A many-to-many resource intelligent allocation method, device, medium and product

Abstract

The application discloses a many-to-many resource intelligent allocation method, device, medium and product, and relates to the field of resource allocation. The method comprises the following steps: determining the matching degree of resources to targets; determining the dynamic matching degree of many-to-many resources from a statistical point of view based on the matching degree; performing priority sorting on resource target allocation based on the dynamic matching degree to obtain a dynamic sorting strategy; constructing a target function based on the matching degree of resources to targets and the dynamic matching degree; performing migration allocation on resources by using a biogeography-based optimization algorithm to obtain an allocation result, regarding the allocation result as a habitat; in each migration allocation process, determining a fitness index of the habitat generated by using the target function, and until an iteration termination condition is reached, taking the habitat corresponding to the maximum fitness index as an optimal allocation result, so as to complete intelligent allocation of many-to-many resources. The application can dynamically, quickly and intelligently allocate multiple types of resources to multiple types of targets, and realize global optimization of the allocation effect.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of resource allocation, and particularly relates to a many-to-many resource intelligent allocation method, device, medium and product. BACKGROUND

[0002] With the development of technologies such as bee colony, many-to-many game technology is increasingly valued. Resource allocation is a key link of many-to-many game, and efficient and accurate resource allocation can help achieve the optimal result. In the resource allocation process, the multiple types of resources of the party A and the multiple types of targets of the party B need to be considered, the matching degree of different resource-target combinations needs to be accurately described, and the global optimal allocation strategy search needs to be implemented. Especially under the condition of strong time constraint, it is crucial to realize the many-to-many resource allocation quickly.

[0003] Now there is no relevant research on the dynamic matching degree of many-to-many resource allocation and the many-to-many fast allocation strategy, and there is no corresponding research on how to dynamically, quickly and intelligently allocate multiple types of resources to multiple types of targets and achieve the global optimal allocation effect. SUMMARY

[0004] The purpose of the present application is to provide a many-to-many resource intelligent allocation method, device, medium and product, which can dynamically, quickly and intelligently allocate multiple types of resources to multiple types of targets and achieve the global optimal allocation effect.

[0005] To achieve the above purpose, the present application provides the following solutions:

[0006] In a first aspect, the present application provides a many-to-many resource intelligent allocation method, comprising:

[0007] determining the matching degree of resources to targets;

[0008] determining the dynamic matching degree of different resources and targets based on the matching degree of resources to targets from a statistical point of view, to obtain the dynamic matching degree of many-to-many resources;

[0009] performing priority sorting on resource-target allocation based on the dynamic matching degree, to obtain a dynamic sorting strategy;

[0010] constructing a target function based on the matching degree of resources to targets and the dynamic matching degree;

[0011] adopting a biogeography-based optimization algorithm to perform migration allocation on resources to obtain allocation results, regarding each allocation result as a habitat;

[0012] In each migration allocation process, the target function is used to determine the fitness index of the habitat generated, until the iteration termination condition is reached, the habitat corresponding to the maximum fitness index is taken as the optimal allocation result, to complete the intelligent allocation of many-to-many resources.

[0013] Optionally, the matching degrees of different resources and targets are determined from a statistical perspective based on the matching degrees of resources to targets, and the dynamic matching degrees of multiple-to-multiple resources are obtained, specifically including:

[0014] selecting a target with the least number of optional resources;

[0015] when the number of optional resources and the number of mandatory resources of the target are the same and are 1, determining that the dynamic matching degree is 1;

[0016] when the number of optional resources of the target is greater than 1, selecting an optional resource corresponding to the maximum resource matching degree, and determining that the dynamic matching degree of the optional resource corresponding to the maximum resource matching degree is r(i) is the number of optional resources of the current target i;

[0017] when the number of optional resources of the target is 0, determining that the dynamic matching degree is 0;

[0018] deleting the optional resource corresponding to the maximum resource matching degree and the target, and returning to "selecting a target with the least number of optional resources", until all resource-target combination modes are traversed, and the dynamic matching degrees of multiple-to-multiple resources are obtained.

