Article storage position determination method and device

Abstract

The invention discloses an article storage position determination method and device, and relates to the technical field of computers. According to one specific embodiment, the method comprises the steps that article information of articles to be shelved and an article storage position contrast relation table are obtained, the article storage position contrast relation table is obtained by solving a storage position recommendation model, and the storage position recommendation model is constructed based on the picking distance and shelving distance of similar articles and associated articles; according to the article information and an article storage position contrast relation table, obtaining a planned storage position of the to-be-shelved article; and in response to the fact that the planned storage position meets the shelving condition, the planned storage position serves as the storage position of the to-be-shelved article. According to the embodiment, the storage positions are allocated in combination with the storage position recommendation model, the classification standard can be richer and more flexible, the storage positions can be planned in combination with the relationship between the change of the storage environment and the material attributes of the articles better, the method can adapt to more complex storage position allocation scenes, and the rationality and success rate of storage position allocation are improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and device for determining a storage location of an item. Background Art

[0002] With the rapid development of e-commerce, the requirements for warehouse cargo processing speed are getting higher and higher. The layout of the storage location (i.e., storage location or placement location) of items in the warehouse will affect the efficiency of outbound operations and warehouse utilization, and directly affect the logistics cost. Therefore, how to optimize the storage location layout in the warehouse is an urgent problem to be solved. At present, when allocating storage locations in the warehouse, the items are mainly classified and stored according to the sales volume of the items.

[0003] However, when using classified storage to allocate storage space, the classification criteria are too simple and fixed, the selection of classification dimensions is relatively complex, and a reasonable balance of various indicators is required. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a method and device for determining the storage location of an item, which can be combined with a storage location recommendation model to perform storage location allocation. The classification standards can be richer and more flexible, and the storage location planning can be better combined with the changes in the storage environment and the relationship between the material properties of the items. It can adapt to more complex storage location allocation scenarios, and improve the rationality and success rate of storage location allocation.

[0005] To achieve the above object, according to one aspect of an embodiment of the present invention, a method for determining a storage location of an item is provided, comprising: Obtaining item information and an item storage location comparison relationship table of items to be put on the shelves, wherein the item storage location comparison relationship table is obtained by solving a storage location recommendation model, wherein the storage location recommendation model is constructed based on the picking distance and the shelving distance of similar items and related items; Obtaining the planned storage location of the item to be put on the shelf according to the item information and the item storage location comparison relationship table; In response to the planned storage location satisfying the shelving condition, the planned storage location is used as the storage location for the item to be shelved.

[0006] Optionally, solving the storage location recommendation model includes: taking each item and each storage location in the warehouse as a vertex to construct edges between items and storage locations; for each item, taking the picking distance and shelf distance of the item when stored in each storage location as the weight corresponding to the edge to generate a weight matrix; constructing a bipartite graph based on the edges between items and storage locations, and the weights corresponding to each edge; and according to the weight matrix, using a bipartite graph maximum weight matching algorithm to completely match the bipartite graph to solve the storage location recommendation model.

[0007] Optionally, before constructing edges between items and storage locations with each item and each storage location in the warehouse as vertices, it also includes: in response to business needs, storing the target item in multiple storage locations, and adding copies of the target item according to the number of storage locations so that each target item corresponds to a storage location; in response to business needs, storing multiple items in one target storage location, and adding copies of the target storage location according to the number of items so that each target storage location corresponds to one item.

[0008] Optionally, according to the weight matrix, a bipartite graph maximum weight matching algorithm is used to completely match the bipartite graph, including: in response to the number of items being equal to the number of storage locations, directly according to the weight matrix, the bipartite graph is completely matched using the bipartite graph maximum weight matching algorithm; in response to the number of items being less than the number of storage locations, according to the difference between the number of storage locations and the number of items, a first weight matrix is ​​obtained by adding a number of zero elements equal to the difference in rows to the weight matrix, and according to the first weight matrix, the bipartite graph is completely matched using the bipartite graph maximum weight matching algorithm.

[0009] Optionally, the method further includes: in response to the planned storage location not satisfying the shelving conditions, acquiring an adjacent storage location of the planned storage location; in response to the adjacent storage location satisfying the shelving conditions, using the adjacent storage location as an item storage location for the items to be shelved.

[0010] Optionally, obtaining the neighboring storage locations of the planned storage location includes: determining a first storage location set based on the distances between each storage location in the warehouse and the planned storage location; sorting the storage locations in the first storage location set by a sorting learning algorithm, and obtaining the neighboring storage locations of the planned storage location based on the sorting results.

