaches the payment device.

When the embodiment of the specification detects the approach of the user, the depth calculation and the face recognition are combined, the depth calculation can quickly calculate whether an object approaches the payment equipment, and after the object approaches the payment equipment, whether the object approaches the payment equipment can be accurately determined through the face recognition technology, so that the efficiency of the approach detection is ensured, and the accuracy of the approach detection is improved.

In some embodiments of the present description, the method further comprises:

acquiring historical payment data of different payment objects in a specified historical time range at specified time intervals, wherein the historical payment data comprises: payment mode, payment success rate and payment interaction time;

determining the optimal payment modes of different payment objects according to the change trends of the payment success rate and the payment interaction time in the historical payment data of the different payment objects;

and when determining that no matched key action exists in the action image information of the payment object or determining that the target payment mode of the payment object is the self-selected payment mode, taking the preferred payment mode of the payment object as a default payment mode.

In a specific implementation process, in the embodiment of the present specification, the preferred payment method of the payment object may also be adjusted by periodic experience polling, specifically, historical payment data of different payment objects within a specified historical time range may be obtained at specified intervals, where the historical payment data includes: payment method, payment success rate and payment interaction time. The payment method may include face-brushing payment, code-scanning payment, autonomous payment method selection, and the like described in the above embodiment, the payment success rate may be understood as a proportion occupied by successful payment of the user, and the payment interaction time may be understood as a time from the start of payment or approach of the user to completion of payment. The preferred payment mode of each payment object can be determined according to the payment success rate of each payment object and the change trend of the payment interaction time. According to the payment success rate and the change trend of the payment interaction time of the payment object in the historical payment data in the appointed historical time range, whether the recommended payment mode meets the requirements of the user based on the approach detection and the action identification can be determined, such as: according to the result of the user periodic data inspection, if the payment success rate of the recent user is improved and the payment interaction time is shortened, the recent user experience is better and better. The preferred payment method of the payment object can be the one with the highest probability in the payment method distribution in the historical payment data. Or, the payment success rates and the change trends of the payment interaction time corresponding to different payment methods in the historical payment data of the payment object can be obtained, and the payment method with the increased payment success rate and/or the decreased payment interaction time is used as the preferred payment method. According to actual needs, other data processing can be carried out on the payment success rate and the payment interaction time, and the preferred payment mode of the payment object is selected.

When the payment object approaches the payment device and needs to pay, if the key action which is not matched in the action image information of the payment object is determined or the target payment mode of the payment object is determined to be the self-selected payment mode based on the action detection of the payment object, the preferred payment mode of the payment object determined by regular inspection can be used as the default payment mode.

The embodiment of the specification analyzes the historical payment data of each payment object to determine the preferred payment mode of each payment object, and when the payment object subsequently uses the payment device for payment, if the payment mode with definite intention of the user is not identified, the preferred payment mode can be recommended for the payment object, so that the payment mode is flexibly adjusted, the payment requirement of the user is met as much as possible, and the payment efficiency is improved.

In some embodiments of the present specification, the taking the preferred payment method of the payment object as a default payment method includes:

and ordering the preferred payment mode of the payment object in the first of a default payment mode list for selection by the payment object.

In a specific implementation process, after the preferred payment method of the payment object is determined based on the historical payment data of the payment object, when it is determined that there is no matched 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 the self-selected payment method, a list of all selectable payment methods can be displayed to a user on a display screen of the payment device, the user selects the payment method by himself, and the preferred payment method of the payment object can be sorted in the list to be the first payment method in the default payment method list, so that the user can directly select the payment method to perform payment operation. For example: and if the payment success rate and the payment interaction time change trend in the historical payment data of the payment object A are based, determining that the preferred payment mode of the payment object A is face brushing payment. If the payment object A uses the payment device for payment later, the key action corresponding to the effective payment mode is not matched with the action detection of the payment object A or no obvious action of the payment object A is determined, namely the target payment mode of the payment object A is determined to be the self-selected payment mode, the face-brushing payment is arranged in the first default payment mode list of the payment object A, so that the payment object A can quickly select the proper payment mode.

If the payment method recommendation processing method is applied to the payment device, after the payment device determines the preferred payment method of the payment object, the payment device can also send the preferred payment method to other payment devices through the server, so that when the payment method of the payment object cannot be determined by other payment devices, a default payment method list of the payment object is set based on the preferred payment method.

The preferred payment method of the payment object is determined through periodic inspection, and when the payment method of the payment object cannot be determined, the preferred payment method is set in the first of the default payment method list, so that the payment object can quickly select a proper payment method, and the payment efficiency is improved.

Fig. 2 is a schematic flow diagram of a payment method recommendation process in another embodiment of this specification, and as shown in fig. 2, the payment method recommendation process method provided in this specification mainly includes the following stages:

1. entrance detection: the payment equipment continuously performs entrance detection and judges whether a user approaches the payment equipment or not;

2. and (3) detecting the user action: training a motion detection and identification model, and detecting a key motion after a user approaches equipment;

3. the intelligent payment mode is switched: according to the result of the action detection, switching the intelligent payment mode;

4. and (3) regular experience inspection: experience indexes before and after the intelligent payment mode is switched are compared regularly, and global adjustment is carried out according to the inspection result.

