Site selection method and device for distribution center

Abstract

The invention discloses a site selection method and device for a distribution center. A specific embodiment of the method comprises the following steps: determining a network point set comprising all service network points in a target area, and a candidate distribution center set comprising all candidate distribution centers in the target area; determining a plurality of target functions representing a target distribution center which is determined from the candidate distribution center set and carries out logistics distribution for the service network points in the network point set; and determining a target distribution center from the candidate distribution center set by adopting a plurality of target functions according to the coded data of the candidate distribution centers in the candidate distribution center set. The problem that an existing algorithm seriously depends on expert experience is solved, and the accuracy of the determined target distribution center is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, specifically to logistics and distribution technology, and in particular to a method, device, computer-readable medium and electronic device for site selection of a distribution center. Background Art

[0002] In the logistics system, distribution is a key link and plays a vital role in the entire logistics network. The location and number of distribution centers have a great impact on the timeliness of logistics distribution and the investment cost of enterprises. At present, distribution centers are generally determined based on algorithms such as AHP (Analytic Hierarchy Process), but in such algorithms, human factors dominate and rely heavily on expert experience, resulting in low accuracy of the distribution centers determined. Summary of the invention

[0003] The embodiments of the present application provide a method, device, computer-readable medium and electronic device for site selection of a distribution center.

[0004] In a first aspect, an embodiment of the present application provides a method for selecting a distribution center, including: determining a network point set and a candidate distribution center set, wherein the network point set includes all service network points in a target area, and the candidate distribution center set includes all candidate distribution centers in the target area; determining multiple objective functions, wherein the multiple objective functions are used to determine, from the candidate distribution center set, a target distribution center for logistics distribution for the service network points in the network point set; and determining the target distribution center from the candidate distribution center set using multiple objective functions based on the coding data of the candidate distribution centers in the candidate distribution center set.

[0005] In some examples, the above-mentioned method of determining a target distribution center from the set of candidate distribution centers using multiple objective functions based on the encoding data of the candidate distribution centers in the set of candidate distribution centers includes: iteratively executing the following genetic operations until a preset end condition is reached to determine the target distribution center from the set of candidate distribution centers: merging the parent population and the child population corresponding to this genetic operation to obtain a merged population, wherein the parent population and the child population corresponding to the first genetic operation are generated based on the encoding data of the candidate distribution centers in the set of candidate distribution centers; determining the parent population corresponding to the next genetic operation from the merged population according to the multiple objective functions; and performing selection, crossover and mutation operations based on the parent population corresponding to the next genetic operation to obtain a child population corresponding to the next genetic operation.

[0006] In some examples, the above-mentioned determining the parent population corresponding to the next genetic operation from the merged population based on multiple objective functions includes: performing non-dominated sorting on the candidate distribution centers in the merged population according to the multiple objective functions to obtain multiple non-dominated sorting layers, and determining the congestion of the candidate distribution centers in the multiple non-dominated sorting layers; determining the parent population corresponding to the next genetic operation from the merged population based on the multiple non-dominated sorting layers and the congestion, and determining the fitness of the candidate distribution centers in the parent population corresponding to the next genetic operation.

[0007] In some examples, the above-mentioned selection operation, crossover operation and mutation operation are performed based on the parent population corresponding to the next genetic operation to obtain a sub-population corresponding to the next genetic operation, including: performing a selection operation on the parent population corresponding to the next genetic operation according to the fitness of the candidate distribution centers in the parent population corresponding to the next genetic operation, and determining multiple target candidate distribution centers from the parent population corresponding to the next genetic operation; performing a crossover operation on the multiple target candidate distribution centers to obtain multiple crossover distribution centers; performing a mutation operation on the multiple crossover distribution centers to obtain a sub-population corresponding to the next genetic operation.

[0008] In some examples, the above-mentioned performing a selection operation on the parent population corresponding to the next genetic operation according to the fitness of the candidate distribution centers in the parent population corresponding to the next genetic operation, and determining multiple target candidate distribution centers from the parent population corresponding to the next genetic operation, includes: performing selection operations on the parent population corresponding to the next genetic operation in parallel according to the fitness of the candidate distribution centers in the parent population corresponding to the next genetic operation through multiple selection threads for performing selection operations, and determining multiple target candidate distribution centers from the parent population corresponding to the next genetic operation.

[0009] In some examples, performing the cross operation on the multiple target candidate distribution centers to obtain the multiple cross distribution centers includes: performing the cross operation on the multiple target candidate distribution centers in parallel through multiple cross threads for performing the cross operation to obtain the multiple cross distribution centers.

[0010] In some examples, performing mutation operations on multiple cross-distribution centers to obtain a subpopulation corresponding to the next genetic operation includes: performing mutation operations on multiple cross-distribution centers in parallel through multiple mutation threads for performing mutation operations to obtain a subpopulation corresponding to the next genetic operation.

[0011] In some examples, the non-dominated sorting of the candidate distribution centers in the merged population according to the multiple objective functions to obtain multiple non-dominated sorting layers includes: for each candidate distribution center in the merged population, determining the domination quantity of other candidate distribution centers that dominate the candidate distribution center and the domination set including other candidate distribution centers dominated by the candidate distribution center according to the multiple objective functions; iteratively performing the following non-dominated sorting operation on the merged population: combining the candidate distribution centers with zero domination quantity in the to-be-sorted population corresponding to the current non-dominated sorting operation into a non-dominated sorting layer, wherein the to-be-sorted population corresponding to the first non-dominated sorting operation is the merged population, and the level corresponding to the non-dominated sorting layer is positively correlated with the order corresponding to the current non-dominated sorting operation; for each candidate distribution center in the non-dominated sorting layer, reducing the domination quantity corresponding to each candidate distribution center in the domination set corresponding to the candidate distribution center by one; removing the candidate distribution centers belonging to the non-dominated sorting layer from the merged population to obtain the to-be-sorted population corresponding to the next non-dominated sorting operation.

[0012] In some examples, the above-mentioned determining the congestion degree of the candidate distribution centers in the multiple non-dominated sorting layers includes: for each non-dominated sorting layer in the multiple non-dominated sorting layers and each objective function in the multiple objective functions, performing the following congestion calculation operation: determining the function value of the candidate distribution centers in the non-dominated sorting layer corresponding to the objective function, and sorting the candidate distribution centers in the non-dominated sorting layer according to the function value; for each candidate distribution center in the non-dominated sorting layer, determining the sub-congestion degree of the candidate distribution center corresponding to the objective function according to the function value of the previous candidate distribution center, the function value of the next candidate distribution center, the maximum function value and the minimum function value, and combining the congestion degree obtained by accumulating the sub-congestions of the candidate distribution center corresponding to other objective functions up to the last congestion calculation operation, to obtain the congestion degree of the candidate distribution center in this congestion calculation operation.

