CN117669905A - Resource allocation method and device, electronic equipment and storage equipment - Google Patents

Abstract

The application provides a resource allocation method, a resource allocation device, electronic equipment and storage equipment. The resource allocation method comprises the following steps: obtaining the resource allocation amount of each refining enterprise and the shadow price of the factory product of each refining enterprise according to the configuration optimization model; establishing a marginal contribution obtaining model corresponding to each refining enterprise according to the resource allocation amount of each refining enterprise and the shadow price of the factory product of each refining enterprise; iteratively adjusting the resource allocation amount in at least one marginal contribution obtaining model, and solving the adjusted marginal contribution obtaining model to obtain the first marginal contribution of the corresponding refining enterprise under different resource variation; when the total amount of the resources to be allocated is changed, the resource allocation amount of each refining enterprise is adjusted according to the first marginal contribution of each refining enterprise under different resource variation amounts. According to the scheme, the marginal contribution is taken as a basis, so that the allocation scheme of resources in different refining enterprises can be reasonably regulated.

Description

Resource allocation method and device, electronic equipment and storage equipment

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a method and apparatus for allocating resources, an electronic device, and a storage device.

Disclosure of Invention

The embodiment of the application provides a resource allocation method, a device, electronic equipment and storage equipment, which are used for reasonably and conveniently adjusting the allocation scheme of resources among a plurality of refining enterprises when the quantity of the resources provided by a resource provider changes.

One embodiment of the application provides a resource allocation method. The resource allocation method comprises the following steps: obtaining the resource allocation amount of each refining enterprise and the shadow price of the factory product of each refining enterprise according to the configuration optimization model; the configuration optimization model is used for determining the resource allocation amount of each refining enterprise when the overall resource utilization rate is maximized; establishing a marginal contribution obtaining model corresponding to each refining enterprise according to the resource allocation amount of each refining enterprise and the shadow price of the factory product of each refining enterprise; the marginal contribution obtaining model is used for calculating first marginal contribution corresponding to resource allocation quantity of the refining enterprise; iteratively adjusting the resource allocation amount in at least one marginal contribution obtaining model, and solving the adjusted marginal contribution obtaining model to obtain the first marginal contribution of the corresponding refining enterprise under different resource variation; the first marginal contribution represents the influence degree of the resource allocation amount of the refining enterprise on the overall resource utilization rate when the resource variation amount changes; when the total amount of the resources to be allocated is changed, the resource allocation amount of each refining enterprise is adjusted according to the first marginal contribution of each refining enterprise under different resource variation amounts.

In some embodiments, the establishing a marginal contribution obtaining model corresponding to each refining enterprise according to the resource allocation amount of each refining enterprise and the shadow price of each factory product of each refining enterprise includes: taking the shadow price of the outgoing product of each refining enterprise as the outgoing price of the outgoing product of each refining enterprise; establishing a marginal contribution obtaining model corresponding to each refining enterprise according to the difference value between the resource allocation quantity of each refining enterprise and the preset fine adjustment quantity and the delivery price of the delivery product of each refining enterprise; the difference value between the resource allocation amount of each refining enterprise and the preset fine adjustment amount is used as the marginal contribution corresponding to each refining enterprise to obtain the resource allocation amount in the model.

In some embodiments, the obtaining the shadow price of the factory product of each refining enterprise according to the configuration optimization model includes: adding constraint equations of a self-pin module and the self-pin submodule for each refining enterprise in the configuration optimization model to obtain an adjusted configuration optimization model; the self-sales sub-module is used for determining the sales quantity of the factory products sold by using the preset price when the resource utilization rate is maximized, and the constraint equation is used for constraining the upper limit of the sales quantity of the factory products in the self-sales sub-module; solving the adjusted configuration optimization model to obtain a second marginal contribution of a constraint equation of the self-marketing submodule; and calculating to obtain the shadow price of the factory product according to the preset price and the second marginal contribution of the constraint equation.

In some embodiments, the iteratively adjusting the resource allocation amount in the at least one marginal contribution obtaining model, and solving the adjusted marginal contribution obtaining model to obtain a first marginal contribution of the corresponding refining enterprise under different resource variation amounts includes: aiming at each marginal contribution obtaining model in the at least one marginal contribution obtaining model, respectively adjusting an upper limit in an upper limit constraint equation and a lower limit in a lower limit constraint equation of the marginal contribution obtaining model according to a preset step length to obtain an adjusted marginal contribution obtaining model; solving the adjusted marginal contribution obtaining model to obtain the adjusted resource allocation amount of the corresponding refining enterprise and the fourth marginal contribution of the upper limit constraint equation and the lower limit constraint equation of the marginal contribution obtaining model; if the adjusted resource allocation amount is not abnormal, adding a third marginal contribution of an upper limit constraint equation and a fourth marginal contribution of a lower limit constraint equation in the marginal contribution obtaining model to obtain the first marginal contribution of the corresponding refining enterprise under the current adjusted resource variation amount, and executing the next iteration; wherein the resource variation is the product of the step length and the iteration number; and if the adjusted resource allocation amount is abnormal, stopping iteration.

In some embodiments, after solving the adjusted marginal contribution obtaining model to obtain the adjusted resource allocation amount of the corresponding refining enterprise, the method further includes: if the adjusted resource allocation amount is within the preset resource threshold range of the refining enterprise, judging that the adjusted resource allocation amount is not abnormal; otherwise, judging that the adjusted resource allocation amount is abnormal.

In some embodiments, the method further comprises: establishing a production plan sub-model of each refining enterprise according to the resource use data of each refining enterprise; wherein the production plan sub-model of the refining enterprise is used for determining the resource allocation amount of the refining enterprise when the resource utilization rate of the refining enterprise is maximized; and establishing the configuration optimization model according to the production plan sub-model of each refining enterprise, the transportation network for transporting resources to each refining enterprise and the sales network of the outgoing products of each refining enterprise.

One of the embodiments of the present application provides a resource allocation apparatus, including: the acquisition module is used for acquiring the resource allocation amount of each refining enterprise and the shadow price of the factory product of each refining enterprise according to the configuration optimization model; the configuration optimization model is used for determining the resource allocation amount of each refining enterprise when the overall resource utilization rate is maximized; the establishing module is used for establishing a marginal contribution obtaining model corresponding to each refining enterprise according to the resource allocation amount of each refining enterprise and the shadow price of the factory product of each refining enterprise; the marginal contribution obtaining model is used for calculating first marginal contribution corresponding to resource allocation quantity of the refining enterprise; the iteration module is used for iteratively adjusting the resource allocation amount in the at least one marginal contribution obtaining model, and solving the adjusted marginal contribution obtaining model to obtain the first marginal contribution of the corresponding refining enterprise under different resource variation; the first marginal contribution represents the influence degree of the resource allocation amount of the refining enterprise on the overall resource utilization rate when the resource variation amount changes; and the adjusting module is used for adjusting the resource allocation quantity of each refining enterprise according to the first marginal contribution of each refining enterprise under different resource variation when the total quantity of the resources to be allocated is changed.

