A stocking method, device, equipment and storage medium

Abstract

An embodiment of the present invention discloses a stock preparation method, device, equipment and storage medium. The method includes: obtaining target item information, a target source warehouse, a set of target platform warehouses, a target demand location, the target item demand quantity, and transportation route cost information corresponding to a target item; performing variable neighborhood search on the basis of an initial platform warehouse subset through a variable neighborhood search method to obtain a target platform warehouse subset; performing transportation route search on a constructed target search network based on the node stock preparation cost in the target search network through a Bellman-Ford search method to determine a target transportation route and a target stock preparation cost; updating the current transportation route; updating the initial platform warehouse subset, and iteratively performing the operation of transportation route search based on the updated initial platform warehouse subset until a preset convergence condition is met, and then performing stock preparation based on the current transportation route, thereby improving the accuracy of stock preparation and reducing the stock preparation cost.

Description

Technical Field

[0001] The embodiments of the present invention relate to computer technology, and in particular, to a stocking method, device, equipment, and storage medium. Background Art

[0002] With the rapid development of the logistics supply chain, e-commerce platforms can provide sub-warehouse stocking services to suppliers, and transport the items in the source warehouses of the suppliers to the platform warehouses of the e-commerce platforms in advance, so as to shorten the distribution time of the items from the supply end to the demand end, thereby improving the item distribution efficiency.

[0003] Currently, usually the suppliers independently select the platform warehouses for stocking and the stocking quantities, and then transport the corresponding quantities of items from the source warehouses to the platform warehouses for stocking.

[0004] However, in the process of implementing the present invention, the inventors found that there are at least the following problems in the prior art:

[0005] The existing stocking method is determined based on manual experience, which is prone to out-of-stock or inventory accumulation, reducing the accuracy of stocking and increasing the stocking cost. Summary of the Invention

[0006] The embodiments of the present invention provide a stocking method, device, equipment, and storage medium to improve the accuracy of stocking and reduce the stocking cost.

[0007] In a first aspect, the embodiments of the present invention provide a stocking method, including:

[0008] Obtain the target item information, target source warehouse, target platform warehouse set, target demand location, target item demand quantity corresponding to the target demand location, and transportation line cost information corresponding to the target item;

[0009] Perform variable neighborhood search on the target platform warehouse set based on the initial platform warehouse subset through the variable neighborhood search method to obtain the searched target platform warehouse subset;

[0010] Perform a transportation path search for the target stocking cost on the target search network constructed according to the available lines in the target source warehouse, the target platform warehouse subset, the target demand location, and the transportation line cost information, based on the node stocking cost in the target search network, to determine the target transportation path and the target stocking cost corresponding to the target transportation path, where the node stocking cost is determined based on the unit transportation cost in the target item information, the target item demand quantity, and the transportation line cost information;

[0011] Update the current transportation route based on the target stocking cost and the current stocking cost corresponding to the current transportation route;

[0012] Update the initial platform warehouse subset based on the target platform warehouses included in the target transportation route, and iteratively execute the operation of searching for the transportation route with the target stocking cost through the variable neighborhood search method and the Bellman-Ford search method based on the updated initial platform warehouse subset until the preset convergence condition is met, and then perform stocking based on the current transportation route and the target item demand.

[0013] In a second aspect, an embodiment of the present invention further provides a stocking device, including:

[0014] An information acquisition module, configured to acquire target item information corresponding to a target item, a target source warehouse, a set of target platform warehouses, a target destination, the target item demand quantity corresponding to the target destination, and transportation line cost information;

[0015] A target platform warehouse subset determination module, configured to perform variable neighborhood search on the set of target platform warehouses on the basis of an initial platform warehouse subset by means of a variable neighborhood search method to obtain a searched target platform warehouse subset;

[0016] A target transportation route determination module, configured to perform a search for a transportation route with a target stocking cost on a target search network constructed according to available routes in the target source warehouse, the target platform warehouse subset, the target destination, and the transportation line cost information, and determine a target transportation route and the target stocking cost corresponding to the target transportation route, where the node stocking cost is determined based on the target item information, the target item demand quantity, and the unit transportation cost in the transportation line cost information;

[0017] A current transportation route update module, configured to update the current transportation route based on the target stocking cost and the current stocking cost corresponding to the current transportation route;

[0018] A stocking module, configured to update the initial platform warehouse subset based on the target platform warehouses included in the target transportation route, and iteratively execute the operation of searching for a transportation route with a target stocking cost through the variable neighborhood search method and the Bellman-Ford search method based on the updated initial platform warehouse subset until the preset convergence condition is met, and then perform stocking based on the current transportation route and the target item demand quantity.

[0019] In a third aspect, an embodiment of the present invention further provides an electronic device, and the electronic device includes:

[0020] One or more processors;

[0021] A memory for storing one or more programs;

[0022] When the one or more programs are executed by the one or more processors, the one or more processors implement the stock preparation method provided in any embodiment of the present invention.

[0023] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the stock preparation method provided in any embodiment of the present invention.

[0024] One embodiment of the above invention has the following advantages or beneficial effects:

[0025] Through the variable neighborhood search method, a variable neighborhood search is performed on the target platform warehouse set corresponding to the target item based on the initial platform warehouse subset to obtain the searched target platform warehouse subset, and through the Bellman-Ford search method, on the target search network constructed according to the available routes in the target source warehouse, target platform warehouse subset, target demand location, and transportation line cost information corresponding to the target item, a transportation path search for the target stock preparation cost is performed based on the node stock preparation cost in the target search network, and the target transportation path and the target stock preparation cost corresponding to the target transportation path are determined, where the node stock preparation cost is determined based on the target item information, the target item demand quantity, and the unit transportation cost in the transportation line cost information. Based on the target stock preparation cost and the current stock preparation cost corresponding to the current transportation path, the current transportation path is updated so that the updated current transportation path is the transportation path with the minimum stock preparation cost. According to the target platform warehouse included in the target transportation path, the initial platform warehouse subset is updated, and based on the updated initial platform warehouse subset, the operation of performing a transportation path search for the target stock preparation cost through the variable neighborhood search method and the Bellman-Ford search method is iteratively executed, so that an optimal current transportation path can be obtained through iterative update, and stock preparation is performed based on the current transportation path and the target item demand quantity, thereby improving the accuracy of stock preparation and reducing the stock preparation cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0027] Figure 1It is a flowchart of a stocking method provided by an embodiment of the present invention;

[0028] Figure 2 It is an example of variable neighborhood search involved in an embodiment of the present invention;

[0029] Figure 3 It is a flowchart of another stocking method provided by an embodiment of the present invention;

[0030] Figure 4 It is an example of a transportation route search process involved in an embodiment of the present invention;

[0031] Figure 5 It is a schematic structural diagram of a stocking device provided by an embodiment of the present invention;

[0032] Figure 6 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0033] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the present invention, rather than limiting the present invention. Additionally, it should be noted that for the sake of description, only parts related to the present invention are shown in the drawings, rather than all the structures.

