CN112308635A

CN112308635A - Data processing method and device and resource providing method and device

Info

Publication number: CN112308635A
Application number: CN202011341750.7A
Authority: CN
Inventors: 谢添; 张逾
Original assignee: Rajax Network Technology Co Ltd
Current assignee: Rajax Network Technology Co Ltd
Priority date: 2020-11-25
Filing date: 2020-11-25
Publication date: 2021-02-02

Abstract

The embodiment of the disclosure discloses a data processing method and device and a resource providing method and device. According to the embodiment of the disclosure, the user characteristics of potential users of a target entity providing resources are obtained; inputting the user characteristics into a pre-trained resource utilization rate prediction model to obtain the predicted resource utilization rates of the potential users for different resource parameters; determining a target parameter from different resource parameters based on predicted resource usage rates of potential users of the target entity for the different resource parameters; and pushing the target parameters to the target entity, the target parameters for improving the level of acquiring the user and the reward from the user can be determined, so that the target entity can provide resources according to the target parameters to acquire more users and acquire better reward from the user.

Description

Data processing method and device and resource providing method and device

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a data processing method and apparatus, and a resource providing method and apparatus.

Background

Various entities may acquire users by providing resources and obtain rewards from users. The entity providing the resource may be a business entity, a computer-implemented virtual entity, or the like, and the resource may include various resources such as coupons, credits, data, and the like. The particular implementation of obtaining a user for an entity by providing resources to obtain a reward from the user typically depends on past experience or human settings. In many cases, it is difficult to set a reasonable amount of resources to achieve better effects of acquiring users and obtaining rewards from users.

Disclosure of Invention

In order to solve the problems in the related art, embodiments of the present disclosure provide a data processing method, a data processing apparatus, a resource providing method, a resource providing apparatus, a corresponding electronic device, and a readable storage medium.

In a first aspect, an embodiment of the present disclosure provides a data processing method, including:

obtaining user characteristics of potential users of a target entity providing resources;

inputting the user characteristics into a pre-trained resource utilization rate prediction model to obtain the predicted resource utilization rates of the potential users for different resource parameters;

determining a target parameter from different resource parameters based on predicted resource usage rates of potential users of the target entity for the different resource parameters; and

and pushing the target parameters to the target entity.

With reference to the first aspect, in a first implementation manner of the first aspect, the determining a target parameter from different resource parameters based on predicted resource usage of potential users of the target entity for the different resource parameters includes:

determining a first report predicted value generated by the potential user for different resource parameters based on the predicted resource utilization rate;

determining a target parameter from different resource parameters based on the first reward prediction values generated by potential users of the target entity for the different resource parameters.

With reference to the first implementation manner of the first aspect, in a second implementation manner of the first aspect, the determining, based on the first reward prediction value generated by the potential user of the target entity for different resource parameters, a target parameter from the different resource parameters includes:

and determining the resource parameter which enables the sum of the first report predicted values generated by the potential users of the target entity to be maximum from the different resource parameters as a target parameter.

With reference to the first aspect, in a third implementation manner of the first aspect, the present disclosure further includes:

receiving a constraint from the target entity,

wherein the determining target parameters from different resource parameters based on predicted resource usage by potential users of the target entity for the different resource parameters comprises:

and determining target parameters from the different resource parameters based on the predicted resource utilization rates of the potential users of the target entity for the different resource parameters and the constraint conditions.

With reference to the first aspect and any one of the first to third implementation manners of the first aspect, in a fourth implementation manner of the first aspect, the resource parameter includes a data pair consisting of a threshold value and a benefit value.

With reference to the fourth implementation manner of the first aspect, in a fifth implementation manner of the first aspect, the obtaining predicted resource usage rates of the potential users for different resource parameters includes:

acquiring respective value ranges of the threshold value and the income value;

and acquiring the predicted resource utilization rate of the potential user on a plurality of resource parameters determined based on the value range.

With reference to the fourth implementation manner of the first aspect, in a sixth implementation manner of the first aspect, the determining a target parameter from the different resource parameters includes:

selecting one resource parameter from the different resource parameters as a target parameter; or

And selecting a plurality of resource parameters from the different resource parameters to form a target parameter group.

With reference to the fourth implementation manner of the first aspect, in a seventh implementation manner of the first aspect, the determining a target parameter from different resource parameters based on predicted resource usage rates of potential users of the target entity for the different resource parameters includes:

determining a resource parameter combination meeting a preset predicted resource utilization rate condition based on the predicted resource utilization rates of different resource parameters of a specific user, wherein the resource parameter combination comprises a plurality of resource parameters;

calculating a normalized resource usage prediction value for the resource parameter combination, wherein the normalized resource usage prediction value comprises a plurality of normalized predicted resource usage values corresponding to a plurality of resource parameters in the resource parameter combination;

calculating a second return predicted value corresponding to the resource parameter combination of the specific user based on the normalized resource utilization rate predicted value;

and determining the resource parameter combination which maximizes the second return prediction value generated by the specific user of the target entity from different resource parameter combinations to be the target parameter combination.

With reference to the seventh implementation manner of the first aspect, in an eighth implementation manner of the first aspect, the calculating, based on the normalized resource usage prediction value, a second reward prediction value corresponding to the resource parameter combination of the specific user includes:

calculating a third reported predicted value for the particular user corresponding to each resource parameter in the resource parameter combination based on a plurality of normalized predicted resource usage rates corresponding to a plurality of resource parameters in the resource parameter combination;

and for the resource parameter combination, calculating the sum of all third return predicted values as a second return predicted value corresponding to the resource parameter combination of the specific user.