[0011] Optionally, the method further includes: in response to the adjacent storage location not satisfying the shelving conditions, obtaining the original storage location of the item to be shelved, the original storage location being a storage location among the storage locations of the item to be shelved that is different from the planned storage location; in response to the original storage location satisfying the shelving conditions, using the original storage location as the item storage location for the item to be shelved.

[0012] Optionally, the method further includes: in response to the original storage location not satisfying the shelving condition, acquiring an empty storage location; in response to the empty storage location satisfying the shelving condition, using the empty storage location as the item storage location for the item to be shelved.

[0013] Optionally, the method further includes: in response to the item to be put on the shelf being not the first item to be put on the shelf in the list of items to be put on the shelf, before obtaining the planned storage location of the item to be put on the shelf based on the item information and the item storage location comparison relationship table, obtaining the storage location of the previous item to be put on the shelf, and confirming that the adjacent storage location of the storage location of the previous item to be put on the shelf does not meet the shelving conditions.

[0014] According to another aspect of an embodiment of the present invention, there is provided a device for determining a storage location of an item, comprising: A data acquisition module, used to acquire item information and an item storage location comparison relationship table of items to be put on the shelves, wherein the item storage location comparison relationship table is obtained by solving a storage location recommendation model, wherein the storage location recommendation model is constructed based on the picking distance and the shelving distance of similar items and related items; A storage location search module, used to obtain the planned storage location of the item to be put on the shelf according to the item information and the item storage location comparison relationship table; The storage location determination module is used to use the planned storage location as the storage location for the items to be put on the shelves in response to the planned storage location satisfying the shelving conditions.

[0015] According to another aspect of an embodiment of the present invention, there is provided an electronic device, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the storage location of an item provided in an embodiment of the present invention.

[0016] According to another aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for determining the storage location of an item provided in an embodiment of the present invention is implemented.

[0017] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the method for determining the storage location of an item provided in an embodiment of the present invention is implemented.

[0018] An embodiment of the above invention has the following advantages or beneficial effects: by obtaining the item information of the items to be put on the shelves and the item storage location comparison relationship table, the item storage location comparison relationship table is obtained by solving the storage location recommendation model, and the storage location recommendation model is constructed based on the picking distance and the shelving distance of similar items and related items; according to the item information and the item storage location comparison relationship table, the planned storage location of the items to be put on the shelves is obtained; in response to the planned storage location meeting the shelving conditions, the planned storage location is used as the storage location of the items to be put on the shelves. The technical solution can be combined with the storage location recommendation model to perform storage location allocation, the classification standard can be richer and more flexible, and the storage location planning can be better combined with the changes in the storage environment and the relationship between the material attributes of the items. It can adapt to more complex storage location allocation scenarios and improve the rationality and success rate of storage location allocation.

[0019] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention. Figure 1 is a schematic diagram of main steps of a method for determining an item storage location according to an embodiment of the present invention; Figure 2 It is a schematic diagram of a solution process of a storage location recommendation model according to an embodiment of the present invention; Figure 3 is a schematic diagram of a solution process of a storage location recommendation model according to another embodiment of the present invention; Figure 4 is a schematic diagram of a process for determining an item storage location according to an embodiment of the present invention; Figure 5 is a schematic diagram of main modules of a device for determining an object storage location according to an embodiment of the present invention; Figure 6 is an exemplary system architecture diagram to which embodiments of the present invention may be applied; Figure 7 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0022] 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 disclosed in the present invention 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.

[0023] When determining the storage location (i.e. storage position) of items, it is necessary to consider the user experience of warehousing and replenishment while reducing the picking distance. For the layout of storage positions in the warehouse, the ideal situation is to place the best-selling products in the storage positions that are most convenient for warehousing, shelving, replenishment and outbound delivery. In this way, the best-selling products will be distributed in the storage positions close to the packing table or near the lane entrance, and the less popular items will be placed in the storage positions far away from the packing table or the lane buckle, which will save the picking distance in the picking stage, thereby improving the outbound efficiency of the warehouse.

[0024] When determining the storage location of an item, the prior art generates a candidate set of storage locations where the item can be stored. When generating a candidate set of storage locations, all storage locations in the warehouse need to be sorted according to the relevance of the information. However, it is difficult for traditional sorting methods to integrate multiple types of information. If there are too many parameters to consider in the sorting, it will also make parameter adjustment very difficult, and overfitting is likely to occur. Therefore, the present invention uses machine learning to solve this problem. The machine learning method can easily integrate multiple features and has a mature and profound theoretical foundation. The parameters are optimized through iteration, and there is a set of mature theories to solve problems such as sparsity and overfitting.