[0013] In some examples, the above-mentioned determination of the fitness of the candidate distribution center in the parent population corresponding to the next genetic operation includes: for the candidate distribution center in each non-dominated sorting layer in the parent population corresponding to the next genetic operation, performing the following fitness calculation operations: determining the Euclidean distance between the candidate distribution center and other candidate distribution centers in the non-dominated sorting layer to which the candidate distribution center belongs; determining the sharing function value between the candidate distribution center and other candidate distribution centers in the non-dominated sorting layer to which the candidate distribution center belongs based on the sharing function and the Euclidean distance, wherein the sharing function is used to characterize the degree of close relationship between two candidate distribution centers in the population; determining the number of microhabitats corresponding to the candidate distribution center based on the sharing function value; determining the fitness of the candidate distribution center based on the number of microhabitats and the virtual fitness, wherein the virtual fitness is negatively correlated with the level corresponding to the non-dominated sorting layer to which the candidate distribution center belongs.

[0014] In some examples, the preset termination condition is that the number of iterations exceeds a preset threshold, and / or the difference between the fitness corresponding to the subpopulation determined by the current genetic operation and the fitness corresponding to the subpopulation determined by the previous genetic operation is less than a preset difference threshold.

[0015] In a second aspect, an embodiment of the present application provides a site selection device for a distribution center, comprising: a first determination unit, configured to determine a network point set and a candidate distribution center set, wherein the network point set includes all service network points in a target area, and the candidate distribution center set includes all candidate distribution centers in the target area; a second determination unit, configured to determine a plurality of objective functions, wherein the plurality of objective functions are used to determine, from the candidate distribution center set, a target distribution center for performing logistics distribution for the service network points in the network point set; a third determination unit, configured to determine, from the candidate distribution center set, a target distribution center using a plurality of objective functions based on coding data of the candidate distribution centers in the candidate distribution center set.

[0016] In some examples, the third determination unit is further configured to: iteratively perform the following genetic operations until a preset end condition is reached, and determine a target distribution center from the set of candidate distribution centers: merge the parent population and child population corresponding to this genetic operation to obtain a merged population, wherein the parent population and child population corresponding to the first genetic operation are generated based on the encoding data of the candidate distribution centers in the set of candidate distribution centers; determine the parent population corresponding to the next genetic operation from the merged population according to multiple objective functions; and perform selection, crossover and mutation operations based on the parent population corresponding to the next genetic operation to obtain a child population corresponding to the next genetic operation.

[0017] In some examples, the third determination unit is further configured to: perform non-dominated sorting on the candidate distribution centers in the merged population according to multiple objective functions to obtain multiple non-dominated sorting layers, and determine the congestion of the candidate distribution centers in the multiple non-dominated sorting layers; determine the parent population corresponding to the next genetic operation from the merged population according to the multiple non-dominated sorting layers and the congestion, and determine the fitness of the candidate distribution centers in the parent population corresponding to the next genetic operation.

[0018] In some examples, the third determination unit is further configured to: perform a selection operation on the parent population corresponding to the next genetic operation according to the fitness of the candidate distribution centers in the parent population corresponding to the next genetic operation, and determine multiple target candidate distribution centers from the parent population corresponding to the next genetic operation; perform a crossover operation on the multiple target candidate distribution centers to obtain multiple crossover distribution centers; perform a mutation operation on the multiple crossover distribution centers to obtain a sub-population corresponding to the next genetic operation.

[0019] In some examples, the third determination unit is further configured to: perform selection operations in parallel on the parent population corresponding to the next genetic operation according to the fitness of the candidate distribution centers in the parent population corresponding to the next genetic operation through multiple selection threads for performing selection operations, and determine multiple target candidate distribution centers from the parent population corresponding to the next genetic operation.

[0020] In some examples, the third determining unit is further configured to: perform the crossover operation on multiple target candidate distribution centers in parallel through multiple crossover threads for performing the crossover operation, so as to obtain multiple crossover distribution centers.

[0021] In some examples, the third determination unit is further configured to: perform mutation operations on multiple crossover distribution centers in parallel through multiple mutation threads for performing mutation operations to obtain a sub-population corresponding to the next genetic operation.

[0022] In some examples, the third determination unit is further configured to: for each candidate distribution center in the merged population, determine the dominated quantity of other candidate distribution centers that dominate the candidate distribution center and the dominated set of other candidate distribution centers dominated by the candidate distribution center according to multiple objective functions; iteratively perform the following non-dominated sorting operation on the merged population: combine the candidate distribution centers with zero dominated quantity in the to-be-sorted population corresponding to this non-dominated sorting operation into a non-dominated sorting layer, wherein the to-be-sorted population corresponding to the first non-dominated sorting operation is the merged population, and the level corresponding to the non-dominated sorting layer is positively correlated with the order corresponding to this non-dominated sorting operation; for each candidate distribution center in the non-dominated sorting layer, reduce the dominated quantity corresponding to each candidate distribution center in the dominated set corresponding to the candidate distribution center by one; remove the candidate distribution centers belonging to the non-dominated sorting layer from the merged population to obtain the to-be-sorted population corresponding to the next non-dominated sorting operation.

[0023] In some examples, the third determination unit is further configured to: for each non-dominated sorting layer in a plurality of non-dominated sorting layers and each objective function in a plurality of objective functions, perform the following congestion calculation operation: determine the function value of the candidate distribution center in the non-dominated sorting layer corresponding to the objective function, and sort the candidate distribution centers in the non-dominated sorting layer according to the function value; for each candidate distribution center in the non-dominated sorting layer, determine the sub-congestion of the candidate distribution center corresponding to the objective function according to the function value of the previous candidate distribution center, the function value of the next candidate distribution center, the maximum function value and the minimum function value, and obtain the congestion obtained by accumulating the sub-congestions of the candidate distribution center corresponding to other objective functions as of the last congestion calculation operation, so as to obtain the congestion of the candidate distribution center in this congestion calculation operation.

[0024] In some examples, the third determination unit is further configured to: for each candidate distribution center in the non-dominated sorting layer in the parent population corresponding to the next genetic operation, perform the following fitness calculation operation: determine the Euclidean distance between the candidate distribution center and other candidate distribution centers in the non-dominated sorting layer to which the candidate distribution center belongs; determine the sharing function value between the candidate distribution center and other candidate distribution centers in the non-dominated sorting layer to which the candidate distribution center belongs based on the sharing function and the Euclidean distance, wherein the sharing function is used to characterize the degree of close relationship between two candidate distribution centers in the population; determine the number of microhabitats corresponding to the candidate distribution center based on the sharing function value; determine the fitness of the candidate distribution center based on the number of microhabitats and the virtual fitness, wherein the virtual fitness is negatively correlated with the level corresponding to the non-dominated sorting layer to which the candidate distribution center belongs.

[0025] In some examples, the preset termination condition is that the number of iterations exceeds a preset threshold, and / or the difference between the fitness corresponding to the subpopulation determined by the current genetic operation and the fitness corresponding to the subpopulation determined by the previous genetic operation is less than a preset difference threshold.

[0026] In a third aspect, an embodiment of the present application provides a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the first aspect is implemented.

[0027] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by one or more processors, the one or more processors implement the method described in any implementation manner of the first aspect.