[0019] Optionally, the resource matching degree of each resource-target combination mode is represented as:

[0020]

[0021] In the formula, p i,j is the resource matching degree, when p i,j ∈(0, 1), the corresponding resource is an optional resource; the related degree in the formula is determined based on a set correlation threshold.

[0022] Optionally, the dynamic sorting strategy is represented as:

[0023] P(temp, i) = (i, j);

[0024] In the formula, P(temp, i) is the dynamic sorting strategy, temp is a temporary quantity, i is a target serial number, and j is a resource serial number.

[0025] Optionally, a target function obtained based on the matching degrees of resources to targets and the dynamic matching degrees is represented as:

[0026]

[0027] In the formula, f represents a total benefit value under a current resource allocation strategy; x ij is a decision variable, representing whether a resource r j is allocated to a target ti , 0 if no, 1 if yes; p j is a dynamic matching degree of resource r j ; p ij is a matching degree of resource r j to target t i , n represents the number of targets, and m represents the number of resources.

[0028] Optionally, the resource is allocated by using a biogeography-based optimization algorithm to obtain an allocation result, each allocation result is regarded as a habitat, and the allocation result is obtained by allocating the resource to the target according to the numerical correspondence, and each allocation result is regarded as a habitat.

[0029] The resource is regarded as a species, and the species is allocated to the target according to the numerical correspondence to obtain an allocation result, and each allocation result is regarded as a habitat.

[0030] The migration direction of the species is guided in combination with a dynamic sorting strategy, and mutation is generated to promote the migration of the species between different habitats until convergence is reached, the migration of the species is completed, and the final habitat is obtained.

[0031] Optionally, the mutation probability of generating mutation is represented as:

[0032]

[0033] In the formula, P s,i is a probability that the number of species of habitat i is s, P s,i (t) is a probability that the number of species of habitat i is s in the t-1th migration allocation, P s,i (t-1) is a probability that the number of species of habitat i is s in the t-1th migration allocation, is a derivative of the probability P s,i , M max () is a maximum value, and P max is a probability that the current habitat has the most species.

[0034] In a second aspect, the present application provides a computer device, comprising: a memory, a processor, a computer program stored on the memory and executable on the processor, and the processor executes the computer program to implement the steps of the multi-to-multi resource intelligent allocation method in any one of the above.

[0035] In a third aspect, the present application provides a computer readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the steps of the multi-to-multi resource intelligent allocation method in any one of the above.

[0036] In a fourth aspect, the present application provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the multi-to-multi resource intelligent allocation method of any one of the above.

[0037] According to the specific embodiments provided in the present application, the present application discloses the following technical effects:

[0038] The present application provides a multi-to-multi resource intelligent allocation method, device, medium and product. Different dynamic matching degrees of multi-to-multi resources are determined according to different interference abilities of different interference resources to different targets, so as to obtain a dynamic sorting strategy. In the optimization allocation solving process of obtaining an allocation result by migrating and allocating resources based on a biogeography optimization algorithm, the dynamic sorting strategy is combined to guide the allocation direction of the resources, which can reduce unnecessary search processes and improve the convergence speed of the algorithm. Moreover, by introducing the dynamic matching degree and the dynamic sorting strategy, the biogeography optimization algorithm is prevented from falling into a local optimum too early. The maximum fitness index of a habitat is determined by constructing a target function, so as to obtain an optimal allocation result. The global optimum of the allocation effect is realized, the loss of advantage information in the search process is reduced, the convergence speed of the algorithm is effectively improved, and then the multi-type resources can be dynamically, quickly and intelligently allocated to multi-type targets. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0040] Figure 1 An application environment diagram of a multi-to-multi resource intelligent allocation method in an embodiment of the present application;

[0041] Figure 2 A flowchart of a multi-to-multi resource intelligent allocation method provided in an embodiment of the present application;

[0042] Figure 3 An implementation architecture diagram of a multi-to-multi resource intelligent allocation method provided in an embodiment of the present application;

[0043] Figure 4 A structural diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] With reference to the drawings and embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present application.

[0045] The above purposes, features and advantages of the present application will be more apparent and understandable. The present application will be further described in detail below with reference to the drawings and specific embodiments.