[0025] In an embodiment of the present invention, Pointwise LTR (Learning to rank, ranking learning refers to any technology used for ranking in machine learning) is used to transform the sorting problem into a classification or regression problem. By training the function f(s,C), for a given item s and a set of related storage location lists C, the ranking of this set of storage locations is predicted, and the storage location with the highest relevance is ranked at the front.

[0026] Figure 1 FIG. 1 is a schematic diagram of the main steps of the method for determining the storage location of an item according to an embodiment of the present invention. Figure 1 As shown, the method for determining the storage location of an item in the embodiment of the present invention mainly includes the following steps S101 to S103.

[0027] Step S101: Obtain the item information of the items to be put on the shelves and the item storage location comparison relationship table, which is obtained by solving the storage location recommendation model, which is constructed based on the picking distance and shelf distance of similar items and related items. According to an embodiment of the present invention, the item information of the items to be put on the shelves includes, for example, item identification (used to uniquely identify an item, such as item name, product style code, etc.), item type, item quantity, item volume, item weight and other information. The item storage location comparison relationship table is, for example, pre-generated and stored in a database.

[0028] In an embodiment of the present invention, the item storage location comparison table is obtained by solving the storage location recommendation model, which is constructed based on the picking distance and shelf distance of similar items and related items. The present invention takes into account the placement of similar items and related items, and calculates the distance from these storage locations to the packing station according to the item demand to find an item placement location closest to the packing station. In one embodiment, the constructed storage location recommendation model is, for example: in, is the distance from storage location j to the packing station; is storage position j to storage position The distance between the two sides is 1 / 2; K is the number of items to be allocated; M is the number of items to be put on the shelves; P is the number of storage locations; It is the storage demand of items; When item i and item j are similar, the value is M (very large), otherwise it is 0; When item i and item j are associated, the value is 0.5, otherwise it is M (very large); is the demand task quantity of item i (i.e. the total quantity of item i in the order); is a decision variable, which has a value of 1 when item i is assigned to storage location j, and 0 otherwise; is the number of order lines for item i to be listed.

[0029] According to an embodiment of the present invention, solving a storage location recommendation model may specifically include: using each item and each storage location in the warehouse as a vertex to construct edges between items and storage locations; for each item, using the picking distance and shelf distance of the item when stored in each storage location as the weight corresponding to the edge to generate a weight matrix; constructing a bipartite graph based on the edges between items and storage locations, and the weights corresponding to each edge; using a bipartite graph maximum weight matching algorithm to perform a complete match on the bipartite graph based on the weight matrix to solve the storage location recommendation model. A so-called complete match is when all points in the first point set and the second point set to be matched have corresponding matches, and all points in the second point set have corresponding matches, and the match is called a complete match.

[0030] Figure 2 : is a schematic diagram of the solution process of the storage location recommendation model of an embodiment of the present invention. In the embodiment of the present invention, the items and storage locations are taken as vertices to obtain the item vertex set V and the storage location vertex set T, and the edges are obtained by connecting the items and the storage locations. Then, the picking distance and the shelf distance when the items are stored in each storage location are used as the weights corresponding to the edges to obtain the weight matrix, and a bipartite graph is constructed by combining the vertices, edges and the weights corresponding to the edges. Among them, the weight of the edge in the bipartite graph is the cost after the commodity storage location is redistributed, and the cost includes the picking distance and the shelf distance. After the bipartite graph is constructed, the greedy algorithm is used to initialize the item vertex value and the storage location vertex value, and then the bipartite graph maximum weight matching algorithm (KM algorithm, the function is to find the maximum weight matching under the complete matching) can be used to perform a complete matching of the bipartite graph. Specifically, the Hungarian algorithm can be used to find a complete matching of equal subgraphs. If a complete matching can be found, the matching result is output as the model solution result; if a complete matching cannot be found, the item vertex value and the storage location vertex value are adjusted, and the bipartite graph is continued to be completely matched until the matching result is output.

[0031] According to one of the embodiments of the present invention, before constructing edges between items and storage locations with each item and each storage location in a warehouse as vertices, it also includes: in response to business needs, storing a target item in multiple storage locations, adding copies of the target item according to the number of storage locations so that each target item corresponds to a storage location; in response to business needs, storing multiple items in one target storage location, adding copies of the target storage location according to the number of items so that each target storage location corresponds to one item.