[0028] The method and device for selecting a distribution center provided in the embodiment of the present application determine a network point set including all service network points in a target area, and a candidate distribution center set including all candidate distribution centers in the target area; determine multiple objective functions representing target distribution centers that are determined from the candidate distribution center set to perform logistics distribution for service network points in the network point set; and determine the target distribution center from the candidate distribution center set using multiple objective functions based on the coding data of the candidate distribution centers in the candidate distribution center set, thereby determining the target distribution center that is performed logistics distribution for service network points in the network point set from the candidate distribution center set, thereby solving the problem of heavy reliance on expert experience in existing algorithms and improving the accuracy of the determined target distribution center. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0030] Figure 1 is an exemplary system architecture diagram in which an embodiment of the present application may be applied;

[0031] Figure 2 is a flow chart of an embodiment of a method for selecting a location for a distribution center according to the present application;

[0032] Figure 3 is a schematic diagram of a crossover operation according to this embodiment;

[0033] Figure 4 Schematic diagram of executing selection operation, crossover operation and mutation operation in parallel according to this embodiment

[0034] Figure 5is a schematic diagram of an application scenario of the method for selecting a location for a distribution center according to this embodiment;

[0035] Figure 6 is a flow chart of another embodiment of the method for selecting a location for a distribution center according to the present application;

[0036] Figure 7 is a structural diagram of an embodiment of a site selection device for a distribution center according to the present application;

[0037] Figure 8 It is a schematic diagram of the structure of a computer system suitable for implementing the embodiments of the present application. DETAILED DESCRIPTION

[0038] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It should also be noted that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0039] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0040] It should be noted that the collection, collection, updating, analysis, processing, use, transmission, storage and other aspects of user personal information involved in the technical solution of this disclosure are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information, network security and national security.

[0041] Figure 1 An exemplary architecture 100 is shown to which the method and apparatus for site selection of a distribution center of the present application can be applied.

[0042] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The communication connection between the terminal devices 101, 102, 103 constitutes a topological network, and the network 104 is used to provide a medium for the communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0043] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Terminal devices 101, 102, 103 can be hardware devices or software that support network connection for data interaction and data processing. When terminal devices 101, 102, 103 are hardware, they can be various electronic devices that support network connection, information acquisition, interaction, display, processing and other functions, including but not limited to smart phones, tablet computers, e-book readers, laptop portable computers and desktop computers, etc. When terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. It can be implemented as multiple software or software modules for providing distributed services, for example, or it can be implemented as a single software or software module. No specific limitation is made here.

[0044] The server 105 may be a server that provides various services, for example, a backend processing server that uses a non-dominated sorting genetic algorithm to determine a target distribution center that performs logistics distribution for the service outlets in the outlet set from the candidate distribution center set, using the outlet set including all service outlets in the target area and the candidate distribution center set including all candidate distribution centers in the target area provided by the terminal devices 101, 102, and 103. As an example, the server 105 may be a cloud server.

[0045] It should be noted that the server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules (for example, software or software modules used to provide distributed services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0046] It should also be noted that the method for selecting a site for a distribution center provided in the embodiments of the present application can be executed by a server, or by a terminal device, or by a server and a terminal device in cooperation with each other. Accordingly, the various parts (e.g., various units) included in the site selection device for a distribution center can be all set in the server, or all set in the terminal device, or can be set in the server and the terminal device respectively.

[0047] It should be understood that Figure 1 The number of terminal devices, networks, and servers in the system is only illustrative. Any number of terminal devices, networks, and servers may be provided as required. When the electronic device on which the method for selecting a site for a distribution center is running does not need to perform data transmission with other electronic devices, the system architecture may only include the electronic device (e.g., server or terminal device) on which the method for selecting a site for a distribution center is running.

[0048] Continue to refer Figure 2 , a process 200 of an embodiment of a method for selecting a distribution center location is shown, comprising the following steps:

[0049] Step 201, determining a set of outlets and a set of candidate distribution centers.

[0050] In this embodiment, the execution entity of the method for selecting a location for a distribution center (eg Figure 1 The terminal device or server in the target area can determine a set of service outlets including all service outlets in the target area, and a set of candidate distribution centers including all candidate distribution centers in the target area.

[0051] A distribution center, also known as a distribution station, is a site responsible for express delivery to service outlets. It has the functions of collecting, storing, sorting, picking, allocating and delivering logistics information, such as collecting, summarizing, storing and transmitting goods.

[0052] The target area may be an area divided based on a preset area division method, in which a target distribution center is to be determined. As an example, the divided administrative areas may be referred to, and when a target distribution center in a certain administrative area needs to be determined, the administrative area is determined as the target area.

[0053] For the target area, the service outlets therein are generally set up in advance, so that the location, distribution volume and other information of all service outlets therein can be determined to generate an outlet set. In order to carry out logistics distribution for the service outlets in the target area, it is generally necessary for relevant operators to determine multiple candidate distribution centers in advance to select the target distribution center from them. The determined multiple candidate distribution centers are combined into a candidate distribution center set.

[0054] Step 202: determine multiple objective functions.

[0055] In this embodiment, the execution subject may determine multiple objective functions, wherein the multiple objective functions are used to determine, from the candidate distribution center set, a target distribution center for performing logistics distribution for the service outlets in the outlet set.

[0056] Determining the target distribution center from the candidate distribution centers in the candidate distribution center set requires certain judgment parameters, and these judgment parameters can be represented by multiple objective functions. Determining the target distribution center from the candidate distribution centers in the candidate distribution center set is essentially an optimization problem. When the objective function of the optimization problem is two or more, the optimization problem is a multi-objective optimization problem.

[0057] Multi-objective optimization problems are very different from single-objective optimization problems. When there is only one objective function, the best solution can be found. This solution is better than all other solutions, usually the global maximum or minimum, that is, the global optimal solution. When there are multiple objectives, it is difficult to find a solution that makes all objective functions optimal at the same time because there are conflicts between the objectives and they cannot be compared. In other words, a solution may be the best for a certain objective function, but not the best for other objective functions, or even the worst. Therefore, for multi-objective optimization problems, there is usually a set of solutions that cannot be compared in terms of all objective functions. Its characteristic is that it is impossible to improve any objective function without weakening at least one other objective function. Such solutions are called non-dominated solutions or Pareto optimal solutions.

[0058] In this embodiment, based on multiple cost factors such as the fixed investment cost of the distribution center, distribution cost, regional purchasing power and distribution range, objective functions corresponding to multiple cost factors can be constructed to obtain multiple objective functions.

[0059] Step 203: According to the coding data of the candidate distribution centers in the candidate distribution center set, a plurality of objective functions are used to determine a target distribution center from the candidate distribution center set.

[0060] In this embodiment, the execution entity may determine the target distribution center from the set of candidate distribution centers by using multiple objective functions according to the coding data of the candidate distribution centers in the set of candidate distribution centers.

[0061] As an example, the execution subject encodes each candidate distribution center in the candidate distribution center set to generate encoding data corresponding to all candidate distribution centers; then processes the encoding data through multiple objective functions to determine the target distribution center from the candidate distribution center set.

