CN109191202B

CN109191202B - Resource allocation method, device, electronic equipment and computer readable storage medium

Info

Publication number: CN109191202B
Application number: CN201810991703.3A
Authority: CN
Inventors: 张秀秀
Original assignee: Rajax Network Technology Co Ltd
Current assignee: Rajax Network Technology Co Ltd
Priority date: 2018-08-28
Filing date: 2018-08-28
Publication date: 2021-09-07
Anticipated expiration: 2038-08-28
Also published as: CN109191202A

Abstract

The embodiment of the disclosure discloses a resource allocation method, a resource allocation device, an electronic device and a computer readable storage medium, wherein the method comprises the following steps: acquiring historical execution data of an object to be distributed in a preset historical time period; calculating distribution reference sub-scores of the objects to be distributed on various distribution reference elements according to the historical execution data, and calculating the distribution reference scores of the objects to be distributed according to the distribution reference sub-scores; and distributing resources for the objects to be distributed according to the distribution reference values. The technical scheme fully considers the performances of the historical execution data of the objects to be distributed in multiple aspects and distributes the resources on the basis of the performances, so that the technical effects of accurately judging the high-quality objects to be distributed, improving the effectiveness of resource distribution and reducing the use cost of the resources are achieved.

Description

Resource allocation method, device, electronic equipment and computer readable storage medium

Technical Field

The present disclosure relates to the field of information processing technologies, and in particular, to a resource allocation method and apparatus, an electronic device, and a computer-readable storage medium.

Background

With the development of internet technology, a plurality of application programs, clients and application platforms are produced at the same time, and a plurality of merchants develop a plurality of internet approaches to implement operation and popularization on the basis of the entity approach. However, the above-mentioned various promotion approaches have more or less differences in terms of audiences, business methods, promotion strategies, etc., and therefore, the effects of completing the operation and promotion tasks of the merchants are different. Based on the limitation and requirement on the operation and popularization cost, merchants need to find high-quality popularization ways from various popularization ways to achieve the effect of achieving twice the result with half the effort. In the prior art, the judgment of high-quality promotion ways is carried out only on the basis of cost indexes and income indexes by combining the number of new users and the retention rate of the users, the judgment factor of the scheme is narrow, the judgment accuracy rate is low, and the requirements of most merchants cannot be met.

Disclosure of Invention

The embodiment of the invention provides a resource allocation method, a resource allocation device, electronic equipment and a computer readable storage medium.

In a first aspect, an embodiment of the present invention provides a resource allocation method.

Specifically, the resource allocation method includes:

acquiring historical execution data of an object to be distributed in a preset historical time period;

calculating distribution reference sub-scores of the objects to be distributed on various distribution reference elements according to the historical execution data, and calculating the distribution reference scores of the objects to be distributed according to the distribution reference sub-scores;

and distributing resources for the objects to be distributed according to the distribution reference values.

With reference to the first aspect, in a first implementation manner of the first aspect, the calculating, according to the historical execution data, distribution reference sub-scores of the to-be-distributed objects on multiple distribution reference elements, and calculating, according to the distribution reference sub-scores, distribution reference scores of the to-be-distributed objects includes:

respectively calculating the distribution reference sub-scores of the objects to be distributed on various distribution reference elements according to the historical execution data;

acquiring a weight value of the distribution reference element;

and carrying out weighted summation on the distribution reference sub-scores based on the weight values to obtain the distribution reference scores of the objects to be distributed.

With reference to the first aspect and the first implementation manner of the first aspect, in a second implementation manner of the first aspect, the allocating, according to the allocation reference score, a resource to the object to be allocated includes:

calculating the resource allocation proportion of the objects to be allocated according to the allocation reference values;

acquiring the total amount of allocable resources;

calculating the number of the distributed resources of the object to be distributed based on the total number of the distributable resources and the resource distribution proportion of the object to be distributed;

and allocating resources for the objects to be allocated according to the allocated resource quantity of the objects to be allocated.

With reference to the first aspect, the first implementation manner of the first aspect, and the second implementation manner of the first aspect, in a third implementation manner of the first aspect, the allocating, according to the allocation reference score, a resource to the object to be allocated includes:

calculating the evaluation score of the historical execution data of the object to be distributed;

calculating the quantity of the distributed resources of the object to be distributed according to the evaluation score;

calculating to obtain the average resource quantity of the object to be distributed in a first preset time period according to the distributed resource quantity of the object to be distributed;

carrying out nonlinear optimization on the average resource quantity to obtain an optimized average resource quantity;

calculating the optimized distribution resource quantity of the object to be distributed according to the optimized average resource quantity;

distributing resources for the objects to be distributed according to the optimized distribution resource quantity of the objects to be distributed;

and sequencing the distribution reference values, and displaying the quantity of the resources distributed to the objects to be distributed according to a sequencing result.

With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, and the third implementation manner of the first aspect, in a fourth implementation manner of the first aspect, the embodiment of the present invention further includes:

sorting the assigned reference scores;

and modifying the resources allocated to the objects to be allocated according to the sequencing result.

In a second aspect, an embodiment of the present invention provides a resource allocation apparatus.