In some embodiments, the establishing module is specifically configured to use a shadow price of the outgoing product of each refining enterprise as the outgoing price of the outgoing product of each refining enterprise; the establishing module is specifically configured to establish a marginal contribution obtaining model corresponding to each refining enterprise according to a difference value between the resource allocation amount of each refining enterprise and the preset fine adjustment amount and a factory price of a factory product of each refining enterprise; the difference value between the resource allocation amount of each refining enterprise and the preset fine adjustment amount is used as the marginal contribution corresponding to each refining enterprise to obtain the resource allocation amount in the model.

The embodiment of the application provides an electronic device, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the method when running the program.

The present embodiments provide a storage device for storing a computer readable program which, when executed, performs the method as described above.

In the embodiment provided by the application, a marginal contribution obtaining model is obtained according to the shadow price of each factory product of each refining enterprise in a plurality of refining enterprises and the resource allocation amount of each refining enterprise. And iteratively adjusting the resource allocation amount in the at least one marginal contribution obtaining model, and solving the adjusted marginal contribution obtaining model to obtain the first marginal contribution of each refining enterprise under different resource variation. The shadow price is the selling price of each factory product sold in the downstream sales market when the sales market of each factory product is in full and insufficient balance, namely the shadow price can reflect the price when the resource utilization rate of each factory enterprise is maximized, so that marginal contribution data of a plurality of factory enterprises have better comparability. Because the resource allocation amount of each refining enterprise for the resources to be allocated is obtained by solving the optimal allocation result of the production resources obtained by the optimal allocation model, the marginal contribution obtaining model is obtained based on the optimal processing amount, and marginal contribution data obtained by adjusting the marginal contribution obtaining model can be used as the basis for reasonably and conveniently adjusting the allocation scheme of the resources among the refining enterprises when the supply direction of the resources to be allocated is increased or decreased compared with the preset supply amount.

The application provides a resource allocation method, a device, electronic equipment and storage equipment. The marginal contribution data of each refining enterprise obtained by the embodiment of the application is taken as a quantitative basis, and the reasons that in the optimal configuration result of the production resources obtained by configuring the optimization model, the load of some refining enterprises is higher and the load of other refining enterprises is lower can be obtained by analysis, so that a guiding basis can be provided for the subsequent resource allocation of each refining enterprise.

Background

Most of comprehensive petroleum companies integrate resource exploitation, resource transportation, resource processing and product sales, and comprise multiple oil fields and multiple refining enterprises. The same resource can be generally configured to a plurality of refining enterprises for production and processing, and each refining enterprise converts the resource into a plurality of types of finished products through a complex processing process. For the comprehensive petroleum company, when a production plan is prepared, the conditions of the production process flow and the geographic position of each refining enterprise, the requirements of the market on the petroleum refining products and the like are combined, the resources are comprehensively optimized, and the optimal quantity of each resource distributed to each refining enterprise is determined through scientific analysis, so that the maximization of the resource utilization rate is realized.

Currently, a resource allocation scheme for maximizing the overall resource utilization of a comprehensive petroleum company can be obtained by establishing and solving a configuration optimization model under the condition that all constraint conditions (such as total resource amount, market demand for products, processing capacity of a refining enterprise, and limitation of various technological parameters) of the configuration optimization model are met.

However, during the resource production process, the number of resources actually provided by the resource provider may be greater than the estimated supply of resources, or may be less than the estimated supply of resources. When the number of resources actually provided by a resource provider changes from the number of resources expected to be provided, it is desirable to quickly adjust the allocation scheme of resources among a plurality of refining enterprises.

Therefore, how to reasonably and conveniently adjust the allocation scheme of the resources among a plurality of refining enterprises when the number of the resources actually provided by the resource provider is changed from the expected number is a technical problem to be solved.

Drawings

The present application will be further illustrated by way of example embodiments, which will be described in detail with reference to the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:

Fig. 1 is a schematic view of an application scenario of a resource allocation method according to some embodiments of the present application;

FIG. 2 is an exemplary flow chart of a resource allocation method according to some embodiments of the present application;

FIG. 3 is an exemplary flow chart of a method of obtaining a shadow price according to some embodiments of the present application;

FIG. 4 is a summary of marginal contributions of a plurality of refining enterprises to process resources to be allocated, according to some embodiments of the present application;

FIG. 5 is a marginal contribution ranking table of a plurality of refining enterprises processing resources to be allocated as the number of resources to be allocated increases, according to some embodiments of the present application;

FIG. 6 is a marginal contribution ranking table of a plurality of refining enterprises processing resources to be allocated as the number of resources to be allocated decreases, according to some embodiments of the present application;

fig. 7 is an exemplary schematic diagram of an allocation adjustment device for resources to be allocated according to some embodiments of the present application;

fig. 8 is an exemplary structural schematic diagram of an electronic device, according to some embodiments of the present application.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present application, and it is obvious to those skilled in the art that the present application may be applied to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.

It will be appreciated that "system," "apparatus," "unit" and/or "module" as used herein is one method for distinguishing between different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

As used in this application and in the claims, the terms "a," "an," "the," and/or "the" are not specific to the singular, but may include the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.

Flowcharts are used in this application to describe the operations performed by systems according to embodiments of the present application. It should be appreciated that the preceding or following operations are not necessarily performed in order precisely. Rather, each step may be processed in reverse order or simultaneously. Also, other operations may be added to or removed from these processes.

Fig. 1 is a schematic application scenario diagram of a resource allocation method according to some embodiments of the present application.

By way of example only, the application scenario of the resource allocation method of the present application will be described below taking the adjustment of the allocation scheme of petroleum raw materials by the comprehensive petroleum company as an example.

As shown in fig. 1, a service terminal 110, a terminal 120, and a network 130 may be included in an application scenario 100.

In some embodiments, the server 110 and the terminal 120 may interact with each other through the network 130. For example, the server 110 may acquire information and/or data in the terminal 120 through the network 130, or may transmit information and/or data to the terminal 120 through the network 130.