[0034] Figure 1 It is a flowchart of a stocking method provided by an embodiment of the present invention. This embodiment is applicable to the situation of stocking the platform warehouse in an e-commerce platform. This method can be executed by a stocking device, and this device can be implemented in a software and / or hardware manner and integrated into an electronic device. As Figure 1 shown, the method specifically includes the following steps:

[0035] S110. Obtain the target item information corresponding to the target item, the target source warehouse, the set of target platform warehouses, the target demand location, the target item demand quantity corresponding to the target demand location, and the transportation line cost information.

[0036] Among them, the target item can be any item that needs to be stocked according to business requirements. In this embodiment, the SKU (Stock Keeping Unit) can be used to represent the item to distinguish different items. The target item information may include, but is not limited to, the weight information of the target item. The target item information may also include the unit storage cost (yuan / item) of the target item to determine the warehousing cost of the target item. The target source warehouse may refer to the supplier warehouse for storing the target item, that is, the seller's warehouse. The number of target source warehouses can be one or more. If there are multiple target source warehouses, an optimal target source warehouse can be selected from the multiple target source warehouses for stocking the target item. The target platform warehouse refers to the platform warehouse that can store the target item. The target platform warehouse set can be a set composed of one or more target platform warehouses to select the optimal target platform warehouse from the target platform warehouse set for stocking. The target demand location may refer to the geographical area with demand for the target item, that is, the geographical area where the target item is to be delivered. For example, different demand locations can be represented by different cities. The target item demand quantity may refer to the demand quantity of the target item in the target demand location. The target item demand quantity can be obtained by predicting based on historical demand quantities in advance. The transportation line cost information may include transportation cost information of multiple available lines. Each transportation cost information of an available line includes: the distance between two warehouses and the unit transportation cost (yuan / (kilometer * kilogram)), or the distance between a warehouse and the target demand location and the unit transportation cost (yuan / (kilometer * kilogram)). Among them, since the transportation volume between the location of the warehouse and the target demand location is greater than the transportation volume between the locations of two warehouses, the unit transportation cost between the location of the warehouse and the target demand location is higher than the unit transportation cost between the locations of two warehouses.

[0037] Specifically, all the basic item information in the database can be processed to obtain the target item information corresponding to the target item and the target source warehouse storing the target item, and based on the category information of the target item, all the target platform warehouses that can store this category information can be determined and combined to obtain the target platform warehouse set, and the target demand location corresponding to the target item, the target item demand quantity corresponding to the target demand location predicted in advance, and the transportation line cost information corresponding to each available line can be obtained.

[0038] S120. Through the variable neighborhood search method, perform variable neighborhood search on the target platform warehouse set based on the initial platform warehouse subset to obtain the searched target platform warehouse subset.

[0039] Among them, the variable neighborhood search method may refer to the method of using the variable neighborhood search algorithm (VNS, Variable Neighborhood Search) to select the target platform warehouse. Both the initial platform warehouse subset and the target platform warehouse subset are subsets of the target platform warehouse set. The initial platform warehouse subset may be a set composed of the initially selected target platform warehouses, which is equivalent to the initial solution corresponding to the target platform warehouse set. The target platform warehouse subset may refer to a set composed of the searched target platform warehouses, which is equivalent to the neighborhood solution corresponding to the target platform warehouse set. The number of target platform warehouse subsets may be one or more.

[0040] Specifically, through the variable neighborhood search method, variable neighborhood search can be performed on the target platform warehouse set based on the initial platform warehouse subset to obtain a target platform warehouse subset that meets the search conditions.

[0041] Exemplarily, S120 may include: determining the initial solution corresponding to the target platform warehouse set based on the target platform warehouse set and the initial platform warehouse subset; through the variable neighborhood search method, performing neighborhood transformation on the initial solution to obtain the transformed neighborhood solution, and determining the target platform warehouse subset corresponding to the neighborhood solution.

[0042] Specifically, whether each target platform warehouse in the target platform warehouse set is selected can be represented by 0 and 1, that is, 1 means the target platform warehouse is selected, and 0 means the target platform warehouse is not selected. The target platform warehouses in the initial platform warehouse subset are all selected, that is, corresponding to 1, and the target platform warehouses not in the initial platform warehouse subset are not selected, that is, corresponding to 0. Thus, the initial solution corresponding to the target platform warehouse set can be obtained based on the initial platform warehouse subset. For example, Figure 2 An example of variable neighborhood search is given, as Figure 2 shown, the target platform warehouse set includes 5 warehouses, namely Warehouse A, Warehouse B, Warehouse C, Warehouse D, and Warehouse E, and the initial platform warehouse subset includes 3 warehouses, namely Warehouse A, Warehouse C, and Warehouse D. At this time, the initial solution is {1, 0, 1, 1, 0}. The neighborhood solution is a new solution obtained by performing a finite number of transformation operations on the initial solution. The initial solution may correspond to multiple neighborhood solutions. The transformation operations may include deletion operations, addition operations, and replacement operations. For example, Figure 2 The neighborhood solution 1 in [] is obtained by adding Warehouse B to the initial solution. Figure 2The neighborhood solution 2 in [it] is obtained by replacing warehouse E with warehouse C on the basis of the initial solution. In this embodiment, all possible neighborhood solutions can be obtained by performing a preset number of transformation steps, such as a number of steps less than or equal to 2 steps, on the basis of the initial solution, and the target platform warehouse corresponding to 1 in each neighborhood solution is combined into a target platform warehouse subset. Thus, for each neighborhood solution, a corresponding target platform warehouse subset can be obtained.

[0043] S130. By means of the Bellman-Ford search method, on the target search network constructed according to the available routes in the target source warehouse, the target platform warehouse subset, the target destination, and the transportation line cost information, a transportation path search for the target stocking cost is performed based on the stocking cost of the nodes in the target search network, and the target transportation path and the target stocking cost corresponding to the target transportation path are determined, where the stocking cost of the node is determined based on the target item information, the target item demand quantity, and the unit transportation cost in the transportation line cost information.

[0044] Among them, the Bellman-Ford search method may be to use the Bellman-Ford algorithm to search for the transportation path with the minimum stocking cost from the target source warehouse to the target destination. The target stocking cost may refer to the minimum stocking cost searched out for the current time. The target transportation path may refer to the transportation path with the minimum stocking cost. The target stocking cost may include the transportation cost corresponding to the target transportation path, and it may also include the warehousing cost of storing the target item in the target transportation path.