With reference to the second implementation manner of the first aspect, in a ninth implementation manner of the first aspect, the potential users are a plurality of potential users,

inputting the user characteristics into a pre-trained resource utilization rate prediction model to obtain the predicted resource utilization rates of the potential users for different resource parameters, wherein the method comprises the following steps:

inputting the user characteristics of each potential user into a pre-trained resource utilization rate prediction model to obtain the predicted resource utilization rate of each potential user for different resource parameters,

wherein the determining a first reward prediction value generated by the potential user for different resource parameters based on the predicted resource usage rate comprises:

determining a plurality of first report predicted values generated by the potential users for different resource parameters based on the predicted resource utilization rate of the potential users for different resource parameters,

wherein the determining, from the different resource parameters, a resource parameter that maximizes a sum of first reward predicted values generated by potential users of the target entity is a target parameter, and includes:

calculating the sum of the first reward predicted values generated by all potential users aiming at each resource parameter based on the respective plurality of first reward predicted values generated by each potential user for different resource parameters;

and determining a resource parameter corresponding to the sum of the first reward predicted values meeting a preset selection condition from the different resource parameters as a target parameter based on the sum of the first reward predicted values generated by all the potential users calculated aiming at each resource parameter.

In a second aspect, an embodiment of the present disclosure provides a text data processing apparatus, including:

a user characteristic acquisition module configured to acquire user characteristics of potential users of a target entity providing a resource;

a predicted resource utilization rate obtaining module configured to input the user characteristics into a pre-trained resource utilization rate prediction model to obtain predicted resource utilization rates of the potential users for different resource parameters;

a determination module configured to determine a target parameter from different resource parameters based on predicted resource usage of different resource parameters by potential users of the target entity; and

a pushing module configured to push the target parameter to the target entity.

In a third aspect, an embodiment of the present disclosure provides a resource providing method, including:

acquiring user characteristics of potential users of target merchants providing resources;

inputting the user characteristics into a pre-trained resource verification rate prediction model to obtain the predicted resource verification rate of the potential user for different resource parameters;

determining target resource parameters from different resource parameters based on predicted resource underwriting rates of potential users of the target merchant for the different resource parameters;

pushing the target resource parameters to the target merchant;

and providing resources to the potential users according to the target resource parameters.

In a fourth aspect, an embodiment of the present disclosure provides a resource providing apparatus, including:

a user characteristic acquisition module configured to acquire user characteristics of potential users of a target merchant providing resources;

a predicted resource core-out rate obtaining module configured to input the user characteristics into a pre-trained resource core-out rate prediction model to obtain predicted resource core-out rates of the potential users for different resource parameters;

a determination module configured to determine a target resource parameter from different resource parameters based on predicted resource underwriting rates of potential users of the target merchant for the different resource parameters;

a push module configured to push the target resource parameters to the target merchant;

a resource provisioning module configured to provision resources to the potential user in accordance with the target resource parameters.

In a fifth aspect, the present disclosure provides an electronic device, including a memory and a processor, where the memory is configured to store one or more computer instructions, where the one or more computer instructions are executed by the processor to implement the method according to the first aspect, the first implementation manner to the ninth implementation manner of the first aspect, and the third aspect.

In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium on which computer instructions are stored, and the computer instructions, when executed by a processor, implement the method according to the first aspect, the first implementation manner to the ninth implementation manner of the first aspect, and the third aspect.

The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:

according to the technical scheme provided by the embodiment of the disclosure, the user characteristics of potential users of the target entity providing resources are obtained; inputting the user characteristics into a pre-trained resource utilization rate prediction model to obtain the predicted resource utilization rates of the potential users for different resource parameters; determining a target parameter from different resource parameters based on predicted resource usage rates of potential users of the target entity for the different resource parameters; and pushing the target parameters to the target entity, the target parameters for improving the level of acquiring the user and the reward from the user can be determined, so that the target entity can provide resources according to the target parameters to acquire more users and acquire better reward from the user.

According to the technical scheme provided by the embodiment of the present disclosure, determining a target parameter from different resource parameters through the predicted resource usage rate of the potential user based on the target entity for the different resource parameters includes: determining a first report predicted value generated by the potential user for different resource parameters based on the predicted resource utilization rate; the target parameters can be determined for improving the level of acquiring users and the return from the users, so that the target entity can provide resources according to the target parameters to acquire more users and acquire better return from the users.

According to the technical solution provided by the embodiment of the present disclosure, determining a target parameter from different resource parameters through the first reported back predicted value generated for different resource parameters based on the potential user of the target entity includes: determining a resource parameter, which maximizes the sum of predicted values of the first replies generated by the potential users of the target entity, from the different resource parameters as a target parameter, and determining a target parameter for improving the level of acquiring users and the replies from the users, so that the target entity can provide resources according to the target parameter to acquire more users and acquire better replies from the users.

According to the technical solution provided by the embodiment of the present disclosure, by receiving a constraint condition from the target entity, wherein the determining a target parameter from different resource parameters based on predicted resource usage rates of potential users of the target entity for the different resource parameters includes: and determining target parameters from the different resource parameters based on the predicted resource utilization rates of the potential users of the target entity for the different resource parameters and the constraint conditions, wherein the target parameters for improving the level of acquiring the users and the return from the users can be determined, so that the target entity can provide resources according to the target parameters to acquire more users and acquire better return from the users.

According to the technical scheme provided by the embodiment of the disclosure, the resource parameters comprise a data pair consisting of a threshold value and an income value, and a target parameter for improving the level of acquiring the user and the return from the user can be determined, so that the target entity can provide resources according to the target parameter to acquire more users and acquire better return from the user.

According to the technical scheme provided by the embodiment of the present disclosure, the obtaining of the predicted resource usage rates of the potential users for different resource parameters includes: acquiring respective value ranges of the threshold value and the income value; obtaining the predicted resource utilization rate of the potential user for a plurality of resource parameters determined based on the value range can determine a target parameter for improving the level of obtaining the user and the return from the user, so that the target entity can provide resources according to the target parameter to obtain more users and obtain better return from the user.

According to the technical scheme provided by the embodiment of the present disclosure, determining the target parameter from the different resource parameters includes: selecting one resource parameter from the different resource parameters as a target parameter; or selecting a plurality of resource parameters from the different resource parameters to form a target parameter group, the target parameters for improving the level of acquiring the user and the return from the user can be determined, so that the target entity can provide resources according to the target parameters to acquire more users and better return from the user.