The terminal 120 is an electronic device used by a user to obtain an allocation scheme of the comprehensive petroleum company for the resources to be allocated. In some embodiments, the terminal 120 may establish a configuration optimization model for a plurality of refining enterprises and obtain a shadow price for each shipped product for each of the plurality of refining enterprises using the configuration optimization model. In some embodiments, terminal 120 may obtain a marginal contribution acquisition model from the shadow price of each shipped product for each refining enterprise and the resource allocation amount of each refining enterprise for the resources to be allocated. In some embodiments, the terminal 120 may use the marginal contribution acquisition model to obtain a first marginal contribution of the processing resources of each of the plurality of refining enterprises. In some embodiments, when the number of resources to be allocated provided to the plurality of refining enterprises increases or decreases from the preset provided number, a user (e.g., an administrator of the comprehensive petroleum company) may increase or decrease the number of resources to be allocated provided to at least one of the plurality of refining enterprises according to the obtained at least one first marginal contribution.

The specific type of the resource is not limited in this application, and may be, for example, petroleum, natural gas, hydrogen, or the like.

In the case that the computing resources of the terminal 120 are limited, the server 110 may also obtain at least one first marginal contribution of the resources to be allocated by each of the plurality of refining enterprises using the embodiments provided in the present application, and send the obtained at least one first marginal contribution to the terminal 120, and display the at least one first marginal contribution to the user through the terminal 120, so that the user may adjust the amount of the resources to be allocated provided to the at least one of the plurality of refining enterprises according to the obtained at least one first marginal contribution. The terminal 120 may be one or any combination of devices with input and/or output capabilities, such as a mobile device, tablet computer, or the like.

The server 110 may be a single server or a group of servers. The server farm may be centralized or distributed (e.g., server 110 may be a distributed system), may be dedicated, or may be serviced concurrently by other devices or systems. In some embodiments, the server 110 may be regional or remote. In some embodiments, the server 110 may be implemented on a cloud platform or provided in a virtual manner. For example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, or the like, or any combination thereof.

In some embodiments, the network 130 may be any one or more of a wired network or a wireless network. For example, the network 130 may include a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), etc., or any combination thereof.

For easy understanding, the technical solutions of the present application are described below with reference to the drawings and examples.

Fig. 2 is an exemplary flow chart of a resource allocation method according to some embodiments of the present application. As shown in fig. 2, the process 200 includes the following steps.

Step S210, establishing a marginal contribution obtaining model corresponding to each refining enterprise according to the resource allocation amount of each refining enterprise and the shadow price of the factory product of each refining enterprise.

The resources to be allocated are resource raw materials which need to be distributed to a refining enterprise for processing. The configuration optimization model is a model which is established based on an operation study method and comprises resource supply to be allocated, production and processing processes of a plurality of refining enterprises and a transportation process of products obtained by processing the resources, and is used for determining the allocation quantity of the production resources of each refining enterprise in the plurality of refining enterprises when the resource utilization rate is maximized. And configuring the resource allocation amount determined by the optimization model as the optimized processing amount. In a specific implementation, the configuration optimization model may be obtained in a variety of ways. For example, the configuration optimization model may be established using MPIMS (headquarter supply chain optimization model) software of aspen corporation, RPMS (advanced planning system) software of HONEYWELL corporation, and PICIO (crude oil industry chain integration optimization platform) software developed by chinese petroleum planning institute.

By way of example only, the following description will be given by taking the use of PICIO software to build a configuration optimization model as an example. In the specific implementation process, a production plan sub-model from resource factory entering, device production processing and product blending to product factory leaving of each refining enterprise can be established according to the resource use data of each refining enterprise in a plurality of refining enterprises. The production plan sub-model is used to determine a configuration of production resources of the refining enterprise when the refining enterprise resource utilization is maximized. Resource usage data for a refining enterprise may include, but is not limited to: the revenue of each outgoing product of each refining enterprise, the procurement cost of the resources to be allocated, and the utility cost. The objective function of the production plan submodel is:

MAX P _r ＝∑ _i d _ri u _ri -∑ _j f _rj v _rj -w _r (1)

in formula (1): p (P) _r The profit of the refining enterprise r; d, d _ri And u _ri The factory price and the output of a product i of a refining enterprise r are respectively; f (f) _rj And v _rj The purchase price and the purchase quantity of the resource j of the refining enterprise r are respectively; w (w) _r To change the processing cost of the refining enterprise r.

In the production plan submodel established for each refining enterprise of the integrated petroleum company, the variables include: the purchase quantity of various resources, the yield of various products, the processing quantity of various devices, the feeding quantity and the discharging quantity of various devices and the like. The parameters of the model include: purchase price of various raw materials, delivery price of various products, unit consumption of raw materials of the device, yield of the products, physical property values of the materials and the like. The constraint equations for the production plan submodel include: the whole plant balance equation of each material, the association relation equation of the amount of input materials and output materials of the device, the upper and lower limits of raw material purchase quantity, the upper and lower limits of product yield, the upper and lower limits of processing capacity of the device, the physical property index requirements of device feeding, the physical property index requirements of blended products and the like.

After the production plan sub-model of each of the plurality of refining enterprises is established, a configuration optimization model may be established based on the production plan sub-model of each of the plurality of refining enterprises, and a transport network from which resources to be allocated are transported from the resource provider to each of the plurality of refining enterprises, and a sales network for the shipped products of each of the plurality of refining enterprises.

In a configuration optimization model established for a comprehensive petroleum company, the overall benefit of the comprehensive petroleum company is: the total income of the product obtained by the resource processing in the terminal market is different from the total cost of purchasing the resource from the resource provider, the transportation cost of transporting the resource from the resource provider to the refining enterprise, the transportation cost of transporting the product obtained by the resource processing from the refining enterprise to the market and the like. The expression is as follows:

MAX ZP＝∑ _m ∑ _i a _mi x _mi -∑ _n ∑ _j b _nj y _nj -∑ _n ∑ _r ∑ _j c _njr z _njr -∑ _r ∑ _m ∑ _i c _rjm z _rim -∑ _r w _r (2)

in formula (2): ZP is the total gain of the comprehensive petroleum company; a, a _mi And x _mi Price and sales of product i in market m, respectively; b _nj And y _nj The price and the supply quantity of the resource j are respectively supplied to the resource provider n; c _njr And z _njr The transportation cost and the transportation quantity of the resource units from the resource provider n to the refining enterprise r are respectively distributed; c _rim And z _rim The unit transportation cost and the transportation quantity of the products from the self-refining enterprises r to the market m are respectively calculated.