[0045] Specifically, a target search network is constructed according to the target source warehouse, the target platform warehouse subset, the target destination, and the available routes in the transportation line cost information, and the stocking cost of each network node corresponding to the target search network is determined based on the target item information, the target item demand quantity, and the unit transportation cost in the transportation line cost information. Thus, by means of the Bellman-Ford search method, on the target search network, a transportation path search for the minimum stocking cost can be performed based on the stocking cost of the nodes, and the target transportation path with the minimum stocking cost and the target stocking cost corresponding to the target transportation path can be searched out.

[0046] Exemplarily, S130 may include: If multiple target platform warehouse subsets are searched out, then for each target platform warehouse subset, through the Bellman-Ford search method, on the target search network constructed based on the available routes in the target source warehouse, the target platform warehouse subset, the target demand location, and the transportation line cost information, a transportation path search for the minimum stocking cost is performed based on the node stocking cost in the target search network, obtaining the first transportation path corresponding to the searched target platform warehouse subset and the first stocking cost corresponding to the first transportation path; according to the first transportation paths and the first stocking costs corresponding to each target platform warehouse subset, a target transportation path is determined from each of the first transportation paths, and the first stocking cost corresponding to the target transportation path is determined as the target stocking cost.

[0047] Specifically, when multiple target platform warehouse subsets are searched out through the variable neighborhood search method, for each target platform warehouse subset, through the Bellman-Ford search method, a transportation path search for the minimum stocking cost is performed on the target search network corresponding to the target platform warehouse subset, obtaining the first transportation path with the minimum stocking cost and the corresponding first stocking cost. At this time, the target platform warehouse in the first transportation path is the target platform warehouse in the target platform warehouse subset. For each target platform warehouse subset, a first transportation path with the minimum stocking cost can be searched out. The first stocking costs corresponding to each first transportation path are compared, and the first transportation path with the minimum first stocking cost is used as the target transportation path, and the minimum first stocking cost is used as the target stocking cost, so that the target transportation path and the corresponding target stocking cost searched out in the current search can be obtained for the currently given initial platform warehouse subset.

[0048] S140. Update the current transportation path based on the target stocking cost and the current stocking cost corresponding to the current transportation path.

[0049] Among them, the current transportation path may refer to the transportation path with the minimum stocking cost searched out as of the current moment. The initial value of the current transportation path is empty. Specifically, after the current search is completed, the target stocking cost corresponding to the target transportation path searched out in the current search and the current stocking cost corresponding to the current transportation path are compared. If the target stocking cost is less than the current stocking cost corresponding to the current transportation path, it indicates that the target transportation path is better than the current transportation path. At this time, the current transportation path can be updated to the target transportation path, and the corresponding current stocking cost is updated to the target stocking cost, so that the updated current transportation path is the transportation path with the minimum stocking cost after the current search.

[0050] S150. Update the initial platform warehouse subset based on the target platform warehouses included in the target transportation path, and iteratively execute the operation of searching for the transportation path of the target stocking cost through the variable neighborhood search method and the Bellman-Ford search method based on the updated initial platform warehouse subset until the preset convergence condition is met. Then, conduct stocking based on the current transportation path and the target item demand.

[0051] Specifically, if the preset convergence condition is not currently met. For example, if the current iteration count is less than the preset count or the current change in the current stocking cost is greater than the preset change, then the target platform warehouses included in the target transportation path can be combined, and the resulting set is used as the updated initial platform warehouse subset. Thus, based on the updated initial platform warehouse subset, the operations in steps S120 - S140 can be re-executed. Consequently, on the basis of the updated initial platform warehouse subset, the target transportation path and the corresponding target stocking cost can be re-searched, and the current transportation path can be updated, thereby enabling iterative update of the current transportation path. If the preset convergence condition is currently met. For example, if the current iteration count is equal to the preset count or the current change in the current stocking cost is less than or equal to the preset change (i.e., the change in the current stocking cost tends to be stable), then the current transportation path can be determined as the optimal transportation path, the transportation path with the minimum stocking cost. At this time, stocking can be conducted based on the current transportation path and the target item demand. For example, based on the current transportation path, transport the target items with the target item demand from the target source warehouse to the optimal target platform warehouse, thereby minimizing the stocking cost, improving the accuracy of stocking, and reducing the stocking cost.

[0052] In the technical solution of this embodiment, through the variable neighborhood search method, a variable neighborhood search is performed on the target platform warehouse set corresponding to the target item based on the initial platform warehouse subset to obtain the searched target platform warehouse subset. And through the Bellman-Ford search method, on the target search network constructed according to the available routes in the target source warehouse, the target platform warehouse subset, the target demand location, and the transportation line cost information corresponding to the target item, a transportation path search for the target stocking cost is performed based on the node stocking cost in the target search network. The target transportation path and the target stocking cost corresponding to the target transportation path are determined, where the node stocking cost is determined based on the target item information, the target item demand quantity, and the unit transportation cost in the transportation line cost information. Based on the target stocking cost and the current stocking cost corresponding to the current transportation path, the current transportation path is updated so that the updated current transportation path is the transportation path with the minimum stocking cost. According to the target platform warehouse included in the target transportation path, the initial platform warehouse subset is updated, and based on the updated initial platform warehouse subset, the operation of performing a transportation path search for the target stocking cost through the variable neighborhood search method and the Bellman-Ford search method is iteratively executed. Thus, an optimal current transportation path can be obtained through iterative update, and stocking is performed based on the current transportation path and the target item demand quantity, thereby improving the accuracy of stocking and reducing the stocking cost.

[0053] Based on the above technical solution, after S120, it may further include: determining the number of platform warehouses corresponding to each searched target platform warehouse subset; screening out the target platform warehouse subsets whose number of platform warehouses is equal to the preset warehouse selection quantity from each target platform warehouse subset.

[0054] Among them, the preset warehouse selection quantity can be set in advance and is used to represent the selection range of the target platform warehouse. By setting different preset warehouse selection quantities, the optimal transportation path under different preset warehouse selection quantities can be obtained to meet the personalized needs of users.

[0055] Specifically, after multiple target platform warehouse subsets are searched through the variable neighborhood search method in each iteration process, the number of platform warehouses included in each target platform warehouse subset can be counted, and it is detected whether the number of platform warehouses corresponding to each target platform warehouse subset is equal to the preset warehouse selection quantity. If so, the target platform warehouse subset can be used as the target platform warehouse subset for subsequent path search. If not, the target platform warehouse subset can be deleted, so that the target platform warehouse subsets whose number of platform warehouses is equal to the preset warehouse selection quantity can be screened out, so as to perform a transportation path search based on the screened target platform warehouse subsets subsequently, and thus the target transportation path with the minimum stocking cost under the preset warehouse selection quantity can be obtained.