[0046] The many-to-many resource intelligent allocation method provided by the embodiments of the present application can be applied to an application environment as shown in the figure. Figure 1 The terminal 102 communicates with the server 104 through the network. The data storage system can store the data required to be processed by the server 104. The data storage system can be separately arranged, or integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the to-be-allocated resource and target to the server 104. After receiving the to-be-allocated resource and target, the server 104 determines the matching degree of the resource to the target for the to-be-allocated resource and target. Based on this matching degree, the dynamic matching degree of the many-to-many resource is determined from a statistical point of view. Based on the dynamic matching degree, the resource target allocation is prioritized to obtain a dynamic sorting strategy. Based on the matching degree of the resource to the target and the dynamic matching degree, a target function is constructed. The biological geographical optimization algorithm is used to migrate and allocate the resource to obtain an allocation result, and the allocation result is regarded as a habitat. In each migration and allocation process, the target function is used to determine the fitness index of the habitat generated, until the iteration termination condition is reached, the habitat corresponding to the maximum fitness index is taken as the optimal allocation result, so as to complete the intelligent allocation of the many-to-many resource. The server 104 can feed back the obtained intelligent allocation result of the many-to-many resource to the terminal 102. In addition, in some embodiments, the many-to-many resource intelligent allocation method can also be realized by the server 104 or the terminal 102 alone, such as the terminal 102 can directly perform intelligent allocation for the to-be-allocated resource and target, or the server 104 can obtain the to-be-allocated resource and target from the data storage system and perform intelligent allocation for the to-be-allocated resource and target.

[0047] The terminal 102 can be, but is not limited to, various desktop computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things device can be a smart speaker, a smart television, a smart air conditioner, a smart vehicle device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The server 104 can be realized by an independent server or a server cluster composed of multiple servers, and can also be a cloud server.

[0048] In an exemplary embodiment, as shown in Figure 2 A multi-to-multi resource intelligent allocation method is provided, which is executed by a computer device, specifically, by a terminal or a server or the like computer device alone or by a terminal and a server together. In the embodiments of the present application, the method is applied to the server 104 in the system 100. Figure 1 The method includes the following steps 201 to 206. Specifically, the steps are as follows.

[0049] Step 201, determining the matching degree of resources to targets.

[0050] Step 202, determining the dynamic matching degree of different resources to targets from a statistical point of view based on the matching degree of resources to targets, to obtain the dynamic matching degree of multi-to-multi resources.

[0051] Step 203, prioritizing the resource-target allocation based on the dynamic matching degree, to obtain a dynamic sorting strategy.

[0052] Step 204, constructing a target function based on the matching degree of resources to targets and the dynamic matching degree.

[0053] Step 205, migrating and allocating resources based on the biogeography-based optimization algorithm to obtain allocation results, regarding each allocation result as a habitat.

[0054] Step 206, in each migration and allocation process, determining the fitness index of the habitat generated by the target function, until the iteration termination condition is reached, taking the habitat corresponding to the maximum fitness index as the optimal allocation result, to complete the intelligent allocation of multi-to-multi resources.

[0055] By implementing the steps 201 to 206, the present application determines the dynamic matching degree of multi-to-multi resources according to the different interference abilities of different interference resources to different targets, to obtain a dynamic sorting strategy. In the optimization allocation solving process of migrating and allocating resources based on the biogeography-based optimization algorithm to obtain allocation results, the dynamic sorting strategy is combined to guide the allocation direction of resources, which can reduce unnecessary search processes and improve the convergence speed of the algorithm. Moreover, by introducing the dynamic matching degree and the dynamic sorting strategy, the biogeography-based optimization algorithm is prevented from falling into local optimum too early. The maximum fitness index of the habitat generated by the target function is determined to obtain the optimal allocation result, which realizes the global optimum of the allocation effect, reduces the loss of advantage information in the search process, effectively improves the convergence speed of the algorithm, and further dynamically, quickly and intelligently allocates multi-type resources to multi-type targets.