Specifically, the resource allocation apparatus includes:

the acquisition module is configured to acquire historical execution data of the object to be distributed in a preset historical time period;

the calculation module is configured to calculate distribution reference sub-scores of the objects to be distributed on various distribution reference elements according to the historical execution data, and calculate distribution reference scores of the objects to be distributed according to the distribution reference sub-scores;

and the distribution module is configured to distribute resources to the objects to be distributed according to the distribution reference scores.

With reference to the second aspect, in a first implementation manner of the second aspect, the computing module includes:

a first calculation submodule configured to calculate distribution reference sub-scores of the objects to be distributed on a plurality of kinds of distribution reference elements, respectively, according to the historical execution data;

a first obtaining submodule configured to obtain a weight value of the assignment reference element;

and the second calculation submodule is configured to perform weighted summation on the distribution reference sub-scores based on the weight values to obtain the distribution reference scores of the objects to be distributed.

With reference to the second aspect and the first implementation manner of the second aspect, in a second implementation manner of the second aspect, the allocating module includes:

the third calculation submodule is configured to calculate the resource allocation proportion of the object to be allocated according to the allocation reference value;

a second obtaining submodule configured to obtain a total number of allocable resources;

a fourth calculating submodule configured to calculate the number of the allocated resources of the object to be allocated based on the total number of the allocable resources and the resource allocation proportion of the object to be allocated;

and the first allocating sub-module is configured to allocate resources for the objects to be allocated according to the allocated resource quantity of the objects to be allocated.

With reference to the second aspect, the first implementation manner of the second aspect, and the second implementation manner of the second aspect, in a third implementation manner of the second aspect, the allocation module includes:

a fifth calculation sub-module configured to calculate a rating score of the history execution data of the object to be allocated;

a sixth calculating submodule configured to calculate the number of allocated resources of the object to be allocated according to the evaluation score;

the seventh calculation submodule is configured to calculate the average resource number of the object to be distributed in a first preset time period according to the distributed resource number of the object to be distributed;

the optimization submodule is configured to perform nonlinear optimization on the average resource quantity to obtain an optimized average resource quantity;

the eighth calculation submodule is configured to calculate the optimal allocation resource quantity of the object to be allocated according to the optimal average resource quantity;

the allocation submodule is configured to allocate resources to the object to be allocated according to the optimized allocation resource quantity of the object to be allocated;

and the sequencing submodule is configured to sequence the distribution reference scores and display the quantity of the resources distributed to the objects to be distributed according to a sequencing result.

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

a ranking module configured to rank the assigned reference scores;

and the correcting module is configured to correct the resources allocated to the objects to be allocated according to the sequencing result.

In a third aspect, an embodiment of the present disclosure provides an electronic device, which includes a memory and a processor, where the memory is used to store one or more computer instructions for supporting a resource allocation apparatus to execute the resource allocation method in the first aspect, and the processor is configured to execute the computer instructions stored in the memory. The resource allocation apparatus may further comprise a communication interface for the resource allocation apparatus to communicate with other devices or a communication network.

In a fourth aspect, the disclosed embodiments provide a computer-readable storage medium for storing computer instructions for a resource allocation apparatus, which contains computer instructions for executing the resource allocation method in the first aspect to the resource allocation apparatus.

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

according to the technical scheme, historical execution data of the object to be distributed in a preset historical time period are collected, the distribution reference score of the object to be distributed is calculated, and resources are distributed to the object to be distributed by means of the distribution reference score which has a data basis and considers various distribution reference elements. The technical scheme fully considers the performances of the historical execution data of the objects to be distributed in multiple aspects and distributes the resources on the basis of the performances, so that the technical effects of accurately judging the high-quality objects to be distributed, improving the effectiveness of resource distribution and reducing the use cost of the resources are achieved.

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 flow diagram of a resource allocation method according to an embodiment of the present disclosure;

FIG. 2 shows a flowchart of step S102 of the resource allocation method according to the embodiment shown in FIG. 1;

FIG. 3 shows a flowchart of step S103 of a resource allocation method according to one embodiment shown in FIG. 1;

FIG. 4 shows a flowchart of step S103 of a resource allocation method according to another embodiment shown in FIG. 1;

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

FIG. 6 is a schematic view of an application scenario for resource allocation of a plurality of objects to be allocated according to an embodiment of the present disclosure;

fig. 7 is a block diagram illustrating a structure of a resource allocation apparatus according to an embodiment of the present disclosure;

FIG. 8 is a block diagram of a computing module 702 of the resource allocation apparatus according to the embodiment shown in FIG. 7;

fig. 9 is a block diagram illustrating an allocation module 703 of the resource allocation apparatus according to an embodiment shown in fig. 7;

fig. 10 is a block diagram illustrating an allocation module 703 of a resource allocation apparatus according to another embodiment illustrated in fig. 7;

fig. 11 is a block diagram illustrating a structure of a resource allocation apparatus according to another embodiment of the present disclosure;

FIG. 12 shows a block diagram of an electronic device according to an embodiment of the present disclosure;

FIG. 13 is a schematic block diagram of a computer system suitable for implementing a resource allocation 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.