[0056] Accordingly, S140 may include: updating the current transportation route corresponding to the preset selected warehouse quantity based on the target stock preparation cost and the current stock preparation cost corresponding to the current transportation route.

[0057] Specifically, by comparing the target stock preparation cost corresponding to the target transportation route with the minimum stock preparation cost under the preset selected warehouse quantity and the current stock preparation cost corresponding to the current transportation route under the preset selected warehouse quantity, and when the target stock preparation cost is less than the current stock preparation cost, the current transportation route corresponding to the preset selected warehouse quantity can be updated to the target transportation route. Thus, through the iterative update method, the transportation route with the minimum stock preparation cost under the preset selected warehouse quantity can be obtained. The user can select a more suitable transportation route for stock preparation from the transportation routes with the minimum stock preparation cost under different preset selected warehouse quantities based on business requirements, further meeting the personalized needs of the user.

[0058] Figure 3 It is a flowchart of another stock preparation method provided by an embodiment of the present invention. Based on the above embodiments, the specific process of the Bellman-Ford search is described in detail. The explanations of the same or corresponding terms in the above embodiments are not repeated here.

[0059] See Figure 3 , another stock preparation method provided by this embodiment specifically includes the following steps:

[0060] S310. Obtain the target item information, target source warehouse, target platform warehouse set, target demand location, target item demand quantity corresponding to the target demand location, and transportation line cost information corresponding to the target item.

[0061] S320. Through the variable neighborhood search method, perform variable neighborhood search on the target platform warehouse set based on the initial platform warehouse subset to obtain the searched target platform warehouse subset.

[0062] S330. If multiple target platform warehouse subsets are searched, for each target platform warehouse subset, construct a target search network corresponding to the target platform warehouse subset according to the available routes in the target source warehouse, target platform warehouse subset, target demand location, and transportation line cost information.

[0063] Specifically, for each searched target platform warehouse subset, various network nodes can be determined according to the target source warehouse, target platform warehouses included in the target platform warehouse subset, and the target demand location, and based on the available routes in the transportation line cost information, connect the transportation relationships between various network nodes, thereby constructing a target search network corresponding to the target platform warehouse subset.

[0064] Exemplarily, S330 may include: determining a target source warehouse, each target platform warehouse in the target platform warehouse subset, and a target demand location as network nodes in a target search network; and connecting the respective network nodes based on the available routes in the transportation route cost information to construct the target search network corresponding to the target platform warehouse subset.

[0065] Specifically, the target source warehouse, each target platform warehouse included in the target platform warehouse subset, and the target demand location may all be regarded as a network node, and based on each available route in the transportation route cost information, two network nodes with an available route therebetween are connected to obtain the target search network corresponding to the target platform warehouse subset. For example, Figure 4 An example of a transportation route search process is given. Figure 4 In [the example], network node O is the target source warehouse, network nodes A, B, and C are the three target platform warehouses included in the target platform warehouse subset, network node H is the target demand location, and the constructed target search network is as Figure 4 shown.

[0066] S340. Determine the node stock preparation cost corresponding to each network node in the target search network according to the target item weight information in the target item information, the unit transportation cost in the transportation route cost information, and the target item demand quantity.

[0067] Specifically, for each network node, the distance and unit transportation cost between the current network node and the previous network node (i.e., the network node connected to the current network node) may be obtained, and based on this distance, unit transportation cost, target item weight information, and target item demand quantity, the node stock preparation cost corresponding to this network node may be determined.

[0068] Exemplarily, S340 may include: for each network node in the target search network, determining the node stock preparation cost corresponding to the current network node according to the distance between the current network node and the previous network node, the target item weight information in the target item information, the target item demand quantity, and the unit transportation cost in the transportation route cost information.

[0069] Specifically, for each network node, the distance between the current network node and the previous network node, the target item weight information, the target item demand quantity, and the unit transportation cost (yuan / (kilometer * kilogram)) can be multiplied, and the obtained multiplication result is used as the node transportation cost, and this node transportation cost can be used as the corresponding node stock preparation cost. Exemplarily, if the current network node is the node corresponding to the target demand location, the unit storage cost (yuan / item) and the target item demand quantity in the target item information can be used to determine the node warehousing cost corresponding to the current network node, and the node warehousing cost and the node transportation cost corresponding to the current network node are added to obtain the node stock preparation cost corresponding to the current network node. If the current network node is not the node corresponding to the target demand location, the node transportation cost corresponding to the current network node can be directly used as the node stock preparation cost corresponding to the current network node. As Figure 4 shown, the value on each connection line is the node stock preparation cost corresponding to the network node connected by the connection line.

[0070] S350. Through the Bellman-Ford search method, on the target search network, based on the preset maximum number of search nodes and the node stock preparation cost, search for the transportation path with the minimum stock preparation cost, and obtain the first transportation path corresponding to the searched target platform warehouse subset and the first stock preparation cost corresponding to the first transportation path.

[0071] Among them, the preset maximum number of search nodes can be pre-set, which is the maximum number of nodes that the searched path passes through at most. The preset maximum number of search nodes does not include the starting node but includes the ending node. For example, if a target platform warehouse for transfer is allowed in the transportation path, the preset maximum number of search nodes can be set to 3. That is to say, starting from the target source warehouse, it can pass through two target platform warehouses to reach the target demand location. It should be noted that the number of search rounds is equal to the preset maximum number of search nodes. In the first round of search, it passes through at most one network node, in the second round of search, it passes through at most two network nodes, and in each subsequent round of search, the number of search nodes is increased by one based on the previous round of search until the preset maximum number of search nodes is reached.

