CN112073454B

CN112073454B - Resource distribution method and device and electronic equipment

Info

Publication number: CN112073454B
Application number: CN202010712767.2A
Authority: CN
Inventors: 俞悦; 杨蕾; 望金蓉; 谢乾龙
Original assignee: Beijing Sankuai Online Technology Co Ltd
Current assignee: Beijing Sankuai Online Technology Co Ltd
Priority date: 2020-07-22
Filing date: 2020-07-22
Publication date: 2022-07-08
Anticipated expiration: 2040-07-22
Also published as: CN112073454A

Abstract

The application discloses a resource distribution method, belongs to the technical field of computers, and is beneficial to improving the resource distribution efficiency. The method comprises the following steps: determining a resource quantity index matched with a current exposure user of a resource provider through a first server; matching the resource quantity index with a pre-stored corresponding relation of the resource quantity and the resource quantity index level, and determining the resource quantity corresponding to the resource quantity index level matched with the current exposure user; the corresponding relation is obtained by performing data processing on the historical behavior data of the full-exposure user of the resource provider aiming at the resource provider in the specified time period through the second server; the first server sends the resources of the resource quantity to the user account of the current exposure user according to the determined resource quantity, and the method can improve the resource distribution efficiency by calculating the corresponding relation between the resource quantity and the index level of the resource quantity in an off-line manner according to the historical behavior data of the full amount of users and distributing the resources on line according to the corresponding relation.

Description

Resource distribution method and device and electronic equipment

Technical Field

The embodiment of the application relates to the technical field of computers, in particular to a resource distribution method, a resource distribution device, electronic equipment and a computer-readable storage medium.

Background

In order to improve user experience and improve interaction frequency between a user and resource providers such as a platform or a merchant, many resource providers distribute resources to the user through an e-commerce platform, so as to improve interaction frequency between the user and the resource providers. Wherein the resources include, but are not limited to: cloud storage space, network traffic, points, subsidy coupons, and the like. In order to improve the utilization efficiency of resources distributed to users and distribute the resources to users who really need the resources, a resource distribution method in the prior art usually calculates the amount of resources distributed to users by a certain resource provider in real time according to user characteristics (such as resource sensitivity). However, since different resource providers may face different user populations, users with the same user characteristics may have different vertical resource distribution weights among the user populations for the different resource providers. Therefore, this resource distribution method in the prior art cannot maximize the resource utilization efficiency for each resource provider.

It is seen that there is still a need for an improved resource distribution method.

Disclosure of Invention

The embodiment of the application provides a resource distribution method which is beneficial to improving the resource distribution efficiency.

In order to solve the above problem, in a first aspect, an embodiment of the present application provides a resource distribution method, including:

the method comprises the steps that a first server determines a resource quantity index matched with a current exposure user of a resource provider;

the first server matches the resource quantity index with a corresponding relation between a pre-stored resource quantity and a resource quantity index level, and determines the resource quantity corresponding to the resource quantity index level matched with the current exposure user; wherein, the corresponding relation between the resource quantity and the index grade of the resource quantity is obtained by the following method: performing data processing on the historical behavior data of the full exposure users of the resource provider aiming at the resource provider in a specified time period through a second server to obtain the corresponding relation between the resource quantity and the index level of the resource quantity;

and the first server sends the resources of the resource quantity to the user account of the current exposure user according to the determined resource quantity.

In a second aspect, an embodiment of the present application provides a resource distribution apparatus, including:

the resource quantity index determining module is used for determining a resource quantity index matched with a current exposure user of the resource provider by the first server;

a matching resource quantity determining module, configured to match, by the first server, the resource quantity index with a correspondence between a pre-stored resource quantity and a resource quantity index level, and determine a resource quantity corresponding to the resource quantity index level matched with the current exposure user; wherein, the corresponding relation between the resource quantity and the index grade of the resource quantity is obtained by the following method: performing data processing on the historical behavior data of the full exposure users of the resource provider aiming at the resource provider in a specified time period through a second server to obtain the corresponding relation between the resource quantity and the index level of the resource quantity;

and the resource distribution module is used for sending the resources of the resource quantity to the user account of the current exposure user by the first server according to the determined resource quantity.

In a third aspect, an embodiment of the present application further discloses an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the resource distribution method according to the embodiment of the present application when executing the computer program.

In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the resource distribution method disclosed in the present application.

According to the resource distribution method disclosed by the embodiment of the application, the resource quantity index matched with the current exposure user of the resource provider is determined through the first server; the first server matches the resource quantity index with a corresponding relation between a pre-stored resource quantity and a resource quantity index level, and determines the resource quantity corresponding to the resource quantity index level matched with the current exposure user; wherein, the corresponding relation between the resource quantity and the index grade of the resource quantity is obtained by the following method: performing data processing on the historical behavior data of the full exposure users of the resource provider aiming at the resource provider in a specified time period through a second server to obtain the corresponding relation between the resource quantity and the index level of the resource quantity; and the first server sends the resources of the resource quantity to the user account of the current exposure user according to the determined resource quantity, so that the resource distribution efficiency is improved.

The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.

Drawings

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

FIG. 1 is a flowchart of a resource distribution method according to a first embodiment of the present application;

fig. 2 is a schematic diagram of an application system in a resource distribution method according to a first embodiment of the present application;

FIG. 3 is another flowchart of a resource distribution method according to a first embodiment of the present application;

fig. 4 is a schematic structural diagram of a resource distribution apparatus according to a second embodiment of the present application;

fig. 5 is a second schematic structural diagram of a resource distribution apparatus according to a second embodiment of the present application;

FIG. 6 schematically shows a block diagram of an electronic device for performing a method according to the present application; and

fig. 7 schematically shows a storage unit for holding or carrying program code implementing a method according to the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Example one

As shown in fig. 1, a resource distribution method disclosed in an embodiment of the present application includes: step 110 to step 130.