The variables of the configuration optimization model include: the amount of a certain resource delivered from a resource provider to a certain refining enterprise, the processing amount of a certain refining enterprise and the yield of each product obtained by processing the resource, the amount of a certain product delivered from a certain refining enterprise to a certain market, and the like. The parameters of the configuration optimization model include: the resource provider supplies a price of a certain resource, a price of a certain product sold in a certain market, a resource unit transportation cost, and a product unit transportation cost. The configuration optimization model includes the following constraint equations.

Resource supply balance equation for resource provider: the amount of resource j supplied by the resource provider n is equal to the sum of the number of resources j delivered from the resource provider n to each of the refining enterprises, expressed as follows:

y _nj ＝∑ _r z _njr (3)

the resource of the refining enterprise enters a factory balance equation: the amount of the resource j purchased by the refining enterprise r is equal to the amount of the resource j delivered from the resource provider n supplying the resource j to the refining enterprise r, and the formula is expressed as follows:

v _rj ＝z _njr (4)

production and marketing balance equation of refining enterprises: the quantity of the product i produced by the refining enterprise r is equal to the sum of the quantity of the product i distributed to each market by the self-refining enterprise r, and the formula is expressed as follows:

u _ri ＝∑ _m z _rim (5)

Marketing balance equation: the amount of product i sold in market m is equal to the sum of the amounts of product i delivered to market m from each refining enterprise, expressed as follows:

x _mi ＝∑ _r z _rim (6)

the configuration optimization model further comprises the following constraint equation: the method comprises the following steps of a supply quantity upper limit and lower limit constraint equation of a certain resource on a certain resource provider, a sales quantity upper limit and lower limit constraint equation of each product obtained by resource processing on a certain market, various transportation network capacity upper limit and lower limit constraint equations, constraint equations to be followed by each integrated production plan sub-model and the like.

In some embodiments, after the configuration optimization model is obtained, a marginal contribution obtaining model corresponding to each refining enterprise may be established according to the resource allocation amount of each refining enterprise and the shadow price of the factory product of each refining enterprise. The marginal contribution acquisition model may then be used to calculate at least one marginal contribution for the resource to be allocated for each of the plurality of refining enterprises.

In some embodiments, a configuration optimization model may be used to obtain a shadow price for each factory product of each refining enterprise, where each factory product is obtained after processing the resources to be allocated. Then, the shadow price of each outgoing product is used as the outgoing price of each outgoing product in each production plan submodel. The shadow price of each outgoing product is set by the refining enterprises to the downstream market when the profit and the loss of each outgoing product in the downstream market are balanced. Details of obtaining the shadow price of each factory product of each refining enterprise by using the configuration optimization model are referred to in relevant content of fig. 3, and are not described herein.

In some embodiments, the upper and lower constraint equations in the production plan sub-models may be utilized to set the purchased quantity of each refining enterprise in the production plan sub-models for the resources to be allocated. The upper limit constraint equation is a constraint equation of each refining enterprise for the upper limit of the purchase quantity of the resources to be allocated, and the lower limit constraint equation is a constraint equation of each refining enterprise for the lower limit of the purchase quantity of the resources to be allocated. Since the amount of the resource allocation of the production resource obtained by configuring the optimization model may already reach the upper limit of the processing capacity of certain refining enterprises, the amount of the resource allocation of each refining enterprise for the resource allocation needs to be increased in the marginal contribution obtaining model, so as to calculate and obtain at least one marginal contribution of each refining enterprise to process the resource to be allocated based on the increased amount of the resource allocation. Thus, in some embodiments, the upper and lower limits of the number of purchases in the upper and lower constraint equations may each be set to optimize the difference between the process number and the preset trim number in each production plan sub-model. And the resource allocation amount is the amount of the resources to be allocated, which are distributed to each refining enterprise by the provider of the resources to be allocated, in the result obtained by solving the configuration optimization model. The preset trimming amount may be a relatively small value compared to the resource allocation amount. For example, the resource allocation amount is 50 ten thousand tons, and the preset trimming amount may be 0.1 ten thousand tons. In the marginal contribution obtaining model, the upper limit constraint equation and the lower limit constraint equation may be expressed as the following formulas, respectively:

In the above-mentioned formula(s),and in the resource allocation amount obtained by solving the configuration optimization model, the number of the resources to be allocated to the refining enterprises r is distributed from the provider n of the resources to be allocated j, and epsilon is a preset fine adjustment number. In the formula, the same numerical value is set for the upper limit of the purchase quantity in the upper limit constraint equation and the lower limit of the purchase quantity in the lower limit constraint equation, so that the prior constraint equation of the production plan sub-model can be utilized, and the marginal contribution is set to obtain the purchase quantity of each refining enterprise aiming at the resources to be allocated in the model.

After setting the purchasing quantity of each refining enterprise aiming at the resources to be allocated in the marginal contribution obtaining model, the marginal contribution obtaining model can be obtained through the following steps:

(1) Setting the resource purchase price of each refining enterprise:

the purchase price of the resource j to be allocated of each refining enterprise r is set as follows: the price of the resource provider n for supplying the resource j to be allocated and the unit transportation cost of the resource provider n for distributing the resource j to each refining enterprise r:

f _rj ＝y _nj +c _njr (9)

(2) Setting the factory price of factory products of a refining enterprise:

the factory price of the factory product i of the smelting enterprise r is set as: the shadow price of the product i is provided at the refining enterprise r.

d _ri ＝h _ri (10)