According to the technical scheme provided by the embodiment of the disclosure, historical execution data of the object to be distributed in a preset historical time period is collected, the distribution reference score of the object to be distributed is calculated, and then resources are distributed to the object to be distributed by means of the distribution reference score which has a data base and considers various distribution reference elements. The technical scheme fully considers the performances of the historical execution data of the objects to be distributed in multiple aspects and distributes the resources on the basis of the performances, so that the technical effects of accurately judging the high-quality objects to be distributed, improving the effectiveness of resource distribution and reducing the use cost of the resources are achieved.

Fig. 1 shows a flowchart of a resource allocation method according to an embodiment of the present disclosure. As shown in fig. 1, the resource allocation method includes the following steps S101 to S103:

in step S101, acquiring historical execution data of an object to be allocated within a preset historical time period;

in step S102, calculating distribution reference sub-scores of the to-be-distributed objects on various distribution reference elements according to the historical execution data, and calculating distribution reference scores of the to-be-distributed objects according to the distribution reference sub-scores;

in step S103, resources are allocated to the object to be allocated according to the allocation reference score.

As mentioned above, with the development of internet technology, many applications, clients, and application platforms have come up, and many merchants have developed various internet approaches to implement operation and promotion on the basis of physical approaches. However, the above-mentioned various promotion approaches have more or less differences in terms of audiences, business methods, promotion strategies, etc., and therefore, the effects of completing the operation and promotion tasks of the merchants are different. Based on the limitation and requirement on the operation and popularization cost, merchants need to find high-quality popularization ways from various popularization ways to achieve the effect of achieving twice the result with half the effort. In the prior art, the judgment of high-quality promotion ways is carried out only on the basis of cost indexes and income indexes by combining the number of new users and the retention rate of the users, the judgment factor of the scheme is narrow, the judgment accuracy rate is low, and the requirements of most merchants cannot be met.

In view of the above-mentioned drawbacks, in this embodiment, a resource allocation method is proposed, which first obtains historical execution data of an object to be allocated within a preset historical time period; then, calculating the distribution reference sub-scores of the objects to be distributed on various distribution reference elements according to the historical execution data, and calculating the distribution reference scores of the objects to be distributed according to the distribution reference sub-scores; and finally, distributing resources for the objects to be distributed according to the distribution reference values. The technical scheme fully considers the performances of the historical execution data of the objects to be distributed in multiple aspects and distributes the resources on the basis of the performances, so that the technical effects of accurately judging the high-quality objects to be distributed, improving the effectiveness of resource distribution and reducing the use cost of the resources are achieved.

Where the resource refers to a resource that can be utilized to create value, such as funds, goods, and the like.

The object to be allocated refers to an object for receiving resource allocation, such as the above-mentioned entity approach and internet approaches of application programs, clients, application platforms, and the like. The invention is illustrated and explained below by way of example of the deployment of an internet platform.

The preset historical time period refers to a time period with a preset length before the current time, and may be a week, a month, or other time periods, and the length of the preset historical time period may be set according to the needs of the actual application, which is not specifically limited in the present invention.

In an optional implementation manner of this embodiment, the historical execution data includes one or more of the following data: the total resource usage amount in the preset historical time period, the average resource usage amount in the first preset time period, the total user activation amount in the preset historical time period, the average user activation amount in the first preset time period, the total new user amount in the preset historical time period, the average new user amount in the first preset time period, the user activation cost in the preset historical time period, the new user cost in the preset historical time period, the active user amount in the preset historical time period, the user repeated transaction amount in the second preset time period, the user repeated transaction total amount in the second preset time period, the average user repeated transaction amount in the second preset time period, and the like.

The first preset time period and the second preset time period are time windows for calculating average data, and may be the same or different, and may be specifically set according to the needs of practical applications. For example, the first preset time period and the second preset time period may be set to one day, or the first preset time period may be set to one day and the second preset time period may be set to one week.

Wherein, the user activation refers to a user downloading registration operation, the new user refers to a user who generates a transaction operation after downloading registration, the user activation cost refers to the cost spent on generating the activation user, and the new user cost refers to the cost spent on generating the new user.

Wherein the active user refers to a user who performs effective operation on the internet platform to be promoted, and the effective operation comprises one or more of the following operations: open, browse, click, log on, place orders, transaction interactions, view platform pages, pick up coupons, pick up red packs, information feedback, comments, and the like.

The total resource usage amount in the preset historical time period, the user repeated transaction amount in the second preset time period and the user repeated transaction total amount in the second preset time period can be obtained through data acquisition; the total number of the user activations in the preset historical time period, the total number of the new users in the preset historical time period and the number of the active users in the preset historical time period are all data obtained through data acquisition and anti-cheating and duplicate removal processing.

In an optional implementation of this embodiment, the allocation reference element comprises one or more of the following reference elements: a massiveness element, a cost element, an activity element, a revenue element, and so on. Wherein the volume element is used for representing the contribution of the object to be distributed to the generation of a new user; the cost element is used for reflecting the cost spent by the object to be distributed; the active elements are used for reflecting the number of active users generated by the object to be distributed; the income element is used for embodying the income amount earned by the object to be allocated for the resource provider.