According to the embodiment of the specification, the payment mode selected by the user at a high probability can be judged through some actions of the user before payment, so that the problem of user experience brought by the existing equipment is reduced.

In the present specification, each embodiment of the method is described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. The relevant points can be obtained by referring to the partial description of the method embodiment.

Based on the payment method recommendation processing method, one or more embodiments of the present specification further provide a device for payment method recommendation processing. The apparatus may include apparatus (including distributed systems), software (applications), modules, plug-ins, servers, clients, etc. that use the methods described in embodiments of the present specification in conjunction with hardware where necessary to implement the methods. Based on the same innovative conception, embodiments of the present specification provide an apparatus as described in the following embodiments. Since the implementation scheme of the apparatus for solving the problem is similar to that of the method, the specific apparatus implementation in the embodiment of the present specification may refer to the implementation of the foregoing method, and repeated details are not repeated. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.

Specifically, fig. 3 is a schematic block configuration diagram of an embodiment of the payment method recommendation processing apparatus provided in this specification, and as shown in fig. 3, the apparatus may be applied to the local server of the public transportation vehicle described above, and the payment method recommendation processing apparatus provided in this specification may include:

an approach detection module 31, configured to identify whether there is a payment object approaching the payment device according to the surrounding environment image information of the payment device;

the action image acquisition module 32 is used for acquiring action image information of the payment object after determining that the payment object is close to the payment device;

the action detection module 33 is configured to match the action image information with key actions corresponding to different preset payment methods, and determine a target payment method corresponding to the payment object;

and the payment method recommending module 34 is configured to show the target payment method to the payment object so that the payment object performs payment operation.

In the embodiment of the specification, before a user approaches a payment device, whether the user needs to use the payment device is determined by identifying the surrounding environment image of the payment device, after the user approaches the payment device, a target payment method which the user wants to use is determined by identifying the action image information of the user before payment, and the determined target payment method is recommended to the user. The user does not need to select the payment mode, the payment requirements of different users are met, the time required by payment is shortened, and the payment efficiency is improved.

It should be noted that the above-mentioned apparatus may also include other embodiments according to the description of the corresponding method embodiment. The specific implementation manner may refer to the description of the above corresponding method embodiment, and is not described in detail herein.

An embodiment of the present specification further provides a payment method recommendation processing apparatus, including: at least one processor and a memory for storing processor-executable instructions, the processor implementing the payment method recommendation processing method of the above embodiment when executing the instructions, the method comprising:

It should be noted that the above-described device or system may also include other embodiments according to the description of the method embodiments. The specific implementation manner may refer to the description of the related method embodiment, and is not described in detail herein.

Referring to the description of the above embodiment, when the payment method recommendation method in the embodiment of the present specification is applied to a server, an embodiment of the present specification provides a payment method recommendation processing system, where the system includes: payment equipment, payment server, wherein:

the payment server comprises at least one processor and a memory for storing processor executable instructions, and when the processor executes the instructions, the payment method recommendation method of the embodiment is implemented, and is used for identifying whether a payment object approaches the payment device according to the image information of the surrounding environment acquired by the payment device, acquiring the action image information of the payment object after determining that the payment object approaches the payment device, matching the action image information with preset key actions corresponding to different payment methods, determining a target payment method corresponding to the payment object, and returning the target payment method to the payment device;

The process of recommending the payment method by the payment server may refer to the description of the above embodiments and is not described herein again.

The payment mode recommendation processing device, the payment mode recommendation processing device and the payment mode recommendation processing system can also be applied to various data analysis processing systems. The system or server or terminal or device may be a single server, or may include a server cluster, a system (including a distributed system), software (applications), actual operating devices, logical gate devices, quantum computers, etc. using one or more of the methods described herein or one or more embodiments of the system or server or terminal or device, in combination with necessary end devices implementing hardware. The system for checking for discrepancies may comprise at least one processor and a memory storing computer-executable instructions that, when executed by the processor, implement the steps of the method of any one or more of the embodiments described above.

The method embodiments provided by the embodiments of the present specification can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Taking an example of the operation on a server, fig. 4 is a block diagram of a hardware structure of a payment method recommendation processing server in an embodiment of the present specification, and the computer terminal may be the payment method recommendation processing server or the payment method recommendation processing apparatus in the foregoing embodiment. The server 10 as shown in fig. 4 may include one or more (only one shown) processors 100 (the processors 100 may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA, etc.), 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 the structure shown in fig. 4 is only an illustration and is not intended to limit the structure of the electronic device. For example, the server 10 may also include more or fewer plug-ins than shown in FIG. 4, and may also include other processing hardware, such as a database or multi-level cache, a GPU, or have a different configuration than shown in FIG. 4, for example.