According to the technical scheme provided by the embodiment of the present disclosure, determining a target parameter from different resource parameters through the predicted resource usage rate of the potential user based on the target entity for the different resource parameters includes: determining a resource parameter combination meeting a preset predicted resource utilization rate condition based on the predicted resource utilization rates of different resource parameters of a specific user, wherein the resource parameter combination comprises a plurality of resource parameters; calculating a normalized resource usage prediction value for the resource parameter combination, wherein the normalized resource usage prediction value comprises a plurality of normalized predicted resource usage values corresponding to a plurality of resource parameters in the resource parameter combination; calculating a second return predicted value corresponding to the resource parameter combination of the specific user based on the normalized resource utilization rate predicted value; and determining a resource parameter combination which maximizes the second return prediction value generated by a specific user of the target entity from different resource parameter combinations to be a target parameter group, and determining a target parameter for improving the level of acquiring the user and the return from the user, so that the target entity can provide resources according to the target parameter to acquire more users and acquire better return from the user.

According to the technical solution provided by the embodiment of the present disclosure, calculating, by the method for predicting a second return corresponding to the resource parameter combination based on the normalized resource usage rate includes: calculating a third reported predicted value for the particular user corresponding to each resource parameter in the resource parameter combination based on a plurality of normalized predicted resource usage rates corresponding to a plurality of resource parameters in the resource parameter combination; for the resource parameter combination, calculating the sum of all third return predicted values as the second return predicted value corresponding to the resource parameter combination of the specific user, and determining a target parameter for improving the level of acquiring the user and the return from the user, so that the target entity can provide resources according to the target parameter to acquire more users and acquire better return from the user.

According to the technical scheme provided by the embodiment of the present disclosure, the method for obtaining the predicted resource utilization rates of the potential users for different resource parameters by inputting the user characteristics into a pre-trained resource utilization rate prediction model includes: inputting user characteristics of each potential user into a pre-trained resource utilization rate prediction model to obtain a predicted resource utilization rate of each potential user for different resource parameters, wherein the determining a first reported predicted value generated by the potential user for different resource parameters based on the predicted resource utilization rate comprises: determining a plurality of first reward prediction values generated by each potential user for different resource parameters based on the predicted resource utilization rate of each potential user for different resource parameters, wherein the determining of the resource parameter which maximizes the sum of the first reward prediction values generated by the potential users of the target entity from the different resource parameters is a target parameter comprises: calculating the sum of the first reward predicted values generated by all potential users aiming at each resource parameter based on the respective plurality of first reward predicted values generated by each potential user for different resource parameters; and determining a resource parameter corresponding to the sum of the first reward predicted values meeting a preset selection condition from the different resource parameters as a target parameter based on the sum of the first reward predicted values generated by all the potential users calculated for each resource parameter, and determining the target parameter for improving the level of acquiring the users and the reward from the users, so that the target entity can provide resources according to the target parameter to acquire more users and acquire better reward from the users.

According to the technical scheme provided by the embodiment of the disclosure, the user characteristic acquisition module is configured to acquire the user characteristics of potential users of the target entity providing resources; a predicted resource utilization rate obtaining module configured to input the user characteristics into a pre-trained resource utilization rate prediction model to obtain predicted resource utilization rates of the potential users for different resource parameters; a determination module configured to determine a target parameter from different resource parameters based on predicted resource usage of different resource parameters by potential users of the target entity; and a pushing module configured to push the target parameters to the target entity, the target parameters for improving the level of acquiring the user and the reward from the user may be determined, so that the target entity may provide resources according to the target parameters to acquire more users and better reward from the user.

According to the technical scheme provided by the embodiment of the disclosure, the user characteristics of potential users of target merchants providing resources are acquired; inputting the user characteristics into a pre-trained resource verification rate prediction model to obtain the predicted resource verification rate of the potential user for different resource parameters; determining target resource parameters from different resource parameters based on predicted resource underwriting rates of potential users of the target merchant for the different resource parameters; pushing the target resource parameters to the target merchant; providing resources to the potential users based on the target resource parameters, target parameters for improving the level of acquiring users and rewards from users may be determined so that target entities may provide resources according to target parameters to acquire more users and better rewards from users.

According to the technical scheme provided by the embodiment of the disclosure, the user characteristic acquisition module is configured to acquire the user characteristics of potential users of target merchants providing resources; a predicted resource core-out rate obtaining module configured to input the user characteristics into a pre-trained resource core-out rate prediction model to obtain predicted resource core-out rates of the potential users for different resource parameters; a determination module configured to determine a target resource parameter from different resource parameters based on predicted resource underwriting rates of potential users of the target merchant for the different resource parameters; a push module configured to push the target resource parameters to the target merchant; and the resource providing module is configured to provide resources for the potential users according to the target resource parameters, and can determine target parameters for improving the level of acquiring the users and the rewards from the users, so that the target entity can provide resources according to the target parameters to acquire more users and acquire better rewards from the users.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

Other features, objects, and advantages of the present disclosure will become more apparent from the following detailed description of non-limiting embodiments when taken in conjunction with the accompanying drawings. In the drawings:

fig. 1 shows a schematic diagram of a scenario for performing a data processing method according to an embodiment of the present disclosure;

FIG. 2 shows a flow diagram of a data processing method according to an embodiment of the present disclosure;

FIG. 3 is a diagram illustrating predicted resource usage obtained by a predicted resource usage model in a data processing method according to an embodiment of the present disclosure;

FIG. 4 shows a block diagram of a data processing apparatus according to an embodiment of the present disclosure;

FIG. 5 shows a flow diagram of a resource provisioning method according to an embodiment of the present disclosure;

fig. 6 illustrates a block diagram of a resource providing apparatus according to an embodiment of the present disclosure;

FIG. 7 shows a block diagram of an electronic device according to an embodiment of the present disclosure;

fig. 8 is a schematic structural diagram of a computer system suitable for implementing a data processing method and a resource providing method according to an embodiment of the present disclosure.