[0032] In an embodiment of the present invention, when using the bipartite graph maximum weight matching algorithm KM algorithm to generate an item storage location comparison relationship table, the following scenario requirements need to be considered: some items need to be placed in multiple storage locations in the warehouse, that is, one product needs to be placed in multiple locations. At this time, it can be solved by adding copies of the item according to the number of locations required for each item in the actual business. For example: a certain product in the warehouse needs to be placed in 3 storage locations, and 2 copies of the product can be added to the product list; and the storage locations in the warehouse may have a demand for multiple products, that is, placing multiple items in one storage location, such as two products in one location. Similarly, a copy of the storage location can be added to the storage location list in a similar way. After the above processing, the storage location allocation problem is transformed into an unbalanced matching problem of n items and m storage locations, where n and m are the numbers after adding copies. Assume is the weight matrix, the rows are the item numbers (including item copies), the columns are the storage location numbers (including storage location copies), It represents the picking distance and shelf distance required to place the j-th item in the i-th storage location, which requires one item to be allocated to one storage location.

[0033] According to an embodiment of the present invention, based on the weight matrix, the bipartite graph is completely matched using the bipartite graph maximum weight matching algorithm, which may specifically include: in response to the number of items being equal to the number of storage locations, directly based on the weight matrix, the bipartite graph is completely matched using the bipartite graph maximum weight matching algorithm; in response to the number of items being less than the number of storage locations, based on the difference between the number of storage locations and the number of items, a first weight matrix is ​​obtained by adding a number of 0 elements equal to the difference in rows to the weight matrix, and based on the first weight matrix, the bipartite graph is completely matched using the bipartite graph maximum weight matching algorithm.

[0034] Figure 3 FIG. 1 is a schematic diagram of a solution process of a storage location recommendation model according to another embodiment of the present invention. Figure 3 As shown, in the embodiment of the present invention, when the KM algorithm is used to solve the storage location recommendation model, the number of item types n and the number of storage locations m are first obtained, and then n and m are compared to determine whether n is not greater than m. There are three cases: (1) When n = m, the number of item types is the same as the number of storage locations, and the KM algorithm is directly used to solve the problem; (2) When n > m, the number of item types is greater than the number of storage locations, and the storage space in the warehouse does not meet the current item storage needs; (3) When n < m, the number of item types is less than the number of storage locations, and some storage locations are not used for storage. At this time, the method of adding virtual items is adopted. Therefore, the weight value corresponding to the added virtual task (i.e., the last (mn) row of the matrix) is set to 0. The weight matrix is ​​converted into a balanced matching problem by adding zero padding to the edge, and then the KM algorithm is called to solve it. Among them, the weight matrix after adding zero padding is as follows: .

[0035] Afterwards, you can Figure 2 The process shown in the figure calls the KM algorithm to solve the storage location recommendation model and obtain the storage location corresponding to the item. Then, a comparison table of item storage locations can be constructed.

[0036] Step S102: Obtain the planned storage locations of the items to be put on the shelves according to the item information and the item storage location comparison relationship table. According to the item storage location comparison relationship table constructed in step S101 and the item information, the planned storage locations of the items to be put on the shelves can be obtained.

[0037] Step S103: In response to the planned storage location satisfying the shelf conditions, the planned storage location is used as the storage location for the items to be put on the shelves. The shelf conditions can be flexibly set according to the needs of the business scenario. For example, when all the items to be put on the shelves are placed in the storage location, the shelf conditions are determined to be satisfied.

[0038] According to one embodiment of the present invention, the method for determining the storage location of an item further includes: in response to the planned storage location not satisfying the shelving conditions, obtaining an adjacent storage location of the planned storage location; in response to the adjacent storage location satisfying the shelving conditions, using the adjacent storage location as the item storage location for the item to be shelved.

[0039] According to an embodiment of the present invention, obtaining the neighboring storage locations of the planned storage location may specifically include: determining a first storage location set based on the distances between each storage location in the warehouse and the planned storage location; sorting the storage locations in the first storage location set by a sorting learning algorithm, and obtaining the neighboring storage locations of the planned storage location based on the sorting result. Specifically, for example, based on the distances between each storage location in the warehouse and the planned storage location, the storage locations whose distances do not exceed a set threshold may be added to the first storage location set, wherein the set threshold may be flexibly set based on business needs. In general, the storage locations located in the same lane as the planned storage location may be set as neighboring storage locations.