The non-volatile memory 200 may be configured to store software programs and modules of application software, such as program instructions/modules corresponding to the payment recommendation processing method in the embodiment of the present specification, and the processor 100 executes various functional applications and resource data updates by running the software programs and modules stored in the non-volatile memory 200. 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 memory located remotely from the processor 100, which may be connected to a computer terminal through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission module 300 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal. In one example, the transmission module 300 includes a Network adapter (NIC) that can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission module 300 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The method or apparatus provided by the present specification and described in the foregoing embodiments may implement service logic through a computer program and record the service logic on a storage medium, where the storage medium may be read and executed by a computer, so as to implement the effect of the solution described in the embodiments of the present specification.

The storage medium may include a physical device for storing information, and typically, the information is digitized and then stored using an electrical, magnetic, or optical media. The storage medium may include: devices that store information using electrical energy, such as various types of memory, e.g., RAM, ROM, etc.; devices that store information using magnetic energy, such as hard disks, floppy disks, tapes, core memories, bubble memories, and usb disks; devices that store information optically, such as CDs or DVDs. Of course, there are other ways of storing media that can be read, such as quantum memory, graphene memory, and so forth.

The payment method recommendation processing method or apparatus provided in the embodiment of the present specification may be implemented by a processor executing corresponding program instructions in a computer, for example, implemented by using a c + + language of a windows operating system on a PC side, a linux system, or implemented by using android and iOS system programming languages on an intelligent terminal, and implemented by using processing logic based on a quantum computer.

The embodiments of the present description are not limited to what must be consistent with industry communications standards, standard computer resource data updating and data storage rules, or what is described in one or more embodiments of the present description. Certain industry standards, or implementations modified slightly from those described using custom modes or examples, may also achieve the same, equivalent, or similar, or other, contemplated implementations of the above-described examples. The embodiments using the modified or transformed data acquisition, storage, judgment, processing and the like can still fall within the scope of the alternative embodiments of the embodiments in this specification.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, 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, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

For convenience of description, the above platform and terminal are described as being divided into various modules by functions and described separately. Of course, when implementing one or more of the present description, the functions of each module may be implemented in one or more software and/or hardware, or a module implementing the same function may be implemented by a combination of multiple sub-modules or sub-units, etc. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or plug-ins may be combined or integrated into another system, or some features may be omitted or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

These computer program instructions may also be loaded onto a computer or other programmable resource data update apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, and the relevant points can be referred to only part of the description of the method embodiments. In the description of the specification, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the specification. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

The above description is merely exemplary of one or more embodiments of the present disclosure and is not intended to limit the scope of one or more embodiments of the present disclosure. Various modifications and alterations to one or more embodiments described herein will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of the present specification should be included in the scope of the claims.

Claims

1. A payment method recommendation processing method, the method comprising:

2. The method of claim 1, wherein the identifying whether a payment object is close to the payment device according to the surrounding environment image information of the payment device comprises:

3. The method of claim 1, wherein the identifying whether a payment object is close to the payment device according to the surrounding environment image information of the payment device comprises:

extracting a designated central area image of the peripheral image information;

4. The method of claim 1, wherein the identifying whether a payment object is close to the payment device according to the surrounding environment image information of the payment device comprises:

extracting a designated central area image of the peripheral image information;

5. The method of claim 1, wherein the matching the motion image information with key motions corresponding to different preset payment methods to determine a target payment method corresponding to the payment object comprises:

6. The method of claim 5, wherein determining the target payment method based on the probability of the payment object hitting a key action of a different payment method comprises:

7. The method of claim 6, wherein the comprehensively determining the target payment method corresponding to the payment object according to the probability of hitting key actions of different payment methods on the payment object in the multi-frame action image information comprises:

8. The method of claim 5, the method of training the motion detection model comprising:

9. The method of claim 1, further comprising:

10. The method of claim 9, wherein the taking the preferred payment method of the payment object as a default payment method comprises:

11. The method of claim 1, the presenting the targeted payment method to the payment object, comprising:

12. The method of claim 1, the payment method comprising: face brushing payment, code scanning payment and automatic payment mode selection.

13. A payment means recommendation processing apparatus, the apparatus comprising:

14. A payment means recommendation processing apparatus comprising: at least one processor and a memory for storing processor-executable instructions, the processor implementing the method of any one of claims 1-12 when executing the instructions.

15. A payment instrument recommendation processing system, the system comprising: payment equipment, payment server, wherein:

the payment server comprises at least one processor and a memory for storing processor executable instructions, and when the processor executes the instructions, the method of any one of claims 1 to 12 is implemented, so as to identify whether a payment object approaches the payment device according to the image information of the surrounding environment acquired by the payment device, acquire the action image information of the payment object after determining that the payment object approaches the payment device, match the action image information with key actions corresponding to different preset payment modes, determine a target payment mode corresponding to the payment object, and return the target payment mode to the payment device;