Detailed Description

Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. Also, for the sake of clarity, parts not relevant to the description of the exemplary embodiments are omitted in the drawings.

In the present disclosure, it is to be understood that terms such as "including" or "having," etc., are intended to indicate the presence of the disclosed features, numbers, steps, behaviors, components, parts, or combinations thereof, and are not intended to preclude the possibility that one or more other features, numbers, steps, behaviors, components, parts, or combinations thereof may be present or added.

It should be further noted that the embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Various entities may acquire users by providing resources and obtain rewards from users. For example, an entity (merchant) on an internet platform may wish to obtain more users and better operational benefits through a marketing campaign configuration tool. However, the current situation is that the resource providing manner (e.g. full-discount activity) set by the merchant is generally unreasonable, which results in low operating efficiency of the merchant and low efficiency of the cost paid in the full-discount activity (money effect). The root cause of this is that merchants (especially small merchants), lack basic information (age, consumption ability, etc.) of visiting users, and it is difficult to accurately judge which marketing campaigns to do can improve the operation profit. Therefore, there is a need to provide a method to calculate resource (e.g., marketing campaign, such as top-down) parameters that a merchant can provide to a user, and recommend to the merchant.

Fig. 1 shows a schematic diagram of a scenario for performing a data processing method according to an embodiment of the present disclosure. As shown in FIG. 1, a merchant 120 operating on an Internet platform 110 may provide products or services to a potential user 130. However, it is difficult for the merchant 120 to obtain basic information of the potential users 130, and it is difficult to accurately determine which marketing campaigns to do can improve revenue. It is necessary to recommend marketing activities and marketing credits to each merchant 120 to improve the operating efficiency of each merchant.

Fig. 2 shows a flow diagram of a data processing method according to an embodiment of the present disclosure. As shown in fig. 1, the data processing method includes the following steps S210 to S240:

in step S210, user characteristics of potential users of the target entity providing the resource are acquired;

in step S220, inputting the user characteristics into a pre-trained resource usage prediction model to obtain predicted resource usage of the potential user for different resource parameters;

in step S230, determining a target parameter from different resource parameters based on predicted resource usage rates of potential users of the target entity for the different resource parameters;

in step S240, the target parameters are pushed to the target entity.

In one embodiment of the present disclosure, the target entity refers to a specific entity of the plurality of entities that needs to acquire the user characteristics of its potential user, for example, a specific merchant of the plurality of merchants on the internet platform. In one embodiment of the present disclosure, a resource refers to various resources, such as coupons, credits, data, etc., that a target entity provides to a user so that the user is willing to use the resource to perform a particular operation at the target entity. For example, when the entity is a merchant, the resources may include coupons, full lines of decrements (consumption full X minus Y), returns, credits consumed, rewards drawn, and the like. When the target merchant provides different resources to the potential user, the consumption behavior of the potential user at the target merchant may be different. Therefore, it is desirable to calculate a better solution for which objective parameters the objective entity provides resources to the potential users, so as to better acquire users, for example, acquire more users and/or acquire users consuming more, and thus acquiring better revenue. In one embodiment of the present disclosure, the resources provided to the user may all come from the target entity. In one embodiment of the present disclosure, the resources provided to the user may be partly from the target entity and partly from the platform. In one embodiment of the present disclosure, the resources provided to the user may all come from the platform. The present disclosure may not be limited to a particular source of the resource.

In one embodiment of the present disclosure, the user characteristics of the user may include any user-related characteristics such as age, gender, work, location, income, and consumption ability of the user, which are not limited by the present disclosure.

In one embodiment of the present disclosure, the characteristics of the potential user may be input into a pre-constructed resource usage prediction model to calculate the predicted resource usage of the potential user for different resource parameters, i.e., the probability that the potential user uses the resource provided by the target entity. For example, when the entity is a merchant and the resource is a full reduction amount (consumption full X minus Y), the predicted resource usage rate may refer to a probability that the user will verify the full reduction amount (consumption full X minus Y), which may also be referred to as a full reduction degree verification probability. In the embodiment of the present disclosure, the verification of the full sales deduction degree refers to that the consumption amount reaches X when the merchant consumes, so that the consumption amount is reduced by Y, that is, the user uses a full deduction amount of consumption full X minus Y provided by the merchant. From another perspective, the full reduction may enhance the user's willingness to consume at the current merchant and reach a specific amount X, and therefore, the full reduction verification probability may also represent to some extent the probability that the potential user is willing to consume at the merchant and reach the specific amount X. Through the embodiment of the disclosure, the defects caused by the scheme of searching the optimal full reduction degree value according to the full reduction degree test one by one in the related art can be overcome: poor yield, time-consuming searching for the best full reduction, difficulty in quantifying the full reduction interval, etc. The full reduction degree underwriting probability obtained using the predicted resource usage model is described below with reference to fig. 3.

Fig. 3 is a diagram illustrating a full reduction degree underwriting probability obtained by a predictive resource usage model in a data processing method according to an embodiment of the present disclosure.

As shown in FIG. 3, for each user U, there is a full derate underwriting probability P for each full derate (full X minus Y), i.e., for the set of potential users U { U }₁,u₂,u₃,…u_nFor each user u in the log, there is a value P on the P-axis of the full derate factoring probability for the value reached by consumption (value X on the X-axis), the value that can be subtracted (value Y on the Y-axis)_x,y. In this case, a predicted resource usage model P (U, X, Y) may be constructed in which the user checks the full reduction amount (full X reduction Y). The prediction resource usage rate model may be constructed by using various prediction models in the related art, for example, a model based on an XGBoost (eXtreme Gradient Boosting) algorithm, and the like. Those skilled in the art will appreciate that any model that enables resource usage prediction using input resource and potential user characteristic information may be used in embodiments of the present disclosure, in which case the present disclosure is not limited to the specific form of the predicted resource usage model.