[0062] In some optional implementations of this embodiment, the execution subject may use a non-dominated sorting genetic algorithm to determine the target distribution center from the candidate distribution center set. The non-dominated sorting genetic algorithm may be a NSGA (Non-Dominated Sorting Genetic Algorithm) algorithm, a NSGA 2 algorithm, or a NSGA 3 algorithm.

[0063] Specifically, the execution subject may perform step 203 in the following manner: iteratively perform the following genetic operations until a preset end condition is reached, and determine a target distribution center from the set of candidate distribution centers:

[0064] First, the parent population and child population corresponding to this genetic operation are merged to obtain a merged population. The parent population and child population corresponding to the first genetic operation are generated based on the encoding data of the candidate distribution center in the candidate distribution center set.

[0065] Among them, the parent population and child population corresponding to the first genetic operation are generated based on the set of candidate distribution centers.

[0066] As an example, first, the execution subject encodes each candidate distribution center in the candidate distribution center set to generate encoding information corresponding to all candidate distribution centers; then, based on the preset population size, the candidate distribution centers of the above population size are determined from the candidate distribution center set to generate the first generation parent population, that is, the parent population corresponding to the first genetic operation. The population size is represented by the number of candidate distribution centers. For example, when 5 distribution centers need to be determined in the target area, the preset population size is 5.

[0067] The sub-population corresponding to the first genetic operation may be generated based on the parent population corresponding to the first genetic operation. For example, the parent population corresponding to the first genetic operation may be directly determined as the sub-population corresponding to the first genetic operation.

[0068] For the parent population and child population corresponding to each genetic operation, it is necessary to merge the parent population and the child population to obtain a merged population with a population size twice that of the parent population.

[0069] The preset end condition can be specifically set according to actual conditions, for example, the number of iterations exceeds a preset number threshold, or the iteration time exceeds a preset time threshold.

[0070] Second, based on multiple objective functions, the parent population corresponding to the next genetic operation is determined from the merged population.

[0071] As an example, based on multiple objective functions, multiple candidate distribution centers are screened out from the merged population to obtain the parent population corresponding to the next genetic operation.

[0072] Third, based on the parent population corresponding to the next genetic operation, selection operation, crossover operation and mutation operation are performed to obtain the child population corresponding to the next genetic operation.

[0073] As an example, the execution subject may sequentially perform a selection operation, a crossover operation, and a mutation operation on a parent population corresponding to the next genetic operation to obtain a child population corresponding to the next genetic operation.

[0074] In some optional implementations of this embodiment, the execution subject may perform the second step in the following manner:

[0075] Step 2.1, according to multiple objective functions, non-dominated sorting is performed on the candidate distribution centers in the merged population to obtain multiple non-dominated sorting layers, and the congestion degree of the candidate distribution centers in the multiple non-dominated sorting layers is determined.

[0076] Taking the minimization multi-objective optimization problem as an example, for n objective components f i (x), i = 1…n, given any two decision variables X a , X b , if the following two conditions are met, then X a DominateX b :

[0077] 1. For All have f i (X a )≤f i (X b ) is established;

[0078] 2. So that f i (X a ) <f i (X b ) was established.

[0079] If there is no other decision variable that can dominate a decision variable, then the decision variable is called a non-dominated solution. In the merged population, the non-dominated solutions are first determined and combined into the first non-dominated sorting layer; then, the non-dominated solutions in the first non-dominated sorting layer are deleted from the merged population, and the non-dominated solutions are determined again from the new merged population, and the second non-dominated sorting layer is generated. The above process is iterated to obtain multiple non-dominated sorting layers corresponding to the merged population.

[0080] The crowding degree of a candidate distribution center is used to characterize the density of candidate distribution centers around the candidate distribution center in the population.

[0081] Step 2.2, according to multiple non-dominated sorting layers and congestion, determine the parent population corresponding to the next genetic operation from the merged population, and determine the fitness of the candidate distribution center in the parent population corresponding to the next genetic operation.

[0082] In this implementation, the population size of the parent population corresponding to each genetic operation is the same. First, the above-mentioned execution subject can add the candidate distribution centers in the non-dominated sorting layer to the parent population corresponding to the next genetic operation, starting from the first non-dominated sorting layer, according to the hierarchical order of multiple non-dominated sorting layers, until the parent population corresponding to the next genetic operation cannot all be placed in an individual in a certain dominant sorting layer. Then, the candidate distribution centers in the dominant sorting layer are added to the parent population corresponding to the next genetic operation in order from large to small in terms of congestion, until the parent population corresponding to the next genetic operation reaches the specified population size. After determining the parent population corresponding to the next genetic operation, the fitness of the candidate distribution centers therein is further determined.

[0083] In some optional implementations of this embodiment, the execution subject may perform the third step in the following manner:

[0084] Step 3.1 performs a selection operation on the parent population corresponding to the next genetic operation according to the fitness of the candidate distribution centers in the parent population corresponding to the next genetic operation, and determines multiple target candidate distribution centers from the parent population corresponding to the next genetic operation.

[0085] In this implementation, a competitive bidding selection algorithm may be used to perform a selection operation on the parent population corresponding to the next genetic operation, thereby determining a plurality of target candidate distribution centers.

[0086] Taking the binary bidding selection algorithm as an example, assuming that the population size of the parent population is N, first, randomly select 2 candidate distribution centers from the N candidate distribution centers in the parent population; then, according to the fitness of the two selected candidate distribution centers, select the candidate distribution center with the best fitness value to join the next generation sub-population. By iteratively executing the above steps, multiple target candidate distribution centers are obtained.

[0087] Step 3.2, performing a cross operation on multiple target candidate distribution centers to obtain multiple cross distribution centers.

[0088] The crossover operation is used to cross the genes (coding information) of two target candidate distribution centers to obtain a new candidate distribution center, that is, the crossover distribution center.

[0089] Continue to refer Figure 3, showing a schematic diagram of the crossover operation. The coding information of the target candidate distribution center includes a 6-bit code. Among them, the coding information of the target candidate distribution center 301 is "Gene1-301 Gene 2-301Gene 3-301Gene4-301 Gene5-301 Gene6-301", and the coding information of the target candidate distribution center 302 is "Gene1-302Gene 2-302Gene 3-302Gene4-302 Gene5-302 Gene6-302", then the coding information of the distribution centers 303 and 304 after the crossover can be "Gene1-301 Gene 2-302Gene 3-301Gene4-301 Gene5-302Gene6-302", "Gene1-302 Gene 2-301Gene 3-302Gene4-302 Gene5-301Gene6-301".

[0090] It should be noted that Figure 3 This is just a schematic illustration of the crossing method and is not intended to limit the crossing method.

[0091] Step 3.3, perform mutation operation on multiple crossover distribution centers to obtain the sub-population corresponding to the next genetic operation.

[0092] The mutation operation is used to randomly mutate the encoding information corresponding to the cross distribution center.

[0093] By iteratively executing the above genetic operations, the distribution center in the subpopulation corresponding to the preset end condition is determined as the target distribution center.

[0094] In this implementation, a specific method for determining a target distribution center using a non-dominated sorting genetic algorithm is provided, which helps to further improve the accuracy of the determined target distribution center.

