A product warehousing method, apparatus, equipment and medium

Abstract

This application discloses a product warehousing method, apparatus, equipment, and medium, belonging to the field of warehouse management technology. The method includes: obtaining the relationships between products and their popularity based on clustering data mining algorithms using the product data; determining the placement location of the products to be warehoused based on the relationships between products and their popularity; acquiring warehouse location data of an existing warehouse; and determining the warehousing route of the products to be warehoused based on the warehouse location data and the placement location of the products to be warehoused. This technical solution achieves the goal of allocating product warehouse locations according to product popularity and relationships between products, improving the rationality of product warehouse location allocation and thus increasing the efficiency of picking orders for warehoused products.

Description

Technical Field

[0001] This application belongs to the field of warehouse management technology, specifically relating to a product warehousing method, apparatus, equipment, and medium. Background Technology

[0002] With the rapid development of the manufacturing industry, more and more products are being produced and distributed in large quantities. In order to achieve mass production and distribution of products, while maintaining minimal inventory throughout the supply chain, efficient warehouse management and warehouse operations have become very important.

[0003] In related technologies, products are primarily stored in corresponding types of shelves according to their production or warehousing time, and the warehousing information is saved. When purchasing personnel make purchases, warehouse management personnel need to locate the corresponding product's location information based on the product's warehousing information in the purchase order, and then move the purchased products out of the warehouse according to the location information.

[0004] Because the storage location allocation of products in the existing technology is determined based on the time of entry into the warehouse, and the time of entry into the warehouse does not represent the popularity of the products or the correlation between products, there is a problem of unreasonable storage location allocation when using the existing technology for product entry into the warehouse, which in turn leads to low picking efficiency for order of products entering the warehouse. Summary of the Invention

[0005] The purpose of this application is to provide a product warehousing method, apparatus, equipment, and medium that solves the problems of unreasonable product storage location allocation and low order picking efficiency. By using clustering data mining algorithms based on the product data to obtain the correlation between products and the popularity of products to be warehoused, the placement location of the products to be warehoused is determined. Based on the storage location data and the placement location, the warehousing route of the products to be warehoused is determined. This achieves the purpose of allocating product storage locations according to the popularity of products and the correlation between products, improving the rationality of product storage location allocation, and thus improving the efficiency of order picking for warehoused products.

[0006] In a first aspect, embodiments of this application provide a product warehousing method, the method comprising:

[0007] Obtain historical sales orders for products to be put into storage, and determine product data for products to be put into storage based on the historical sales orders;

[0008] Based on the product data, clustering data mining algorithms are used to obtain the relationships between products in the products to be added to the database and the popularity of the products;

[0009] The storage location of the products to be stored is determined based on the relationships between the products and their popularity.

[0010] Obtain the storage location data of the constructed warehouse, and determine the storage route of the products to be stored based on the storage location data and the storage location of the products to be stored; wherein, the storage location data includes: storage location, warehouse entrance and exit location, and distance between storage locations.

[0011] Furthermore, the step of obtaining the relationships between products and their popularity among the products to be added to the database using clustering data mining algorithms based on the product data includes:

[0012] The product data is converted to binary to obtain a vector set of the product data;

[0013] Cluster the vector set of products to be added to the warehouse to obtain product similarity items, and determine the association between products in the products to be added to the warehouse based on the product similarity items.

[0014] Calculate the entries of each centroid vector in the cluster, and round up the entries of the centroid vector to obtain the candidate itemsets of the frequent itemset in the product data; wherein, the entries of the centroid vector are the frequency of the products that make up the cluster in the cluster;

[0015] The popularity of the products to be added to the database is obtained by pruning the candidates in the frequent itemset according to a preset minimum support threshold.

[0016] Furthermore, the entries of the centroid vector are rounded up using a rounding formula, which is:

[0017] ;

[0018] in, This is the rounding threshold; The centroid of the cluster is defined as follows; Represents a given centroid vector The item;

[0019] Accordingly, the step of rounding up the entries of the centroid vector to obtain candidate itemsets for the frequent itemset in the product data includes:

[0020] The centroid vector entries are rounded up using a rounding formula, and each rounded vector obtained from the rounding up operation is determined as a candidate for the frequent itemset in the product data.