[0056] In another exemplary embodiment of the present application, since there are a large number of different types of resources and targets, the matching degree calculation methods are different. The present application focuses on dynamic matching degree calculation and global optimal result search under the condition of known resource matching degree, and therefore only the resource matching degree is standardized. Based on this, in step 201, the resource r j The matching degree p i of the target t i,j may be defined as:

[0057]

[0058] In the formula, the numerical interval is left closed and right open. p i,j is the resource matching degree, and when p i,j ∈(0, 1), the corresponding resource is the optional resource. The correlation degree in the formula is determined based on the set correlation threshold.

[0059] In another exemplary embodiment of the present application, the dynamic matching degree p j between different resources and targets can be measured from a statistical perspective, and based on this, the dynamic matching degree p of multiple-to-multiple resources is defined as:

[0060]

[0061] In the formula, r(i) is the number of optional resources of the current target i.

[0062] Based on the above formula, in the actual application process, the determination process of the dynamic matching degree of multiple-to-multiple resources can be described as:

[0063] Step 1: initialize the temporary variable temp, temp = 1.

[0064] Step 2: select the target t i with the least number of optional resources. If there are multiple targets with the same matching degree and the least number of optional resources, one of them is selected.

[0065] Step 3: when the number of optional resources and the number of mandatory resources are the same and are 1, then p j = 1.

[0066] Step 4: when there are multiple optional resources, select one with the maximum matching degree r j , and the dynamic matching

[0067] Step 5: delete the resource r j and the target t i , delete the selected combination mode, let temp' = temp + 1 and return to step 1 to calculate the remaining combination modes.

[0068] This process continues until all resources are deleted. j Or target t i If a locally optimal combination is found, the dynamic matching degree of the current locally optimal combination is obtained.

[0069] In another exemplary embodiment of this application, by calculating the dynamic matching degree, a corresponding priority ranking can be generated for resource target allocation. This application refers to this priority ranking result as a dynamic ranking strategy. During the dynamic matching degree calculation process, the resource r in the k-th cycle... j If the dynamic matching degree is Then in the current loop, resource r j The dynamic sorting strategy is: P(temp,i)=(i,j), where P(temp,i) is the dynamic sorting strategy, temp≤i, i is the target sequence number, and j is the resource sequence number.

[0070] In another exemplary embodiment of this application, with the goal of achieving the maximum total allocation benefit through the optimal resource allocation strategy, the objective function constructed in step 204 can be expressed as:

[0071]

[0072] In the formula, f represents the total benefit value under the current resource allocation strategy. ij Let r be the decision variable. j Is it assigned to target t? i ρ is 0 if it is not true, and 1 if it is true. j For resource r j The dynamic matching degree. ij For resource r j For target t i The matching degree is given by n, where n represents the number of targets and m represents the number of resources.

[0073] In another exemplary embodiment of this application, a heuristic intelligent algorithm can be used to solve the above-mentioned optimization problem. Based on this, this application proposes a biogeography-based optimization (BBO) algorithm in step 205. This algorithm designs a step-by-step optimization algorithm to achieve rapid allocation of resource targets. Based on this, the implementation process of using the biogeography-based optimization algorithm to migrate and allocate resources to obtain allocation results in step 205 can be as follows:

[0074] 1) Treat resources as species, allocate species to the target according to numerical correspondence to obtain allocation results, and regard each allocation result as a habitat.

[0075] 2) Combined with the dynamic ranking strategy to guide the migration direction of species, and promote the migration of species between different habitats by generating mutations until convergence is reached, complete the migration of species, and get the final habitat.

[0076] In practical application, the main process of using biogeography-based optimization algorithm to allocate resources to obtain allocation results contains the following three parts:

[0077] A) Initialization: Under the premise of m resources and n targets, randomly generate several n-dimensional allocation results, each dimension represents the allocation of the resource represented by its value to the target of the current dimension number. Each allocation result is regarded as an independent habitat, and each resource is regarded as a species. The habitat suitability index (HSI) is determined according to the established objective function, which represents the degree of excellence of the allocation result, wherein the habitat suitability index is mainly determined based on the total benefit value under the current resource allocation strategy. The habitat suitability index variable (SIV) is randomly generated, which represents a set of external factors that can affect the HSI, such as weather, vegetation, etc. Sort the habitats according to HSI, and design the number of species S that each habitat can contain.