After establishing the marginal contribution obtaining model, PICIO software can be applied to solve the marginal contribution obtaining model to obtain the third marginal contribution l of the upper limit constraint equation _rj ^A And a fourth marginal contribution q of the lower bound constraint equation _rJ ^A . Third boundary contribution l _rJ ^A The mathematical meaning of (2) is: if the upper limit of the processing amount of the resource j to be allocated by the refining enterprise r is defined byIs changed intoSlope of the effect on objective function value. Fourth marginal contribution q _rj ^A The mathematical meaning of (2) is: if the lower limit of the processing amount of the resource j to be allocated by the refining enterprise r is defined by +.>Changes to->Slope of the effect on objective function value. Delta is a value far below +.>Numerical values of (e.g.)>1 ten thousand tons, delta may be 10 ^-8 Ten thousand tons. Third boundary contribution l _rj ^A And fourth inter-margin contribution q _rj ^A The method can reflect the contribution of the refining enterprises to the resource utilization rate of the refining enterprises by purchasing and processing a certain amount of resources to be allocated under the condition that the processing amount of the resources to be allocated by the refining enterprises is slightly lower than the optimized processing amount. If the refining enterprise r is in the processing amount +.>On the basis, the resource utilization rate of the refining enterprise can be improved by processing the resources j to be allocated more, i _rh ^A ＞0，q _rj ^A =0, if the refining enterprise r is at process level +.>On the basis, the utilization rate of the resources of the refining enterprise can be improved by the few processing resources j (which is equivalent to the utilization rate of the resources of the refining enterprise can be reduced by the more processing resources j to be allocated), then l _rj ^A ＝0，q _rj ^A ＜0，Thus, l _rj And q _rj Not both non-zero values and l _rj And q _rj While there will be a zero value. Thus, each refining enterprise processes a first marginal contribution s of the resource to be allocated _rj ^A The calculation formula of (2) is as follows:

s _rj ^A ＝l _rj ^A +q _rj ^A (11)

the relative size of marginal contributions of each refinery to process the same resource j is a direct cause of relatively high load of some refining enterprises and relatively low load of some refining enterprises in the resource allocation amount of the production resources obtained by using the configuration optimization model.

Step S220, iteratively adjusting the resource allocation amount in at least one marginal contribution obtaining model, and solving the adjusted marginal contribution obtaining model to obtain the first marginal contribution of the corresponding refining enterprise under different resource variation amounts; the first marginal contribution characterizes the degree of influence on the overall resource utilization rate when the resource allocation amount of the refining enterprise changes by the resource variation amount.

In some embodiments, in order to quickly adjust the allocation scheme of resources among the plurality of refining enterprises when the number of resources actually provided by the resource provider increases compared to the expected number of the resources provided by the resource provider, it is required to obtain at least one first marginal contribution of each of the plurality of refining enterprises to process the resources to be allocated in the case that the number of the processed resources increases relative to the preset processing number, so that the resources provided by the resource provider and the expected number of the resources provided by the resource provider can be allocated among the plurality of refining enterprises according to the at least one first marginal contribution. In a specific implementation process, a step size for calculating the marginal contribution of the resource may be set for each refining enterprise, and each step size is increased by the processing amount of the resource to be allocated provided to the refining enterprise, a first marginal contribution may be obtained until the processing amount of the resource to be allocated provided to the refining enterprise exceeds the upper limit of the processing capacity of the refining enterprise, so that at least one first marginal contribution may be obtained for each refining enterprise.

In a specific implementation process, in at least one iteration process, the upper limit of the purchase quantity in the upper limit constraint equation and the lower limit of the purchase quantity in the lower limit constraint equation of the marginal contribution obtaining model are respectively added with a preset marginal contribution analysis step length (for example, 1 ten thousand tons), so as to obtain the adjusted upper limit of the purchase quantity in the upper limit constraint equation and the adjusted lower limit of the purchase quantity in the lower limit constraint equation of the marginal contribution obtaining model. For convenience of description, the marginal contribution obtaining model adjusted in the 1 st iteration process is hereinafter referred to as a model a+1, the marginal contribution obtaining model adjusted in the 2 nd iteration process is hereinafter referred to as a model a+2, and so on.

The upper limit constraint equation and the lower limit constraint equation in the adjusted marginal contribution acquisition model are respectively expressed as:

in the formulas (12) and (13), β is a marginal contribution analysis step size, m represents the number of iterative calculations, the value of m is 1 for the model a+1, the value of m is 2 for the model a+2, and so on.

In some embodiments, the adjusted marginal contribution obtaining model obtained above may be solved to obtain the adjusted resource allocation amount, the third marginal contribution of the upper constraint equation, and the fourth marginal contribution of the lower constraint equation.

If the adjusted resource allocation amount does not have an abnormal result, adding the third marginal contribution of the upper limit constraint equation and the fourth marginal contribution of the lower limit constraint equation to obtain a first marginal contribution s of the corresponding refining enterprise for processing the resources to be allocated under the current adjusted resource variation amount _rj ^A+m . The resource variation is the processing quantity of the resources to be allocated by the refining enterprise in the adjusted marginal contribution obtaining model and the resources to be allocated by the refining enterprise in the marginal contribution obtaining modelThe increment of the processing number (or the optimized processing number, because the value of the preset fine tuning number is small and can be ignored in the calculation result), and the resource variation can be obtained by calculating the product of the marginal contribution analysis step length and the iteration number. For example only, the marginal contribution analysis step size is 1 ten thousand tons, and as shown in fig. 4, during iteration 1, the resource variation is: for a refining enterprise D, 1X 1 ten thousand tons of marginal contribution of processing resources to be allocated corresponding to processing of more than 1 ten thousand tons of resources is obtained: 320. In the 2 nd iteration process, the resource variation is: 2×1 ten thousand tons, for the refining enterprise D, the marginal contribution of the processing resources to be allocated corresponding to the processing of 2 ten thousand tons of resources is obtained: 230, a step of; in the 3 rd iteration process, the resource variation is: for a refining enterprise D, the marginal contribution of processing resources to be allocated corresponding to processing of 3 ten thousand tons of resources is obtained: 200.

After the marginal contribution of this time is obtained, the next iteration can be performed based on the adjusted marginal contribution obtaining model. In the specific implementation process, m=m+1 can be made, an upper limit constraint equation and a lower limit constraint equation of a model A+m are obtained according to a formula (12) and a formula (13), then the model A+m is solved, and marginal contribution of the to-be-allocated resource processed by each refining enterprise corresponding to the resource variation (the value is: marginal contribution analysis step size x m) is obtained until an abnormal result exists in the obtained resource allocation amount.

If an abnormal result exists in the resource allocation quantity, the set resource purchasing quantity exceeds the upper limit of the processing capacity of the refining enterprise, and iteration is stopped. Abnormal results may include, but are not limited to: abnormal conditions such as unbalanced materials and exceeding set upper and lower limits of the processing amount of the device.

In some embodiments, in order to quickly adjust the allocation of resources among the plurality of refining enterprises when the number of resources actually provided by the resource provider is reduced compared to the expected number of provided resources, it is desirable to obtain at least one first marginal contribution of each of the plurality of refining enterprises to process the resource to be allocated if the number of processed resources is reduced relative to the preset processing number.

