CN116433287A

CN116433287A - Information recommendation method and system based on payment behaviors

Info

Publication number: CN116433287A
Application number: CN202310391485.0A
Authority: CN
Inventors: 胡鹏飞; 杨永强; 汪奕文
Original assignee: AlipayCom Co ltd
Current assignee: AlipayCom Co ltd
Priority date: 2023-04-13
Filing date: 2023-04-13
Publication date: 2023-07-14

Abstract

According to the information recommendation method based on the payment behaviors, after a payment platform receives a payment request initiated by a target user on a target terminal, a matched recommendation information set is determined for the target user. In the recommendation information set, the benefit value of the recommendation information is calculated by taking the total benefit constraint as a constraint condition and taking the maximum total payment conversion rate as a constraint target, namely, the payment platform can give the benefit value with the maximum total conversion rate under the control of cost constraint when the benefit pricing is carried out, and the payment conversion rate of the target user is improved from the target recommendation information determined for the target user based on the recommendation information set.

Description

Information recommendation method and system based on payment behaviors

Technical Field

The present disclosure relates to the field of information processing, and in particular, to an information recommendation method and system based on payment behavior.

Background

In the process of using the terminal to pay, a payment platform (such as a payment treasury) can recommend rights and interests to the terminal of the user in order to increase the payment willingness of the user, promote the successful payment or increase the drainage of a third party service platform in the payment platform. For example, "cash available for payment of this bill 0.8 yuan", "pay for this bill can return 1 yuan of telephone fee red package", etc. are recommended to the user terminal. How to recommend rights to the target user can improve the payment conversion rate of the user, so that the user can successfully complete the payment of the current transaction order at maximum probability is a problem to be solved.

Therefore, it is necessary to provide an information recommendation method based on payment behavior to improve the payment conversion rate of the user.

Disclosure of Invention

The information recommendation method and the system based on the payment behavior can improve the payment conversion rate of the user.

In a first aspect, the present disclosure provides a payment behavior-based information recommendation method, applied to a payment platform, the method including: receiving a payment request initiated by a target user through a target terminal; determining a recommendation information set matched with a user portrait of the target user, wherein the recommendation information set comprises recommendation information under at least one configuration platform, the recommendation information represents a type of rights and interests available for completing a payment action corresponding to the payment request and corresponding rights and interests values, the user portrait comprises a plurality of feature tags of the target user, and the rights and interests values are calculated by taking total rights and interests value constraint as constraint conditions and taking total payment conversion rate as constraint targets at maximum; and determining target recommendation information from the recommendation information set and sending the target recommendation information to the target terminal.

In some embodiments, the total benefit value constraint comprises a first constraint comprising, for each of the at least one configuration platform: the sum of the benefit values of the user sets matched with the benefit type sets corresponding to the current configuration platform is smaller than a first total budget, and the user sets comprise the target users.

In some embodiments, the total benefit value constraint includes a second constraint comprising, for each of the set of benefit types: the sum of the benefit values of the sub-user sets matching the current benefit type is smaller than the second total budget, said user sets comprising said sub-user sets.

In some embodiments, the total payment conversion comprises, for each of the configuration platforms: and the sum of payment conversion rates corresponding to the rights and interests values of the user set.

In some embodiments, the benefit value is obtained by: determining at least one interest type matched with each user in the user set and a plurality of candidate interest values corresponding to each interest type in the at least one interest type; and determining a corresponding equity value from the candidate equity values for each equity type of each user by taking the total equity value constraint as a constraint condition and taking the maximum total payment conversion rate as a constraint target.

In some embodiments, determining the plurality of candidate equity values comprises: obtaining a plurality of right value intervals corresponding to each right type in the at least one right type, wherein the right value intervals comprise a plurality of basic right values, and the plurality of right value intervals are arranged according to the size sequence of the basic right values; and determining one candidate benefit value from within each of the plurality of benefit value intervals to obtain the plurality of candidate benefit values.

In some embodiments, in each of the right value intervals, the marginal benefit corresponding to the candidate right value is greater than the marginal benefit corresponding to any non-candidate right value other than the candidate right value, and the marginal benefit is the benefit increased or decreased by each unit of the basic right value increased or decreased by each configuration platform.

In some embodiments, the total payout conversion is obtained by the following method: determining the payment conversion rate corresponding to each interest type of each user comprises the following steps: determining a candidate payment conversion rate corresponding to each candidate equity value in the plurality of candidate equity values of the current equity type; determining the candidate payment conversion rate corresponding to the benefit value of the current benefit type as the corresponding payment conversion rate; and taking the sum of the payment conversion rates corresponding to the user sets as the total payment conversion rate.

In some embodiments, the candidate payment conversion rate is obtained by the following method: determining an initial probability value for the candidate payment conversion rate; performing pre-estimated calibration on the initial probability value based on the mapping relation between the initial probability value and the target probability value of the candidate payment conversion rate to obtain the target probability value; and

And determining the target probability value as the candidate payment conversion rate.

In some embodiments, the set of recommended information is recalled from an original set of information that matches the user representation.

In some embodiments, the recall includes at least one of the following recall modes: recall first sub-recommendation information matching a first recall condition of a recall platform, the at least one configuration platform comprising the recall platform; recall the second sub-recommended information that the first payment conversion rate of the target user is greater than a preset conversion rate threshold; recall a third sub-recommendation message containing a preference type of the target user, wherein the preference type is a type of interest with a preference value greater than a preset preference threshold value determined based on the first historical behavior data of the target user; and recall fourth sub-recommendation information matched with a second recall condition determined based on expert experience data, wherein the recommendation information set includes at least one of the first sub-recommendation information, the second sub-recommendation information, the third sub-recommendation information, and the fourth sub-recommendation information.

In some embodiments, the recommendation information set is ordered in order of magnitude of the target user's first payment conversion rate for recommendation information in the recommendation information set.

In some embodiments, the determining target recommendation information from the recommendation information set comprises: determining a second payment conversion rate of the target user for recommendation information in the recommendation information set based on the attribute data of the target user; sequencing the recommended information in the recommended information set according to the order of the second payment conversion rate to obtain a target information set; and determining the target recommendation information in the target information set.

In some embodiments, the attribute data includes at least one of: the target user second historical behavior data, a geographic location at which the target terminal is located, a current weather condition, and a current budget for the at least one configuration platform.

In some embodiments, the number of target recommendation information is one or more pieces.

In some embodiments, the equity type includes at least one of cash, credit, energy, feed, and props.

In some embodiments, the sending to the target terminal includes: and indicating the target terminal to display the target recommendation information on a payment page, wherein the payment page comprises at least one of a front payment page, a withdrawal page, a failure withdrawal page, a payment result page and a post-payment recommendation page.