In one embodiment of the present disclosure, assuming that the set of potential users for each merchant is U, for each user U in the set U, there is a combination of users and a full reduction underwriting probability (i.e., resource usage)<u_i，p_i>Then, the expected GMV (total volume of transaction) that each user u can generate is defined as formula 1:

wherein the content of the first and second substances,

the full reduction degree accounting probability on the accounting probability P axis of the full reduction limit (full x minus y) is shown for the user u, and the (x-y) is the transaction amount after the user uses the full reduction limit (namely, the resource). In this embodiment, the same full reduction may result in different GMVs for different subscribers, since the probability of the verification of the same full reduction for each potential subscriber is not necessarily the same. The GMVs generated by the same user for different full decrements may be different and therefore one or more full decrements values for which the generated GMV meets preset conditions may be selected as target parameters to be provided to potential users.

For example, if the user A has a verification probability of 0.7 for a full reduction rate of "full 60 yuan minus 10 yuan", GMV is determined_A0.7 ═ 35 yuan (60-10). Then for any one full-minus combination (x, y). The expected GMVs generated by all users can be calculated by the following equation 2:

wherein, GMV_i,x,yThe sum of the GMVs generated for subscriber i for the full decrement value (full x minus y), where n is the number of potential subscribers. In one embodiment of the present disclosure, it may be considered that for the merchant, the GMV is made available_x,yThe maximum full reduction amount (full x minus y) is the target full reduction degree of the merchant, i.e. the optimal or cost benefit maximization full reduction amount. In one embodiment of the present disclosure, various full reduction amount values (which may be referred to as resource parameters) such as full 30 minus 5, full 45 minus 8, full 50 minus 10 may be substituted for equations 1 and 2 to calculate a target full reduction value for a particular merchant, which may also be referred to as a target parameter.

Table 1 below shows an example of the result of executing the full reduction policy provided to merchants (convenience stores) in several regions using the target full reduction degree calculated by equation 2 as a target parameter. Table 1 shows the net amount increase for a merchant (convenience store) in the case where the merchant provides a target full reduction to potential users.

TABLE 1

As can be seen from table 1, in the case of sales to potential users according to the target full reduction degree calculated by equation 2, the actual net volume increase rate of the merchant of 6.26% significantly exceeds the set target net volume increase rate of 3.0%. Obviously, the scheme according to the embodiment of the disclosure can determine that the merchant improves the level of acquiring the user and the target parameter of the reward from the user, so that the merchant can provide resources according to the target parameter to acquire more users and acquire better reward from the user.

In one embodiment of the present disclosure, only one target parameter may be determined for the target entity, or a set of target parameters may be determined for the target entity. For example, a plurality of resource parameters may be selected among different resource parameters (full-reduction limit) to form a target parameter (target full-reduction limit) group or a combination of a plurality of target parameters (target full-reduction limit) for a specific user (or a specific user group).

For example, in some scenarios, a merchant may desire a set of target parameters (target full-minus) such as: full 39 minus 2, full 69 minus 5, full 99 minus 10, etc. The main purpose of providing a target full reduction group is to give different full reductions to different consumer groups. Based on this scenario, the embodiment of the present disclosure obtains formula 3 on the basis of formula 1:

wherein, GMV_uThe average of GMVs (total volume of transaction) that can be generated for a particular user u for a corresponding set of core cancellation probabilities on the core cancellation probability P axis for a full decrement value (full x minus y) set. The specific calculation manner of equation 3 is described below using the above target parameter (target full-reduction amount) set example. User A decrements the full decrements by 39, 695. The core-cancellation probabilities (resource usage) of full 99 minus 10 are 0.8, 0.7, 0.3, respectively. Normalizing the set of full reduction degree core-canceling probabilities to obtain corresponding core-canceling probabilities substituted into formula 3

0.44444, 0.38888, 0.16666. That is, the expected GMVs of the full credit line group of the full credit degree "full 39 minus 2, full 69 minus 5, full 99 minus 10" of the specific user (specific user group) a for the target merchant are: GMV_A(39-2) × 0.4444+ (69-5) × 0.3888+ (99-10) × 0.1666 ═ 56.1 members.

In one embodiment of the present disclosure, step 230 comprises: determining a first report predicted value generated by the potential user for different resource parameters based on the predicted resource utilization rate; determining a target parameter from different resource parameters based on the first reward prediction values generated by potential users of the target entity for the different resource parameters.

In one embodiment of the disclosure, the first reward prediction value may refer to the GMV of the potential user for different resource parameters (full-minus amount), for example, the calculation result of formula 1. Based on the calculation results of equation 1, a satisfactory target parameter can be determined from a large number (e.g., thousands) of resource parameters (full-reduction amount). For example, one or more GMVs are selected from the GMVs calculated based on thousands of full reduction rates, one or more resource parameters corresponding to the selected GMVs are pushed to a target entity (merchant) as target parameters, and the target entity provides resources (e.g., executes full reduction rate) to potential users according to the target parameters.

In one embodiment of the disclosure, the determining a target parameter from different resource parameters based on the first reward prediction value generated for the different resource parameters by the potential user of the target entity includes: and determining the resource parameter which enables the sum of the first report predicted values generated by the potential users of the target entity to be maximum from the different resource parameters as a target parameter.

In one embodiment of the present disclosure, the sum of the first reward prediction values, i.e., the sum of GMVs generated by all users in the set U of potential users for the full derating degree, may be understood based on equation 2 above. It can be understood that, since the first reward prediction values of different users for the same resource parameter are different, the sum of the first reward prediction values generated by the potential users for different resource parameters as a whole is also different. In this case, the target entity may be determined from the perspective of the potential user as a whole, rather than from the perspective of a single potential user. On the basis, all users on the platform can be classified from various angles such as distance from a target entity, age of the potential user, gender of the potential user, consumption capacity of the potential user and the like, a potential user group executing the scheme according to the embodiment of the disclosure is obtained, and the sum of the first reward predicted values generated by the potential users of the potential user group is based on the potential users of the potential user group. The sum of the first reward prediction values generated by the potential users may be determined in various ways or from various angles by those skilled in the art in light of the teachings of the present disclosure, and the present disclosure will not be described in detail herein.