[0072] Specifically, through the Bellman-Ford search method, the transportation path can be searched on the target search network to find the first transportation path with the minimum stock preparation cost. For example, the number of search rounds is controlled by the preset maximum number of search nodes, and in each search, the minimum stock preparation cost from the network node to the starting node is updated. After the search is completed, the first transportation path corresponding to the minimum stock preparation cost can be obtained based on the search result, that is, the transportation path with the minimum stock preparation cost required in the process of reaching the target demand location from the target source warehouse. For example, Figure 4It is necessary to find the minimum-cost path from network node O to network node H, with a requirement of passing through at most 3 network nodes. In the first round of search, the paths from the starting point to other points are allowed to pass through 1 node. At this time, the minimum cost from the starting point O to A is 1, the minimum cost to B is 4, the minimum distance to C is 7, and there is no path to reach H by passing through only one node, so it is infinite (∞). In the second round of search, the paths from the starting point to other points are allowed to pass through 2 nodes. The cost of O going to A first and then to B is less than the cost of O going directly to B, so the minimum cost is updated to 3. Similarly, the minimum cost of O to C is updated to 5, and the minimum cost of O to D is updated to 7. In the third round of search, the paths from the starting point to other points are allowed to pass through 3 nodes. The minimum-cost path of O to C is O->A->B->C, and the minimum cost is updated to 4; the minimum-cost path of O to H is O->A->B->H, and the minimum cost is updated to 6. Although the shortest path from O to H is O->A->B->C->H with a minimum cost of 6, the number of nodes it passes through is 4, which is greater than the preset maximum number of search nodes. Therefore, the minimum-cost path from node O to node H is O->A->B->H with a minimum cost of 6. That is to say, in the first transportation path corresponding to the target platform warehouse subset (i.e., the set containing network nodes A, B, and C), it is O->A->B->H, and the first stocking cost corresponding to this first transportation path is 6.

[0073] It should be noted that if there are multiple target source warehouses, a non-existent virtual source can be set above the multiple target source warehouses, and this virtual source is used as the starting node. Connect the node corresponding to this virtual source with the nodes corresponding to each target source warehouse, and determine the node stocking cost corresponding to each node corresponding to the target source warehouse as 0, so as to obtain a single-source target search network, so that the transportation path of this target search network can be searched by the Bellman-Ford search method to ensure the accuracy of the search results.

[0074] S360. According to the first transportation path and the first stocking cost corresponding to each target platform warehouse subset, determine the target transportation path from each first transportation path, and determine the first stocking cost corresponding to the target transportation path as the target stocking cost.

[0075] S370. Update the current transportation path based on the target stocking cost and the current stocking cost corresponding to the current transportation path.

[0076] Based on the target platform warehouse included in the target transportation path, update the initial subset of platform warehouses, and iteratively execute the operation of searching for the transportation path of the target stocking cost through the variable neighborhood search method and the Bellman-Ford search method based on the updated initial subset of platform warehouses until the preset convergence condition is met, and then perform stocking based on the current transportation path and the target item demand.

[0077] In the technical solution of this embodiment, through the Bellman-Ford search method, the preset maximum number of search nodes, and the node stocking cost, search for the transportation path of the constructed target search network to obtain the first transportation path with the minimum stocking cost found, so that the Bellman-Ford search method can perform the minimum cost path search more quickly and accurately, thereby further improving the accuracy and efficiency of stocking.

[0078] On the basis of the above technical solution, a stocking model for solving the minimum stocking cost can be constructed, and by solving the stocking model, the transportation path with the minimum stocking cost can be obtained.

[0079] Among them, the objective function of this stocking model can be as follows:

[0080]

[0081] The corresponding constraint conditions are as follows:

[0082]

[0083]

[0084]

[0085]

[0086]

[0087] ∑ p∈P x jp ≤M*u j (6)

[0088] ∑ j∈J u j =α (7)

[0089]

[0090]

[0091]

[0092]

[0093] Among them, in the stocking model, the set \(I\) refers to the set of source warehouses \(I = \{1, 2, \cdots\}\); the set \(J\) refers to the set of platform warehouses \(J = \{1, 2, \cdots\}\). Warehouses \(j'\) and \(j\) respectively refer to a platform warehouse in the set \(J\) of platform warehouses. And warehouse \(j'\) is the platform warehouse for transshipment, and warehouse \(j\) is the platform warehouse for final stocking. When warehouse \(j\) and warehouse \(j'\) are the same platform warehouse, it indicates that there is no transshipment warehouse. The set \(P\) refers to the set of items to be stocked \(P = \{1, 2, \cdots\}\); the set \(L\) refers to the set of demand locations \(L = \{1, 2, \cdots\}\).

[0094] Among them, the parameter \(h\) in the stocking model p refers to the weight of item \(p\); \(c\ ij′ refers to the unit transportation cost from source warehouse \(i\) to platform warehouse \(j'\) (unit: yuan / (kilometer * kilogram)); \(c\ j′j refers to the unit transportation cost from platform warehouse \(j'\) to platform warehouse \(j\) (unit: yuan / (kilometer * kilogram)); \(c\ jl refers to the unit transportation cost from platform warehouse \(j\) to demand location \(l\) (unit: yuan / (kilometer * kilogram)). \(d\ ij′ refers to the distance from source warehouse \(i\) to platform warehouse \(j'\); \(d\ j′j refers to the distance from platform warehouse \(j'\) to platform warehouse \(j\); \(d\ jl is the distance from platform warehouse \(j\) to demand location \(l\). \(g\ lp refers to the demand quantity of item \(p\) at demand location \(l\). \(s\ p is the unit storage cost of item \(p\) stored in only one warehouse. If the number of warehouses for storage is \(n\), then the unit storage cost for storage in \(n\) warehouses is \(\alpha\) is the preset number of selected warehouses. \(M\) is infinity.

[0095] Among them, the variable \(y\) in the stocking model ijp refers to the quantity of item \(p\) transported from source warehouse \(i\) to platform warehouse \(j\); \(y\ j′jp refers to the quantity of item \(p\) transported from platform warehouse \(j'\) to platform warehouse \(j\); \(y\ jlp refers to the quantity of item \(p\) transported from platform warehouse \(j\) to demand location \(l\); \(x\ jp is a 0 - 1 variable used to represent whether platform warehouse \(j\) can store item \(p\); \(z\ ij′p is a 0 - 1 variable used to represent whether source warehouse \(i\) transports item \(p\) to platform warehouse \(j'\); \(z\ j′jp is a 0 - 1 variable used to represent whether platform warehouse \(j'\) transports item \(p\) to platform warehouse \(j\); \(z\ jlp is a 0 - 1 variable used to represent whether platform warehouse \(j\) transports item \(p\) to demand location \(l\); \(u\ j is a 0 - 1 variable used to represent whether platform warehouse \(j\) is selected.