In step 110, the first server determines a resource quantity index matched with a currently exposed user of the resource provider.

The resource quantity index is used for indicating the promotion degree of the quantity of the resources on the preset operation executed by the current exposure user aiming at the resource provider. For example, the resource quantity index is the resource sensitivity of the user. Taking the resource as a subsidy ticket for example, the resource quantity index matched by the user may be a subsidy ticket sensitivity of the user, and the subsidy ticket sensitivity of the user is used for indicating the ordering probability of the user at the resource provider under the condition of distributing different subsidy ticket quantities. Taking the resource as the network traffic, for example, the resource quantity index matched by the user may be a download data traffic promotion ratio of the user, where the download data traffic promotion ratio of the user is used to indicate a traffic used by the user to upload or download data at a resource provider (such as a network disk platform or a content website) when the user configures different network traffic and a traffic used when the user does not configure network traffic.

The resource provider in the embodiment of the present application may be any registered merchant in the e-commerce platform, and the currently exposed user in the embodiment of the present application refers to a user currently browsing a page of an e-commerce platform website where the resource provider is displayed or a page of an e-commerce platform application client.

In some embodiments of the present application, the currently exposed user is a registered user of the e-commerce platform.

The resource distribution method described in the embodiment of the present application is applied to an e-commerce platform shown in fig. 2. As shown in fig. 2, the electronic commerce platform includes: a user management system 210, a logging system 220, a resource distribution system 230. The user management system 210 is configured to store user information, where the user information includes a resource amount bound to a user account and may further include a resource amount indicator associated with the user account; the log system 220 is configured to store historical behavior data of the user for the merchant, for example, order data, click data, and the like of the user; the resource distribution system 230 further comprises: the system comprises a first server 2301 and a second server 2302, wherein the second server 2302 is used for calculating the corresponding relation between the resource quantity and the resource quantity index level according to historical behavior data of the user for the merchant, which is stored by the log system 220, and the resource quantity index of the user, which is stored by the user management system 210; the first server 2301 is configured to periodically download and update the correspondence between the resource quantity and the resource quantity index level calculated by the second server 2302, and perform resource distribution on the current exposure user of the target merchant according to the correspondence.

In some embodiments of the present application, the user management system 210 may calculate, store, and update the resource quantity index level of the user according to the historical behavior data period of the user, and the resource distribution system 230 may obtain the resource quantity index level matched with the user through an interface provided by the user management system 210.

In some embodiments of the present application, the user management system 210 may also calculate, in real time, a resource quantity index matched to the currently exposed user.

The present application does not limit the specific implementation of determining the resource quantity index matched with the current exposure user.

And step 120, the first server matches the resource quantity index with a pre-stored corresponding relationship between the resource quantity and the resource quantity index level, and determines the resource quantity corresponding to the resource quantity index level matched with the current exposure user.

In the embodiment of the application, in order to improve the resource distribution efficiency, merchants are used as the granularity, the corresponding relation between different resource quantity index levels and the resource quantity is determined in an offline period, and the resource distribution is performed on the user online according to the corresponding relation. For example, with T days as a period, calculating the corresponding relationship between the resource quantity and the resource quantity index level once every T days according to the historical data of the resource provider, and storing the corresponding relationship between the resource quantity and the resource quantity index level obtained by the latest calculation into a preset server according to the corresponding relationship between the corresponding relationship obtained by the latest calculation and the previous period.

Wherein, the corresponding relation between the resource quantity and the index grade of the resource quantity is obtained by the following method: and performing data processing on the historical behavior data of the full exposure users of the resource provider aiming at the resource provider in a specified time period through a second server to obtain the corresponding relation between the resource quantity and the index level of the resource quantity. The specified time period is determined according to the time of the current update cycle. For example, the specified time period may be the first 2 weeks of the current update cycle. The update period described in the embodiment of the present application is determined according to specific service requirements, and may be set to 1 week or 2 weeks, or may also be set to 1 month or 1 day.

In some embodiments of the present application, as shown in fig. 3, the method further comprises: step 100.

And step 100, performing data processing on the historical behavior data of the full-exposure users of the resource provider aiming at the resource provider in a specified time period through a second server to obtain the corresponding relation between the resource quantity and the index level of the resource quantity.

In some embodiments of the application, the performing, by the second server, data processing on the historical behavior data of the resource provider for the full-exposure users of the resource provider in the specified time period to obtain the correspondence between the resource quantity and the resource quantity index level includes: the second server pre-estimates a resource distribution efficiency index corresponding to each combination when resource distribution is carried out according to each combination of each resource quantity index level matched by the full exposure user and different quantities of resources according to the historical behavior data of the resource provider under different resource quantity configuration conditions of the full exposure user of the resource provider in a specified time period; and determining the combination with the minimum resource distribution quantity when the combination is used for distributing resources, and determining the corresponding relation between the resource quantity and the resource quantity index grade according to the combination with the minimum resource distribution quantity.