In one embodiment of the present disclosure, the data processing method further includes: constraints from the target entity are received. Wherein step 230 comprises: and determining target parameters from the different resource parameters based on the predicted resource utilization rates of the potential users of the target entity for the different resource parameters and the constraint conditions.

In one embodiment of the present disclosure, the constraints from the target entity may refer to the merchant's limitations on the resources to be provided to the potential user. In one embodiment of the present disclosure, the preset condition may include a limitation on the resource parameter, for example, x is greater than a first preset value (e.g., 40, 45, 50, etc.) in a full-minus quota of full x minus y elements, and/or y is less than a second preset value (e.g., 2, 5, 8, etc.), and/or (x-y) is greater than a third preset value (e.g., 25, 30, 35, etc.), and/or (x-y)/x is greater than a fourth preset value (e.g., 0.85, 0.9, 0.92, etc.), and/or any limitation on the resource parameter. In this embodiment, by this constraint, resources that the merchant does not want to provide to the potential user for such factors as business efficiency, brand influence, etc. can be excluded, thereby obtaining better revenue.

In one embodiment of the present disclosure, the constraint may include setting different resource parameters at different time periods. For example, the merchant employs a first resource parameter (or set of parameters) on monday through friday of each week, and employs a second resource parameter (or set of parameters) on saturday and sunday. For example, the merchant employs the third resource parameter (or set of parameters) at 11:00-13:00 and 18:00-20:00 of the day and the second resource parameter (or set of parameters) at other time periods within the day. In this embodiment, by using this constraint, the resources that can be provided to the potential user can be determined according to the business capacity of the merchant itself, so as to obtain better profit.

In one embodiment of the present disclosure, the constraint may include any condition from the target entity that may be used to determine the target parameter, and the present disclosure is not limited thereto.

In one embodiment of the present disclosure, the resource parameter includes a data pair consisting of a threshold value and a benefit value.

In one embodiment of the present disclosure, the data pair consisting of the threshold value and the profit value refers to the aforementioned full decrement amount, i.e., the full threshold value X minus the profit value Y. It should be noted that the profit value Y in this embodiment refers to the profit that the user can obtain when the merchant consumes the threshold value X, rather than the profit obtained by the merchant.

In one embodiment of the present disclosure, step S220 includes: acquiring respective value ranges of the threshold value and the income value; and acquiring the predicted resource utilization rate of the potential user on a plurality of resource parameters determined based on the value range.

In one embodiment of the disclosure, the threshold value and the profit value in the full reduction amount may have different value ranges for different target entities. For example, for a merchant selling furniture, the threshold value in the full credit may range from thousands of yuan to tens of thousands of yuan, and the profit value may range from hundreds of yuan to thousands of yuan. For example, for a food export merchant, the threshold value of the full-minus amount may range from tens of yuan to hundreds of yuan, and the profit value may range from tens of yuan to tens of yuan. The above threshold values and the profit values are merely examples, and the present disclosure may determine larger or smaller value ranges of the threshold values and the profit values for the target entity, and determine the threshold values and the profit values meeting the requirements according to the calculated values of the GMV by using the manner of calculating the GMV in the foregoing embodiments.

In one embodiment of the present disclosure, step S230 includes: selecting one resource parameter from the different resource parameters as a target parameter; or selecting a plurality of resource parameters from the different resource parameters to form a target parameter group.

In one embodiment of the present disclosure, the manner of selecting one resource parameter from the different resource parameters as the target parameter may be to calculate an appropriate one of the plurality of resource parameters (full reduction amount values) using the above formula 1 or 2, for example, a full reduction degree value that makes the GMV highest may be selected as the target parameter. In an embodiment of the present disclosure, the manner of selecting the plurality of resource parameters from the different resource parameters as the target parameter group may be to calculate a suitable part of the plurality of resource parameters (full reduction amount value) as the target parameter group by using the above equation 3. In one embodiment of the present disclosure, a plurality of target parameters (full reduction amount values) that are suitable among the plurality of resource parameters (full reduction amount values) may also be calculated as the target parameter group using the above equation 1 or 2, for example, a plurality of full reduction degree values that make the GMV reach a preset condition as the target parameter group.

In one embodiment of the present disclosure, step S230 includes: determining a resource parameter combination meeting a preset predicted resource utilization rate condition based on the predicted resource utilization rates of different resource parameters of a specific user, wherein the resource parameter combination comprises a plurality of resource parameters; calculating a normalized resource usage prediction value for the resource parameter combination, wherein the normalized resource usage prediction value comprises a plurality of normalized predicted resource usage values corresponding to a plurality of resource parameters in the resource parameter combination; calculating a second return predicted value corresponding to the resource parameter combination of the specific user based on the normalized resource utilization rate predicted value; and determining the resource parameter combination which maximizes the second return prediction value generated by the specific user of the target entity from different resource parameter combinations to be the target parameter combination.

In one embodiment of the present disclosure, the full reduction amount value combination satisfying the preset full reduction degree verification probability condition may be determined by using equation 3 above. In this case, the combination of resource parameters that satisfies the preset full reduction degree verification probability condition may be determined based on the predicted full reduction degree verification probability of the specific user for different full reduction amount values. The normalized resource usage prediction value refers to a normalized predicted full reduction degree core-out probability obtained by normalizing a plurality of predicted full reduction degree core-out probabilities as described with reference to equation 3 above. The second reward prediction value refers to the GMV calculated based on a different combination of full derating factoring probabilities when there are multiple full derating factoring probabilities. This GMV may be the GMV for a particular user (a particular user population). Determining the resource parameter combination which maximizes the second return prediction value generated by the specific user of the target entity from the different resource parameter combinations as the target parameter group refers to using the full reduction combination which maximizes the GMV generated by the specific user (specific user group) of the merchant as the target parameter group.