[0096] Specifically, the above constraint (1) means that the same type of commodity in each demand area can only be distributed by one platform warehouse. Constraint (2) means that each type of item in each platform warehouse can only have one source, such as obtained from the source warehouse or from the platform warehouse for transshipment. Constraint (3) means that the inbound quantity of each type of item in the platform warehouse is equal to the outbound quantity. Constraint (4) means that the platform warehouse can receive item p only when item p can be stored in platform warehouse j. Constraint (5) means that the platform warehouse j can transport item p to the demand area l only when item p is stored in platform warehouse j. Constraint (6) means that items can be stored only when the platform warehouse is selected. Constraint (7) means that the selected warehouse quantity corresponding to the platform warehouse meets the requirements. Constraints (8)-(10) mean that the transportation of item p is allowed only when the transportation route is an available route. Constraint (11) means the value range of each variable. By minimizing the objective function based on the above constraints, the transportation route with the minimum stocking cost can be obtained, so that subsequent stocking can be carried out based on this transportation route, improving the accuracy of stocking and reducing the stocking cost.

[0097] The following is an embodiment of the stocking device provided by the embodiment of the present invention. This device and the stocking methods of the above embodiments belong to the same inventive concept. Details not described in detail in the embodiment of the stocking device can refer to the embodiments of the above stocking methods.

[0098] Figure 5 FIG. is a schematic structural diagram of a stocking device provided by an embodiment of the present invention. This embodiment is applicable to the situation of stocking the platform warehouses in an e-commerce platform. As Figure 5 shown, the device specifically includes: an information acquisition module 510, a target platform warehouse subset determination module 520, a target transportation route determination module 530, a current transportation route update module 540, and a stocking module 550.

[0099] Among them, the information acquisition module 510 is used to acquire the target item information corresponding to the target item, the target source warehouse, the target platform warehouse set, the target demand location, the target item demand quantity corresponding to the target demand location, and the transportation line cost information; the target platform warehouse subset determination module 520 is used to perform variable neighborhood search on the target platform warehouse set on the basis of the initial platform warehouse subset by means of variable neighborhood search to obtain the searched target platform warehouse subset; the target transportation path determination module 530 is used to perform a transportation path search for the target stocking cost on the target search network constructed according to the available lines in the target source warehouse, the target platform warehouse subset, the target demand location, and the transportation line cost information, based on the node stocking cost in the target search network, to determine the target transportation path and the target stocking cost corresponding to the target transportation path, where the node stocking cost is determined based on the target item information, the target item demand quantity, and the unit transportation cost in the transportation line cost information; the current transportation path update module 540 is used to update the current transportation path based on the target stocking cost and the current stocking cost corresponding to the current transportation path; the stocking module 550 is used to update the initial platform warehouse subset based on the target platform warehouse included in the target transportation path, and iteratively execute the operation of performing a transportation path search for the target stocking cost by means of the variable neighborhood search method and the Bellman-Ford search method based on the updated initial platform warehouse subset, until when the preset convergence condition is met, perform stocking based on the current transportation path and the target item demand quantity.

[0100] In the technical solution of this embodiment, through the variable neighborhood search method, a variable neighborhood search is performed on the target platform warehouse set corresponding to the target item based on the initial platform warehouse subset to obtain the searched target platform warehouse subset. And through the Bellman-Ford search method, on the target search network constructed according to the available routes in the target source warehouse, the target platform warehouse subset, the target demand location, and the transportation line cost information corresponding to the target item, a transportation path search for the target stocking cost is performed based on the node stocking cost in the target search network to determine the target transportation path and the target stocking cost corresponding to the target transportation path. Among them, the node stocking cost is determined based on the target item information, the target item demand quantity, and the unit transportation cost in the transportation line cost information. Based on the target stocking cost and the current stocking cost corresponding to the current transportation path, the current transportation path is updated so that the updated current transportation path is the transportation path with the minimum stocking cost. According to the target platform warehouse included in the target transportation path, the initial platform warehouse subset is updated, and based on the updated initial platform warehouse subset, the operations of performing a transportation path search for the target stocking cost through the variable neighborhood search method and the Bellman-Ford search method are iteratively executed. Thus, an optimal current transportation path can be obtained through iterative update, and stocking is performed based on the current transportation path and the target item demand quantity, thereby improving the accuracy of stocking and reducing the stocking cost.

[0101] Optionally, the target platform warehouse subset determination module 520 is specifically configured to:

[0102] Based on the target platform warehouse set and the initial platform warehouse subset, determine the initial solution corresponding to the target platform warehouse set; through the variable neighborhood search method, perform neighborhood transformation on the initial solution to obtain the transformed neighborhood solution, and determine the target platform warehouse subset corresponding to the neighborhood solution.

[0103] Optionally, the target transportation path determination module 530 includes:

[0104] The first transportation path determination unit is configured to, if multiple target platform warehouse subsets are searched, for each of the target platform warehouse subsets, through the Bellman-Ford search method, on the target search network constructed according to the available routes in the target source warehouse, the target platform warehouse subset, the target demand location, and the transportation line cost information, perform a transportation path search for the minimum stocking cost based on the node stocking cost in the target search network to obtain the first transportation path corresponding to the searched target platform warehouse subset and the first stocking cost corresponding to the first transportation path;

[0105] A target transportation path determination unit, configured to determine a target transportation path from each of the first transportation paths according to the first transportation paths and the first stock preparation costs corresponding to each of the target platform warehouse subsets, and determine the first stock preparation cost corresponding to the target transportation path as the target stock preparation cost.

[0106] Optionally, the first transportation path determination unit includes:

[0107] A target search network construction subunit, configured to construct a target search network corresponding to the target platform warehouse subset according to the available routes in the target source warehouse, the target platform warehouse subset, the target demand location, and the transportation line cost information;

[0108] A node stock preparation cost determination subunit, configured to determine the node stock preparation cost corresponding to each node in the target search network according to the target item weight information in the target item information, the unit transportation cost in the transportation line cost information, and the target item demand;

[0109] A first transportation path determination subunit, configured to perform a transportation path search with the minimum stock preparation cost on the target search network based on a preset maximum number of search nodes and the node stock preparation cost through the Bellman-Ford search method, and obtain the first transportation path corresponding to the target platform warehouse subset obtained by the search and the first stock preparation cost corresponding to the first transportation path.

[0110] Optionally, the target search network construction subunit is specifically configured to:

[0111] Determine the target source warehouse, each target platform warehouse in the target platform warehouse subset, and the target demand location as network nodes in the target search network; and connect the network nodes based on the available routes in the transportation line cost information to construct a target search network corresponding to the target platform warehouse subset.

[0112] Optionally, the node stock preparation cost determination subunit is specifically configured to:

[0113] For each network node in the target search network, determine the node stock preparation cost corresponding to the current network node according to the distance between the current network node and the previous network node, the target item weight information in the target item information, the target item demand, and the unit transportation cost in the transportation line cost information.

[0114] Optionally, the current transportation path update module 540 is specifically configured to: if the target stock preparation cost is less than the current stock preparation cost corresponding to the current transportation path, update the current transportation path to the target transportation path.