[0040] According to another embodiment of the present invention, the method for determining the storage location of an item further includes: in response to the adjacent storage location not satisfying the shelf condition, obtaining the original storage location of the item to be shelf-mounted, the original storage location being a storage location different from the planned storage location among the storage locations of the item to be shelf-mounted; in response to the original storage location satisfying the shelf condition, using the original storage location as the item storage location of the item to be shelf-mounted. In the embodiment of the present invention, the original storage location is, for example, the storage location where the item is placed before the storage location planning is performed.

[0041] According to another embodiment of the present invention, the method for determining the storage location of an item further includes: in response to the original storage location not satisfying the shelving conditions, acquiring an empty storage location; in response to the empty storage location satisfying the shelving conditions, using the empty storage location as the item storage location for the item to be shelved.

[0042] According to another embodiment of the present invention, the method for determining the storage location of an item further includes: in response to the item to be put on the shelf not being the first item to be put on the shelf in the list of items to be put on the shelf, before obtaining the planned storage location of the item to be put on the shelf according to the item information and the item storage location comparison relationship table, obtaining the storage location of the previous item to be put on the shelf, and confirming that the adjacent storage location of the storage location of the previous item to be put on the shelf does not meet the shelving conditions. When putting items on the shelf,

[0043] Figure 4 FIG. 1 is a schematic diagram of a flow chart of determining the storage location of an item according to an embodiment of the present invention. Figure 4 As shown, in one embodiment of the present invention, when determining the storage location of an item, taking the scenario of putting a product on the shelf as an example, firstly, a product is taken out from the list of products to be put on the shelf and put on the shelf; then, it is determined whether the product is the first product to be put on the shelf.

[0044] If it is the first commodity to be put on the shelf, the commodity information and the commodity storage location comparison table are obtained for the commodity to obtain the planned storage location corresponding to the commodity; then, the planned storage location is checked to determine whether it can be put on the shelf. If it can be put on the shelf, the planned storage location is used as the determined item storage location to put the commodity on the shelf; otherwise, the adjacent storage location of the planned storage location is obtained, and the adjacent storage location is checked to determine whether it can be put on the shelf. If it can be put on the shelf, the adjacent storage location is used as the determined item storage location to put the commodity on the shelf; otherwise, the original storage location of the commodity is obtained, and the original storage location is checked to determine whether it can be put on the shelf. If it can be put on the shelf, the original storage location is used as the determined item storage location to put the commodity on the shelf; otherwise, an empty storage location is obtained, and an empty storage location check is performed to determine whether it can be put on the shelf. If it can be put on the shelf, the empty storage location is used as the determined item storage location to put the commodity on the shelf; otherwise, the commodity fails to be put on the shelf. Then, it is determined whether the commodity list is empty. If it is not empty, another commodity is taken out from the commodity list for putting on the shelf until the commodity list is empty.

[0045] If it is not the first product to be put on the shelf, for this product, first obtain the item storage location of the last product on the shelf, then obtain the adjacent storage location of the item storage location of the last product on the shelf, and perform an adjacent storage location check to determine whether it can be put on the shelf. If it can be put on the shelf, the adjacent storage location of the item storage location of the last product on the shelf is used as the determined item storage location to put the product on the shelf; otherwise, obtain the product information and the product storage location comparison relationship table to obtain the planned storage location corresponding to the product; then perform a planned storage location check to determine whether it can be put on the shelf. If it can be put on the shelf, use the planned storage location as the determined item storage location to put the product on the shelf; otherwise, obtain the adjacent storage location of the planned storage location, and perform an adjacent storage location check to determine whether it can be put on the shelf. If it can be put on the shelf, use the adjacent storage location as the determined item storage location to put the product on the shelf; otherwise, obtain the original storage location of the product, and perform an original storage location check to determine whether it can be put on the shelf. If it can be put on the shelf, the original storage location is used as the determined item storage location to put the product on the shelf; otherwise, an empty storage location is obtained and an empty storage location check is performed to determine whether it can be put on the shelf. If it can be put on the shelf, the empty storage location is used as the determined item storage location to put the product on the shelf; otherwise, the product fails to be put on the shelf. Then, it is determined whether the product list is empty. If it is not empty, another product is taken from the product list and put on the shelf until the product list is empty.

[0046] Figure 5 Schematic diagram of the main modules of the device for determining the storage location of an item according to an embodiment of the present invention. Figure 5 As shown, the device 500 for determining the storage location of an item according to an embodiment of the present invention mainly includes a data acquisition module 501 , a storage location search module 502 and a storage location determination module 503 .