In an embodiment of the disclosure, the calculating, based on the normalized resource usage prediction value, a second reward prediction value corresponding to the resource parameter combination for the specific user includes: calculating a third reported predicted value for the particular user corresponding to each resource parameter in the resource parameter combination based on a plurality of normalized predicted resource usage rates corresponding to a plurality of resource parameters in the resource parameter combination; and for the resource parameter combination, calculating the sum of all third return predicted values as a second return predicted value corresponding to the resource parameter combination of the specific user.

In one embodiment of the present disclosure, calculating the third reward prediction value corresponding to each resource parameter in the resource parameter combination for the specific user may refer to a value obtained by multiplying the normalized full reduction degree verification probability by the corresponding full reduction degree value as described above with reference to equation 3. And calculating corresponding third return predicted values for each resource parameter in one resource parameter combination, and adding the third return predicted values to obtain a second return predicted value corresponding to the resource parameter combination. It will be appreciated that there may be a plurality of resource parameter combinations, and that the number of resource parameters in each resource parameter combination may be any positive integer value.

In one embodiment of the present disclosure, the potential user is a plurality of potential users. Wherein, step S220 includes: and inputting the user characteristics of each potential user into a pre-trained resource utilization rate prediction model to obtain the predicted resource utilization rate of each potential user for different resource parameters. Wherein the determining a first reward prediction value generated by the potential user for different resource parameters based on the predicted resource usage rate comprises: and determining a plurality of first report predicted values generated by the potential users for different resource parameters based on the predicted resource utilization rate of the potential users for different resource parameters. Wherein the determining, from the different resource parameters, a resource parameter that maximizes a sum of first reward predicted values generated by potential users of the target entity is a target parameter, and includes: calculating the sum of the first reward predicted values generated by all potential users aiming at each resource parameter based on the respective plurality of first reward predicted values generated by each potential user for different resource parameters; and determining a resource parameter corresponding to the sum of the first reward predicted values meeting a preset selection condition from the different resource parameters as a target parameter based on the sum of the first reward predicted values generated by all the potential users calculated aiming at each resource parameter.

In one embodiment of the disclosure, a full reduction degree verification probability of a different full reduction amount may be calculated for each of all potential users, and a plurality of GMVs under different full reduction degrees may be calculated for each potential user, and a full reduction degree different for each potential user may be pushed to the merchant. In one embodiment of the disclosure, the sum of the GMVs at each full reduction degree may be calculated based on the full reduction degree underwriting probability of all potential users for the same full reduction degree, so that the full reduction degree value corresponding to the sum of the GMVs meeting the preset selection condition may be selected and pushed to the merchant. In one embodiment of the present disclosure, the satisfaction of the preset selection condition may refer to the satisfaction of a condition that the sum of GMVs is maximum, or the satisfaction of a condition that the sum of several GMVs that are maximum is selected.

The above embodiments discussed with the merchant as the target entity are merely examples, and the present disclosure is not limited thereto, for example, the target entity may be a virtual entity or a real entity implemented with a computer, and the resource may be data or points, etc.

A block diagram of a data processing apparatus according to an embodiment of the present disclosure is described below with reference to fig. 4.

Fig. 4 shows a block diagram of a data processing apparatus according to an embodiment of the present disclosure. The apparatus may be implemented as part or all of an electronic device through software, hardware, or a combination of both. As shown in fig. 4, the data processing apparatus 400 includes a user characteristic obtaining module 410, a predicted resource usage obtaining module 420, a determining module 430, and a pushing module 440.

The user characteristic acquisition module 410 is configured to acquire user characteristics of potential users of a target entity that provides a resource.

The predicted resource usage acquisition module 420 is configured to input the user characteristics into a pre-trained resource usage prediction model to acquire the predicted resource usage of the potential user for different resource parameters.

The determination module 430 is configured to determine a target parameter from the different resource parameters based on predicted resource usage of the different resource parameters by potential users of the target entity.

The pushing module 440 is configured to push the target parameters to the target entity.

It will be understood by those skilled in the art that the technical solution described with reference to fig. 4 may be combined with the embodiment described with reference to fig. 1 to 3, so as to have the technical effects achieved by the embodiment described with reference to fig. 1 to 3. For details, reference may be made to the description made above with reference to fig. 1 to 3, and details thereof are not repeated herein.

A flowchart of a resource providing method according to an embodiment of the present disclosure is described below with reference to fig. 5.

Fig. 5 shows a flowchart of a resource providing method according to an embodiment of the present disclosure. As shown in fig. 5, the resource providing method includes steps S510 to S550.

In step S510, user characteristics of potential users of target merchants providing the resources are obtained.

In step S520, the user characteristics are input into a resource verification rate prediction model trained in advance to obtain the predicted resource verification rate of the potential user for different resource parameters.

In step S530, a target resource parameter is determined from the different resource parameters based on the predicted resource underwriting rates of the potential users of the target merchant for the different resource parameters.

In step S540, the target resource parameters are pushed to the target merchant.

In step S550, resources are provided to the potential user according to the target resource parameters.

The resource providing method described with reference to fig. 5 differs from the data processing method described with reference to fig. 2 in that it comprises providing resources to potential users in dependence of target resource parameters. In an embodiment of the present disclosure, the resource to the user may be entirely from the target entity (merchant), or may be partly from the target entity and partly from other entities, for example, a platform providing an operation environment of the target entity, for example, a network platform in the related art. However, in the embodiments of the present disclosure, the target entity may provide the resource to the user without paying attention to the specific source of the resource, and the source of the resource may not be described.

In the embodiment of the present disclosure, it can be understood that, because the number of users that each target entity has access to is limited, a platform providing an operating environment of the target entity may generally obtain information of more potential users of the target entity, and therefore, the scheme disclosed in the embodiment of the present disclosure may be executed on the platform operating the target entity.

It will be understood by those skilled in the art that the technical solution described with reference to fig. 5 may be combined with the embodiment described with reference to fig. 1 to 4, so as to have the technical effects achieved by the embodiment described with reference to fig. 1 to 4. For details, reference may be made to the description made above with reference to fig. 1 to 4, and details thereof are not repeated herein.

A block diagram of a resource providing apparatus according to an embodiment of the present disclosure is described below with reference to fig. 6.