In a specific implementation process, in at least one iteration process, the upper limit of the purchase quantity of the resources to be allocated by each refining enterprise in the upper limit constraint equation of the marginal contribution obtaining model and the lower limit of the purchase quantity of the resources to be allocated by each refining enterprise in the lower limit constraint equation are subtracted from the marginal contribution analysis step length (for example, 1 ten thousand tons) respectively, so as to obtain the upper limit of the purchase quantity of the resources to be allocated by each refining enterprise in the upper limit constraint equation of the adjusted marginal contribution obtaining model and the lower limit of the purchase quantity of the resources to be allocated by each refining enterprise in the lower limit constraint equation. For convenience of description, the model obtained by the marginal contribution adjusted in the 1 st iteration process is hereinafter referred to as model a-1, and the model obtained by the marginal contribution adjusted in the 2 nd iteration process is hereinafter referred to as model a-2 ….

The upper limit constraint equation and the lower limit constraint equation in the adjusted marginal contribution acquisition model are respectively expressed as:

in equations (14) and (15), β is the marginal contribution analysis step size, n represents the number of iterative calculations, the value of n is 1 for model A-1, and the value of n is 2 … for model A-2.

In some embodiments, the adjusted marginal contribution obtaining model obtained above may be solved to obtain the resource allocation amount, the third marginal contribution of the upper constraint equation, and the fourth marginal contribution of the lower constraint equation.

If the abnormal result does not exist in the resource allocation quantity, subtracting the third marginal contribution of the upper limit constraint equation from the fourth marginal contribution of the lower limit constraint equation to obtain the first marginal contribution of each refining enterprise corresponding to the marginal contribution analysis reduction quantity aiming at the resources to be allocated, and obtaining a model based on the adjusted marginal contribution to carry out the next iteration. The marginal contribution analysis reduction amount is the reduction amount of the processing amount of the resource to be allocated by each refining enterprise in the adjusted marginal contribution obtaining model and the processing amount (or the optimized processing amount of the resource to be allocated by each refining enterprise in the marginal contribution obtaining model, because the value of the preset fine adjustment amount is small and can be ignored in the calculation result), and the marginal contribution analysis reduction amount can be obtained by calculating the product of the marginal contribution analysis step length and the iteration number. For example only, the marginal contribution analysis step size is 1 ten thousand tons, and as shown in fig. 4, during iteration 1, the marginal contribution analysis is reduced by the following amount: for a refining enterprise A, 1X 1 ten thousand tons of marginal contribution of processing resources to be allocated corresponding to less processing of 1 ten thousand tons of resources is obtained: 520; in the 2 nd iteration, the marginal contribution analysis is reduced by the following amount: 2×1 ten thousand tons, for the refining enterprise a, the marginal contribution of processing resources to be allocated corresponding to less processing of 2 ten thousand tons of resources is obtained: 530; in the 3 rd iteration, the marginal contribution analysis is reduced by the following amount: for a refining enterprise A, the marginal contribution of processing resources to be allocated corresponding to less processing of 3 ten thousand tons of resources is obtained: 550.

After the current marginal contribution is obtained, the next iteration can be performed based on the adjusted marginal contribution obtaining model. In the implementation process, n=n+1 can be made, an upper limit constraint equation and a lower limit constraint equation of a model A-n are obtained according to a formula (14) and a formula (15), then the model A-n is solved, and the marginal contribution of each refining enterprise corresponding to the marginal contribution analysis reduction number (the value is: the marginal contribution analysis step size is x n) is obtained until an abnormal result exists in the obtained resource allocation amount.

If an abnormal result exists in the resource allocation quantity, the set resource purchasing quantity is lower than the lower limit of the processing capacity of the refining enterprise, and the iteration is stopped.

At least one first marginal contribution data of the resources to be allocated processed by each of the plurality of refining enterprises can be obtained through the calculation.

In step S230, when the total amount of resources to be allocated changes, the resource allocation amount of each refining enterprise is adjusted according to the first marginal contribution of each refining enterprise under different resource variation amounts.

In a specific implementation process, the first marginal contribution data of the to-be-allocated resources processed by each of the plurality of refining enterprises may be summarized and ordered, so as to obtain a first marginal contribution summary table of the to-be-allocated resources processed by the plurality of refining enterprises as shown in fig. 4, a first marginal contribution ordering table of the to-be-allocated resources processed by the plurality of refining enterprises as shown in fig. 5 when the number of to-be-allocated resources increases, and a first marginal contribution ordering table of the to-be-allocated resources processed by the plurality of refining enterprises as shown in fig. 6 when the number of to-be-allocated resources decreases. From fig. 4 to 6, it is clear that the relative size of the first marginal contribution of the resources to be allocated is processed by each of the plurality of refining enterprises under different processing loads.

In the implementation process, the direct basis of the relative high load of the resources to be allocated processed by each refining enterprise can be obtained according to the analysis of the first marginal contribution data of the resources to be allocated processed by each refining enterprise in the plurality of refining enterprises to obtain the configuration optimization model. As shown in fig. 4, in the result of the optimal configuration of the production resources, the first marginal contribution sequence of the processing to-be-allocated resources of the refining enterprise is as follows: a refining enterprise A, a refining enterprise B, a refining enterprise C, a refining enterprise D, a refining enterprise E and a refining enterprise F.

In some embodiments, when the number of resources to be allocated provided to the plurality of refining enterprises increases or decreases from the preset provided number, the number of resources to be allocated provided to at least one of the plurality of refining enterprises may be increased or decreased according to the marginal contribution ranking of the plurality of refining enterprises to process the resources to be allocated as shown in fig. 4 to 6.

For example, if the number of resources offered by the resource provider is increased by 3 ten thousand tons compared to the expected number, ordered by the first marginal contribution shown in fig. 5, then each of the converting enterprise D, the converting enterprise a, and the converting enterprise E should be arranged to process 1 ten thousand tons more; if the number of resources offered by the resource provider is reduced by 2 ten thousand tons compared to the expected offered number, and ordered by the first marginal contribution shown in fig. 6, the enterprises E and D should be arranged to each be reduced by 1 ten thousand tons.

FIG. 3 is an exemplary flow chart of a method of obtaining a shadow price according to some embodiments of the application. As shown in fig. 3, the process 300 includes the following steps.

And step S310, adding constraint equations of a self-pin module and the self-pin submodule for each refining enterprise in the configuration optimization model to obtain an adjusted configuration optimization model.