[0115] Optionally, the device further includes:

[0116] A target platform warehouse subset screening module, configured to determine the number of platform warehouses corresponding to each of the searched target platform warehouse subsets after obtaining the searched target platform warehouse subsets; and screen out the target platform warehouse subsets with the number of platform warehouses equal to the preset warehouse selection number from each of the target platform warehouse subsets;

[0117] The current transportation path updating module 540 is specifically configured to: update the current transportation path corresponding to the preset warehouse selection number based on the target stock preparation cost and the current stock preparation cost corresponding to the current transportation path.

[0118] The stock preparation device provided by the embodiment of the present invention can execute the stock preparation method provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the stock preparation method.

[0119] It should be noted that in the embodiments of the above stock preparation device, the included units and modules are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0120] Figure 6 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Figure 6 It shows a block diagram of an exemplary electronic device 12 suitable for implementing the embodiments of the present invention. Figure 6 The displayed electronic device 12 is only an example and should not bring any limitation to the functions and usage scope of the embodiments of the present invention.

[0121] As Figure 6 shown, the electronic device 12 is presented in the form of a general-purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0122] The bus 18 represents one or more of several types of bus structures, including a memory bus or a memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the multiple bus structures. For example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0123] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0124] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 can be used for reading and writing on non-removable, non-volatile magnetic media ( Figure 6 not shown, typically referred to as a "hard disk drive"). Although Figure 6 not shown in the figure, a disk drive for reading and writing on removable non-volatile disks (such as "floppy disks"), and an optical disk drive for reading and writing on removable non-volatile optical disks (such as CD-ROM, DVD-ROM or other optical media) can be provided. In these cases, each drive can be connected to the bus 18 through one or more data media interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0125] A program / utility 40 having a set (at least one) of program modules 42 can be stored, for example, in the system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment. The program modules 42 generally perform the functions and / or methods in the embodiments described in the present invention.

[0126] The electronic device 12 can also communicate with one or more external devices 14 (such as a keyboard, a pointing device, a display 24, etc.), and can also communicate with one or more devices that enable a user to interact with the electronic device 12, and / or communicate with any device that enables the electronic device 12 to communicate with one or more other computing devices (such as a network card, a modem, etc.). Such communication can be carried out through the input / output (I / O) interface 22. Moreover, the electronic device 12 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 20. As shown in the figure, the network adapter 20 communicates with other modules of the electronic device 12 through the bus 18. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in combination with the electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0127] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, for example, implementing the steps of a stock preparation method provided by the present embodiment. The method includes:

[0128] Obtaining the target item information corresponding to the target item, the target source warehouse, the set of target platform warehouses, the target demand location, the target item demand quantity corresponding to the target demand location, and the transportation line cost information;

[0129] Through the variable neighborhood search method, perform variable neighborhood search on the set of target platform warehouses based on the initial subset of platform warehouses to obtain the subset of target platform warehouses found;

[0130] Through the Bellman-Ford search method, on the target search network constructed according to the available routes in the target source warehouse, the subset of target platform warehouses, the target demand location, and the transportation line cost information, perform a transportation path search for the target stock preparation cost based on the node stock preparation cost in the target search network, and determine the target transportation path and the target stock preparation cost corresponding to the target transportation path, where the node stock preparation cost is determined based on the unit transportation cost in the target item information, the target item demand quantity, and the transportation line cost information;

[0131] Update the current transportation path based on the target stock preparation cost and the current stock preparation cost corresponding to the current transportation path;

[0132] Based on the target platform warehouses included in the target transportation route, update the initial subset of platform warehouses, and iteratively execute the operation of searching for the transportation route with the target stocking cost through the variable neighborhood search method and the Bellman-Ford search method based on the updated initial subset of platform warehouses until the preset convergence condition is met, and then perform stocking based on the current transportation route and the target item demand.

[0133] Of course, those skilled in the art can understand that the processor can also implement the technical solutions of the stocking method provided in any embodiment of the present invention.

[0134] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the steps of the stocking method provided in any embodiment of the present invention. The method includes:

[0135] Obtain the target item information corresponding to the target item, the target source warehouse, the set of target platform warehouses, the target destination, the target item demand corresponding to the target destination, and the transportation line cost information;

[0136] Through the variable neighborhood search method, perform variable neighborhood search on the set of target platform warehouses based on the initial subset of platform warehouses to obtain the searched subset of target platform warehouses;

[0137] Through the Bellman-Ford search method, on the target search network constructed based on the available routes in the target source warehouse, the subset of target platform warehouses, the target destination, and the transportation line cost information, perform a transportation route search for the target stocking cost based on the node stocking cost in the target search network, and determine the target transportation route and the target stocking cost corresponding to the target transportation route, where the node stocking cost is determined based on the unit transportation cost in the target item information, the target item demand, and the transportation line cost information;

[0138] Update the current transportation route based on the target stocking cost and the current stocking cost corresponding to the current transportation route;

[0139] Based on the target platform warehouses included in the target transportation route, update the initial subset of platform warehouses, and iteratively execute the operation of searching for the transportation route with the target stocking cost through the variable neighborhood search method and the Bellman-Ford search method based on the updated initial subset of platform warehouses until the preset convergence condition is met, and then perform stocking based on the current transportation route and the target item demand.

[0140] The computer storage medium of an embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable media may be computer-readable signal media or computer-readable storage media. The computer-readable storage media may be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, the computer-readable storage media may be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, device, or component.

[0141] The computer-readable signal media may include data signals propagated in a baseband or as part of a carrier wave, which carry computer-readable program codes. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal media may also be any computer-readable medium other than the computer-readable storage media, and the computer-readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, device, or component.

[0142] The program codes contained on the computer-readable media can be transmitted by any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0143] The computer program codes for performing the operations of the present invention can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages - such as the "C" language or similar programming languages. The program codes can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's 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 can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0144] Those of ordinary skill in the art should understand that the various modules or steps of the present invention described above can be implemented using a general-purpose computing device. They can be centralized on a single computing device or distributed across a network composed of multiple computing devices. Optionally, they can be implemented using program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0145] Note that the above is only a preferred embodiment of the present invention and the technical principles applied. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein. Various obvious changes, re-adjustments, and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments only. Without departing from the concept of the present invention, it can also include more other equivalent embodiments, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A stocking method, characterized in that, Including: Obtaining target item information corresponding to a target item, a target source warehouse, a set of target platform warehouses, a target destination, the target item demand quantity corresponding to the target destination, and transportation route cost information; Performing variable neighborhood search on the set of target platform warehouses based on an initial platform warehouse subset through a variable neighborhood search method to obtain a searched target platform warehouse subset; Performing a transportation path search for the target stocking cost based on the node stocking cost in a target search network constructed according to available routes among the target source warehouse, the target platform warehouse subset, the target destination, and the transportation route cost information through a Bellman-Ford search method, determining a target transportation path and the target stocking cost corresponding to the target transportation path, where the node stocking cost is determined based on the target item information, the target item demand quantity, and the unit transportation cost in the transportation route cost information; Updating the current transportation path based on the target stocking cost and the current stocking cost corresponding to the current transportation path; Updating the initial platform warehouse subset based on the target platform warehouses included in the target transportation path, and iteratively performing the operation of performing a transportation path search for the target stocking cost through the variable neighborhood search method and the Bellman-Ford search method based on the updated initial platform warehouse subset until a preset convergence condition is met, and then performing stocking based on the current transportation path and the target item demand quantity.