[0021] Furthermore, the step of pruning the candidates in the frequent itemset according to a preset minimum support threshold to obtain the product popularity of the product to be added to the database includes:

[0022] The candidate items in the frequent itemset are compared with the preset minimum support to identify whether the candidate items are greater than the preset minimum support.

[0023] If so, the candidate items with a support greater than the preset minimum support in the comparison results will be directly added to the pre-built frequent itemset list;

[0024] If not, the maximum frequent itemset in the candidate itemset is extracted using the MAFIA algorithm, and the maximum frequent itemset is added to the pre-constructed frequent itemset list;

[0025] The popularity of the products to be added to the warehouse is determined based on the sales data of each product in the frequent itemset list.

[0026] Furthermore, determining the storage location of the products to be stored based on the relationships between the products and their popularity includes:

[0027] Based on the correlation between products in the products to be put into the warehouse and the popularity of the products, weights are assigned to the correlation strength and weighted travel distance of each product in the products to be put into the warehouse.

[0028] The suitability value of each product in the products to be put into storage is calculated according to the weight, and the storage location with the largest suitability value is selected as the current storage location for the products to be put into storage.

[0029] Furthermore, based on the aforementioned weights, the suitability value of each product in the products to be put into storage is calculated using a suitability weighted formula at different storage locations. The suitability weighted formula is as follows:

[0030] ;

[0031] in, Let be the fit value of product i at storage location j. Let j be the distance between storage location j and the warehouse entrance / exit location; This is the set of all storage locations adjacent to storage location j within a predetermined straight-line distance; The strength of the association between product i and the product placed at storage location k; Let i represent the importance of product i; k represents the storage location adjacent to location j. and These are the weights assigned to the correlation strength and the weighted travel distance, respectively.

[0032] Furthermore, determining the warehousing route of the product to be warehoused based on the warehouse location data and the placement location of the product to be warehoused includes:

[0033] The number of transport equipment to transport the products to be stored is determined based on the capacity of the transport equipment and the quantity of the products to be stored, and corresponding routes are planned for the transport equipment based on the storage location data and the storage location of the products to be stored.

[0034] Assign a first transport device to the products whose storage location is furthest from the warehouse entrance / exit location among the products to be put into the warehouse, and obtain the corresponding route of the first transport device;

[0035] Other products with the lowest additional cost among the products to be put into storage are added to the corresponding route of the first transportation equipment until the first transportation equipment reaches its capacity limit; wherein, the lowest additional cost is the shortest sum of the paths of each product to be put into storage to its placement location;

[0036] The remaining products of the products to be put into storage are allocated to a second transport device until all products to be put into storage are allocated.

[0037] Secondly, embodiments of this application provide a product warehousing method, the method comprising:

[0038] The product data acquisition module is used to acquire the historical sales orders of products to be put into the warehouse, and to determine the product data of the products to be put into the warehouse based on the historical sales orders.

[0039] The product association acquisition module is used to obtain the association relationship and product popularity among the products to be added to the warehouse based on the product data and a clustering data mining algorithm.

[0040] The placement location determination module is used to determine the placement location of the products to be put into storage based on the relationship between the products and the popularity of the products.

[0041] The inbound route determination module is used to acquire the storage location data of the constructed warehouse, and determine the inbound route of the product to be inbound based on the storage location data and the storage location where the product to be inbound is placed; wherein, the storage location data includes: storage location, warehouse entrance and exit location, and distance between storage locations.

[0042] Thirdly, embodiments of this application provide an electronic device including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method described in the first aspect.

[0043] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect.

[0044] Fifthly, embodiments of this application provide a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the method as described in the first aspect.

[0045] In this embodiment, clustering data mining algorithms are used to obtain the relationships and popularity of products among those to be put into storage based on the product data. The placement location of the products to be put into storage is determined based on these relationships and popularity. Storage location data of the constructed warehouse is obtained, and the storage route of the products to be put into storage is determined based on this data and the placement location. The storage location data includes: storage location, warehouse entrance / exit location, and distance between storage locations. This product warehousing method solves the problems of unreasonable product storage location allocation and low order picking efficiency. By using clustering data mining algorithms to obtain the relationships and popularity of products among those to be put into storage based on the product data, and determining the placement location of the products to be put into storage based on the storage location data and placement location, the goal of allocating product storage locations according to product popularity and relationships can be achieved, improving the rationality of product storage location allocation and thus improving the efficiency of order picking for inbound products. Attached Figure Description