The method comprises the steps of firstly determining distribution information of exposure users of a resource provider in each resource quantity index level according to historical behavior data of all the exposure users of the resource provider in a period of historical time, then integrating the historical data in the period of historical time, predicting the exposure users corresponding to each resource quantity index level, and when different quantities of resources are configured, estimating behavior parameters (such as single probability, uploading data flow and the like) of the exposure users in the corresponding resource quantity index levels at the resource provider. And then, according to the estimated behavior parameters, further estimating exposure users in the index level corresponding to the quantity of each resource, and when configuring different quantities of resources, the resource distribution efficiency. And finally, judging the estimated resource distribution efficiency by using a preset constraint condition, determining the resource distribution efficiency meeting the preset constraint condition, and selecting the combination of the resource quantity index grade and the quantity resource corresponding to the optimal resource distribution efficiency by combining the resource distribution quantity in the resource distribution efficiency meeting the preset constraint condition.

In some embodiments of the present application, when the second server predicts, according to historical behavior data of the resource provider under different resource quantity configuration conditions of a full-exposure user of the resource provider within a specified time period, resource distribution efficiency indexes corresponding to each combination when resource distribution is performed according to each combination of each resource quantity index level matched by the full-exposure user and different quantities of resources, the resource distribution efficiency indexes corresponding to each combination include: substeps S1 to substep S4.

And a substep S1, performing data processing on the historical behavior data of the user for the resource provider in a specified time period by the second server, and determining resource quantity index levels corresponding to the full-exposure independent visitors of the resource provider and distribution information of each resource quantity index level.

In some embodiments of the present application, performing data processing on historical behavior data of a user for the resource provider within a specified time period, and determining resource quantity index levels corresponding to full-exposure independent visitors of the resource provider and distribution information of each resource quantity index level, includes: processing historical behavior data of the user aiming at the resource provider in the specified time period, and determining an exposure independent visitor of the resource provider; determining a resource quantity index corresponding to each exposure independent visitor; dividing the resource quantity index into a plurality of resource quantity index levels, and determining the distribution information of each resource quantity index level corresponding to the full-exposure independent visitor.

In some embodiments of the present application, in order to facilitate readers to understand the present solution, a specific technical solution of resource distribution is illustrated by taking distributed resources as a subsidy coupon as an example. Accordingly, the resource quantity index rating may be a user's subsidy ticket sensitivity rating. Those skilled in the art will appreciate that if the distributed resource is network traffic or storage space, the resource quantity index level will correspond to a network traffic sensitivity level, a storage space sensitivity level. The resource quantity index level can be a ratio for representing that a user uploads data to the resource provider under the condition of different quantities of storage space, and the like.

In some embodiments of the present application, processing historical behavior data of the user for the resource provider in the specified time period, and determining an exposure independent visitor of the resource provider includes: and clustering the historical behavior data of the user aiming at the resource provider based on the user identification, wherein the user identification of each category corresponds to one exposure independent visitor of the resource provider. For example, log data stored in the log system 220 for a specified period of time for a resource provider is first traversed, ordering data and/or access data for a user at the resource provider is determined, and all exposed independent guests of the resource provider are determined.

Then, the user management system 210 obtains the subsidy coupon sensitivity level (i.e. resource quantity index) of each exposed independent visitor, and further determines the resource quantity index level distribution information of each exposed independent visitor according to the subsidy coupon sensitivity matched with each exposed independent visitor.

In some embodiments of the present application, the dividing the resource quantity index into multiple resource quantity index levels and determining distribution information of each resource quantity index level corresponding to the full-exposure independent visitor includes: establishing a resource quantity index distribution curve in a plane rectangular coordinate system by taking a resource quantity index as a first coordinate and taking the number of the exposure independent visitors corresponding to each resource quantity index as a second coordinate; dividing the first coordinate into a plurality of first coordinate intervals at equal intervals, wherein each first coordinate interval corresponds to one index grade, and each first coordinate interval corresponds to one section of the resource quantity index distribution curve; and taking the area formed by the resource quantity index distribution curve corresponding to each first coordinate interval and the first coordinate interval as the distribution information of the full-exposure independent visitor in the resource quantity index level corresponding to the corresponding first coordinate interval.

For example, a resource quantity index distribution curve is established in a rectangular plane coordinate system with the sensitivity level of the patch ticket as an abscissa and the sensitivity level corresponding to the patch ticket as an ordinate. Then, in order to simplify the calculated amount, equally dividing the abscissa into N (N is a positive integer) coordinate intervals, wherein each abscissa interval corresponds to a resource quantity index level, and each abscissa interval corresponds to a section of the resource quantity index distribution curve; and taking the area formed by the resource quantity index distribution curve corresponding to each abscissa interval and the abscissa interval as the distribution information of the exposure user in the resource quantity index level corresponding to the corresponding abscissa interval.

In other embodiments of the present application, the resource quantity index interval of the full exposure users of the resource provider may be equally divided into N intervals, each interval corresponds to one resource quantity index level, the quantity of the full exposure users covered by each interval is calculated, and the quantity of the full exposure users covered by each interval is used as distribution information of the full exposure users in the resource quantity index level corresponding to the interval.

The substep S2 determines all combinations of the resource number index levels and the resource numbers indicating the resource allocation conditions of the respective resource number index levels.

Taking the example that the total exposure users of the resource provider are distributed at N resource quantity index levels, assuming that the resource provider countsAllocating I number of resources to obtain I^NA combination of resource allocation cases. For example, a number J of resources is allocated to N resource number index level users, each resource number index level user configured all combinations of resource numbers.