[0047] The data acquisition module 501 is used to obtain the item information of the items to be put on the shelves and the item storage location comparison relationship table, wherein the item storage location comparison relationship table is obtained by solving the storage location recommendation model, and the storage location recommendation model is constructed based on the picking distance and the shelf distance of similar items and related items; A storage location search module 502, used to obtain the planned storage location of the item to be put on the shelf according to the item information and the item storage location comparison relationship table; The storage location determination module 503 is used to use the planned storage location as the storage location for the items to be put on the shelves in response to the planned storage location satisfying the shelving conditions.

[0048] According to one embodiment of the present invention, the device 500 for determining the storage location of an item may further include a model solving module (not shown in the figure), which is used to solve the storage location recommendation model, specifically for: taking each item and each storage location in the warehouse as a vertex to construct an edge between the item and the storage location; for each item, taking the picking distance and the shelf distance of the item when stored in each storage location as the weight corresponding to the edge, generating a weight matrix; constructing a bipartite graph based on the edges between the item and the storage location, and the weights corresponding to each edge; and using the bipartite graph maximum weight matching algorithm to completely match the bipartite graph based on the weight matrix to solve the storage location recommendation model.

[0049] According to another embodiment of the present invention, before the model solving module (not shown in the figure) constructs the edges between the items and the storage locations with each item and each storage location in the warehouse as vertices, it can also be used to: store the target item in multiple storage locations in response to business needs, and increase the copies of the target item according to the number of storage locations so that each target item corresponds to a storage location; store multiple items in one target storage location in response to business needs, and increase the copies of the target storage location according to the number of items so that each target storage location corresponds to an item.

[0050] According to another embodiment of the present invention, when the model solving module (not shown in the figure) uses the bipartite graph maximum weight matching algorithm to completely match the bipartite graph according to the weight matrix, it can be specifically used to: in response to the number of items being equal to the number of storage locations, directly use the bipartite graph maximum weight matching algorithm to completely match the bipartite graph according to the weight matrix; in response to the number of items being less than the number of storage locations, according to the difference between the number of storage locations and the number of items, add a number of 0 elements equal to the difference in rows to obtain a first weight matrix, and according to the first weight matrix, use the bipartite graph maximum weight matching algorithm to completely match the bipartite graph.

[0051] According to another embodiment of the present invention, the storage location determination module 503 can also be used for: in response to the planned storage location not satisfying the shelving conditions, obtaining an adjacent storage location of the planned storage location; in response to the adjacent storage location satisfying the shelving conditions, using the adjacent storage location as the item storage location for the item to be shelved.

[0052] According to another embodiment of the present invention, when obtaining the adjacent storage locations of the planned storage location, the storage location determination module 503 can be specifically used to: determine a first storage location set based on the distances between each storage location in the warehouse and the planned storage location; sort the storage locations in the first storage location set by a sorting learning algorithm, and obtain the adjacent storage locations of the planned storage location based on the sorting results.

[0053] According to another embodiment of the present invention, the storage location determination module 503 can also be used for: in response to the adjacent storage location not satisfying the shelving conditions, obtaining the original storage location of the item to be shelved, the original storage location being a storage location among the storage locations of the item to be shelved that is different from the planned storage location; in response to the original storage location satisfying the shelving conditions, using the original storage location as the item storage location of the item to be shelved.

[0054] According to another embodiment of the present invention, the storage location determination module 503 can also be used to: in response to the original storage location not satisfying the shelving conditions, obtain an empty storage location; in response to the empty storage location satisfying the shelving conditions, use the empty storage location as the item storage location for the items to be shelved.

[0055] According to another embodiment of the present invention, the device 500 for determining the storage location of an item may further include a storage location pre-determination module (not shown in the figure), which is used to: in response to the item to be put on the shelf being not the first item to be put on the shelf in the list of items to be put on the shelf, before obtaining the planned storage location of the item to be put on the shelf based on the item information and the item storage location comparison relationship table, obtain the storage location of the previous item to be put on the shelf, and confirm that the adjacent storage location of the storage location of the previous item to be put on the shelf does not meet the shelving conditions.