2. The method according to claim 1, characterized in that, The performing variable neighborhood search on the set of target platform warehouses based on an initial platform warehouse subset through a variable neighborhood search method to obtain a searched target platform warehouse subset includes: Determining an initial solution corresponding to the set of target platform warehouses based on the set of target platform warehouses and the initial platform warehouse subset; Performing neighborhood transformation on the initial solution through a variable neighborhood search method to obtain a transformed neighborhood solution, and determining the target platform warehouse subset corresponding to the neighborhood solution.

3. The method according to claim 1, characterized in that, The performing a transportation path search for the target stocking cost based on the node stocking cost in a target search network constructed according to available routes among the target source warehouse, the target platform warehouse subset, the target destination, and the transportation route cost information through a Bellman-Ford search method, determining a target transportation path and the target stocking cost corresponding to the target transportation path includes: If multiple target platform warehouse subsets are searched, for each of the target platform warehouse subsets, performing a transportation path search for the minimum stocking cost based on the node stocking cost in a target search network constructed according to available routes among the target source warehouse, the target platform warehouse subset, the target destination, and the transportation route cost information through a Bellman-Ford search method to obtain a first transportation path corresponding to the searched target platform warehouse subset and the first stocking cost corresponding to the first transportation path; Determine a target transportation route from each of the first transportation routes according to the first transportation route and the first stock preparation cost corresponding to each target platform warehouse subset, and determine the first stock preparation cost corresponding to the target transportation route as the target stock preparation cost.

4. The method according to claim 3, characterized in that, The method of obtaining the first transportation route corresponding to the target platform warehouse subset and the first stock preparation cost corresponding to the first transportation route by performing a transportation route search for the minimum stock preparation cost based on the node stock preparation cost in the target search network constructed by the Bellman-Ford search method according to the available routes in the target source warehouse, the target platform warehouse subset, the target destination, and the transportation line cost information includes: Construct a target search network corresponding to the target platform warehouse subset according to the target source warehouse, the target platform warehouse subset, the target destination, and the available routes in the transportation line cost information; Determine the node stock preparation cost corresponding to each node in the target search network according to the target item weight information in the target item information, the unit transportation cost in the transportation line cost information, and the target item demand; By the Bellman-Ford search method, perform a transportation route search for the minimum stock preparation cost on the target search network based on the preset maximum number of search nodes and the node stock preparation cost, and obtain the first transportation route corresponding to the target platform warehouse subset obtained by the search and the first stock preparation cost corresponding to the first transportation route.

5. The method according to claim 4, characterized in that, The constructing a target search network corresponding to the target platform warehouse subset according to the target source warehouse, the target platform warehouse subset, the target destination, and the available routes in the transportation line cost information includes: Determine the target source warehouse, each target platform warehouse in the target platform warehouse subset, and the target destination as network nodes in the target search network; Based on the available routes in the transportation line cost information, connect the network nodes to construct a target search network corresponding to the target platform warehouse subset.

6. The method according to claim 4, characterized in that, The determining the node stock preparation cost corresponding to each network node in the target search network according to the target item weight information in the target item information, the unit transportation cost in the transportation line cost information, and the target item demand includes: For each network node in the target search network, determine the node stock preparation cost corresponding to the current network node according to the distance between the current network node and the previous network node, the target item weight information in the target item information, the target item demand, and the unit transportation cost in the transportation line cost information.

7. The method according to claim 1, characterized in that, The updating the current transportation route based on the target stock preparation cost and the current stock preparation cost corresponding to the current transportation route includes: If the target stock preparation cost is less than the current stock preparation cost corresponding to the current transportation route, update the current transportation route to the target transportation route.

8. The method according to any one of claims 1-7, characterized in that, After obtaining the target platform warehouse subset obtained by the search, it further includes: Determine the number of platform warehouses corresponding to each of the searched target platform warehouse subsets; Filter out the target platform warehouse subsets with the number of platform warehouses equal to the preset warehouse selection quantity from each of the target platform warehouse subsets; The updating of the current transportation route based on the target stocking cost and the current stocking cost corresponding to the current transportation route includes: Updating the current transportation route corresponding to the preset warehouse selection quantity based on the target stocking cost and the current stocking cost corresponding to the current transportation route.

9. A stocking device, characterized in that, Including: An information acquisition module, configured to acquire target item information corresponding to a target item, a target source warehouse, a target platform warehouse set, a target demand location, the target item demand quantity corresponding to the target demand location, and transportation route cost information; A target platform warehouse subset determination module, configured to perform variable neighborhood search on the target platform warehouse set based on an initial platform warehouse subset by means of variable neighborhood search to obtain the searched target platform warehouse subsets; A target transportation route determination module, configured to perform a transportation route search for the target stocking cost on a target search network constructed according to available routes in the target source warehouse, the target platform warehouse subsets, the target demand location, and the transportation route cost information, and determine a target transportation route and the target stocking cost corresponding to the target transportation route, wherein the node stocking cost is determined based on the target item information, the target item demand quantity, and the unit transportation cost in the transportation route cost information; A current transportation route update module, configured to update the current transportation route based on the target stocking cost and the current stocking cost corresponding to the current transportation route; A stocking module, configured to update the initial platform warehouse subset based on the target platform warehouses included in the target transportation route, and iteratively execute the operation of performing a transportation route search for the target stocking cost by means of the variable neighborhood search method and the Bellman-Ford search method based on the updated initial platform warehouse subset, and perform stocking based on the current transportation route and the target item demand quantity until a preset convergence condition is met.

10. An electronic device, characterized in that, The electronic device includes: One or more processors; A memory, configured to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the stocking method according to any one of claims 1-8.

11. A computer-readable storage medium, on which a computer program is stored, characterized in that, When the program is executed by the processor, it implements the stocking method according to any one of claims 1-8.

Images