In an optional implementation manner of this embodiment, as shown in fig. 2, the step S102, namely, the step of calculating the distributed reference sub-scores of the to-be-distributed objects on the multiple distributed reference elements according to the history execution data, and calculating the distributed reference scores of the to-be-distributed objects according to the distributed reference sub-scores, includes steps S201 to S203:

in step S201, respectively calculating the distribution reference sub-scores of the objects to be distributed on various distribution reference elements according to the historical execution data;

in step S202, a weight value of the assignment reference element is obtained;

in step S203, based on the weight values, the assigned reference sub-scores are weighted and summed to obtain an assigned reference score of the object to be assigned.

In order to fully reflect the working effectiveness of the objects to be distributed, in the embodiment, the distribution reference sub-scores are comprehensively considered according to the weight values of the distribution reference elements. Specifically, after the weight values of the distribution reference elements are obtained, the distribution reference sub-scores are weighted and summed based on the weight values, so as to obtain the distribution reference score of the object to be distributed.

The weight values of the allocation reference elements may be set according to the needs of the actual application, and optionally, the sum of the weight values of the allocation reference elements is equal to one. For example, a default weight value of 0.25 may be set for the four allocation reference elements, and then the weight values may be adjusted according to the actual application requirements, or the weight values of the allocation reference elements may be directly set, which is not limited in the present invention.

In an optional implementation manner of this embodiment, the assigned reference score of the object to be assigned may be calculated according to the following formula:

wherein s represents the assigned reference score of the object to be assigned, w_iWeight value, s, representing the ith assigned reference element_iAnd M represents the number of the distributed reference elements.

In an optional implementation manner of this embodiment, the allocating a reference element includes: the system comprises a body volume element, a cost element, an active element and a profit element, wherein the first preset time period is one day, and the second preset time period is one week.

In this implementation, the assignment of the sub-scores s of the objects to be assigned to the massic elements₁Can be calculated according to the following formula:

h represents the number of the new users on the day of the object to be distributed, H is F/d, F represents the total number of the new users of the object to be distributed in the preset historical time period, d represents the number of days in the preset historical time period, and MIN (H)₁:H_N) Denotes the minimum value, MAX (H), of the number of daily average new users of the N objects to be allocated₁:H_N) And the maximum value of the number of new users in the number of N objects to be distributed is shown, wherein N is the total number of the objects to be distributed.

The distribution reference sub-score s of the object to be distributed on the cost element₂Can be calculated according to the following formula:

wherein J represents a new user cost of the object to be allocated in the preset history time period, J is D/H, D represents a daily average cost of the object to be allocated, D is C/D, C represents a total resource usage amount of the object to be allocated in the preset history time period, D represents a number of days in the preset history time period, and MIN (J) represents₁:J_N) Represents the minimum value, MAX (J), of the new user costs of the N objects to be allocated within the preset historical period of time₁:J_N) And representing the maximum value of the new user cost of the N objects to be distributed in the preset historical time period.

Allocation of the object to be allocated on an active elementReference sub-score s₃Can be calculated according to the following formula:

wherein K represents the number of active users obtained by the object to be distributed in the preset historical time period, MIN (K)₁:K_N) Represents the minimum value, MAX (K), of the number of active users obtained by the N objects to be distributed within the preset historical time period₁:K_N) And the maximum value of the number of the active users obtained by the N objects to be distributed in the preset historical time period is represented.

The distribution reference sub-score s of the object to be distributed on the income element₄Can be calculated according to the following formula:

wherein Q represents the average repeated transaction amount of the users in the seven days of the object to be distributed, Q is M/L, M represents the total repeated transaction amount of the users in the seven days of the object to be distributed, L represents the repeated transaction amount of the users in the seven days of the object to be distributed, and MIN (Q)₁:Q_N) Representing the minimum value, MAX (Q), of the repeat transaction amounts of the average user over seven days for the N objects to be allocated₁:Q_N) And the maximum value of the average user repeated transaction amount in seven days of the N objects to be distributed is shown.

In an optional implementation manner of this embodiment, as shown in fig. 3, the step S103 of allocating resources to the object to be allocated according to the allocation reference score includes steps S301 to S304:

in step S301, calculating a resource allocation proportion of the object to be allocated according to the allocation reference score;

in step S302, the total number of allocable resources is obtained;

in step S303, calculating the number of allocated resources of the object to be allocated based on the total number of allocable resources and the resource allocation proportion of the object to be allocated;

in step S304, resources are allocated to the object to be allocated according to the allocated resource quantity of the object to be allocated.

In order to fully reflect the expression of the object to be allocated on the various allocation reference elements, in the embodiment, the resource allocation is performed on the object to be allocated according to the allocation reference scores obtained by integrating the allocation reference sub-scores of the object to be allocated on the various allocation reference elements. Specifically, the resource allocation proportion of the object to be allocated is obtained by calculation according to the allocation reference score, wherein the proportion of the allocation reference score of the object to be allocated in the sum of the allocation reference scores of all the objects to be allocated can be used as the resource allocation proportion of the object to be allocated; then acquiring the total amount of the allocable resources; calculating the number of the distributed resources of the object to be distributed based on the total number of the distributable resources and the resource distribution proportion of the object to be distributed, wherein the number of the distributed resources of the object to be distributed is the product of the total number of the distributable resources and the resource distribution proportion of the object to be distributed; and finally, distributing resources for the objects to be distributed according to the quantity of the distributed resources of the objects to be distributed.