[0078] B) Species migration: Species can migrate between habitats to exchange information. Based on this, combined with the dynamic ranking strategy to guide the migration direction of species. The calculation method of immigration rate λ, emigration rate μ and migration operation is:

[0079]

[0080] x i,j ′=α·x i,j +(1-α)x i,j

[0081] Where I and E are the maximum values of immigration rate and emigration rate, S is the number of species that each habitat can contain, S max is the maximum number of species that can coexist in the habitat, x i,j is the j-th dimension of the habitat x i 's suitability index variable, x i,j ' is the j-th dimension of the updated habitat x i 's suitability index variable.

[0082] C) Species variation: Promote the migration of species between different habitats by generating mutations, the mutation probability M s,i and the calculation method of mutation operation are as follows:

[0083]

[0084] x i,j ′=x i,j +d i,j

[0085] In the formula, P s,i Let be the probability that the number of species in habitat i is s, and t represent the t-th iteration. For P s,i The corresponding derivative, M max () represents the maximum value, P max d represents the probability of having the most species in the current habitat. i,j For x i,j The current degree of mutation, λ i Let μ be the migration rate of habitat i. i μ represents the emigration rate of habitat i. i+1 P represents the emigration rate of habitat i+1. s,i+1 Let λ be the probability that the number of species in habitat i+1 is s. i-1 P represents the migration rate to habitat i-1. s,i-1 Let S be the probability that the number of species in habitat i-1 is s. i P represents the number of species in habitat i. s,i P(t) represents the probability that the number of species in habitat i is s in the (t-1)th migration allocation. s,i (t-1) represents the probability that the number of species in habitat i is s in the (t-1)th migration allocation.

[0086] By highlighting randomness through the above mutation methods, the global search capability of the algorithm can be improved.

[0087] Through the three steps A)-C) described above, the proposed heuristic intelligent algorithm can efficiently and accurately solve the resource allocation problem proposed in this invention. During the algorithm's evolution, starting with a random population leads to numerous trial searches in the early stages, resulting in slow convergence. Therefore, combining dynamic sorting strategies in the early stages of algorithm evolution to guide its search direction reduces unnecessary search processes and improves convergence speed. Introducing dynamic matching degree and dynamic sorting strategies prevents the algorithm from prematurely falling into "local optima." Employing an elite retention strategy to screen the elite population (i.e., the optimal allocation result) during the evolution process reduces the loss of advantageous information during the search process, effectively improving the algorithm's convergence speed. Based on this, the entire implementation process of the many-to-many intelligent resource allocation method provided in this application can be found in [reference needed]. Figure 3The method proposes a dynamic matching degree of multiple interference resources according to different target interference capabilities of different interference resources, and the matching degree between different resource-target pairs can be calculated according to the resource and target types. In combination with the optimization allocation solving process, a multi-to-multi fast allocation strategy is proposed to efficiently and accurately realize the resource fast allocation under the multi-to-multi condition, and then facilitate the resource fast and intelligent allocation in the multi-to-multi game process. Figure 3 V(tr,n) = P(temp) = x i,j , represents the j-dimensional SIV of the habitat xi in the trth generation population. temp' represents the updated temporary variable.

[0088] The application further provides an application scenario of the multi-to-multi resource intelligent allocation method. Specifically, the multi-to-multi resource intelligent allocation method can be applied in a content distribution scenario. The content distribution scenario includes a content production link, a content processing link and a content distribution link. The resources and targets enter the content processing link from the content production link, obtain the corresponding allocation result through human-computer cooperation, and enter the downstream content distribution link. The multi-to-multi resource intelligent allocation method belongs to the intelligent classification link in the content processing link. Specifically, in the content processing link of the resources, the resources can be allocated to the corresponding targets based on the cooperation of machine allocation and manual allocation.

[0089] In an exemplary embodiment, a computer device, which can be a server or a terminal, is provided, and an internal structure diagram of the computer device can be as shown in Figure 4 The computer device includes a processor, a memory, an input / output interface (I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store video tag processing data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement a multi-to-multi resource intelligent allocation method.