[0056] According to the technical solution of the embodiment of the present invention, by obtaining the item information and the item storage location comparison relationship table of the items to be put on the shelves, the item storage location comparison relationship table is obtained by solving the storage location recommendation model, and the storage location recommendation model is constructed based on the picking distance and the shelving distance of similar items and related items; according to the item information and the item storage location comparison relationship table, the planned storage location of the items to be put on the shelves is obtained; in response to the planned storage location meeting the shelving conditions, the planned storage location is used as the storage location of the items to be put on the shelves. The technical solution can be combined with the storage location recommendation model to perform storage location allocation, the classification standard can be richer and more flexible, and the storage location planning can be better combined with the changes in the storage environment and the relationship between the material attributes of the items. It can adapt to more complex storage location allocation scenarios and improve the rationality and success rate of storage location allocation.

[0057] Figure 6 An exemplary system architecture 600 is shown to which the method for determining an item storage location or the apparatus for determining an item storage location according to an embodiment of the present invention can be applied.

[0058] like Figure 6 As shown, system architecture 600 may include terminal devices 601, 602, 603, network 604 and server 605. Network 604 is used to provide a medium for communication links between terminal devices 601, 602, 603 and server 605. Network 604 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0059] The user can use the terminal devices 601, 602, 603 to interact with the server 605 through the network 604 to receive or send messages, etc. Various client applications can be installed on the terminal devices 601, 602, 603, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0060] The terminal devices 601 , 602 , and 603 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, etc.

[0061] The server 605 may be a server that provides various services, such as a background management server that provides support for websites browsed by users using terminal devices 601, 602, and 603 (for example only). The background management server may obtain the item information and the item storage location comparison relationship table of the items to be put on the shelves from the received data such as the request for determining the storage location of the items. The item storage location comparison relationship table is obtained by solving the storage location recommendation model, which is constructed based on the picking distance and the shelf distance of similar items and related items; obtain the planned storage location of the items to be put on the shelves according to the item information and the item storage location comparison relationship table; in response to the planned storage location meeting the shelf conditions, process the planned storage location as the storage location of the items to be put on the shelves, etc., and feed back the processing result (such as the storage location of the items to be put on the shelves - for example only) to the terminal device.

[0062] It should be noted that the method for determining the storage location of an item provided in the embodiment of the present invention is generally executed by the server 605 , and accordingly, the device for determining the storage location of an item is generally disposed in the server 605 .

[0063] It should be understood that Figure 6The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0064] Reference below Figure 7 , which shows a schematic diagram of the structure of a computer system 700 of a terminal device or a server suitable for implementing an embodiment of the present invention. Figure 7 The terminal device or server shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0065] like Figure 7 As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0066] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage section 708 as needed.

[0067] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the central processing unit (CPU) 701, the above-mentioned functions defined in the system of the present invention are executed.

[0068] It should be noted that the computer-readable medium shown in the present invention 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 invention, 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 invention, 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. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, 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.

[0069] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. 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 above-mentioned module, program segment, or a part of a 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 or flow chart, and the combination of the boxes in the block diagram 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.

[0070] The units or modules involved in the embodiments of the present invention may be implemented in software or hardware. The units or modules described may also be arranged in a processor. For example, they may be described as: a processor includes a data acquisition module, a storage location search module, and a storage location determination module. The names of these units or modules do not, in some cases, constitute limitations on the units or modules themselves. For example, the storage location determination module may also be described as "a module for using the planned storage location as the storage location for the items to be put on the shelf in response to the planned storage location satisfying the shelving conditions."

[0071] As another aspect, the present invention 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 a device, the device includes: obtaining the item information of the items to be put on the shelf and the item storage location comparison relationship table, the item storage location comparison relationship table is obtained by solving the storage location recommendation model, and the storage location recommendation model is constructed based on the picking distance and the shelving distance of similar items and related items; according to the item information and the item storage location comparison relationship table, the planned storage location of the items to be put on the shelf is obtained; in response to the planned storage location meeting the shelving conditions, the planned storage location is used as the storage location of the items to be put on the shelf.

[0072] According to the technical solution of the embodiment of the present invention, by obtaining the item information and the item storage location comparison relationship table of the items to be put on the shelves, the item storage location comparison relationship table is obtained by solving the storage location recommendation model, and the storage location recommendation model is constructed based on the picking distance and the shelving distance of similar items and related items; according to the item information and the item storage location comparison relationship table, the planned storage location of the items to be put on the shelves is obtained; in response to the planned storage location meeting the shelving conditions, the planned storage location is used as the storage location of the items to be put on the shelves. The technical solution can be combined with the storage location recommendation model to perform storage location allocation, the classification standard can be richer and more flexible, and the storage location planning can be better combined with the changes in the storage environment and the relationship between the material attributes of the items. It can adapt to more complex storage location allocation scenarios and improve the rationality and success rate of storage location allocation.