In some embodiments, the instructing the target terminal to display the target recommendation information on a payment page includes instructing the target terminal to: and displaying the acquisition mode of the target recommendation information on the payment page, wherein the acquisition mode comprises at least one of payment vertical reduction and payment return.

In a second aspect, the present disclosure further provides an information recommendation system based on payment behavior, applied to a payment platform, including at least one storage medium, storing at least one instruction set for implementing the information recommendation; and at least one processor communicatively coupled to the at least one storage medium, wherein the at least one processor reads the at least one instruction set and implements the information recommendation method of the first aspect when the information recommendation system is operating.

According to the technical scheme, in the information recommendation method based on the payment behavior, after the payment platform receives the payment request initiated by the target user on the target terminal, the matched recommendation information set is determined for the target user. In the recommendation information set, the benefit value of the recommendation information is calculated by taking the total benefit constraint as a constraint condition and taking the maximum total payment conversion rate as a constraint target, namely, the payment platform gives out the pricing with the maximum conversion rate under the lowest cost control when the benefit is priced, so that the payment conversion rate of the target user can be improved and the accompanying cost can be reduced based on the target recommendation information determined by the recommendation information set for the target user.

Additional functionality of the payment behavior-based information recommendation method and system provided herein will be set forth in part in the description that follows. The following numbers and examples presented will be apparent to those of ordinary skill in the art in view of the description. The inventive aspects of the payment behavior-based information recommendation methods and systems provided herein may be fully explained by practicing or using the methods, devices, and combinations described in the following detailed examples.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present description, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present description, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 illustrates an application scenario of an information recommendation method based on payment behavior according to some embodiments of the present disclosure;

FIG. 2 illustrates a schematic diagram of a payment behavior-based information recommendation system provided in accordance with some embodiments of the present description;

FIG. 3 illustrates a hardware architecture diagram of a computing device provided in accordance with some embodiments of the present description;

FIG. 4 illustrates a flow chart of a payment behavior-based information recommendation method provided in accordance with some embodiments of the present description;

FIG. 5 illustrates a schematic diagram of a payment front page provided in accordance with some embodiments of the present description;

FIG. 6 illustrates a flow chart of a method of equity pricing provided in accordance with some embodiments of the present specification;

FIG. 7 illustrates a schematic diagram of displaying target recommendation information on a payment home page provided in accordance with some embodiments of the present description; and

FIG. 8 illustrates a schematic block diagram of an information recommendation provided in accordance with some embodiments of the present description.

Detailed Description

The following description is presented to enable one of ordinary skill in the art to make and use the invention, and is provided in the context of a particular application and its requirements. Various modifications to the disclosed embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the disclosure. Thus, the present description is not limited to the embodiments shown, but is to be accorded the widest scope consistent with the claims.

The terminology used herein is for the purpose of describing particular example embodiments only and is not intended to be limiting. For example, as used herein, the singular forms "a", "an" and "the" include plural referents unless the context clearly dictates otherwise. The terms "comprises," "comprising," "includes," and/or "including," when used in this specification, are taken to specify the presence of stated integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

These and other features of the present specification, as well as the operation and function of the related elements of structure, as well as the combination of parts and economies of manufacture, may be significantly improved upon in view of the following description. All of which form a part of this specification, reference is made to the accompanying drawings. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the description. It should also be understood that the drawings are not drawn to scale.

The flowcharts used in this specification illustrate operations implemented by systems according to some embodiments in this specification. It should be clearly understood that the operations of the flow diagrams may be implemented out of order. Rather, operations may be performed in reverse order or concurrently. Further, one or more other operations may be added to the flowchart. One or more operations may be removed from the flowchart.

Before describing the specific embodiments of the present specification, the application scenario of the present specification will be described as follows:

when a user pays for an order on an e-commerce platform (e-commerce platform for short) by using a terminal, a payment platform is required to complete payment. The e-commerce platform may be a platform capable of implementing payment activities, such as a shopping platform, a take-away platform, a taxi taking platform, and the like. The payment platform can be a third party payment platform which is in communication connection with the e-commerce platform, such as a payment device, and can also be an e-commerce payment platform of the e-commerce platform. Fig. 1 illustrates an application scenario of an information recommendation method based on payment behavior according to some embodiments of the present disclosure. As shown in fig. 1, a user may send a payment request to a paymate through a terminal. The payment platform can determine recommendation information for the user according to the payment conversion rate of the crowd (such as crowd 1/crowd 2) to which the user belongs, namely, instruct the terminal to display rights and interests and a rights acquisition mode on a payment page. The payment page can comprise at least one of a front payment page, a withdrawal page, a failure withdrawal page, a post-payment recommendation page and a payment result page. The equity may include an equity type and an equity value. The equity type may include at least one of cash, credit, feed, red envelope, ticket, energy, prop. The rights acquisition mode may include at least one of payment establishment, payment return, and banking charge. For example, the payable platform may instruct the terminal to show that the bill payable cash is 0.8 yuan in the front page of the payment, to show that the bill payable 1 yuan of the fee red package and 5 points in the front page of the payment, to show that the bill payable can be immediately subtracted by 1.88 yuan in the back page of the payment, to show the binding card in the failure page of the payment and continue to pay to obtain 10 yuan of the red package, and/or to show that 10 points and 5 forest energies are available in the result page of the payment. For convenience of description, the present specification will mainly describe an information recommendation method of a user before confirming payment.

For convenience of description, the present specification explains terms that will appear from the following description:

user portrayal: a highly refined feature tag is obtained by analyzing the massive information of a user, and the result obtained by the user is visually represented by a plurality of feature tags.

Rights and interests: broadly refers to various incentives or tools available to users in paymate including cash, credit, phone bill package, energy, feed, props, etc.

Recall: and selecting the recommended information meeting the requirements from the full information set according to certain requirements.

Fig. 2 illustrates a schematic diagram of a payment behavior-based information recommendation system 001 provided in accordance with some embodiments of the present description. As shown in fig. 2, system 001 may include target user 100 and paymate 200. Paymate 200 includes target terminal 210, server 230, and network 250.

The target user 100 may use the target terminal 210 to conduct payment for a transaction order.

The target terminal 210 may detect a payment request initiated by the target user 100. In some embodiments, the information recommendation method may be performed on the server 230. At this time, the target terminal 210 may transmit the payment request to the server 230 through the network 250. The server 230 may receive the payment request and determine a set of recommendation information matching the user profile of the target user 100, thereby determining target recommendation information from the set of recommendation information and transmitting the target recommendation information to the target terminal 210 over the network 250. Thus, the target recommendation information may be displayed on the target terminal 210 for viewing by the target user 100. In some embodiments, the information recommendation method may be performed on the target terminal 210. At this time, when the target terminal 210 detects a payment request initiated by the target user 100, it may determine a recommendation information set matching the user portrait of the target user 100 by itself, and determine and display target recommendation information from the recommendation information set for viewing by the target user 100. In some embodiments, the information recommendation method may be partially performed on the target terminal 210 and partially performed on the server 230. For example, the target terminal 210 may transmit the detected payment request to the server 230 through the network 250. The server 230 may receive the payment request and determine a set of recommendation information matching the user profile of the target user 100 and send the set of recommendation information to the target terminal 210 over the network 250. The target terminal 210 determines target recommendation information from the recommendation information set and displays it for viewing by the target user 100.