And a substep S3, predicting behavior parameters of the full exposure independent visitor at each resource quantity index level corresponding to the combination to the resource provider when resource distribution is performed on the full exposure independent visitor corresponding to the resource quantity index level in the combination according to the resource quantity in each combination.

Still taking the example that the full exposure users of the resource provider are distributed in N resource quantity index levels, suppose that the resource provider plans to distribute I quantities of resources, and each resource quantity index level is represented as M_n,0≤n<N, identifying the number of each resource as J_i，0≤i<I, then for the resource quantity index level M_nAnd number of resources J_iRespectively predicting the ordering probability of the full-exposure independent visitor to the resource provider corresponding to each combination. In some embodiments of the present application, the resource quantity may be indexed by a rank M_nTaking the average value of the singles probability of the exposure independent visitors in the middle distribution when configuring different quantities of resources as the index level M of the quantity of the resources_nThe probability of placing orders of the exposure independent visitors distributed in the system when configuring the corresponding quantity of resources. For example, for a scenario with 3 resource quantity index levels and 2 resource quantities, 8 combinations of resource quantity index levels and resource quantities, respectively denoted as [ J ] can be obtained₁,J₁,J₁]、[J₁,J₁,J₂]、[J₁,J₂,J₁]、[J₁,J₂,J₂]、[J₂,J₁,J₁]、[J₂,J₁,J₂]、[J₂,J₂,J₁]、[J₂,J₂,J₂]Each element in the combination represents the number of resources configured per resource number index level.

Index rating for each resource quantityAnd the number of resources, in which case the probability of ordering the full-exposure independent guest at the resource provider is predicted, e.g. for combination [ J [ ]₁,J₁,J₂]Estimating the resource quantity index level M₀Exposure independent visitor distribution number J of medium distribution₁Resource, index level M for resource quantity₁Medium distributed exposure independent visitor distribution number J₁Resource, index level M for resource quantity₂Exposure independent visitor distribution number J of medium distribution₂When the resource is used, the full exposure of the independent visitor in each resource quantity index level of the resource provider is the single probability P of the resource provider_cnWherein, C is a combination identifier, and n is a resource quantity index grade identifier. In the embodiment of the application, in the scene of distributing the subsidy tickets, the lower single probability P_cnAnd the full exposure independent visitor representing the resource quantity index level n exposes the behavior parameters of the user to the resource provider under the condition of the resource configuration of the combination c of each resource quantity index level and the resource quantity.

And a substep S4, estimating resource distribution efficiency indexes corresponding to the combinations of each resource quantity index level and the resource quantity when the full-exposure users of each resource quantity index level distribute resources according to different resource quantity combinations according to the distribution information of the resource quantity index level in each combination and the behavior parameters corresponding to the combinations.

Through the steps, I can be obtained^NAnd the behavior parameters of the users of the resource provider at the index level of the number of the resources corresponding to each combination in the combinations. Next, the obtained I is calculated respectively^NAnd in each combination, the resource distribution efficiency index corresponding to each combination.

In some embodiments of the application, the step of predicting, according to the distribution information of each resource quantity index level in each combination and the behavior parameters corresponding to each resource quantity index level and the combination, a resource distribution efficiency index corresponding to each combination of the resource quantity index level and the resource quantity when the full-exposure user of each resource quantity index level performs resource distribution according to different resource quantity combinations includes: for each combination, taking the distribution information of each resource quantity index level in the combination and the product of the resource quantity index level and the behavior parameter corresponding to the combination as a first distribution quantity of the exposure independent visitor corresponding to the combination; and dividing the first distribution number of the independent exposure visitor corresponding to each combination by the cumulative sum of the distribution information of each resource number index level in the combination to obtain a resource distribution efficiency index corresponding to the combination of the resource number index level and the resource number.

For example, it can be represented by a formula

Calculating resource distribution efficiency index D corresponding to each combination of resource quantity index grade and resource quantity_CWherein c represents a combined identifier; n represents a resource quantity index level identification; UV (ultraviolet) light_nDistribution information (e.g., the number of exposed users) indicating the nth resource number index level; p_cnThe resource allocation of the combination c indicates the probability of placing an order of the exposure user at the nth resource number index level.

According to the method, the resource distribution efficiency index corresponding to each combination of the resource quantity index level and the resource quantity can be determined.

In some embodiments of the present application, determining, among the combinations corresponding to the resource distribution efficiency indicators that satisfy preset resource distribution efficiency conditions, the combination with the smallest number of distributed resources when performing resource distribution according to the combination, and determining, according to the combination with the smallest number of distributed resources, a correspondence between the number of resources and the level of the resource number indicator, includes: substeps S5 to substep S7.

And a substep S5, determining the resource quantity and the resource quantity index grade corresponding to the resource distribution efficiency index meeting the preset resource distribution efficiency condition, and respectively using the resource quantity and the resource quantity index grade as the combination of the resource quantity and the resource quantity index grade meeting the preset resource distribution efficiency condition.

In some embodiments of the present application, the resource distribution efficiency condition is set in advance. The condition that the preset resource distribution efficiency is met may be that the resource distribution efficiency is greater than or equal to a preset resource distribution efficiency threshold. In some embodiments of the present application, the preset resource distribution efficiency threshold may be determined according to expert experience, or may be determined according to a single probability of a full exposure user at each resource quantity index level when a fixed quantity of resources is configured. For example, the preset resource distribution efficiency threshold is determined by the following formula:

wherein D is_TWhen all resource quantity index levels are configured with fixed resource quantities, corresponding preset resource distribution efficiency thresholds are set; n represents a resource quantity index level identification; UV light_nDistribution information (e.g., the number of exposed users) indicating the index level of the nth resource number; p_{Fixed n}And the order probability of the exposure user of the nth resource quantity index level under the condition of the fixed quantity resource configuration is shown.