[0095] In some optional implementations of the present embodiment, the execution subject may execute step 3.1 in the following manner: by using a plurality of selection threads for executing selection operations, the selection operation is executed in parallel on the parent population corresponding to the next genetic operation according to the fitness of the candidate distribution centers in the parent population corresponding to the next genetic operation, and a plurality of target candidate distribution centers are determined from the parent population corresponding to the next genetic operation.

[0096] In some optional implementations of this embodiment, the execution subject may perform step 3.2 in the following manner: by performing cross operations on multiple target candidate distribution centers in parallel through multiple cross operations, to obtain multiple cross distribution centers.

[0097] In some optional implementations of this embodiment, the execution subject may perform step 3.3 in the following manner: by using multiple mutation threads for performing mutation operations, performing mutation operations on multiple crossover distribution centers in parallel to obtain a subpopulation corresponding to the next genetic operation.

[0098] Regardless of the selection process, the crossover process, or the mutation process, the number of the multiple threads used can be specifically set according to actual conditions and is not limited here.

[0099] Continue to refer Figure 4 , showing a schematic diagram of parallel execution of selection, crossover, and mutation operations. For the 2N candidate distribution centers 401 in the parent population corresponding to the next genetic operation, according to their fitness, a binary competition selection algorithm is used to select N target candidate distribution centers 402 from the 2N candidate distribution centers through N selection threads; for the N target candidate distribution centers 402, N / 2 crossover threads are used to perform crossover operations in parallel to obtain N crossover distribution centers 403; for the N crossover distribution centers 403, N mutation threads are used to perform mutation operations in parallel to obtain a subpopulation corresponding to the next genetic operation including N mutated candidate centers 404.

[0100] In this implementation, the selection operation, crossover operation, and mutation operation are executed in parallel by multithreading, thereby improving the execution efficiency of the selection process, crossover process, and mutation process, thereby improving the iteration efficiency of genetic operations and the determination efficiency of the target distribution center.

[0101] In some optional implementations of this embodiment, the above execution subject may perform non-dominated sorting in the following manner:

[0102] First, for each candidate distribution center in the merged population, the domination quantity of other candidate distribution centers dominating the candidate distribution center and the domination set including other candidate distribution centers dominated by the candidate distribution center are determined according to multiple objective functions.

[0103] Second, the following non-dominated sorting operation is iterated on the merged population: first, the candidate distribution centers with zero dominance quantity in the to-be-sorted population corresponding to this non-dominated sorting operation are combined into a non-dominated sorting layer, where the to-be-sorted population corresponding to the first non-dominated sorting operation is the merged population, and the level corresponding to the non-dominated sorting layer is positively correlated with the order corresponding to this non-dominated sorting operation; then, for each candidate distribution center in the non-dominated sorting layer, the dominance quantity corresponding to each candidate distribution center in the dominance set corresponding to the candidate distribution center is reduced by one; finally, the candidate distribution centers belonging to the non-dominated sorting layer are removed from the merged population to obtain the to-be-sorted population corresponding to the next non-dominated sorting operation.

[0104] As an example, the processing logic of the non-dominated sort operation is as follows:

[0105] Input: merged population P; Output: non-dominated sorting layer and rank.

[0106]

[0107]

[0108] In this implementation, a fast non-dominated sorting implementation is provided, which helps to reduce the computational complexity of the non-dominated sorting process and improve the execution speed of the non-dominated sorting process.

[0109] In some optional implementations of this embodiment, the execution subject may determine the congestion degree of the candidate distribution centers in the multiple non-dominated sorting layers in the following manner: for each non-dominated sorting layer in the multiple non-dominated sorting layers and each objective function in the multiple objective functions, perform the following congestion degree calculation operation:

[0110] First, the function value of the candidate distribution centers in the non-dominated sorting layer corresponding to the objective function is determined, and the candidate distribution centers in the non-dominated sorting layer are sorted according to the function value; then, for each candidate distribution center in the non-dominated sorting layer, the sub-crowding degree of the candidate distribution center corresponding to the objective function is determined according to the function value of the previous candidate distribution center, the function value of the next candidate distribution center, the maximum function value and the minimum function value of the candidate distribution center, and the congestion degree obtained by accumulating the sub-crowding degrees of the candidate distribution center corresponding to other objective functions up to the last congestion calculation operation is combined to obtain the congestion degree of the candidate distribution center in this congestion calculation operation.

[0111] As an example, the processing logic of the congestion calculation operation is as follows:

[0112] 1. Let the congestion degree n d =0, n=1...N (N is the size of the non-dominated sorting layer)

[0113] 2. For each objective function f in multiple objective functions m DO

[0114] 3. Sort the candidate distribution centers according to the function value of the objective function corresponding to the candidate distribution centers in the non-dominated sorting layer, and record the largest function value as The minimum function value is

[0115] The congestion degree L of the two candidate distribution centers at the border after sorting d and N d Set Infinity

[0116] 4. Calculation Among them, f m (i+1) is the objective function f of the next candidate distribution center after candidate distribution center i m The function value, f m (i-1) is the objective function f of the previous candidate distribution center i m The function value of .

[0117] In this implementation, an implementation method of a congestion degree calculation operation is provided, which helps to improve the calculation efficiency and accuracy of the congestion degree calculation.

[0118] In some optional implementations of this embodiment, the execution subject may determine the fitness of the candidate distribution center in the parent population corresponding to the next genetic operation in the following manner: for the candidate distribution center in each non-dominated sorting layer in the parent population corresponding to the next genetic operation, perform the following fitness calculation operation:

[0119] First, determine the Euclidean distance between the candidate distribution center and other candidate distribution centers in the non-dominated sorting layer to which the candidate distribution center belongs; second, determine the sharing function value between the candidate distribution center and other candidate distribution centers in the non-dominated sorting layer to which the candidate distribution center belongs based on the sharing function and the Euclidean distance, wherein the sharing function is used to characterize the degree of close relationship between two candidate distribution centers in a group; third, determine the number of microhabitats corresponding to the candidate distribution center based on the sharing function value; fourth, determine the fitness of the candidate distribution center based on the number of microhabitats and the virtual fitness, wherein the virtual fitness is negatively correlated with the level corresponding to the non-dominated sorting layer to which the candidate distribution center belongs.

[0120] As an example, suppose that the non-dominated sorting layer g includes n g candidate distribution centers, and the virtual fitness of each candidate distribution center is f g , and let i, j = 1...n g .

[0121] First, the Euclidean distance between the candidate distribution center and other candidate distribution centers in the non-dominated sorting layer to which the candidate distribution center belongs is calculated by the following formula:

[0122]

[0123] Where L represents the number of variables in the multi-objective optimization problem, For x l The upper and lower bounds of .

[0124] Then, the sharing function value between the candidate distribution center and other candidate distribution centers in the non-dominated sorting layer to which the candidate distribution center belongs is determined by the following sharing function:

[0125]

[0126] Among them, σ share Represents the shared radius, and α is a preset constant.