When the information recommendation method is performed on the target terminal 210, the target terminal 210 may store data or instructions for performing the information recommendation method described in the present specification, and may perform or be used to perform the data or instructions. In some embodiments, the target terminal 210 may include a hardware device having a data information processing function and a program necessary to drive the hardware device to operate. As shown in fig. 2, the target terminal 210 may be communicatively connected to a server 230. In some embodiments, the server 230 may be communicatively coupled to a plurality of target terminals 210. In some embodiments, target terminal 210 may interact with server 230 over network 250 to receive or send messages, etc. In some embodiments, the target terminal 210 may include a mobile device, a tablet, a laptop, a built-in device for a motor vehicle or the like, a dragonfly device for a payroll, a vending machine, a sales counter, or any combination thereof. In some embodiments, the mobile device may include a smart home device, a smart mobile device, a virtual reality device, an augmented reality device, or the like, or any combination thereof. In some embodiments, the smart home device may include a smart television, a desktop computer, or the like, or any combination. In some embodiments, the smart mobile device may include a smart phone, personal digital assistant, gaming device, navigation device, etc., or any combination thereof. In some embodiments, the virtual reality device or augmented reality device may include a virtual reality helmet, virtual reality glasses, virtual reality patch, augmented reality helmet, augmented reality glasses, augmented reality patch, or the like, or any combination thereof. For example, the virtual reality device or the augmented reality device may include google glass, head mounted display, VR, or the like. In some embodiments, the built-in devices in the motor vehicle may include an on-board computer, an on-board television, and the like. In some embodiments, the target terminal 210 may include an image capturing device for capturing a biometric image, such as a face image, a fingerprint image, an iris image, a retina image, a hand image, etc., of the target user 100. Of course, the target terminal 210 may also collect sound features, behavior features, gait features, etc. of the target user 100. The image acquisition device may be a two-dimensional image acquisition device (such as an RGB camera), or may be a two-dimensional image acquisition device (such as an RGB camera) and a depth image acquisition device (such as a 3D structured light camera, a laser detector, etc.). In some embodiments, the target terminal 210 may be a device with positioning technology for locating the position of the target terminal 210.

In some embodiments, the target terminal 210 may be installed with one or more Applications (APP). The APP can provide the target user 110 with the ability to interact with the outside world via the network 250 as well as an interface. The APP includes, but is not limited to: web browser-like APP programs, search-like APP programs, chat-like APP programs, shopping-like APP programs, video-like APP programs, financial-like APP programs, instant messaging tools, mailbox terminals, social platform software, and the like. In some embodiments, the target terminal 210 may have a target APP installed thereon, where the target APP may be an APP corresponding to the e-commerce platform. The target user 100 may initiate a transaction order in the target APP and trigger a payment request. Paymate 200 may perform information recommendation methods in response to the payment request. The target APP is, for example, a shopping APP, a take-away APP, a taxi taking APP, etc.

The server 230 may be a server providing various services, such as a background server providing support for pages displayed on the target terminal 210. When the information recommendation method is performed on the server 230, the server 230 may store data or instructions for performing the information recommendation method described in the present specification, and may perform or be used to perform the data or instructions. In some embodiments, the server 230 may include a hardware device having a data information processing function and a program necessary to drive the hardware device to operate. The server 230 may be communicatively connected to a plurality of target terminals 210 and receive data transmitted by the target terminals 210.

Network 250 is the medium used to provide communication connections between target terminal 210 and server 230. Network 250 may facilitate the exchange of information or data. As shown in fig. 2, the target terminal 210 and the server 230 may be connected to a network 250 and transmit information or data to each other through the network 250. In some embodiments, network 250 may be any type of wired or wireless network, or a combination thereof. For example, network 250 may include a cable network, a wired network, a fiber optic network, a telecommunications network, an intranet, the internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Wide Area Network (WAN), a Public Switched Telephone Network (PSTN), a bluetooth network, a ZigBee network, a Near Field Communication (NFC) network, or the like. In some embodiments, network 250 may include one or more network access points. For example, network 250 may include a wired or wireless network access point, such as a base station or an internet switching point, through which one or more components of target terminal 210 and server 230 may connect to network 250 to exchange data or information.

It should be understood that the number of target terminals 210, servers 230, and networks 250 in fig. 2 are merely illustrative. There may be any number of target terminals 210, servers 230, and networks 250, as desired for implementation.

Fig. 3 illustrates a hardware block diagram of a computing device 600 provided in accordance with some embodiments of the present specification. The computing device 600 may perform the payment behavior-based information recommendation method described herein. The information recommendation method is described in other parts of the specification. When the information recommendation method is performed on the target terminal 210, the computing device 600 may be the target terminal 210. When the information recommendation method is performed on the server 230, the computing device 600 may be the server 230. While the information recommendation method may be partially performed on the target terminal 210 and partially performed on the server 230, the computing device 600 may be the target terminal 210 and the server 230.

As shown in fig. 3, computing device 600 may include at least one storage medium 630 and at least one processor 620. In some embodiments, computing device 600 may also include a communication port 650 and an internal communication bus 610. Meanwhile, computing device 600 may also include I/O component 660.

Internal communication bus 610 may connect the various system components including storage medium 630, processor 620, and communication ports 650.

I/O component 660 supports input/output between computing device 600 and other components.

Communication port 650 is for communication of data between computing device 600 and the outside world, e.g., communication port 650 may be for communication of data between computing device 600 and network 250. The communication port 650 may be a wired communication port or a wireless communication port.

The storage medium 630 may include a data storage device. The data storage device may be a non-transitory storage medium or a transitory storage medium. For example, the data storage devices may include one or more of magnetic disk 632, read Only Memory (ROM) 634, or Random Access Memory (RAM) 636. The storage medium 630 may store at least one set of instructions for implementing payment behavior based information recommendation. The instructions are computer program code that may include programs, routines, objects, components, data structures, procedures, modules, etc. that perform the payment behavior-based information recommendation methods provided herein.