In a specific application process, the resource distribution efficiency index corresponding to each combination determined in the signing step is respectively compared with the preset resource distribution efficiency threshold, and the combination with the resource distribution efficiency index being greater than or equal to the preset resource distribution efficiency threshold is determined to serve as a candidate combination.

And a substep S6 of respectively predicting the number of resources distributed when distributing the resources according to each combination of the number of resources and the index level of the number of resources satisfying the preset resource distribution efficiency condition.

Further, for each candidate combination, the resources are respectively configured according to the combination condition of the index level of the number of each resource in the candidate combination and the number of the resources, and the total number of the resources required to be distributed by each combination under the current resource configuration condition is estimated, for example, the subsidy cost under each combination condition is calculated. For example, by formula

Calculating subsidy cost C under each combination condition_cWherein c represents a combined identifier; n represents a resource quantity index grade mark; UV (ultraviolet) light_nDistribution information (e.g., the number of exposed users) indicating the index level of the nth resource number; j. the design is a square_cnIndicating the resource quantity (such as subsidy amount) allocated to the exposure user at the nth resource quantity index level in the case of the resource allocation of the combination c; p_cnAnd (4) the probability of placing an order of the exposure user of the nth resource quantity index level under the condition of the resource configuration of the combination c. When a specified number of resources are configured, the ordering probability of the exposure users matched with different resource number index levels is pre-estimated by using a method in the prior art, which is not described in the embodiment of the application again.

According to the method, when the resource allocation condition in each candidate combination is adopted for resource distribution, the total quantity of the resources (namely subsidy cost) required to be distributed to the user by the resource provider can be determined.

And a substep S7 of determining a correspondence between the resource quantity and the resource quantity index level according to the combination of at least one group of resource quantity and resource quantity index level with the least distributed resource quantity.

Next, the resource allocation condition in a candidate combination with the minimum total number of resources (i.e., the minimum subsiding cost), i.e., the corresponding relationship of the number of resources allocated at each resource number index level, is selected as the corresponding relationship between each resource number index level and the number of resources.

And then, the second server stores the corresponding relation between the determined index level of each resource quantity and the resource quantity, and the second server is ready for downloading by the first server. As can be seen from the foregoing description, the second server performs resource distribution efficiency estimation according to the distribution information of the resource quantity index level of the user determined by the user for the historical behavior data of the resource provider in a specified time period before the current time, and selects an appropriate specified time period, which can more accurately reflect the recent real user distribution condition of the resource provider, and is beneficial to improving the resource distribution efficiency.

In some embodiments of the present application, as shown in fig. 3, the method further comprises:

step 140, the second server determines and updates the corresponding relationship between the index level of each resource quantity and the resource quantity according to a preset period.

After the second server performs data processing on the historical behavior data of the full-exposure users of the resource provider for the resource provider within a specified time period to obtain the corresponding relationship between the resource quantity and the resource quantity index level, the method further includes: starting the update cycle timing of the corresponding relation; responding to the update cycle timing of the corresponding relation to meet a preset update cycle condition, and executing the following operations: determining a specified time period before the current time, and processing the historical behavior data of the total exposure users of the resource provider aiming at the resource provider in the specified time period to obtain the corresponding relation between the resource quantity and the resource quantity index level corresponding to the current period; and updating the corresponding relation stored in advance according to the corresponding relation corresponding to the current period.

And after the corresponding relation of the current period is updated, the second server starts the updating period timing of the corresponding relation, determines a time period matched with the historical behavior data used for calculating the new corresponding relation dependency when the updating period of the corresponding relation reaches a preset updating period time threshold, and repeatedly executes the steps, and processes the historical behavior data of the resource provider by the full-exposure users of the resource provider in the determined time period so as to obtain the latest corresponding relation between the resource quantity and the index levels of the resource quantity. And then, updating the corresponding relation between the resource quantity and each resource quantity index level calculated and stored in the previous period according to the latest corresponding relation obtained by calculation.

Step 130, the first server sends the resource of the resource quantity to the user account of the current exposure user according to the determined resource quantity.

When the first server 2301 distributes resources to a current exposure user of a resource provider, the first server 2301 queries a corresponding relationship between the number of locally pre-downloaded and stored resources and each resource number index level, determines the number of resources corresponding to the resource number index level to which the current exposure user belongs, and then executes a resource increasing operation of the resource number on a user account of the current exposure user by the first server to complete sending of the resource number to the user account of the current exposure user.

According to the resource distribution method disclosed by the embodiment of the application, the corresponding relation between the resource quantity and the index level of the resource quantity is periodically calculated off-line according to the historical behavior data of the full quantity of users of the resource provider (such as a merchant), and the resource distribution is carried out on line according to the predetermined corresponding relation.

On the other hand, the resource distribution method disclosed in the embodiment of the present application introduces the resource quantity index (e.g., the sensitivity of the subsidy coupon) of the user when establishing the corresponding relationship, so that the resource distribution can be performed according to the attribute of the user, and the resource distribution efficiency is further improved.

According to the resource distribution method disclosed by the embodiment of the application, the electronic commerce platform in the prior art is improved, the second server is added in the resource distribution system, the corresponding relation between the index level of the resource quantity and the resource quantity is calculated and updated through the second server, the resource quantity is downloaded and used on line through the first server, the calculation amount of the first server during resource distribution is reduced, and the calculation speed of on-line resource distribution can be improved.