In another optional implementation manner of this embodiment, as shown in fig. 4, the step S103 of allocating resources to the object to be allocated according to the allocation reference score includes steps S401 to S407:

in step S401, a rating score of the history execution data of the object to be allocated is calculated;

in step S402, calculating the number of the allocated resources of the object to be allocated according to the evaluation score;

in step S403, calculating an average resource quantity of the object to be allocated in a first preset time period according to the quantity of the allocated resources of the object to be allocated;

in step S404, performing nonlinear optimization on the average resource number to obtain an optimized average resource number;

in step S405, calculating the optimal allocation resource quantity of the object to be allocated according to the optimal average resource quantity;

in step S406, allocating resources to the object to be allocated according to the optimized allocated resource quantity of the object to be allocated;

in step S407, the allocation reference scores are sorted, and the number of resources allocated to the object to be allocated is displayed according to the sorting result.

In order to further improve the accuracy of resource allocation, in this embodiment, after obtaining the preliminary allocation resource amount according to the historical execution data, optimization processing is also performed on the preliminary allocation resource amount. Specifically, first, an evaluation score of the historical execution data of the object to be distributed is calculated; then calculating the quantity of the distributed resources of the objects to be distributed according to the evaluation scores; then, calculating according to the quantity of the distributed resources of the object to be distributed to obtain the average quantity of the resources of the object to be distributed in a first preset time period; carrying out nonlinear optimization on the average resource quantity to obtain an optimized average resource quantity; calculating the optimized distribution resource quantity of the object to be distributed according to the optimized average resource quantity; and finally, distributing resources for the objects to be distributed according to the optimized distributed resource quantity of the objects to be distributed, and displaying the resource quantity distributed to the objects to be distributed according to the sequencing result of the distributed reference scores.

In an optional implementation manner of this embodiment, the allocated resource quantity u of the object to be allocated is calculated according to the evaluation score based on the following formula:

wherein s is_iAn assigned reference score representing the ith object to be assigned, T the number of objects to be assigned, m the upper limit of the number of assigned resources, p_iRepresents the proportion of the ith object class to be distributed, and P represents the number of the object classes to be distributed, wherein the object classes to be distributed can be, for example, the number of the object classes to be distributedWith stores, advertising platforms, general web sites, and so forth.

In an optional implementation manner of this embodiment, an average resource quantity v of the object to be allocated within a first preset time period is calculated according to the allocation resource quantity of the object to be allocated based on the following formula:

v＝u/d′

wherein d 'represents the number of unit time in the time period in which the resource allocation is required, and the unit time can be set to one day, then d' represents the number of days in the time period in which the resource allocation is required.

In an optional implementation manner of this embodiment, an average activated number a of users of the object to be allocated in the first preset time period and an average new number b of users in the first preset time period may also be obtained through calculation for reference.

Wherein, a is v/e, and e represents the activation cost of the target user and is a known value; and b is equal to v/f, and f represents the target new user cost and is a known value.

In an optional implementation manner of this embodiment, the average resource quantity is subjected to nonlinear optimization based on an objective function shown in the following formula, so as to obtain an optimized average resource quantity v':

the constraint conditions of the objective function are as follows:

l_l≤v′≤l_u，

wherein y represents a target value of the objective function, v_iRepresents the average resource quantity, v, of the ith object to be allocated_i' represents the optimized average resource quantity, l, of the ith object to be allocated_l，l_uRespectively representing the upper and lower limits of the average resource quantity of the objects to be distributed, which can be determined according to practical applicationIs set as required.

Wherein the objective function can be solved using a smooth nonlinear programming solution method.

In an optional implementation manner of this embodiment, the optimal allocation resource quantity u 'of the object to be allocated is calculated according to the optimal average resource quantity v' based on the following formula:

u′＝v′×d′。

in an optional implementation manner of this embodiment, the allocation reference scores are sorted from large to small, and the number of resources allocated to the object to be allocated is displayed according to a sorting result.

In an optional implementation manner of this embodiment, the average number of activated users of the object to be allocated in the first preset time period and the average number of new users in the first preset time period may also be optimized.

Specifically, the average user activation number a' of the objects to be allocated in the first preset time period may be calculated based on the following formula:

wherein, c_dRepresenting the daily average resource usage amount in a preset historical time period, which can be obtained by performing data calculation according to the history of the objects to be distributed, n_aRepresenting the daily average user natural activation number, wherein the daily average user natural activation number refers to the daily average user activation number without any anti-cheating and de-duplication processing, p_aRepresenting a user activation cost over the preset historical time period.

The average new user number b' of the object to be allocated in the first preset time period may be calculated based on the following formula:

wherein, c_dRepresenting a preset historical timeAverage daily resource usage number, n, within a segment_cRepresenting the number of the daily-average natural new users, wherein the daily-average natural new user number refers to the daily-average new user number without any anti-cheating and de-duplication processing, p_cRepresenting the cost of the new user within the preset historical time period.