The at least one processor 620 may be communicatively coupled with at least one storage medium 630 and a communication port 650 via an internal communication bus 610. The at least one processor 620 is configured to execute the at least one instruction set. When the computing device 600 is running, the at least one processor 620 may read the at least one instruction set and, according to an indication of the at least one instruction set, perform the payment behavior based information recommendation method provided herein. The processor 620 may perform all steps involved in the payment behavior based information recommendation method. The processor 620 may be in the form of one or more processors, and in some embodiments, the processor 620 may include one or more hardware processors, such as microcontrollers, microprocessors, reduced Instruction Set Computers (RISC), application Specific Integrated Circuits (ASICs), application specific instruction set processors (ASIPs), central Processing Units (CPUs), graphics Processing Units (GPUs), physical Processing Units (PPUs), microcontroller units, digital Signal Processors (DSPs), field Programmable Gate Arrays (FPGAs), advanced RISC Machines (ARM), programmable Logic Devices (PLDs), any circuit or processor capable of executing one or more functions, or the like, or any combination thereof. For illustrative purposes only, only one processor 620 is depicted in the computing device 600 in this specification. It should be noted, however, that computing device 600 may also include multiple processors, and thus, operations and/or method steps disclosed in this specification may be performed by one processor as described herein, or may be performed jointly by multiple processors. For example, if the processor 620 of the computing device 600 performs steps a and B in this specification, it should be understood that steps a and B may also be performed by two different processors 620 in combination or separately (e.g., a first processor performs step a, a second processor performs step B, or the first and second processors perform steps a and B together).

Fig. 4 illustrates a flowchart of a payment behavior-based information recommendation method P100 provided in accordance with some embodiments of the present description. As described above, the target terminal 210 and/or the server 230 may perform the payment behavior-based information recommendation method P100 described in the present specification. The method P100 is described below by way of example as being performed by the server 230. As shown in fig. 4, the method P100 may include:

s120: a payment request initiated by the target user 100 through the target terminal 210 is received.

The target user 100 may trigger a payment request for a transaction of the e-commerce platform through the target terminal 210, and the target terminal 210 may send the payment request to the server 230 of the paymate 200 when the payment request is detected, so that the server 230 receives the payment request.

The payment request is for requesting payment for a current trade order. In some embodiments, the payment request may be triggered by the target user 100 through an order submission option on an order details page. In some embodiments, the payment request may be triggered by the target user 100 on the payment pre-page by confirming the transaction option. For example, the order details page displays details of the purchased goods and a "submit order" option, and the target user 100 may trigger the payment request while clicking on the "submit order" option. The payment front page may be displayed after the target terminal 210 detects a trigger instruction to "submit order" option. The payment front page may include a plurality of candidate payment platforms' names and confirmation options thereon, and when the target user 100 selects one of the plurality of candidate payment platforms as the payment platform 200, the payment request may be initiated while clicking the "confirm transaction" option. The candidate payment platform can comprise a third party payment platform, such as a payment treasury, and can also comprise an e-commerce payment platform of the e-commerce platform. Fig. 5 illustrates a schematic diagram of a payment front page provided in accordance with some embodiments of the present description. As shown in FIG. 5, the front page of payment shows three candidate payment platforms XX payment, payment device payment, and A E-commerce payment corresponding to A E-commerce platform, and shows confirmation options corresponding to the three candidate payment platforms respectively. The target user 100 clicks on the confirm option for payment of the payment instrument and when clicks on the confirm transaction option of "confirm payment 50-ary", the payment request can be triggered.

S140: a set of recommendation information matching the user portrayal of the target user 100 is determined.

In some embodiments, the server 230 may first determine the original information set of the target user 100 and recall from the original information set to obtain the recommended information set. In some embodiments, the server 230 may also use the original information set as the recommended information set of the target user 100, without performing a recall action, which is not limited by the embodiment of the present specification.

If the server 230 recalls the recommended information set from the original information set, the method S140 may include determining two procedures, the original information set and the recall. If the server 230 directly takes the original information set as the recommended information set without performing a recall action, the method S140 may include a process of determining the original information set. The process of determining the original information set and recall, respectively, is described below.

(1) Determining an original information set

The server 230 may obtain a user representation of the target user 100, determine an original set of information matching the user representation of the target user 100, and include a plurality of recommended information. Wherein the user representation of the target user 100 includes a plurality of feature tags of the target user 100, such as hobbies of interest, liveness paid using the paymate 200, consumption level, purchase type, education level, consumption credit level, and so forth.

The original information set may include recommended information under at least one configuration platform. Each configuration platform can configure various recommendation information related to itself, including configuring the interest type and the interest value in the recommendation information. It should be noted that the recommendation information may also include the rights type and the location where the rights value is to be displayed, i.e. on which payment page is displayed, such as a front payment page, or a pull-out page. The recommendation information may also include the type of rights and the manner in which the rights and benefit values are obtained, such as payment statement, payment return, etc.

When the target user 100 completes the payment (e.g., the virtual currency in the account of the target user 100 reaches the account of the e-commerce platform) and obtains the rights under the configuration platform, the user may enter the configuration platform to cancel the rights, thereby achieving the goal of the configuration platform drainage.

In some embodiments, the configuration platform may be a third party service platform with respect to target user 100 and paymate 200. In this case, the third party service platform may include a server 230, and the server 230 of the third party service platform may be communicatively connected to the server 230 of the paymate 200 to enable a communicative connection between the third party service platform and the paymate 200. The third party service platform may transmit the configured recommendation information to the paymate 200, and the paymate 200 may determine whether to transmit the recommendation information to the target terminal 210. The payment platform 200 is for example a payment bank, and the third party service platform is for example one or more of a flower, an ant forest, an ant garden, a ballet farm, a recharging center, hungry.

In some embodiments, the configuration platform may be paymate 200 itself, such as paymate 200 may configure recommendation information for competition with other paymate 200. It should be noted that, the recommended information set is derived based on the original information set, so the recommended information set may also include recommended information under at least one configuration platform.

The recommendation information may be recommendation information about interests, that is, recommending interests to the target user 100 to motivate payment conversion of the target user 100 by interests. Specifically, the recommendation information may characterize the type of interests available for completing the payment action corresponding to the payment request and the corresponding interest value thereof. Wherein the equity type includes at least one type of cash, credit, energy, feed, and props. Various values may exist for each equity type, for example, the cash or phone fee red packet may have a value of 0.1, 0.5, 1, 1.5, 2, etc.; the basic equity value of the points may be 2, 10, 50, etc.; the basic equity value of the energy may be 1g (gram), 5g, 10g, etc.; the basic rights and interests value of the feed can be 30g (g), 50g, 100g, 180g and the like; the basic equity value of the prop can be 1 energy protection cover, 1 time accelerator, 1 energy double click card, etc.