[0073] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for determining a storage location of an item, characterized in that: include: Obtaining item information and an item storage location comparison relationship table of items to be put on the shelves, wherein the item storage location comparison relationship table is obtained by solving a storage location recommendation model, wherein the storage location recommendation model is constructed based on the picking distance and the shelving distance of similar items and related items; Obtaining the planned storage location of the item to be put on the shelf according to the item information and the item storage location comparison relationship table; In response to the planned storage location satisfying the shelving condition, the planned storage location is used as the storage location for the item to be shelved.

2. The method according to claim 1, characterized in that: The solving of the storage location recommendation model includes: Take each item and each storage location in the warehouse as a vertex and construct the edges between the items and the storage locations; For each item, the picking distance and shelf distance of the item when stored in each storage location are used as the weight corresponding to the edge to generate a weight matrix; Construct a bipartite graph based on the edges between items and storage locations, and the weights corresponding to each edge; According to the weight matrix, a bipartite graph maximum weight matching algorithm is used to perform a complete match on the bipartite graph to solve the storage location recommendation model.

3. The method according to claim 2, characterized in that Before building the edges between items and storage locations with each item and each storage location in the warehouse as vertices, it also includes: In response to business needs, the target item is stored in multiple storage locations, and copies of the target item are added according to the number of storage locations so that each target item corresponds to one storage location; In response to business needs, multiple items are stored in one target storage location, and copies of the target storage location are added according to the number of items so that each target storage location corresponds to one item.

4. The method according to claim 3, characterized in that According to the weight matrix, a bipartite graph maximum weight matching algorithm is used to perform complete matching on the bipartite graph, including: In response to the number of items being equal to the number of storage locations, performing complete matching on the bipartite graph using a bipartite graph maximum weight matching algorithm directly according to the weight matrix; In response to the number of items being less than the number of storage locations, according to the difference between the number of storage locations and the number of items, a number of zero elements equal to the difference is added to the weight matrix to obtain a first weight matrix, and according to the first weight matrix, a bipartite graph maximum weight matching algorithm is used to perform a complete match on the bipartite graph.

5. The method according to claim 1, characterized in that The method further comprises: In response to the planned storage location not satisfying the shelf condition, obtaining a storage location adjacent to the planned storage location; In response to the adjacent storage location satisfying the shelving condition, the adjacent storage location is used as the item storage location for the item to be shelved.

6. The method according to claim 5, characterized in that Acquiring the adjacent storage location of the planned storage location, including: Determine a first storage location set according to the distance between each storage location in the warehouse and the planned storage location; The storage locations in the first storage location set are sorted by a sorting learning algorithm, and the adjacent storage locations of the planned storage locations are obtained according to the sorting result.

7. The method according to claim 5, characterized in that The method further comprises: In response to the adjacent storage location not satisfying the shelf condition, obtaining the original storage location of the item to be shelf-mounted, the original storage location being a storage location different from the planned storage location in the storage position of the item to be shelf-mounted; In response to the original storage location satisfying the shelving condition, the original storage location is used as the item storage location for the item to be shelved.

8. The method according to claim 7, characterized in that The method further comprises: In response to the original storage location not satisfying the shelf condition, obtaining an empty storage location; In response to the empty storage location satisfying the shelving condition, the empty storage location is used as the item storage location for the item to be shelved.

9. The method according to claim 1, characterized in that: The method further comprises: In response to the fact that the item to be put on the shelf is not the first item to be put on the shelf in the list of items to be put on the shelf, before obtaining the planned storage location of the item to be put on the shelf according to the item information and the item storage location comparison relationship table, the storage location of the previous item to be put on the shelf is obtained, and it is confirmed that the adjacent storage location of the storage location of the previous item to be put on the shelf does not meet the shelving conditions.

10. A device for determining a storage location of an item, characterized in that: include: A data acquisition module, used to acquire item information and an item storage location comparison relationship table of items to be put on the shelves, wherein the item storage location comparison relationship table is obtained by solving a storage location recommendation model, wherein the storage location recommendation model is constructed based on the picking distance and the shelving distance of similar items and related items; A storage location search module, used to obtain the planned storage location of the item to be put on the shelf according to the item information and the item storage location comparison relationship table; The storage location determination module is used to use the planned storage location as the storage location for the items to be put on the shelves in response to the planned storage location satisfying the shelving conditions.

11. An electronic device, characterized in that: include: one or more processors; a storage device for storing 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 method according to any one of claims 1 to 9.

12. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images