[0046] Figure 1 This is a flowchart illustrating the product warehousing method provided in Embodiment 1 of this application;

[0047] Figure 2 This is a flowchart illustrating the product warehousing method provided in Embodiment 2 of this application;

[0048] Figure 3 This is a flowchart illustrating the product warehousing method provided in Embodiment 3 of this application;

[0049] Figure 4 This is a schematic diagram of the warehouse structure provided in an embodiment of this application;

[0050] Figure 5 This is a schematic diagram of the product warehousing device provided in Embodiment 4 of this application;

[0051] Figure 6 This is a schematic diagram of the structure of the electronic device provided in Embodiment Six of this application. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this application clearer, specific embodiments of this application will be described in further detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely for explaining this application and not for limiting it. It should also be noted that, for ease of description, only the parts relevant to this application are shown in the drawings, not all of them. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe operations (or steps) as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but may also have additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0053] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0054] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0055] The product warehousing method, apparatus, equipment, and medium provided in this application will be described in detail below with reference to the accompanying drawings and through specific embodiments and application scenarios.

[0056] Example 1

[0057] Figure 1 This is a flowchart illustrating the product warehousing method provided in Embodiment 1 of this application. Figure 1 As shown, the specific steps include the following:

[0058] S101, Obtain historical sales orders for the products to be put into storage, and determine the product data of the products to be put into storage based on the historical sales orders;

[0059] First, this solution can be used in scenarios where products are stored in warehouses, especially in scenarios where warehouse locations are allocated when products are stored in warehouses.

[0060] Based on the above usage scenarios, it is understandable that the implementing entity of this solution can be an electronic device used in the warehouse management system that has data reading, data processing and path planning capabilities, such as smart terminals such as mobile phones, tablets and desktop computers, without further restrictions.

[0061] The products to be received can be products to be stored in warehouse locations. Product data can include product attribute data and sales data for the products to be received. The product attribute data includes: product type, product name, and product characteristics, etc.

[0062] In one embodiment, historical sales orders of products to be received can be obtained from data stored in the warehouse management system, and product data of the products to be received can be determined based on various parameters in the historical sales orders.

[0063] S102, Based on the product data, obtain the correlation between products in the products to be added to the warehouse and the popularity of the products through clustering data mining algorithm;

[0064] The clustering data mining algorithm can be an algorithm that divides a dataset into different classes or clusters according to a specific criterion (such as distance). This algorithm aims to maximize the similarity of data objects within the same cluster while maximizing the differences between data objects in different clusters; that is, after clustering, data of the same class should be grouped together as much as possible, while data of different classes should be separated as much as possible. In this solution, the clustering data mining algorithm can be an algorithm that divides the product data according to product attributes and sales volume. The relationship between products can be the similarity between them. This relationship includes: similar or identical product types, similar or identical product functions, and similar or identical product attributes, etc. Product popularity can be determined based on product sales volume and / or sales speed.

[0065] In one embodiment, clustering data mining algorithms can be used to perform attribute clustering and sales clustering on the product data, and the correlation between products and the popularity of each product can be determined based on the clustered product data.

[0066] S103, determine the storage location of the products to be stored based on the relationship between the products and their popularity.

[0067] In one embodiment, based on the relationships between the products to be put into storage and their popularity, storage locations that are similar or close together can be used as storage locations for products with a high degree of correlation or relationship; storage locations that are closer to the warehouse entrance and exit can be used as storage locations for products with higher popularity.

[0068] In one feasible embodiment, optionally, determining the storage location of the products to be stored based on the relationships between the products and their popularity includes:

[0069] Based on the correlation between products in the products to be put into the warehouse and the popularity of the products, weights are assigned to the correlation strength and weighted travel distance of each product in the products to be put into the warehouse.

[0070] The suitability value of each product in the products to be put into storage is calculated according to the weight, and the storage location with the largest suitability value is selected as the current storage location for the products to be put into storage.