Since there are multiple valuations for each equity type, server 230 needs to price equity in order to be able to give each configuration platform the maximum payment conversion rate under the budget of each configuration platform. That is, when the configuration platform allocates recommendation information to each user in the corresponding user set, how much the rights and interests value in the recommendation information of each user should be set can make the payment conversion rate of the corresponding user set of the configuration platform maximum under the budget constraint (cost constraint) of the configuration platform. The process of equity pricing in the original information set and the recommended information set may be the same.

In particular, each configuration platform may configure one or more equity types for each user to which it matches and price each equity type. For example, the user a often uses the bar, which is a user matched by the bar, and the bar configures two types of interests of cash and points for the user a, and the server 230 may determine the respective interest values corresponding to the two types of interests for the user a.

The method of rights pricing may be performed by server 230 of paymate 200 or by server 230 of the configuration platform. Rights pricing is described below in terms of server 230 implementation of paymate 200. FIG. 6 illustrates a flow chart of a equity pricing method provided in accordance with some embodiments of the present specification. As illustrated in fig. 6, the method of equity pricing may include:

S210: for each set of users for which the platform is configured, the server 230 may determine at least one interest type that matches each user in the set of users, and a plurality of candidate interest values for each of the at least one interest type.

The user set may be a set of users that match a set of interest types corresponding to each configuration platform. The set of interest types may be a set of interest types configured by the configuration platform in the recommendation information. For example, the set of interest types corresponding to the flower's number of flowers includes cash, points, and energy. The set of rights and interests corresponding to the ant forest comprises energy, props and feeds. In some embodiments, the set of users may include a set of users that open a corresponding configuration platform. In some embodiments, the set of users may be a set of users that have used/entered the corresponding configuration platform within a second preset period of time prior to the current time, such as 1 year, half year, 1 quarter, 1 month, etc. In some embodiments, the set of users may be a set of users whose user portraits satisfy a configuration condition for a corresponding configuration platform, such as a frequency of use of the configuration platform being above a preset frequency and/or a total amount of consumption on the configuration platform being above a preset amount, and so on.

In some embodiments, the server 230 may obtain a plurality of rights value intervals corresponding to each of the at least one rights type, where the rights value intervals include a plurality of basic rights values, and the plurality of rights value intervals are arranged according to a size order of the basic rights values. For example, when the server 230 configures the points in the hand to the user a, a plurality of interest value intervals amt (a 1, a 2..an, b1, b2...bn, c1, c2, c3...cn) corresponding to the points are acquired. Wherein (a 1, a 2..an) is a benefit value interval, (b 1, b2...bn) is a benefit value interval, (c 1, c2, c3...cn) is a benefit value interval, and amt represents a base benefit value within the benefit value interval. The plurality of interest value intervals are ordered, for example, in order of decreasing magnitude. The server 230 may calculate the gain of each user in the user set for each base benefit value according to the update model, that is, calculate the sensitivity of each user for each base benefit value, and determine the multiple benefit value intervals according to the sensitivity. For example, each right value interval includes a base right value with a sensitivity greater than a preset sensitivity threshold.

Further, the server 230 may determine a candidate benefit value from within each of the plurality of benefit value intervals to obtain the plurality of candidate benefit values. In some embodiments, the server 230 may select, as candidate equity values, a base equity value within each equity value interval that has a highest marginal benefit, which is the benefit increased or decreased per unit of base equity value added or subtracted by each configuration platform, based on random pricing sample presentations of multiple equity value intervals. At this time, in each of the right value intervals, the marginal benefit corresponding to the selected candidate right value is greater than the marginal benefit corresponding to any non-candidate right value other than the candidate right value. For example, the server 230 selects three candidate equity values amt' (a 2, b4, c 3) from among the three equity value intervals of the above example. In some embodiments, the server 230 may also determine the plurality of candidate equity values not based on equity value intervals, but by other means, such as directly retrieving the plurality of candidate equity values from a database. In some embodiments, server 230 may also select candidate equity values from within each equity value interval based on other metrics such as cost, profit, etc.

The method of equity pricing may further comprise:

s230: and determining a corresponding interest value from the candidate interest values for each interest type of each user by taking the constraint of the total interest value as a constraint condition and taking the maximum total payment conversion rate as a constraint target.

The server 230 may first calculate a candidate payment conversion rate corresponding to each of a plurality of candidate equity values of the current equity type, such as calculating a candidate payment conversion rate p (pa 2, pb4, pc 3) corresponding to each of the candidate equity values amt' (a 2, b4, c 3). In some embodiments, the server 230 may first determine an initial probability value of the candidate payment conversion rate, such as s (sa 2, sb4, sc 3), and obtain a mapping relationship, such as f (s ', p'), between the initial probability value and a target probability value of the candidate payment conversion rate, and then perform pre-estimated calibration on the initial probability value based on the mapping relationship, so as to obtain the target probability value, and determine the target probability value as the candidate payment conversion rate. The mapping relationship f (s ', p') may be obtained by training, in advance, the server 230 on the relationship between the training probability value obtained by training the sample under random pricing and the true probability value represented by the sample. In some embodiments, server 230 may also train a mapping between candidate equity values and candidate payment conversions, and determine candidate payment conversions based on the mapping and candidate equity values.

Further, the server 230 may calculate a total payout conversion rate based on the candidate payout conversion rate corresponding to each candidate equity value, respectively. Specifically, the server 230 may first select a candidate benefit value for each user in the user set corresponding to the configuration platform, and obtain a candidate payment conversion rate of the selected candidate benefit value corresponding to each user, so that each user in the user set corresponds to one candidate payment conversion rate, and the server 230 may add the candidate payment conversion rates to obtain a total payment conversion rate. That is, the server 230 may take the sum of payment conversions corresponding to the set of users as the total payment conversion.

In some embodiments, the total benefit value constraint may include a first constraint. The first constraint may be: for each configuration platform, the sum of the benefit values of a set of users matching the set of benefit types corresponding to the current configuration platform, the set of users including the target user 100, is less than the first total budget. Assuming that the number of users in the user set corresponding to the flower is 2 ten thousand, and the first total budget B of the flower is 1 ten thousand yuan, the first constraint may be: the sum of the benefit values allocated to the 2 ten thousand users by the flower number is less than 1 ten thousand yuan.

In some embodiments, the total benefit value constraint may include a second constraint. The second constraint may be: for each of the set of interest types for each configuration platform, the sum of the interest values of the subset of users that match the current interest type is less than the second total budget Bi. The Bi may be a second total budget corresponding to the ith interest type under each configuration platform.