In an optional implementation manner of this embodiment, the method further includes a step of modifying the resource allocated to the object to be allocated according to the allocation reference score, that is, as shown in fig. 5, the method includes steps S501 to S505:

in step S501, historical execution data of an object to be allocated in a preset historical time period is acquired;

in step S502, calculating distribution reference sub-scores of the to-be-distributed object on various distribution reference elements according to the historical execution data, and calculating distribution reference scores of the to-be-distributed object according to the distribution reference sub-scores;

in step S503, allocating resources to the object to be allocated according to the allocation reference score;

in step S504, the assigned reference scores are sorted;

in step S505, the resources allocated to the object to be allocated are modified according to the sorting result.

In order to fully reflect the tendency of allocating the reference element, in this embodiment, the resource allocated to the object to be allocated is also modified according to the allocation reference score. Specifically, the assigned reference scores are sorted first; and then modifying the resources allocated to the objects to be allocated according to the sequencing result. For example, for an object to be allocated with a top assigned reference score, the object to be allocated is considered to perform better, and the number of resources allocated to the object to be allocated can be increased within an allowable range, whereas for an object to be allocated with a back assigned reference score, the object to be allocated is considered to be deficient in some aspects, and therefore the number of resources allocated to the object to be allocated can be decreased within the allowable range.

Fig. 6 is a schematic view of an application scenario for resource allocation of a plurality of objects to be allocated according to an embodiment of the present disclosure, in fig. 6, a channel side refers to the objects to be allocated, a channel type refers to a type to which the objects to be allocated belong, and data statistics of different objects to be allocated and resource conditions that can be allocated to the objects can be obtained from fig. 6.

The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods.

Fig. 7 shows a block diagram of a resource allocation apparatus according to an embodiment of the present disclosure, which may be implemented as part or all of an electronic device by software, hardware, or a combination of the two. As shown in fig. 7, the resource allocation apparatus includes:

an obtaining module 701 configured to obtain historical execution data of an object to be allocated in a preset historical time period;

a calculating module 702 configured to calculate sub-scores of the objects to be distributed on various distribution reference elements according to the historical execution data, and calculate the sub-scores of the objects to be distributed according to the sub-scores of the distribution reference elements;

an allocating module 703 configured to allocate resources to the object to be allocated according to the allocation reference score.

In view of the above drawbacks, in this embodiment, a resource allocation apparatus is proposed, in which the apparatus acquisition module 701 acquires history execution data of an object to be allocated in a preset history time period; the calculation module 702 calculates the sub-scores of the distribution references of the objects to be distributed on various distribution reference elements according to the historical execution data, and calculates the sub-scores of the distribution references of the objects to be distributed according to the sub-scores of the distribution references; the distribution module 703 distributes resources to the objects to be distributed according to the distribution reference scores. The technical scheme fully considers the performances of the historical execution data of the objects to be distributed in multiple aspects and distributes the resources on the basis of the performances, so that the technical effects of accurately judging the high-quality objects to be distributed, improving the effectiveness of resource distribution and reducing the use cost of the resources are achieved.

In an optional implementation manner of this embodiment, as shown in fig. 8, the calculating module 702 includes:

a first calculating sub-module 801 configured to calculate, according to the historical execution data, distribution reference sub-scores of the objects to be distributed on a plurality of kinds of distribution reference elements, respectively;

a first obtaining submodule 802 configured to obtain a weight value of the assignment reference element;

the second calculating sub-module 803 is configured to perform weighted summation on the distribution reference sub-scores based on the weight values, so as to obtain distribution reference scores of the objects to be distributed.

In order to fully reflect the working effectiveness of the objects to be distributed, in the embodiment, the distribution reference sub-scores are comprehensively considered according to the weight values of the distribution reference elements. Specifically, after the first obtaining sub-module 802 obtains the weight values of the allocation reference elements, the second calculating sub-module 803 performs weighted summation on the allocation reference sub-scores obtained by the calculation of the first calculating sub-module 801 based on the weight values, so as to obtain the allocation reference scores of the objects to be allocated.

wherein J represents a new user cost of the object to be allocated in the preset history time period, J is D/H, D represents a daily average cost of the object to be allocated, D is C/D, and C represents the object to be allocated in the preset history time periodTotal number of resource usage in a time period, d represents the number of days in the preset historical time period, MIN (J)₁:J_N) Represents the minimum value, MAX (J), of the new user costs of the N objects to be allocated within the preset historical period of time₁:J_N) And representing the maximum value of the new user cost of the N objects to be distributed in the preset historical time period.

The distribution reference sub-score s of the object to be distributed on the active element₃Can be calculated according to the following formula:

In an optional implementation manner of this embodiment, as shown in fig. 9, the allocating module 703 includes:

a third computing submodule 901 configured to compute a resource allocation proportion of the object to be allocated according to the allocation reference score;

a second obtaining submodule 902 configured to obtain a total number of allocable resources;

a fourth calculating submodule 903, configured to calculate, based on the total number of allocable resources and the resource allocation proportion of the object to be allocated, the number of allocated resources of the object to be allocated;

a first allocating sub-module 904 configured to allocate resources for the object to be allocated according to the allocated resource amount of the object to be allocated.