The self-sales sub-module is used for determining the sales quantity of the factory products sold by using the preset price when the resource utilization rate is maximized, and the constraint equation is used for constraining the upper limit of the sales quantity of the factory products in the self-sales sub-module.

In the specific implementation process, a structure capable of selling the product i directly in the refining enterprises is set for each refining enterprise r, and the selling price can be set to be higher than the price a of other markets _ri (e.g., 10000 yuan/ton), the upper limit of sales is set to a smaller amount β (e.g., 1 ton).

The objective function of the configuration optimization model is changed into:

MAX ZP2＝ZP+∑ _r ∑ _i a _ri x _ri (16)

in formula (16), a _ri And x _ri The price and sales of the product i delivered by the refining enterprise r are respectively.

The production and marketing balance equation of the refining enterprise is changed from the formula (5):

u _ri ＝∑ _m z _rim x _ri (17)

constraint equation from pin module:

x _ri ≤α (18)

Since the value of α is small, the above modification has negligible effect on the calculation result of the original configuration optimization model.

And step S320, solving the adjusted configuration optimization model to obtain a second marginal contribution of the constraint equation of the self-marketing submodule.

In the specific implementation process, PICIO software may be applied to solve the configuration optimization model adjusted in step S310. The result obtained by solving contains the following information:

the resource allocation amount, i.e. the optimal amount of resources to be allocated to each refining enterprise r is configured from each resource provider n.

Constraint equation x _ri Second marginal contribution g of alpha _ri . Based on the linear programming theory, PICIO outputs the second marginal contribution of each constraint equation in the calculation result, and the mathematical meaning of the constraint equation is: if the right term of the constraint equation changes slightly, the slope of the model objective function value effect. For constraint equation x _ri Alpha, the second marginal contribution g _ri Meaning of (2): if the upper limit of the sales of the product i at the refining enterprise r is changed from alpha to alpha+delta (delta is a very small value), the slope of the influence on the objective function value is changed.

And step S330, calculating to obtain the shadow price of the factory product according to the preset price and the second marginal contribution of the constraint equation.

In some embodiments, the second marginal contribution of the constraint equation may be subtracted from the preset price to obtain the shadow price. Calculating a shadow price h of each refining enterprise r for supplying a factory product i _ri The formula of (2) is as follows:

h _ri ＝a _ri -g _ri (19)

for example only, if the price of r sales resources is 10000 yuan/ton per refining enterprise in the configuration optimization model, the constraint equation x is correspondingly defined _ri The marginal contribution of alpha is 2000 yuan/ton, and the shadow price of the sales resource of the refinery is: 10000-2000=8000 yuan/ton. The economic meaning is as follows: if resources are supplied to the downstream market at 8000 yuan/ton at the refinery, the downstream is just in balance.

Fig. 7 is an exemplary schematic diagram of an allocation adjustment device for resources to be allocated according to some embodiments of the present application.

As shown in fig. 7, the resource allocation apparatus includes: acquisition module 710, setup module 720, iteration module 730, and adjustment module 740.

The obtaining module 710 is configured to obtain, according to the configuration optimization model, a resource allocation amount of each refining enterprise and a shadow price of a factory product of each refining enterprise; the configuration optimization model is used for determining the resource allocation amount of each refining enterprise when the overall resource utilization rate is maximized;

The establishing module 720 is configured to establish a marginal contribution obtaining model corresponding to each refining enterprise according to the resource allocation amount of each refining enterprise and the shadow price of the factory product of each refining enterprise; the marginal contribution obtaining model is used for calculating first marginal contribution corresponding to resource allocation quantity of the refining enterprise;

the iteration module 730 is configured to iteratively adjust the resource allocation amount in the at least one marginal contribution obtaining model, and solve the adjusted marginal contribution obtaining model to obtain a first marginal contribution of the corresponding refining enterprise under different resource variation amounts; the first marginal contribution represents the influence degree of the resource allocation amount of the refining enterprise on the overall resource utilization rate when the resource variation amount changes;

the adjustment module 740 is configured to adjust the resource allocation amount of each refining enterprise according to the first marginal contribution of each refining enterprise under different resource variation amounts when the total amount of the resources to be allocated is changed.

In the above embodiment of the allocation adjustment device for resources to be allocated, specific processing of each module and technical effects brought by the same may refer to the related descriptions in the corresponding method embodiment, and are not described herein again.

Fig. 8 is an exemplary structural schematic diagram of an electronic device, according to some embodiments of the present application.

As shown in fig. 8, the electronic device includes: at least one processor 801, at least one communication interface 802, at least one memory 803, and at least one communication bus 804; alternatively, the communication interface 802 may be an interface of a communication module, such as an interface of a GSM module; the processor 801 may be a processor CPU or a specific integrated circuit ASIC (Application Specific Integrated Circuit) or one or more integrated circuits configured to implement embodiments of the present invention. The memory 803 may comprise a high-speed RAM memory or may further comprise a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory. The memory 803 stores a program, and the processor 801 calls the program stored in the memory 803 to execute some or all of the above-described method embodiments.

The present application relates to a storage device for storing a computer readable program which, when executed, performs some or all of the method embodiments described above.

While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations of the present application may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this application, and are therefore within the spirit and scope of the exemplary embodiments of this application.

Meanwhile, the present application uses specific words to describe embodiments of the present application. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present application. Thus, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this application are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present application may be combined as suitable.

Furthermore, the order in which the elements and sequences are presented, the use of numerical letters, or other designations are used in the application and are not intended to limit the order in which the processes and methods of the application are performed unless explicitly recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present application. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.

Likewise, it should be noted that in order to simplify the presentation disclosed herein and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the subject application. Indeed, less than all of the features of a single embodiment disclosed above.

In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the number allows for a 20% variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations that may be employed in some embodiments to confirm the breadth of the range, in particular embodiments, the setting of such numerical values is as precise as possible.

Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., cited in this application is hereby incorporated by reference in its entirety. Except for application history documents that are inconsistent or conflicting with the present application, documents that are currently or later attached to this application for which the broadest scope of the claims to the present application is limited. It is noted that the descriptions, definitions, and/or terms used in the subject matter of this application are subject to such descriptions, definitions, and/or terms if they are inconsistent or conflicting with such descriptions, definitions, and/or terms.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present application. Other variations are also possible within the scope of this application. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present application may be considered in keeping with the teachings of the present application. Accordingly, embodiments of the present application are not limited to only the embodiments explicitly described and depicted herein.