[0090] Those skilled in the art can understand, Figure 4The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0091] In an exemplary embodiment, a computer device is also provided, including a memory and a processor, the memory storing a computer program, and the processor implementing the steps in the above method embodiments when executing the computer program.

[0092] In an exemplary embodiment, a computer readable storage medium is provided, storing a computer program, and the computer program implements the steps in the above method embodiments when executed by a processor.

[0093] In an exemplary embodiment, a computer program product is provided, including a computer program, and the computer program implements the steps in the above method embodiments when executed by a processor.

[0094] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0095] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, databases or other media used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0096] The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a blockchain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0097] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combinations of the technical features do not exist, they should be considered as the scope of the present application.

[0098] The principles and implementation modes of the present application are described by applying specific examples herein. The above description of the embodiments is only used to help understand the method and its core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range can be changed. In conclusion, the content of the present application should not be understood as a limitation.

Claims

1. A method for intelligent allocation of many-to-many resources, characterized in that, The many-to-many intelligent resource allocation method includes: Determine the degree of matching between resources and objectives; Based on the resource-target matching degree, the dynamic matching degree between different resources and targets is determined from a statistical perspective to obtain the dynamic matching degree of many-to-many resources. This includes: selecting the target with the fewest optional resources; when the number of optional resources and the number of required resources of the target are the same and are 1, the dynamic matching degree is determined to be 1; when the number of optional resources of the target is greater than 1, the optional resource corresponding to the maximum resource matching degree is selected, and the dynamic matching degree of the optional resource corresponding to the maximum resource matching degree is determined to be 1. ; For the current goal i The number of optional resources; when the number of optional resources for the target is 0, the dynamic matching degree is determined to be 0; the optional resources corresponding to the maximum resource matching degree and the target are deleted, and "select the target with the fewest optional resources" is returned, until all resource target combination methods are traversed to obtain the dynamic matching degree of many-to-many resources; Based on the dynamic matching degree, the resource target allocation is prioritized to obtain a dynamic ranking strategy; the dynamic ranking strategy is expressed as follows: ； In the formula, It is a dynamic sorting strategy. temp It's a temporary quantity. i For the target sequence number, j For resource serial number; An objective function is constructed based on the matching degree of resources to the target and the dynamic matching degree; the objective function is expressed as: ； In the formula, This represents the total benefit value under the current resource allocation strategy; For decision variables, representing resources Assign to target If not, it is 0; if yes, it is 1. For resources Dynamic matching degree; For resources For the target The degree of matching, n Indicates the number of targets. m Indicates the number of resources; A biogeographical optimization algorithm is used to migrate and allocate resources to obtain allocation results. Each allocation result is regarded as a habitat. This includes: treating resources as species and allocating species to the target according to numerical correspondence to obtain allocation results, with each allocation result regarded as a habitat; combining a dynamic sorting strategy to guide the migration direction of species, and promoting species migration between different habitats by generating mutations until convergence is reached, thus completing the species migration and obtaining the final habitat. In each migration and allocation process, the objective function is used to determine the suitability index of the generated habitat. When the iteration termination condition is reached, the habitat corresponding to the maximum suitability index is taken as the optimal allocation result to complete the intelligent allocation of many-to-many resources.

2. The many-to-many intelligent resource allocation method according to claim 1, characterized in that, The resource matching degree of each resource target combination method is expressed as: ； In the formula, For resource matching degree, when When the corresponding resource is selected, it is considered as an optional resource; the degree of relevance in the formula is determined based on the set relevance threshold.

3. The many-to-many intelligent resource allocation method according to claim 1, characterized in that, The mutation probability that produces a mutation is expressed as: ； In the formula, habitat i The number of species is s The probability, , For the first t In secondary migration and allocation, habitat i The number of species is s The probability, For the first t -1 migration allocation, habitat i The number of species is s The probability, For probability The derivative of M max () represents the maximum value. This represents the probability of having the most species in the current habitat.

4. A computer device, comprising: The memory and processor contain a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the many-to-many resource intelligent allocation method according to any one of claims 1-3.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the many-to-many resource intelligent allocation method as described in any one of claims 1-3.

6. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the many-to-many resource intelligent allocation method as described in any one of claims 1-3.

Images