[0127] Then, the number of niches corresponding to the candidate distribution center is determined by the following sharing function:

[0128]

[0129] Niche is a concept from biology, which refers to a living environment under a specific environment. In the process of evolution, organisms generally live together with the same species as themselves and reproduce together. The niche technology adopted in this implementation method is to re-specify the previously specified virtual fitness value through the method of fitness sharing function.

[0130] Finally, the fitness of the candidate distribution center is calculated by the following formula:

[0131]

[0132] In this implementation, an implementation method of a fitness calculation operation is provided, which helps to improve the calculation efficiency and accuracy of the fitness calculation.

[0133] In some optional implementations of this embodiment, in order to improve the accuracy of the iterative execution process of the genetic operation, the preset end condition is that the number of iterations exceeds the preset number threshold, and / or the difference between the fitness corresponding to the subpopulation determined by the current genetic operation and the fitness corresponding to the subpopulation determined by the previous genetic operation is less than the preset difference threshold, so that the end time of the iterative process of the genetic operation can be accurately determined. Among them, the preset difference threshold can be specifically set according to actual conditions and is not limited here.

[0134] Continue to see Figure 5 , Figure 5 FIG. 5 is a schematic diagram 500 of an application scenario of the method for selecting a distribution center according to this embodiment. Figure 5In the application scenario, a large number of service outlets 502 are distributed in the target area 501, and all service outlets 502 are combined into an outlet set. The relevant operator pre-specifies multiple candidate distribution centers 503 in the target area 501, and the multiple candidate distribution centers 503 are combined into a candidate distribution center set. In addition, the relevant operator constructs multiple objective functions 504 that represent the target distribution centers that are determined from the candidate distribution center set to perform logistics distribution for the service outlets in the outlet set.

[0135] The server first obtains the network point set and the candidate distribution center set corresponding to the target area 501, and obtains multiple objective functions 504; then, based on the multiple objective functions, a non-dominated sorting genetic algorithm is used to determine multiple target distribution centers 505 from the candidate distribution center set.

[0136] The method provided by the above-mentioned embodiment of the present application determines an outlet set including all service outlets in the target area, and a candidate distribution center set including all candidate distribution centers in the target area; determines multiple objective functions that characterize the target distribution centers that are determined from the candidate distribution center set to perform logistics distribution for the service outlets in the outlet set; and determines the target distribution center from the candidate distribution center set using multiple objective functions based on the coding data of the candidate distribution centers in the candidate distribution center set, thereby solving the problem of heavy reliance on expert experience in existing algorithms and improving the accuracy of the determined target distribution center.

[0137] Continue to refer Figure 6 , shows a schematic process 600 of an embodiment of a method for selecting a distribution center according to the present application, including the following steps:

[0138] Step 601, determining a network point set including all service network points in a target area, and a candidate distribution center set including all candidate distribution centers in the target area.

[0139] Step 602 , determining a plurality of objective functions representing target distribution centers that are determined from the candidate distribution center set to perform logistics distribution for service outlets in the outlet set.

[0140] Step 603, iteratively perform the following genetic operations until a preset end condition is reached, and determine the target distribution center from the set of candidate distribution centers:

[0141] Step 6031, merge the parent population and child population corresponding to this genetic operation to obtain a merged population.

[0142] Among them, the parent population and child population corresponding to the first genetic operation are generated based on the set of candidate distribution centers.

[0143] Step 6032: perform non-dominated sorting on the candidate distribution centers in the merged population according to multiple objective functions to obtain multiple non-dominated sorting layers, and determine the congestion degree of the candidate distribution centers in the multiple non-dominated sorting layers.

[0144] Step 6033, according to the multiple non-dominated sorting layers and the congestion degree, determine the parent population corresponding to the next genetic operation from the merged population, and determine the fitness of the candidate distribution center in the parent population corresponding to the next genetic operation.

[0145] Step 6034, through multiple selection threads for performing selection operations, according to the fitness of the candidate distribution centers in the parent population corresponding to the next genetic operation, the selection operation is performed in parallel on the parent population corresponding to the next genetic operation, and multiple target candidate distribution centers are determined from the parent population corresponding to the next genetic operation.

[0146] Step 6035: perform the cross operation on multiple target candidate distribution centers in parallel through multiple cross threads for performing the cross operation, and obtain multiple cross distribution centers.

[0147] Step 6036, using multiple mutation threads for performing mutation operations, the mutation operation is performed in parallel on multiple crossover distribution centers to obtain a sub-population corresponding to the next genetic operation.

[0148] It can be seen from this embodiment that Figure 2 Compared with the corresponding embodiments, the process 600 of the distribution center location selection method in this embodiment specifically illustrates the calculation process of the non-dominated sorting genetic algorithm, the parallel execution process of the selection operation, the crossover operation, and the mutation operation, which further improves the efficiency and accuracy of determining the target distribution center.

[0149] Continue to refer Figure 7 As an implementation of the methods shown in the above figures, the present application provides an embodiment of a site selection device for a distribution center. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0150] like Figure 7As shown, the site selection device for the distribution center includes: a first determination unit 701, which is configured to determine a network point set and a candidate distribution center set, wherein the network point set includes all service network points in the target area, and the candidate distribution center set includes all candidate distribution centers in the target area; a second determination unit 702, which is configured to determine a plurality of objective functions, wherein the plurality of objective functions are used to determine, from the candidate distribution center set, a target distribution center for performing logistics distribution for the service network points in the network point set; a third determination unit 703, which is configured to determine a target distribution center from the candidate distribution center set using a plurality of objective functions based on the coding data of the candidate distribution centers in the candidate distribution center set.

[0151] In some optional implementations of the present embodiment, the third determination unit 703 is further configured to: iteratively perform the following genetic operations until a preset end condition is reached, and determine the target distribution center from the set of candidate distribution centers: merge the parent population and the child population corresponding to this genetic operation to obtain a merged population, wherein the parent population and the child population corresponding to the first genetic operation are generated based on the encoding data of the candidate distribution centers in the set of candidate distribution centers; determine the parent population corresponding to the next genetic operation from the merged population according to multiple objective functions; and perform selection, crossover and mutation operations based on the parent population corresponding to the next genetic operation to obtain a child population corresponding to the next genetic operation.

[0152] In some optional implementations of the present embodiment, the third determination unit 703 is further configured to: perform non-dominated sorting on the candidate distribution centers in the merged population according to multiple objective functions to obtain multiple non-dominated sorting layers, and determine the congestion of the candidate distribution centers in the multiple non-dominated sorting layers; determine the parent population corresponding to the next genetic operation from the merged population according to the multiple non-dominated sorting layers and the congestion, and determine the fitness of the candidate distribution centers in the parent population corresponding to the next genetic operation.

[0153] In some optional implementations of the present embodiment, the third determination unit 703 is further configured to: perform a selection operation on the parent population corresponding to the next genetic operation according to the fitness of the candidate distribution centers in the parent population corresponding to the next genetic operation, and determine a plurality of target candidate distribution centers from the parent population corresponding to the next genetic operation; perform a crossover operation on the plurality of target candidate distribution centers to obtain a plurality of crossover distribution centers; perform a mutation operation on the plurality of crossover distribution centers to obtain a sub-population corresponding to the next genetic operation.