In order to fully reflect the expression of the object to be allocated on the various allocation reference elements, in the embodiment, the resource allocation is performed on the object to be allocated according to the allocation reference scores obtained by integrating the allocation reference sub-scores of the object to be allocated on the various allocation reference elements. Specifically, the third computing submodule 901 calculates the resource allocation proportion of the objects to be allocated according to the allocation reference scores, wherein the proportion of the allocation reference scores of the objects to be allocated in the total allocation reference scores of all the objects to be allocated may be used as the resource allocation proportion of the objects to be allocated; the second obtaining sub-module 902 obtains the total amount of the allocable resources; the fourth calculating submodule 903 calculates, based on the total amount of the allocable resources and the resource allocation proportion of the object to be allocated, the amount of the allocated resources of the object to be allocated, where the amount of the allocated resources of the object to be allocated is a product of the total amount of the allocable resources and the resource allocation proportion of the object to be allocated; the first allocating sub-module 904 allocates resources to the object to be allocated according to the allocated resource quantity of the object to be allocated.

In another optional implementation manner of this embodiment, as shown in fig. 10, the allocating module 703 includes:

a fifth calculation submodule 1001 configured to calculate an evaluation score of the history execution data of the object to be allocated;

a sixth calculating submodule 1002, configured to calculate, according to the evaluation score, the number of allocated resources of the object to be allocated;

a seventh calculating submodule 1003 configured to calculate, according to the number of the allocated resources of the object to be allocated, to obtain an average number of the resources of the object to be allocated in a first preset time period;

an optimization submodule 1004 configured to perform a non-linear optimization on the average number of resources, resulting in an optimized average number of resources;

an eighth calculating submodule 1005 configured to calculate, according to the optimized average resource quantity, an optimized distribution resource quantity of the object to be distributed;

a second allocating submodule 1006, configured to allocate resources to the object to be allocated according to the optimized allocated resource quantity of the object to be allocated;

and the sorting submodule 1007 is configured to sort the allocation reference scores and display the number of resources allocated to the object to be allocated according to a sorting result.

In order to further improve the accuracy of resource allocation, in this embodiment, after obtaining the preliminary allocation resource amount according to the historical execution data, optimization processing is also performed on the preliminary allocation resource amount. Specifically, the fifth calculation sub-module 1001 calculates an evaluation score of the history execution data of the object to be allocated; the sixth calculating submodule 1002 calculates the number of allocated resources of the object to be allocated according to the evaluation score; the seventh calculation submodule 1003 calculates, according to the number of the allocated resources of the object to be allocated, to obtain an average number of the resources of the object to be allocated in a first preset time period; the optimization submodule 1004 performs nonlinear optimization on the average resource quantity to obtain an optimized average resource quantity; the eighth calculating submodule 1005 calculates the optimal allocation resource quantity of the object to be allocated according to the optimal average resource quantity; the second allocating submodule 1006 allocates resources to the object to be allocated according to the optimized allocated resource quantity of the object to be allocated, and the sorting submodule 1007 displays the resource quantity allocated to the object to be allocated according to the sorting result of the allocation reference score.

wherein s is_iAn assigned reference score representing the ith object to be assigned, T the number of objects to be assigned, m the upper limit of the number of assigned resources, p_iThe ratio of the ith object category to be allocated is shown, and P is the number of the object categories to be allocated, wherein the object categories to be allocated can be application stores, advertisement platforms, common websites and the like.

v＝u/d′

the constraint conditions of the objective function are as follows:

l_l≤v′≤l_u，

wherein y represents a target value of the objective function, v_iRepresenting the average resource quantity v 'of the ith object to be distributed'_iRepresents the optimized average resource quantity, l, of the ith object to be distributed_l，l_uThe upper and lower limits respectively representing the average resource quantity of the objects to be distributed can be set according to the requirements of practical application.

u′＝v′×d′。

wherein, c_dRepresenting the daily average resource usage amount in a preset historical time period, and can be executed according to the history of the objects to be distributedData is calculated to obtain n_aRepresenting the daily average user natural activation number, wherein the daily average user natural activation number refers to the daily average user activation number without any anti-cheating and de-duplication processing, p_aRepresenting a user activation cost over the preset historical time period.

wherein, c_dRepresenting the daily average resource usage number, n, in a preset historical time period_cRepresenting the number of the daily-average natural new users, wherein the daily-average natural new user number refers to the daily-average new user number without any anti-cheating and de-duplication processing, p_cRepresenting the cost of the new user within the preset historical time period.

In an optional implementation manner of this embodiment, the apparatus further includes a part that corrects the resource allocated to the object to be allocated according to the allocation reference score, that is, as shown in fig. 11, the apparatus includes:

an obtaining module 1101 configured to obtain historical execution data of an object to be allocated in a preset historical time period;

a calculating module 1102, configured to calculate distribution reference sub-scores of the to-be-distributed objects on various distribution reference elements according to the historical execution data, and calculate distribution reference scores of the to-be-distributed objects according to the distribution reference sub-scores;

an allocating module 1103 configured to allocate resources to the object to be allocated according to the allocation reference score;

a ranking module 1104 configured to rank the assigned reference scores;

and a correcting module 1105 configured to correct the resource allocated to the object to be allocated according to the sorting result.