Fig. 6 illustrates a block diagram of a resource providing apparatus according to an embodiment of the present disclosure. The apparatus may be implemented as part or all of an electronic device through software, hardware, or a combination of both. As shown in fig. 6, the data processing apparatus 600 includes a user characteristic obtaining module 610, a predicted resource usage obtaining module 620, a determining module 630, a pushing module 640, and a resource providing module 650.

User characteristics acquisition module 610 is configured to acquire user characteristics of potential users of a target merchant that provides resources.

The predicted resource core-out rate obtaining module 620 is configured to input the user characteristics into a pre-trained resource core-out rate prediction model to obtain the predicted resource core-out rates of the potential users for different resource parameters.

The determination module 630 is configured to determine a target resource parameter from the different resource parameters based on a predicted resource underwriting rate for the different resource parameters by the potential users of the target merchant.

The push module 640 is configured to push the target resource parameters to the target merchant.

The resource provisioning module 650 is configured to provision resources to the potential user in accordance with the target resource parameters.

It will be appreciated by those skilled in the art that the technical solution described with reference to fig. 6 may be combined with the embodiments described with reference to fig. 1 to 5, so as to achieve the technical effects achieved by the embodiments described with reference to fig. 1 to 5. For details, reference may be made to the description made above with reference to fig. 1 to 5, and details thereof are not repeated herein.

The foregoing embodiments describe the internal functions and structures of the data processing apparatus and the resource providing apparatus, and in one possible design, the structures of the data processing apparatus and the resource providing apparatus may be implemented as an electronic device, such as shown in fig. 7, and the electronic device 700 may include a processor 701 and a memory 702.

The memory 702 is configured to store a program that supports an electronic device to execute the corpus generating method or the code generating method in any of the above embodiments, and the processor 701 is configured to execute the program stored in the memory 702.

In one embodiment of the present disclosure, the memory 702 is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor 701 to implement the steps of:

and pushing the target parameters to the target entity.

In one embodiment of the present disclosure, the determining a target parameter from different resource parameters based on predicted resource usage of different resource parameters by potential users of the target entity includes:

In one embodiment of the disclosure, the determining a target parameter from different resource parameters based on the first reward prediction value generated for the different resource parameters by the potential user of the target entity includes:

In one embodiment of the present disclosure, the memory 702 is configured to store one or more computer instructions, wherein the one or more computer instructions are further executable by the processor 701 to implement the steps of:

receiving a constraint from the target entity,

In an embodiment of the present disclosure, the obtaining the predicted resource usage rates of the potential users for different resource parameters includes:

acquiring respective value ranges of the threshold value and the income value;

In an embodiment of the present disclosure, the determining a target parameter from the different resource parameters includes:

In an embodiment of the disclosure, the calculating, based on the normalized resource usage prediction value, a second reward prediction value corresponding to the resource parameter combination for the specific user includes:

In one embodiment of the present disclosure, the potential user is a plurality of potential users,

pushing the target resource parameters to the target merchant;

Exemplary embodiments of the present disclosure also provide a computer storage medium for storing computer software instructions for the positioning apparatus, which includes a program for executing any of the above embodiments, thereby providing technical effects brought by the method.

As shown in fig. 8, a computer system 800 includes a processing unit (CPU, GPU, NPU, FPGA, etc.) 801 that can execute various processes in the embodiments shown in the above-described drawings according to a program stored in a Read Only Memory (ROM)802 or a program loaded from a storage section 808 into a Random Access Memory (RAM) 803. In the RAM803, various programs and data necessary for the operation of the system 800 are also stored. The processing unit 801, the ROM802, and the RAM803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to bus 804.

The following components are connected to the I/O interface 805: an input portion 806 including a keyboard, a mouse, and the like; an output section 807 including a signal such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 808 including a hard disk and the like; and a communication section 809 including a network interface card such as a LAN card, a modem, or the like. The communication section 809 performs communication processing via a network such as the internet. A drive 810 is also connected to the I/O interface 805 as necessary. A removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 810 as necessary, so that a computer program read out therefrom is mounted on the storage section 808 as necessary.

In particular, according to embodiments of the present disclosure, the methods described above with reference to the figures may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a medium readable thereby, the computer program comprising program code for performing the methods of the figures. In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 809 and/or installed from the removable medium 811.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowcharts or block diagrams may represent a module, a program segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units or modules described in the embodiments of the present disclosure may be implemented by software or hardware. The units or modules described may also be provided in a processor, and the names of the units or modules do not in some cases constitute a limitation of the units or modules themselves.

As another aspect, the present disclosure also provides a computer-readable storage medium, which may be the computer-readable storage medium included in the apparatus in the above-described embodiment; or it may be a separate computer readable storage medium not incorporated into the device. The computer-readable storage medium stores one or more programs which are used by one or more processors to perform the methods described in the present disclosure, thereby providing technical effects brought by the methods.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is possible without departing from the inventive concept. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.

Claims

1. A method of data processing, comprising:

and pushing the target parameters to the target entity.

2. The method of claim 1, wherein the determining a target parameter from different resource parameters based on predicted resource usage of different resource parameters by potential users of the target entity comprises:

3. The method of claim 2, wherein the determining a target parameter from different resource parameters based on the first reward prediction value generated for the different resource parameters by the potential user of the target entity comprises:

4. The method of claim 1, further comprising:

receiving a constraint from the target entity,

5. A method according to any one of claims 1 to 4, wherein the resource parameters comprise a data pair consisting of a threshold value and a benefit value.

6. A data processing apparatus comprising:

a pushing module configured to push the target parameter to the target entity.

7. A resource provisioning method, comprising:

pushing the target resource parameters to the target merchant;

8. A resource providing apparatus, comprising:

9. An electronic device comprising a memory and a processor; wherein the memory is configured to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method steps of any of claims 1-5, 7.

10. A readable storage medium having stored thereon computer instructions, characterized in that the computer instructions, when executed by a processor, carry out the method steps of any of claims 1-5, 7.