As previously described, each configuration platform matching user set is described, which may include the sub-user set. For example, the summation of the plurality of sub-user sets corresponding to the plurality of interest types under each configuration platform may be the user set. In some embodiments, the sub-user set may be a set of users that have priced the corresponding interest type within the second preset period of time, for example, the sub-user set that has matched a phone bill red packet may be a set of users that have priced the phone bill red packet in the near 1 month core. In some embodiments, the set of sub-users may be a set of users whose user portraits satisfy a matching condition for the equity type, the matching condition may be a duration of spending on related activities of the equity type greater than a preset duration of spending, a frequency of executing the related activities greater than a preset frequency, and/or a total amount of consumption of executing the related activities greater than a preset amount, or the like. For example, if a user frequently calls, and the call duration, the call number, and/or the call fee consumption amount are relatively large, the user may belong to a sub-user set matched with the call fee red packet. For another example, a user often plays an ant forest, and the forest energy is collected every day and time, then the user may belong to a subset of users for which the energy matches.

Assuming that the number of users in the sub-user set corresponding to the number of flower is 5000 and the second total budget Bi configured by the number of flower is 3000, the second constraint may be: the sum of the benefit values of the scores allocated to the 5000 users is less than 3000 yuan.

It should be noted that the total benefit value constraint may include a first constraint, a second constraint, or both a first constraint and a second constraint, which is not limited in this embodiment of the present disclosure.

Since a total payout conversion rate can be calculated for each candidate equity value, in order to obtain the maximum total payout conversion rate, the embodiment of the specification can make the total payout conversion rate the maximum as a constraint target, and determine, for each equity type of each user, a equity value corresponding to the equity value from a plurality of candidate equity values by taking the constraint of the total equity value as a constraint condition. After determining the equity value from the plurality of candidate equity values for each equity type, the total payment conversion rate includes a sum of payment conversion rates corresponding to equity values of a set of users corresponding to each configuration platform.

After the rights pricing, the rights value in the recommendation information under each configuration platform in the original dataset/recommendation dataset is determined, and the rights value is obtained by taking the total rights value constraint as a constraint condition and taking the total payment conversion rate as a constraint target, so that the specification can give the maximum payment conversion rate of each configuration platform under the lowest cost control from the rights pricing aspect.

(2) Recall back

Server 230 may recall from the original set of information for target user 100 in one or more recall manners to obtain a recommended dataset.

In some embodiments, server 230 may recall the first sub-recommendation information that matches the first recall condition of the recall platform. The at least one configuration platform includes the recall platform, which may be part or all of the at least one configuration platform. The recall platform can train a recall model in advance according to the first recall condition of the recall platform, and recall the first sub-recommended information through the recall model. The first recall condition may be a condition related to activity of the recall platform. For example, the flower's stalk configures both cash and point interest types for the target user 100, and the first recall condition of the flower's stalk may be recall point related recommendation information, such as recalled recommendation information q1 (c 1, c3, c4..). For another example, the charging center configures the target user 100 with two types of interests, namely a telephone fee red package and a credit, and the first recall condition of the charging center may be to recall the recommendation information related to the telephone fee red package, e.g., the recall recommendation information is q2 (c 2, c5, c7..). The first sub-recommended information includes, for example, q1 (c 1, c3, c4..) and q2 (c 2, c5, c7..).

In some embodiments, the server 230 may recall the second sub-recommended information that the first payment conversion rate of the target user 100 is greater than the preset conversion rate threshold. The preset conversion threshold is, for example, 50%, 60%, 75%, 80%, 95% and the second sub-recommended information is, for example, q3 (c 1, c2, c 5). The first payment conversion rate of the target user 100 for a certain recommendation is large, which indicates that the recommendation has a positive effect on the target user 100, and is helpful for the payment conversion of the target user 100. In some embodiments, the server 230 may train an upshift model (gain model) through which the second sub-recommendation information is recalled. By recalling the second sub-recommended information that acts positively on the target user 100, the marketing countersensitivity of the target user 100 can be reduced, thereby improving the payment conversion rate.

In some embodiments, the server 230 may recall the third sub-recommendation information containing the preference type of the target user 100, which is a type of interest having a preference value determined based on the first historical behavior data of the target user 100 greater than the preset preference threshold. The first historical behavior data may be payment behavior data within a first preset period, or may be payment behavior data of a first preset number of times. For example, in a near day payment or in a near ten payment, the server 230 pushes a charge 5 wool red pack to the target terminal 210 of the target user 100, but the target user 100 does not pay but exits the payment, and when pushing a minus red pack, the payment is successful, which may indicate that the preference rights type of the target user 100 is cash, so that a third sub-recommendation message containing cash may be recalled for the target user 100. The third sub-recommendation information is, for example, q5 (c 6, c 7).

In some embodiments, server 230 may recall the fourth sub-recommendation information that matches a second recall condition determined based on expert empirical data. The second recall condition may be associated with a user representation of target user 100. For example, the target user 100 belongs to a low-activity group (group with low activity of payment), but charges a fee frequently, and the second recall condition may be determined to be recall of recommended information including a fee red package based on expert experience data. The third sub-recommendation information is, for example, q4 (c 2, c 4).

Any two of the first sub-recommendation information, the second sub-recommendation information, the third sub-recommendation information, and the fourth sub-recommendation information may include the same recommendation information. The recommendation information set may include at least one of first sub-recommendation information, second sub-recommendation information, third sub-recommendation information, and fourth sub-recommendation information.

It should be noted that, the server 230 may sort the recommended information sets obtained through recall. In some embodiments, the recommendation information sets are ordered in order of magnitude of payment conversion rate for recommendation information in the recommendation information sets by the target user 100. For example, the server 230 ranks q1 (c 1, c3, c4.), q2 (c 2, c5, c7.), q3 (c 1, c2, c5,) q4 (c 2, c4,) and q5 (c 6, c7,) in order of the first payment conversion rate from the higher to the lower in order of c' (c 1, c2, c3, c4, c5, c6, c7.). In particular, server 230 may rank the recommendation information sets using a payment conversion rate model.

In some embodiments, server 230 may pre-determine a set of recommendation information corresponding to respective user images for each user in a payment user dataset including target users 100 prior to receiving the payment request. Further, the server 230 may directly acquire the recommendation information set of the target user 100 upon receiving the payment request. The payment user data set may be a set of registered users of the payment platform 200, or a set of users logged into the payment platform 200 within a first preset period of time, such as 1 year, half year, 1 quarter, 1 month, etc., before the current time. In some embodiments, the server 230 may also determine a recommendation information set corresponding to the target user 100 after receiving the payment request.

S160: and determining target recommendation information from the recommendation information set and sending the target recommendation information to the target terminal 210.

In order to recommend more accurate recommendation information, the server 230 may determine a second payment conversion rate of the recommendation information in the recommendation information set by the target user 100 based on the attribute data of the target user 100, and order the recommendation information in the recommendation information set according to the order of magnitude of the second payment conversion rate, so as to obtain a target information set. Further, the target recommendation information is determined in the target information set.

Wherein the attribute data includes at least one of: second historical behavior data of the target user 100, a geographic location at which the target terminal 210 is located, current weather conditions, and a current budget for the at least one configuration platform.