In order to fully reflect the tendency of allocating the reference element, in this embodiment, the resource allocated to the object to be allocated is also modified according to the allocation reference score. Specifically, the ranking module 1104 ranks the assigned reference scores; the modification module 1105 modifies the resources allocated to the objects to be allocated according to the sorting result. For example, for an object to be allocated with a top assigned reference score, the object to be allocated is considered to perform better, and the number of resources allocated to the object to be allocated can be increased within an allowable range, whereas for an object to be allocated with a back assigned reference score, the object to be allocated is considered to be deficient in some aspects, and therefore the number of resources allocated to the object to be allocated can be decreased within the allowable range.

The present disclosure also discloses an electronic device, fig. 12 shows a block diagram of an electronic device according to an embodiment of the present disclosure, and as shown in fig. 12, the electronic device 1200 includes a memory 1201 and a processor 1202; wherein the content of the first and second substances,

the memory 1201 is used to store one or more computer instructions, which are executed by the processor 1202 to implement any of the method steps described above.

FIG. 13 is a schematic diagram of a computer system suitable for implementing a resource allocation method according to an embodiment of the present disclosure.

As shown in fig. 13, the computer system 1300 includes a Central Processing Unit (CPU)1301 that can execute various processes in the above-described embodiments according to a program stored in a Read Only Memory (ROM)1302 or a program loaded from a storage portion 1308 into a Random Access Memory (RAM) 1303. In the RAM1303, various programs and data necessary for the operation of the system 1300 are also stored. The CPU1301, the ROM1302, and the RAM1303 are connected to each other via a bus 1304. An input/output (I/O) interface 1305 is also connected to bus 1304.

The following components are connected to the I/O interface 1305: an input portion 1306 including a keyboard, a mouse, and the like; an output section 1307 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 1308 including a hard disk and the like; and a communication section 1309 including a network interface card such as a LAN card, a modem, or the like. The communication section 1309 performs communication processing via a network such as the internet. A drive 1310 is also connected to the I/O interface 1305 as needed. A removable medium 1311 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 1310 as necessary, so that a computer program read out therefrom is mounted into the storage portion 1308 as necessary.

In particular, the above described methods may be implemented as computer software programs, according to embodiments of the present disclosure. 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 resource allocation method. In such embodiments, the computer program may be downloaded and installed from a network via communications component 1309 and/or installed from removable media 1311.

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 for use by one or more processors in performing the methods described in the present disclosure.

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 for allocating resources on a channel side, comprising:

acquiring historical execution data of an object to be distributed in a preset historical time period, wherein the historical execution data comprises the following data: the total number of new users in the preset historical time period, the average number of new users in the first preset time period, the total number of resource usage in the preset historical time period, the average number of resource usage in the first preset time period, the cost of new users in the preset historical time period, the number of active users in the preset historical time period, the number of repeated transactions of users in the second preset time period, the total amount of repeated transactions of users in the second preset time period and the average amount of repeated transactions of users in the second preset time period;

calculating the distribution reference sub-scores of the objects to be distributed on various distribution reference elements according to the historical execution data, and calculating the distribution reference scores of the objects to be distributed according to the distribution reference sub-scores, wherein the distribution reference elements comprise the following reference elements: a volume element, a cost element, an active element and a benefit element;

2. The method according to claim 1, wherein the calculating the assigned reference sub-scores of the objects to be assigned on various assigned reference elements according to the historical execution data and calculating the assigned reference scores of the objects to be assigned according to the assigned reference sub-scores comprises:

acquiring a weight value of the distribution reference element;

3. The method according to claim 1 or 2, wherein the allocating resources to the objects to be allocated according to the allocation reference scores comprises:

acquiring the total amount of allocable resources;

4. The method according to claim 1 or 2, wherein the allocating resources to the objects to be allocated according to the allocation reference scores comprises:

5. The method of claim 1 or 2, further comprising:

sorting the assigned reference scores;

6. An apparatus for allocating resources on a channel side, comprising:

the acquisition module is configured to acquire historical execution data of the object to be distributed in a preset historical time period, wherein the historical execution data comprises the following data: the total number of new users in the preset historical time period, the average number of new users in the first preset time period, the total number of resource usage in the preset historical time period, the average number of resource usage in the first preset time period, the cost of new users in the preset historical time period, the number of active users in the preset historical time period, the number of repeated transactions of users in the second preset time period, the total amount of repeated transactions of users in the second preset time period and the average amount of repeated transactions of users in the second preset time period;

the calculation module is configured to calculate the distribution reference sub-scores of the objects to be distributed on various distribution reference elements according to the historical execution data, and calculate the distribution reference scores of the objects to be distributed according to the distribution reference sub-scores, wherein the distribution reference elements comprise the following reference elements: a volume element, a cost element, an active element and a benefit element;

7. The apparatus of claim 6, wherein the computing module comprises:

8. The apparatus according to claim 6 or 7, wherein the allocation module comprises:

9. The apparatus according to claim 6 or 7, wherein the allocation module comprises:

the second allocation submodule is configured to allocate resources to the objects to be allocated according to the optimized allocation resource quantity of the objects to be allocated;

10. The apparatus according to claim 6 or 7, further comprising:

a ranking module configured to rank the assigned reference scores;

11. An electronic device comprising a memory and a processor; wherein the content of the first and second substances,

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.

12. A computer-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.