Example two

As shown in fig. 4, a resource distribution apparatus disclosed in an embodiment of the present application includes:

a resource quantity index determining module 410, configured to determine, by the first server, a resource quantity index matched with a currently exposed user of the resource provider;

a matching resource quantity determining module 420, configured to match, by the first server, the resource quantity index with a pre-stored correspondence between the resource quantity and the resource quantity index level, and determine a resource quantity corresponding to the resource quantity index level matched with the current exposure user; the corresponding relation between the resource quantity and the index level of the resource quantity is obtained by the following method: performing data processing on the historical behavior data of the full exposure users of the resource provider aiming at the resource provider in a specified time period through a second server to obtain the corresponding relation between the resource quantity and the index level of the resource quantity;

the resource distribution module 430 is configured to send, by the first server, the resource of the resource amount to the user account of the currently exposed user according to the determined resource amount.

In some embodiments of the application, the performing, by the second server, data processing on the historical behavior data of the resource provider for the full-exposure users of the resource provider in the specified time period to obtain the correspondence between the resource quantity and the resource quantity index level includes:

the second server pre-estimates a resource distribution efficiency index corresponding to each combination when resource distribution is carried out according to each combination of each resource quantity index level matched by the full exposure user and different quantities of resources according to the historical behavior data of the resource provider under different resource quantity configuration conditions of the full exposure user of the resource provider in a specified time period;

and determining the combination with the minimum resource quantity when the resource distribution is carried out according to the combination in the combination corresponding to the resource distribution efficiency index meeting the preset resource distribution efficiency condition, and determining the corresponding relation between the resource quantity and the resource quantity index grade according to the combination with the minimum resource distribution quantity.

In some embodiments of the application, when the second server predicts, according to historical behavior data of the resource provider under different resource quantity configuration conditions of a full-exposure user of the resource provider within a specified time period, resource distribution efficiency indexes corresponding to each combination when resource distribution is performed according to each combination of each resource quantity index level matched by the full-exposure user and different quantities of resources, the resource distribution efficiency indexes corresponding to each combination include:

the second server performs data processing on historical behavior data of a user aiming at the resource provider in a specified time period, and determines resource quantity index levels corresponding to full-exposure independent visitors of the resource provider and distribution information of the resource quantity index levels;

determining all combinations of the resource quantity index levels and the resource quantity which represent the resource allocation conditions of all the resource quantity index levels;

predicting behavior parameters of the full exposure independent visitor at each resource quantity index level corresponding to the combination to the resource provider when the full exposure independent visitor corresponding to the resource quantity index level in the combination is subjected to resource distribution according to the resource quantity in each combination;

and estimating resource distribution efficiency indexes corresponding to the combination of each resource quantity index grade and the resource quantity when the full-exposure user of each resource quantity index grade distributes resources according to different resource quantity combinations according to the distribution information of each resource quantity index grade in each combination and the behavior parameters corresponding to each resource quantity index grade and the combination.

In some embodiments of the present application, the performing data processing on historical behavior data of a user for the resource provider in a specified time period, and determining resource quantity index levels corresponding to full-exposure independent visitors of the resource provider and distribution information of each resource quantity index level includes:

processing historical behavior data of the user aiming at the resource provider in the specified time period, and determining an exposure independent visitor of the resource provider;

determining a resource quantity index corresponding to each exposure independent visitor;

dividing the resource quantity index into a plurality of resource quantity index levels, and determining the distribution information of each resource quantity index level corresponding to the full-exposure independent visitor.

In some embodiments of the present application, the dividing the resource quantity index into a plurality of resource quantity index levels, and determining distribution information of each resource quantity index level corresponding to the full-exposure independent visitor includes:

establishing a resource quantity index distribution curve in a plane rectangular coordinate system by taking a resource quantity index as a first coordinate and taking the number of the exposure independent visitors corresponding to each resource quantity index as a second coordinate;

dividing the first coordinate into a plurality of first coordinate intervals at equal intervals, wherein each first coordinate interval corresponds to one index grade, and each first coordinate interval corresponds to one section of the resource quantity index distribution curve;

and taking the area formed by the resource quantity index distribution curve corresponding to each first coordinate interval and the first coordinate interval as the distribution information of the full-exposure independent visitor in the resource quantity index grade corresponding to the corresponding first coordinate interval.

In some embodiments of the application, when the full-exposure user of each resource quantity index level performs resource distribution according to different resource quantity combinations according to the distribution information of each resource quantity index level in each combination and the behavior parameters corresponding to each resource quantity index level and the combination, the resource distribution efficiency index corresponding to each combination of the resource quantity index level and the resource quantity is estimated, including:

for each combination, taking the distribution information of each resource quantity index level in the combination and the product of the resource quantity index level and the behavior parameter corresponding to the combination as a first distribution quantity of the exposure independent visitor corresponding to the combination;

and dividing the first distribution number of the independent exposure visitor corresponding to each combination by the cumulative sum of the distribution information of each resource number index level in the combination to obtain a resource distribution efficiency index corresponding to the combination of the resource number index level and the resource number.