The second historical behavior data may be payment behavior data within a second preset period, or may be payment behavior data of a second preset number of times. The values of the second preset time period and the second preset times can be set smaller, for example, the second historical behavior data of the target user 100 in the last 1 day is obtained or the payment record of the last five pens is obtained, so that the target recommendation information can be rapidly determined, and the information recommendation efficiency is improved. For the geographic location, for example, where the target user 100 is located in a country when the payment request is initiated, the server 230 may not recommend recommendation information containing a ticket to the target user 100. The current weather condition may be a weather condition of the paymate 200 when the payment request is received, for example, the current weather is a rainy day, and the probability of the target user 100 selling is increased, so the server 230 may recommend the recommendation information including the take-out ticket to the target user 100. The budget of each configuration platform may vary, and the current budget of the at least one configuration platform may be the budget of paymate 200 upon receipt of the payment request. For example, the current budget comparison is strained, and the server 230 may recommend recommendation information with a lower interest value to the target user 100.

It should be noted that the number of the target recommendation information may be one or more. That is, the embodiment of the specification can recommend single recommendation information and combined recommendation information, and enriches the recommendation form of information recommendation.

As previously mentioned, each piece of recommendation information may also include the type of equity and the location where the equity value is to be displayed, i.e., on which payment page is to be displayed, such as on the front payment page, or the pull-out page. The recommendation information may also include the type of rights and the manner in which the rights and benefit values are obtained, such as payment statement, payment return, etc. Accordingly, the server 230 may instruct the target terminal 210 to display the target recommendation information on the payment page corresponding to the target recommendation information. The payment page may include at least one of a payment front page, an exit retrieval page, a fail retrieval page, a payment result page, and a post-payment recommendation page. As shown in fig. 5, the target recommendation information is displayed on the payment front page, the payment platform 200 is a payment instrument, and the target recommendation information 211 is "can be subtracted 1 element". FIG. 7 illustrates a schematic diagram of displaying target recommendation information on a payment home page, other payment pages not being presented, provided in accordance with some embodiments of the present description. As shown in fig. 7, the target recommendation information 211 is "this list can return 1-yuan telephone fee red package and 5g forest energy".

In some embodiments, the server 230 may determine, after receiving the payment request, one target recommendation for each payment page, where the target recommendation for each payment page may be determined with the constraint of the total equity value and the constraint target of the maximum total payment conversion rate. The target terminal 210 displays which payment page on which the corresponding target recommendation information can be displayed. In this way, the target recommendation information can be configured for multiple payment pages through one payment request of the target user 100, and each payment page does not need to be configured individually, so that the information recommendation efficiency is improved, and the information recommendation is intelligent.

When the target user 100 completes the payment action corresponding to the payment request through the target terminal 210, the equity type and equity value in the target recommendation information can be acquired, and the equity type and equity value in the target recommendation information can be verified.

In some embodiments, FIG. 8 illustrates a schematic block diagram of an information recommendation provided in accordance with some embodiments of the present description. As shown in fig. 8, the target user 100 may initiate a payment decision through the target terminal 210. Target terminal 210 may consult paymate 200 with recommendation information. Paymate 200 may consult the equity platform for the manner in which recommended information is obtained and the equity (including equity type and equity value). The rights platform may be the server 230 of the paymate 200 or the server 230 of the configuration platform. The equity platform may first price equity. The equity pricing process may include pricing strategies, pre-estimated calibration, online planning. The pricing strategy is used for determining candidate equity values, the pre-estimated calibration is used for determining candidate payment conversion rates of the candidate equity values, and the online programming is used for calculating the total payment conversion rate with the total equity value constraint as a constraint condition and with the maximum total payment conversion rate as a constraint target, so that an original information set is obtained. The equity pricing may be followed by recalling a recommendation information set from the original information set, including platform activity recall, gain model (update) recall, pay-line history recall, and expert experience recall. The platform activity recall is used for recalling the first sub-recommendation information, the gain model recall is used for recalling the second sub-recommendation information, the payment line history recall is used for recalling the third sub-recommendation information, and the expert experience recall is used for recalling the four sub-recommendation information. The recommendation information sets may then be refined according to the first payment conversion rate of the target user 100. And rearranging the refined recommendation information sets according to the attribute data of the target user 100. Further, it is determined from the rearranged recommendation information set that the target recommendation information is returned to the paymate 200, so that the paymate 200 can transmit the target recommendation information to the target terminal 210.

In summary, according to the information recommendation method and system provided by the specification, the payment platform can provide the pricing with the maximum conversion rate under the lowest cost control for the recommendation information in the recommendation information set, so that the target recommendation information is determined for the target user based on the recommendation information set, the payment conversion rate of the target user can be improved, and the accompanying cost is reduced.

Another aspect of the present description provides a non-transitory storage medium storing at least one set of executable instructions for performing a payment behavior based information recommendation method. When executed by a processor, the executable instructions direct the processor to perform the steps of the payment behavior based information recommendation method P100 described herein. In some possible implementations, aspects of the specification can also be implemented in the form of a program product including program code. The program code is for causing the payment behavior based information recommendation system 001 to perform the steps of the payment behavior based information recommendation method P100 described in the present specification when the program product is run on the payment behavior based information recommendation system 001. The program product for implementing the above method may employ a portable compact disc read only memory (CD-ROM) comprising program code and may run on the payment behavior based information recommendation system 001. However, the program product of the present specification is not limited thereto, and in the present specification, the readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system. The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. The computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable storage medium may also be any readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing. Program code for carrying out operations of the present specification may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the payment behavior-based information recommendation system 001, partially on the payment behavior-based information recommendation system 001, as a stand-alone software package, partially on the payment behavior-based information recommendation system 001, partially on a remote computing device, or entirely on the remote computing device.

The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can 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 are also possible or may be advantageous.

In view of the foregoing, it will be evident to a person skilled in the art that the foregoing detailed disclosure may be presented by way of example only and may not be limiting. Although not explicitly described herein, those skilled in the art will appreciate that the present description is intended to encompass various adaptations, improvements, and modifications of the embodiments. Such alterations, improvements, and modifications are intended to be proposed by this specification, and are intended to be within the spirit and scope of the exemplary embodiments of this specification.

Furthermore, certain terms in the present description have been used to describe embodiments of the present description. For example, "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present description. Thus, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various portions of this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined as suitable in one or more embodiments of the invention.

It should be appreciated that in the foregoing description of embodiments of the present specification, various features have been combined in a single embodiment, the accompanying drawings, or description thereof for the purpose of simplifying the specification in order to assist in understanding one feature. However, this is not to say that a combination of these features is necessary, and it is entirely possible for a person skilled in the art to label some of the devices as separate embodiments to understand them upon reading this description. That is, embodiments in this specification may also be understood as an integration of multiple secondary embodiments. While each secondary embodiment is satisfied by less than all of the features of a single foregoing disclosed embodiment.