[0154] In some optional implementations of the present embodiment, the third determination unit 703 is further configured to: perform the selection operation in parallel on the parent population corresponding to the next genetic operation according to the fitness of the candidate distribution centers in the parent population corresponding to the next genetic operation through a plurality of selection threads for performing the selection operation, and determine a plurality of target candidate distribution centers from the parent population corresponding to the next genetic operation.

[0155] In some optional implementations of this embodiment, the third determining unit 703 is further configured to: perform the crossover operation on multiple target candidate distribution centers in parallel through multiple crossover threads for performing the crossover operation, so as to obtain multiple crossover distribution centers.

[0156] In some optional implementations of this embodiment, the third determining unit 703 is further configured to: perform mutation operations on multiple crossover distribution centers in parallel through multiple mutation threads for performing mutation operations to obtain a sub-population corresponding to the next genetic operation.

[0157] In some optional implementations of this embodiment, the third determining unit 703 is further configured to: for each candidate distribution center in the merged population, determine the dominated quantity of other candidate distribution centers that dominate the candidate distribution center and the dominated set including other candidate distribution centers dominated by the candidate distribution center according to multiple objective functions; iteratively perform the following non-dominated sorting operation on the merged population: combine the candidate distribution centers with zero dominated quantity in the to-be-sorted population corresponding to this non-dominated sorting operation into a non-dominated sorting layer, wherein the to-be-sorted population corresponding to the first non-dominated sorting operation is the merged population, and the level corresponding to the non-dominated sorting layer is positively correlated with the order corresponding to this non-dominated sorting operation; for each candidate distribution center in the non-dominated sorting layer, reduce the dominated quantity corresponding to each candidate distribution center in the dominated set corresponding to the candidate distribution center by one; remove the candidate distribution centers belonging to the non-dominated sorting layer from the merged population to obtain the to-be-sorted population corresponding to the next non-dominated sorting operation.

[0158] In some optional implementations of the present embodiment, the third determining unit 703 is further configured to: for each non-dominated sorting layer in the multiple non-dominated sorting layers and each objective function in the multiple objective functions, perform the following congestion calculation operation: determine the function value of the candidate distribution center in the non-dominated sorting layer corresponding to the objective function, and sort the candidate distribution centers in the non-dominated sorting layer according to the function value; for each candidate distribution center in the non-dominated sorting layer, determine the sub-congestion of the candidate distribution center corresponding to the objective function according to the function value of the previous candidate distribution center, the function value of the next candidate distribution center, the maximum function value and the minimum function value, and obtain the congestion obtained by accumulating the sub-congestions of the candidate distribution center corresponding to other objective functions as of the last congestion calculation operation, so as to obtain the congestion of the candidate distribution center in this congestion calculation operation.

[0159] In some optional implementations of the present embodiment, the third determining unit 703 is further configured to: perform the following fitness calculation operations for the candidate distribution center in each non-dominated sorting layer in the parent population corresponding to the next genetic operation: determine the Euclidean distance between the candidate distribution center and other candidate distribution centers in the non-dominated sorting layer to which the candidate distribution center belongs; determine the sharing function value between the candidate distribution center and other candidate distribution centers in the non-dominated sorting layer to which the candidate distribution center belongs according to the sharing function and the Euclidean distance, wherein the sharing function is used to characterize the degree of close relationship between two candidate distribution centers in the population; determine the number of microhabitats corresponding to the candidate distribution center according to the sharing function value; determine the fitness of the candidate distribution center according to the number of microhabitats and the virtual fitness, wherein the virtual fitness is negatively correlated with the level corresponding to the non-dominated sorting layer to which the candidate distribution center belongs.

[0160] In some optional implementations of this embodiment, the above-mentioned preset termination condition is that the number of iterations exceeds a preset threshold, and / or the difference between the fitness corresponding to the sub-population determined by this genetic operation and the fitness corresponding to the sub-population determined by the previous genetic operation is less than a preset difference threshold.

[0161] In this embodiment, the first determination unit in the site selection device of the distribution center determines an outlet set including all service outlets in the target area, and a candidate distribution center set including all candidate distribution centers in the target area; the second determination unit determines a plurality of objective functions representing the target distribution centers determined from the candidate distribution center set for logistics distribution for the service outlets in the outlet set; the third determination unit uses a plurality of objective functions to determine the target distribution center from the candidate distribution center set based on the coding data of the candidate distribution centers in the candidate distribution center set, so that the target distribution center for logistics distribution for the service outlets in the outlet set can be determined from the candidate distribution center set, which solves the problem of heavy reliance on expert experience in the existing algorithms and improves the accuracy of the determined target distribution centers.

[0162] Reference below Figure 8 , which shows a device suitable for implementing the embodiments of the present application (eg Figure 1 Schematic diagram of the structure of a computer system 800 of the devices 101, 102, 103, 105 shown. Figure 8 The device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0163] like Figure 8 As shown, the computer system 800 includes a processor (e.g., CPU, central processing unit) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage part 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the system 800 are also stored. The processor 801, ROM 802, and RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0164] The following components are connected to the I / O interface 805: an input section 806 including a keyboard, a mouse, etc.; an output section 807 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN card, a modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I / O interface 805 as needed. A removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 810 as needed, so that a computer program read therefrom is installed into the storage section 808 as needed.

[0165] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part 809, and / or installed from a removable medium 811. When the computer program is executed by the processor 801, the above-mentioned functions defined in the method of the present application are executed.

[0166] It should be noted that the computer-readable medium of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0167] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the client computer, partially on the client computer, as a separate software package, partially on the client computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the client computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0168] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the device, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0169] The units involved in the embodiments described in the present application may be implemented by software or by hardware. The units described may also be set in a processor, for example, may be described as: a processor comprising a first determination unit, a second determination unit, and a third determination unit. The names of these units do not constitute a limitation on the units themselves in certain circumstances. For example, the third determination unit may also be described as "a unit that determines a target distribution center from a set of candidate distribution centers using a non-dominated sorting genetic algorithm based on multiple objective functions."

[0170] As another aspect, the present application also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by the device, the computer device: determines a set of outlets including all service outlets in the target area, and a set of candidate distribution centers including all candidate distribution centers in the target area; determines multiple objective functions representing the target distribution centers determined from the set of candidate distribution centers for logistics distribution for the service outlets in the set of outlets; and determines the target distribution center from the set of candidate distribution centers using multiple objective functions based on the coded data of the candidate distribution centers in the set of candidate distribution centers.

[0171] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above invention concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. A method for selecting a distribution center location. include: Determine a network point set and a candidate distribution center set, wherein the network point set includes all service network points in the target area, and the candidate distribution center set includes all candidate distribution centers in the target area; Determine a plurality of objective functions, wherein the plurality of objective functions are used to determine, from the set of candidate distribution centers, a target distribution center for performing logistics distribution for the service outlets in the set of outlets; The target distribution center is determined from the candidate distribution center set by using the multiple objective functions according to the coding data of the candidate distribution centers in the candidate distribution center set.