In some embodiments of the present application, in the combination corresponding to the resource distribution efficiency index that meets the preset resource distribution efficiency condition, the combination with the minimum resource distribution quantity when performing resource distribution according to the combination, and the corresponding relationship between the resource quantity and the resource quantity index level according to the combination with the minimum resource distribution quantity, are determined, including:

determining the resource quantity and the resource quantity index grade corresponding to the resource distribution efficiency index meeting the preset resource distribution efficiency condition, and respectively using the resource quantity and the resource quantity index grade as the combination of the resource quantity and the resource quantity index grade meeting the preset resource distribution efficiency condition;

respectively pre-estimating the quantity of the resources distributed when the resources are distributed according to the combination of the quantity of the resources meeting the preset resource distribution efficiency condition and the index level of the quantity of the resources;

and determining the corresponding relation between the resource quantity and the resource quantity index level according to the combination of at least one group of resource quantity with the minimum distributed resource quantity and the resource quantity index level.

In some embodiments of the present application, as shown in fig. 5, the apparatus further comprises: the update process module 440 is configured to update the data,

after the historical behavior data of the full exposure users of the resource provider for the resource provider within the specified time period is processed by the second server to obtain the corresponding relationship between the resource quantity and the resource quantity index level, the update processing module 440 is configured to:

starting the update cycle timing of the corresponding relation;

responding to the update cycle timing of the corresponding relation to meet a preset update cycle condition, and executing the following operations:

determining a specified time period before the current time, and processing the historical behavior data of the total exposure users of the resource provider aiming at the resource provider in the specified time period to obtain the corresponding relation between the resource quantity and the resource quantity index level corresponding to the current period;

and updating the corresponding relation stored in advance according to the corresponding relation corresponding to the current period.

The resource distribution device disclosed in the embodiment of the present application is used to implement the resource distribution method described in the first embodiment of the present application, and specific implementation of each module of the device is not described again, and reference may be made to specific implementation of corresponding steps in the method embodiment.

The resource distribution device disclosed by the embodiment of the application determines the resource quantity index matched with the current exposure user of the resource provider through the first server; the first server matches the resource quantity index with a corresponding relation between a pre-stored resource quantity and a resource quantity index level, and determines the resource quantity corresponding to the resource quantity index level matched with the current exposure user; wherein, the corresponding relation between the resource quantity and the index grade of the resource quantity is obtained by the following method: performing data processing on the historical behavior data of the full exposure users of the resource provider aiming at the resource provider in a specified time period through a second server to obtain the corresponding relation between the resource quantity and the index level of the resource quantity; and the first server sends the resources of the resource quantity to the user account of the current exposure user according to the determined resource quantity, so that the resource distribution efficiency is improved.

According to the resource distribution device disclosed by the embodiment of the application, the corresponding relation between the resource quantity and the index level of the resource quantity is periodically calculated in an off-line mode according to the historical behavior data of the full quantity of users of a resource provider (such as a merchant), and the resource distribution is carried out on line according to the predetermined corresponding relation.

On the other hand, the resource distribution device disclosed in the embodiment of the present application introduces the resource quantity index (e.g., the sensitivity of the subsidy coupon) of the user when establishing the correspondence, so that the resource distribution can be performed according to the attribute of the user, and the resource distribution efficiency is further improved.

The resource distribution device disclosed in the embodiment of the application improves an e-commerce platform in the prior art, adds the second server in the resource distribution system, calculates and updates the corresponding relation between the index level of the resource quantity and the resource quantity through the second server, downloads the resource quantity from the first server and uses the resource quantity on line, reduces the calculation amount of the first server when the resource distribution is carried out, and can improve the calculation speed of the on-line resource distribution.

The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.

The foregoing describes a resource distribution method and apparatus provided by the present application in detail, and a specific example is applied to illustrate the principle and implementation manner of the present application, and the description of the foregoing embodiment is only used to help understand the method and a core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

The various component embodiments of the present application may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components in an electronic device according to embodiments of the present application. The present application may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present application may be stored on a computer readable medium or may be in the form of one or more signals. Such a signal may be downloaded from an internet website, or provided on a carrier signal, or provided in any other form.

For example, fig. 6 illustrates an electronic device that may implement a method in accordance with the present application. The electronic device can be a PC, a mobile terminal, a personal digital assistant, a tablet computer and the like. The electronic device conventionally comprises a processor 610 and a memory 620 and program code 630 stored on said memory 620 and executable on the processor 610, said processor 610 implementing the method described in the above embodiments when executing said program code 630. The memory 620 may be a computer program product or a computer readable medium. The memory 620 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. The memory 620 has a storage space 6201 for program code 630 of a computer program for performing any of the method steps described above. For example, the storage space 6201 for the program code 630 may include respective computer programs for implementing the various steps in the above method, respectively. The program code 630 is computer readable code. The computer programs may be read from or written to one or more computer program products. These computer program products comprise a program code carrier such as a hard disk, a Compact Disc (CD), a memory card or a floppy disk. The computer program comprises computer readable code which, when run on an electronic device, causes the electronic device to perform the method according to the above embodiments.

The embodiment of the present application further discloses a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the resource distribution method according to the first embodiment of the present application.

Such a computer program product may be a computer-readable storage medium that may have memory segments, memory spaces, etc. arranged similarly to the memory 620 in the electronic device shown in fig. 6. The program code may be stored in a computer readable storage medium, for example, compressed in a suitable form. The computer readable storage medium is typically a portable or fixed storage unit as described with reference to fig. 7. Typically, the storage unit comprises computer readable code 630 ', said computer readable code 630' being code read by a processor, which when executed by the processor implements the steps of the method described above.