Each patent, patent application, publication of patent application, and other material, such as articles, books, specifications, publications, documents, articles, and the like, in addition to any historical prosecution documents associated therewith, any identical or conflicting material to the present document or any identical historical prosecution document which may have a limiting effect on the broadest scope of the claims, is incorporated herein by reference for all purposes now or later associated with the present document. Furthermore, the terms in this document are used in the event of any inconsistency or conflict between the description, definition, and/or use of terms associated with any of the incorporated materials.

Finally, it is to be understood that the embodiments of the application disclosed herein are illustrative of the principles of the embodiments of the present specification. Other modified embodiments are also within the scope of this specification. Accordingly, the embodiments disclosed herein are by way of example only and not limitation. Those skilled in the art can adopt alternative arrangements to implement the application in the specification based on the embodiments in the specification. Therefore, the embodiments of the present specification are not limited to the embodiments precisely described in the application.

Claims

1. An information recommendation method based on payment behaviors is applied to a payment platform, and the method comprises the following steps:

receiving a payment request initiated by a target user through a target terminal;

determining a set of recommendation information matching a user representation of the target user, the set of recommendation information comprising recommendation information under at least one configuration platform, the recommendation information characterizing a type of equity obtainable for completing a payment action corresponding to the payment request and its corresponding equity value, the user representation comprising a plurality of feature tags of the target user,

the right value is calculated by taking the constraint of the total right value as a constraint condition and taking the maximum total payment conversion rate as a constraint target; and

And determining target recommendation information from the recommendation information set and sending the target recommendation information to the target terminal.

2. The method of claim 1, wherein the total benefit value constraint comprises a first constraint comprising, for each of the at least one configuration platform:

the sum of the benefit values of the user sets matched with the benefit type sets corresponding to the current configuration platform is smaller than a first total budget, and the user sets comprise the target users.

3. The method of claim 2, wherein the total equity value constraint comprises a second constraint comprising, for each equity type in the set of equity types:

the sum of the benefit values of the sub-user sets matching the current benefit type is smaller than the second total budget, said user sets comprising said sub-user sets.

4. The method of claim 3, wherein the total payment conversion comprises, for each configuration platform:

and the sum of payment conversion rates corresponding to the rights and interests values of the user set.

5. The method of claim 4, wherein the benefit value is obtained by:

determining at least one interest type matched with each user in the user set and a plurality of candidate interest values corresponding to each interest type in the at least one interest type; and

And determining a corresponding equity value from the candidate equity values for each equity type of each user by taking the total equity value constraint as a constraint condition and taking the maximum total payment conversion rate as a constraint target.

6. The method of claim 5, wherein determining the plurality of candidate equity values comprises:

obtaining a plurality of right value intervals corresponding to each right type in the at least one right type, wherein the right value intervals comprise a plurality of basic right values, and the plurality of right value intervals are arranged according to the size sequence of the basic right values; and

determining one candidate benefit value from each of the plurality of benefit value intervals to obtain the plurality of candidate benefit values.

7. The method of claim 6, wherein, within each of the equity intervals, the marginal benefit corresponding to the candidate equity value is greater than the marginal benefit corresponding to any non-candidate equity value other than the candidate equity value, the marginal benefit being an increased or decreased benefit per unit of increase or decrease of the base equity value by the each configuration platform.

8. The method of claim 5, wherein the total pay conversion is obtained by:

Determining the payment conversion rate corresponding to each interest type of each user comprises the following steps:

determining a candidate payment conversion rate corresponding to each candidate equity value of the plurality of candidate equity values of the current equity type,

determining the candidate payment conversion rate corresponding to the benefit value of the current benefit type as the corresponding payment conversion rate;

and taking the sum of the payment conversion rates corresponding to the user sets as the total payment conversion rate.

9. The method of claim 8, wherein the candidate payment conversion rate is obtained by:

determining an initial probability value for the candidate payment conversion rate;

performing pre-estimated calibration on the initial probability value based on the mapping relation between the initial probability value and the target probability value of the candidate payment conversion rate to obtain the target probability value; and

10. The method of claim 1, wherein the set of recommended information is recalled from an original set of information that matches the user representation.

11. The method of claim 10, wherein the recall comprises at least one of the following recalls:

Recall first sub-recommendation information matching a first recall condition of a recall platform, the at least one configuration platform comprising the recall platform;

recall the second sub-recommended information that the first payment conversion rate of the target user is greater than a preset conversion rate threshold;

recall a third sub-recommendation message containing a preference type of the target user, wherein the preference type is a type of interest with a preference value greater than a preset preference threshold value determined based on the first historical behavior data of the target user; and

recall the fourth sub-recommendation information that matches a second recall condition, the second recall condition determined based on expert empirical data,

the recommendation information set comprises at least one of first sub-recommendation information, second sub-recommendation information, third sub-recommendation information and fourth sub-recommendation information.

12. The method of claim 10, wherein the set of recommendation information is ordered in order of magnitude of a first payment conversion rate of recommendation information in the set of recommendation information by the target user.

13. The method of claim 1, wherein the determining target recommendation information from the set of recommendation information comprises:

Determining a second payment conversion rate of the target user for recommendation information in the recommendation information set based on the attribute data of the target user;

sequencing the recommended information in the recommended information set according to the order of the second payment conversion rate to obtain a target information set; and

and determining the target recommendation information in the target information set.

14. The method of claim 13, wherein the attribute data comprises at least one of:

the target user second historical behavior data, a geographic location at which the target terminal is located, a current weather condition, and a current budget for the at least one configuration platform.

15. The method of claim 13, wherein the number of target recommendation information is one or more pieces.

16. The method of claim 1, wherein the equity type comprises at least one of cash, credit, energy, feed, and props.

17. The method of claim 1, wherein the transmitting to the target terminal comprises:

the target terminal is instructed to display the target recommendation information on a payment page,

The payment page comprises at least one of a front payment page, a withdrawal page, a failure withdrawal page, a payment result page and a recommendation page after payment.

18. The method of claim 17, wherein the instructing the target terminal to display the target recommendation information on a payment page comprises instructing the target terminal to:

displaying the acquisition mode of the target recommendation information on the payment page,

wherein the acquisition mode comprises at least one of payment standing and subtracting and payment returning.

19. An information recommendation system based on payment behavior is applied to a payment platform and comprises:

at least one storage medium storing at least one set of instructions for implementing the information recommendation; and

at least one processor communicatively coupled to the at least one storage medium,

wherein the at least one processor reads the at least one instruction set and implements the information recommendation method of any of claims 1-18 when the information recommendation system is running.