2. The method according to claim 1, in, The step of determining the target distribution center from the set of candidate distribution centers by using the plurality of objective functions according to the coded data of the candidate distribution centers in the set of candidate distribution centers comprises: The following genetic operations are iteratively performed until a preset end condition is reached, and the target distribution center is determined from the set of candidate distribution centers: Merging the parent population and the child population corresponding to the current genetic operation to obtain a merged population, wherein the parent population and the child population corresponding to the first genetic operation are generated based on the encoding data of the candidate distribution center in the candidate distribution center set; Determining, from the merged population, a parent population corresponding to the next genetic operation according to the multiple objective functions; Based on the parent population corresponding to the next genetic operation, selection operation, crossover operation and mutation operation are performed to obtain the child population corresponding to the next genetic operation.

3. The method according to claim 2, in, The step of determining a parent population corresponding to a next genetic operation from the merged population according to the multiple objective functions includes: According to the multiple objective functions, non-dominated sorting is performed on the candidate distribution centers in the merged population to obtain multiple non-dominated sorting layers, and the congestion degree of the candidate distribution centers in the multiple non-dominated sorting layers is determined; According to the multiple non-dominated sorting layers and the congestion degree, a parent population corresponding to the next genetic operation is determined from the merged population, and the fitness of the candidate distribution center in the parent population corresponding to the next genetic operation is determined.

4. The method according to claim 2, in, The step of performing a selection operation, a crossover operation, and a mutation operation based on the parent population corresponding to the next genetic operation to obtain a child population corresponding to the next genetic operation includes: According to the fitness of the candidate distribution centers in the parent population corresponding to the next genetic operation, a selection operation is performed on the parent population corresponding to the next genetic operation, and a plurality of target candidate distribution centers are determined from the parent population corresponding to the next genetic operation; Performing a cross operation on the multiple target candidate distribution centers to obtain multiple cross-distribution centers; A mutation operation is performed on the multiple crossover distribution centers to obtain a sub-population corresponding to the next genetic operation.

5. The method according to claim 4, in, The step of performing a selection operation on the parent population corresponding to the next genetic operation according to the fitness of the candidate distribution centers in the parent population corresponding to the next genetic operation, and determining a plurality of target candidate distribution centers from the parent population corresponding to the next genetic operation, includes: Through multiple selection threads for performing selection operations, the selection operation is performed in parallel on the parent population corresponding to the next genetic operation according to the fitness of the candidate distribution centers in the parent population corresponding to the next genetic operation, and the multiple target candidate distribution centers are determined from the parent population corresponding to the next genetic operation.

6. The method according to claim 4, in, The performing a cross operation on the plurality of target candidate distribution centers to obtain a plurality of cross-operated distribution centers includes: The crossover operation is performed in parallel on the multiple target candidate distribution centers through multiple crossover threads for performing the crossover operation, so as to obtain the multiple crossover distribution centers.

7. The method according to claim 4, in, The performing mutation operation on the multiple crossover distribution centers to obtain a subpopulation corresponding to the next genetic operation includes: The mutation operation is performed in parallel on the multiple crossover distribution centers through a plurality of mutation threads for performing the mutation operation, so as to obtain a sub-population corresponding to the next genetic operation.

8. The method according to claim 3, in, The non-dominated sorting of the candidate distribution centers in the merged population is performed according to the multiple objective functions to obtain multiple non-dominated sorting layers, including: For each candidate distribution center in the merged population, determining, according to the multiple objective functions, the domination quantity of other candidate distribution centers that dominate the candidate distribution center and the domination set including other candidate distribution centers dominated by the candidate distribution center; The following non-dominated sorting operation is iteratively performed on the merged population: In the to-be-sorted population corresponding to this non-dominated sorting operation, the candidate distribution centers with zero dominance quantity are combined into a non-dominated sorting layer, wherein the to-be-sorted population corresponding to the first non-dominated sorting operation is the merged population, and the level corresponding to the non-dominated sorting layer is positively correlated with the order corresponding to this non-dominated sorting operation; For each candidate distribution center in the non-dominated sorting layer, the dominance quantity corresponding to each candidate distribution center in the dominance set corresponding to the candidate distribution center is reduced by one; The candidate distribution centers belonging to the non-dominated sorting layer are removed from the merged population to obtain a population to be sorted corresponding to the next non-dominated sorting operation.

9. The method according to claim 3, in, The determining the congestion degree of the candidate distribution centers in the plurality of non-dominated sorting layers comprises: For each non-dominated sorting layer in the plurality of non-dominated sorting layers and each objective function in the plurality of objective functions, the following congestion calculation operation is performed: Determining a function value of the candidate distribution centers in the non-dominated sorting layer corresponding to the objective function, and sorting the candidate distribution centers in the non-dominated sorting layer according to the function value; For each candidate distribution center in the non-dominated sorting layer, the sub-crowding degree of the candidate distribution center corresponding to the objective function is determined according to the function value of the previous candidate distribution center, the function value of the next candidate distribution center, the maximum function value and the minimum function value of the candidate distribution center, and the congestion degree obtained by accumulating the sub-crowding degrees of the candidate distribution center corresponding to other objective functions up to the last congestion calculation operation is combined to obtain the congestion degree of the candidate distribution center in this congestion calculation operation.

10. The method according to claim 3, in, The step of determining the fitness of the candidate distribution center in the parent population corresponding to the next genetic operation includes: For each candidate distribution center in the non-dominated sorting layer of the parent population corresponding to the next genetic operation, perform the following fitness calculation operation: Determine the Euclidean distance between the candidate distribution center and other candidate distribution centers in the non-dominated sorting layer to which the candidate distribution center belongs; Determine, according to the sharing function and the Euclidean distance, a sharing function value between the candidate distribution center and other candidate distribution centers in the non-dominated sorting layer to which the candidate distribution center belongs, wherein the sharing function is used to characterize the close relationship between two candidate distribution centers in the group; Determining the number of microhabitats corresponding to the candidate distribution center according to the shared function value; The fitness of the candidate distribution center is determined according to the number of microhabitats and the virtual fitness, wherein the virtual fitness is negatively correlated with the level corresponding to the non-dominated sorting layer to which the candidate distribution center belongs.

11. The method according to claim 2, in, The preset end condition is that the number of iterations exceeds a preset number threshold, and / or the difference between the fitness corresponding to the subpopulation determined by this genetic operation and the fitness corresponding to the subpopulation determined by the previous genetic operation is less than a preset difference threshold.

12. A site selection device for a distribution center, include: A first determining unit is configured to determine a network point set and a candidate distribution center set, wherein the network point set includes all service network points in a target area, and the candidate distribution center set includes all candidate distribution centers in the target area; A second determination unit is configured to determine a plurality of objective functions, wherein the plurality of objective functions are used to determine, from the set of candidate distribution centers, a target distribution center for performing logistics distribution for a service outlet in the set of outlets; The third determining unit is configured to determine the target distribution center from the set of candidate distribution centers by using the multiple objective functions according to the coding data of the candidate distribution centers in the set of candidate distribution centers.

13. A computer readable medium having a computer program stored thereon, in, When the program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

14. An electronic device, include: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 11.

Images