Reference herein to "one embodiment," "an embodiment," or "one or more embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Moreover, it is noted that instances of the word "in one embodiment" are not necessarily all referring to the same embodiment.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means can be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

Claims

1. A method for resource distribution, comprising:

the first server matches the resource quantity index with a corresponding relation between a pre-stored resource quantity and a resource quantity index level, and determines the resource quantity corresponding to the resource quantity index level matched with the current exposure user;

the corresponding relation between the resource quantity and the index level of the resource quantity is obtained by the following method: performing data processing on the historical behavior data of the full-exposure users of the resource provider aiming at the resource provider in a specified time period through a second server to obtain a corresponding relation between the resource quantity and the resource quantity index level, wherein the corresponding relation between the resource quantity and the resource quantity index level is determined according to the following combination: in a plurality of combinations obtained by combining each resource quantity index grade with different quantities of resources, the resource distribution efficiency index meets the preset resource distribution efficiency condition, and the combination with the minimum resource quantity is distributed when distribution is carried out; a combined resource distribution efficiency indicator is determined based on the following parameters: the full amount of the resource quantity index level in the combination exposes the behavior parameters of the user to the resource provider; and the first server sends the resources of the resource quantity to the user account of the current exposure user according to the determined resource quantity.

2. The method according to claim 1, wherein the step of obtaining the corresponding relationship between the resource quantity and the resource quantity index level by performing data processing on the historical behavior data of the resource provider by the second server for the full-exposure users of the resource provider in the specified time period comprises:

3. The method according to claim 2, wherein the step of the second server predicting, according to historical behavior data of the resource provider under different resource quantity configuration conditions of the full-exposure user of the resource provider within a specified time period, a resource distribution efficiency index corresponding to each combination of each resource quantity index level matched with the full-exposure user and each combination of different quantities of resources when performing resource distribution according to the combination, comprises:

determining all combinations of the resource quantity index grades and the resource quantities representing the resource allocation conditions of the resource quantity index grades;

4. The method of claim 3, wherein the step of performing data processing on historical behavior data of the user for the resource provider in a specified time period, determining resource quantity index levels corresponding to full exposure of individual visitors to the resource provider, and distribution information of each resource quantity index level comprises:

processing historical behavior data of the user aiming at the resource provider in the specified time period, and determining exposure independent visitors of the resource provider;

5. The method of claim 4, wherein the step of dividing the resource quantity index into a plurality of resource quantity index levels and determining distribution information of the full-exposure independent guest for each resource quantity index level comprises:

and taking the area formed by the resource quantity index distribution curve corresponding to each first coordinate interval and the first coordinate interval as the distribution information of the full-exposure independent visitor in the resource quantity index level corresponding to the corresponding first coordinate interval.

6. The method according to claim 3, wherein the step of predicting resource distribution efficiency indexes corresponding to each combination of resource quantity index levels and resource quantity when the full-exposure user of each resource quantity index level distributes resources according to different resource quantity combinations according to the distribution information of each resource quantity index level in each combination and the behavior parameters corresponding to each resource quantity index level and the combination comprises:

and dividing the first distribution number of the exposure independent visitor corresponding to each combination by the cumulative sum of the distribution information of each resource number index level in the combination to obtain a resource distribution efficiency index corresponding to the combination of the resource number index level and the resource number.

7. The method according to claim 2, wherein the step of determining the combination with the least number of distributed resources when performing resource distribution according to the combination, among the combinations corresponding to the resource distribution efficiency indicators satisfying the preset resource distribution efficiency condition, and determining the correspondence between the number of resources and the level of the resource number indicator according to the combination with the least number of distributed resources comprises:

and determining the corresponding relation between the resource quantity and the resource quantity index grade according to the combination of at least one group of resource quantity and resource quantity index grade with the least distributed resource quantity.

8. The method according to any one of claims 1 to 7, wherein the step of obtaining the corresponding relationship between the resource quantity and the resource quantity index level by performing data processing on the historical behavior data of the resource provider by the full-exposure users of the resource provider for the specified time period through the second server comprises:

starting the updating period timing of the corresponding relation;

9. A resource distribution apparatus, comprising:

a matching resource quantity determining module, configured to match, by the first server, the resource quantity index with a correspondence between a pre-stored resource quantity and a resource quantity index level, and determine a resource quantity corresponding to the resource quantity index level matched with the current exposure user; wherein, the corresponding relation between the resource quantity and the index grade of the resource quantity is obtained by the following method: performing data processing on the historical behavior data of the full-exposure users of the resource provider aiming at the resource provider in a specified time period through a second server to obtain a corresponding relation between the resource quantity and the resource quantity index level, wherein the corresponding relation between the resource quantity and the resource quantity index level is determined according to the following combination: in a plurality of combinations obtained by combining each resource quantity index grade with different quantities of resources, the resource distribution efficiency index meets the preset resource distribution efficiency condition, and the combination with the minimum resource quantity is distributed when distribution is carried out; a combined resource distribution efficiency indicator is determined based on the following parameters: the full amount of the resource quantity index level in the combination exposes the behavior parameters of the user to the resource provider;

10. The apparatus according to claim 9, wherein the obtaining, by the second server, the corresponding relationship between the resource quantity and the resource quantity index level by performing data processing on historical behavior data of the resource provider for a full-exposure user of the resource provider within a specified time period comprises:

11. An electronic device comprising a memory, a processor, and program code stored on the memory and executable on the processor, wherein the processor implements the resource distribution method of any one of claims 1 to 8 when executing the program code.

12. A computer-readable storage medium, on which a program code is stored, characterized in that the program code realizes the steps of the resource distribution method of any one of claims 1 to 8 when executed by a processor.