Claims (10)

1. A method for resource allocation, comprising:

obtaining the resource allocation amount of each refining enterprise and the shadow price of the factory product of each refining enterprise according to the configuration optimization model; the configuration optimization model is used for determining the resource allocation amount of each refining enterprise when the overall resource utilization rate is maximized;

Establishing a marginal contribution obtaining model corresponding to each refining enterprise according to the resource allocation amount of each refining enterprise and the shadow price of the factory product of each refining enterprise; the marginal contribution obtaining model is used for calculating first marginal contribution corresponding to resource allocation quantity of the refining enterprise;

iteratively adjusting the resource allocation amount in at least one marginal contribution obtaining model, and solving the adjusted marginal contribution obtaining model to obtain the first marginal contribution of the corresponding refining enterprise under different resource variation; the first marginal contribution represents the influence degree of the resource allocation amount of the refining enterprise on the overall resource utilization rate when the resource variation amount changes;

when the total amount of the resources to be allocated is changed, the resource allocation amount of each refining enterprise is adjusted according to the first marginal contribution of each refining enterprise under different resource variation amounts.

2. The method of claim 1, wherein the establishing a marginal contribution obtaining model corresponding to each refining enterprise according to the resource allocation amount of each refining enterprise and the shadow price of each factory product of each refining enterprise comprises:

taking the shadow price of the outgoing product of each refining enterprise as the outgoing price of the outgoing product of each refining enterprise;

Establishing a marginal contribution obtaining model corresponding to each refining enterprise according to the difference value between the resource allocation quantity of each refining enterprise and the preset fine adjustment quantity and the delivery price of the delivery product of each refining enterprise; the difference value between the resource allocation amount of each refining enterprise and the preset fine adjustment amount is used as the marginal contribution corresponding to each refining enterprise to obtain the resource allocation amount in the model.

3. The method of claim 1, wherein obtaining the shadow prices for the factory products of each refining enterprise according to the configuration optimization model comprises:

adding constraint equations of a self-pin module and the self-pin submodule for each refining enterprise in the configuration optimization model to obtain an adjusted configuration optimization model; the self-sales sub-module is used for determining the sales quantity of the factory products sold by using the preset price when the resource utilization rate is maximized, and the constraint equation is used for constraining the upper limit of the sales quantity of the factory products in the self-sales sub-module;

solving the adjusted configuration optimization model to obtain a second marginal contribution of a constraint equation of the self-marketing submodule;

and calculating to obtain the shadow price of the factory product according to the preset price and the second marginal contribution of the constraint equation.

4. The method of claim 1, wherein iteratively adjusting the resource allocation amount in the at least one marginal contribution acquisition model and solving the adjusted marginal contribution acquisition model to obtain a first marginal contribution of the corresponding refined enterprise under different resource variation amounts comprises:

aiming at each marginal contribution obtaining model in the at least one marginal contribution obtaining model, respectively adjusting an upper limit in an upper limit constraint equation and a lower limit in a lower limit constraint equation of the marginal contribution obtaining model according to a preset step length to obtain an adjusted marginal contribution obtaining model;

solving the adjusted marginal contribution obtaining model to obtain the adjusted resource allocation amount of the corresponding refining enterprise and the fourth marginal contribution of the upper limit constraint equation and the lower limit constraint equation of the marginal contribution obtaining model;

if the adjusted resource allocation amount is not abnormal, adding a third marginal contribution of an upper limit constraint equation and a fourth marginal contribution of a lower limit constraint equation in the marginal contribution obtaining model to obtain the first marginal contribution of the corresponding refining enterprise under the current adjusted resource variation amount, and executing the next iteration; wherein the resource variation is the product of the step length and the iteration number;

And if the adjusted resource allocation amount is abnormal, stopping iteration.

5. The method of claim 4, wherein the solving the adjusted marginal contribution obtaining model to obtain the adjusted resource allocation amount of the corresponding refining enterprise further comprises:

if the adjusted resource allocation amount is within the preset resource threshold range of the refining enterprise, judging that the adjusted resource allocation amount is not abnormal; otherwise, judging that the adjusted resource allocation amount is abnormal.

6. The method according to any one of claims 1 to 5, further comprising:

establishing a production plan sub-model of each refining enterprise according to the resource use data of each refining enterprise; wherein the production plan sub-model of the refining enterprise is used for determining the resource allocation amount of the refining enterprise when the resource utilization rate of the refining enterprise is maximized;

and establishing the configuration optimization model according to the production plan sub-model of each refining enterprise, the transportation network for transporting resources to each refining enterprise and the sales network of the outgoing products of each refining enterprise.

7. A resource allocation apparatus, the apparatus comprising:

The acquisition module is used for acquiring the resource allocation amount of each refining enterprise and the shadow price of the factory product of each refining enterprise according to the configuration optimization model; the configuration optimization model is used for determining the resource allocation amount of each refining enterprise when the overall resource utilization rate is maximized;

the establishing module is used for establishing a marginal contribution obtaining model corresponding to each refining enterprise according to the resource allocation amount of each refining enterprise and the shadow price of the factory product of each refining enterprise; the marginal contribution obtaining model is used for calculating first marginal contribution corresponding to resource allocation quantity of the refining enterprise;

the iteration module is used for iteratively adjusting the resource allocation amount in the at least one marginal contribution obtaining model, and solving the adjusted marginal contribution obtaining model to obtain the first marginal contribution of the corresponding refining enterprise under different resource variation; the first marginal contribution represents the influence degree of the resource allocation amount of the refining enterprise on the overall resource utilization rate when the resource variation amount changes;

and the adjusting module is used for adjusting the resource allocation quantity of each refining enterprise according to the first marginal contribution of each refining enterprise under different resource variation when the total quantity of the resources to be allocated is changed.

8. The apparatus of claim 7, wherein the device comprises a plurality of sensors,

the building module is specifically configured to take a shadow price of a factory product of each refining enterprise as a factory price of the factory product of each refining enterprise;

the establishing module is specifically configured to establish a marginal contribution obtaining model corresponding to each refining enterprise according to a difference value between the resource allocation amount of each refining enterprise and the preset fine adjustment amount and a factory price of a factory product of each refining enterprise; the difference value between the resource allocation amount of each refining enterprise and the preset fine adjustment amount is used as the marginal contribution corresponding to each refining enterprise to obtain the resource allocation amount in the model.

9. An electronic device comprising a memory storing a computer program and a processor that when executing the program performs the method of any one of claims 1 to 6.

10. A storage device for storing a computer readable program which, when executed, performs the method of any of claims 1 to 6.