[0071] The association strength can be used to describe the strength of a certain regularity between the values ​​of two or more variables. In this scheme, the association strength of each product can be the degree of similarity between the products. The association strength can be extracted by an association rule mining algorithm. The association rule mining algorithm can be used to discover interesting connections hidden in large datasets, and the discovered patterns are usually represented in the form of association rules or frequent itemsets. The association rules reflect the interdependence and correlation between one thing and other things. If there is a certain correlation between two or more things, then the occurrence of one thing can predict the occurrence of other related things. The weighted travel distance can be the weighted result of the distance from the warehouse entrance / exit to the product placement location. The weight in the weighted travel distance represents the importance of the product placed in that location. The larger the importance value, the closer the product should be placed to the warehouse entrance / exit. The importance value can be calculated using the Pareto principle based on the product data.

[0072] In one embodiment, an association rule mining algorithm can be used to extract the association strength of each product among the products to be put into storage, and the Pareto principle can be used to calculate the weighted travel distance of each product from the warehouse entrance / exit to its placement location. Weights are assigned to the association strength and weighted travel distance of each product among the products to be put into storage based on the association relationships and product popularity. The suitability value of each product among the products to be put into storage in different storage locations is calculated based on the weights, the association strength of each product, and the weighted travel distance, and the storage location with the highest suitability value is selected as the current placement location for the product to be put into storage.

[0073] This solution determines the suitability value of each product in different storage locations by calculating the weighted sum of the correlation strength of each product and the weighted travel distance. The storage location with the highest suitability value is then used as the current storage location for the product to be stored. This achieves the goal of determining storage locations by comprehensively considering product correlation and popularity, thus improving the rationality of product storage location allocation.

[0074] In one feasible embodiment, optionally, the suitability value of each product in the products to be put into storage at different storage locations is calculated according to the weights using a suitability weighting formula, wherein the suitability weighting formula is:

[0075] ;

[0076] in, Let be the fit value of product i at storage location j. Let j be the distance between storage location j and the warehouse entrance / exit location; This is the set of all storage locations adjacent to storage location j within a predetermined straight-line distance; The strength of the association between product i and the product placed at storage location k; Let i represent the importance of product i; k represents the storage location adjacent to location j. and These are the weights assigned to the correlation strength and the weighted travel distance, respectively.

[0077] In one embodiment, the fitness value of each product in the products to be put into storage at different storage locations can be calculated using a fitness weighting formula, wherein the fitness weighting formula is:

[0078] ;

[0079] in, Let be the fit value of product i at storage location j. Let j be the distance between storage location j and the warehouse entrance / exit location; This is the set of all storage locations adjacent to storage location j within a predetermined straight-line distance; The strength of the association between product i and the product placed at storage location k; Let i represent the importance of product i; k represents the storage location adjacent to location j. and These are the weights assigned to the correlation strength and the weighted travel distance, respectively. The value can be calculated using the Pareto principle based on the historical sales data of product i.

[0080] This solution uses a suitability weighted formula to calculate the suitability value of each product in different storage locations, thereby determining the storage location for each product and improving the reliability of allocating storage locations for each product.

[0081] S104, Obtain the storage location data of the constructed warehouse, and determine the storage route of the products to be stored based on the storage location data and the storage location of the products to be stored; wherein, the storage location data includes: storage location, warehouse entrance and exit location and distance between storage locations.

[0082] The inbound route for products to be put into storage can be the route with the shortest distance or the shortest travel time from the warehouse entrance / exit to the storage location.

[0083] In one embodiment, the storage location data of the constructed warehouse can be obtained by reading data stored in memory, and the optimal storage route for the products to be stored can be determined based on the storage location data and the placement location of the products to be stored. The storage location data includes: storage location, warehouse entrance / exit location, and distance between storage locations.

[0084] In one feasible embodiment, optionally, determining the storage route of the product to be stored based on the storage location data and the storage location of the product to be stored includes:

[0085] The number of transport equipment to transport the products to be stored is determined based on the capacity of the transport equipment and the quantity of the products to be stored, and corresponding routes are planned for the transport equipment based on the storage location data and the storage location of the products to be stored.

[0086] Assign a first transport device to the products whose storage location is furthest from the warehouse entrance / exit location among the products to be put into the warehouse, and obtain the corresponding route of the first transport device;

[0087] Other products with the lowest additional cost among the products to be put into storage are added to the corresponding route of the first transportation equipment until the first transportation equipment reaches its capacity limit; wherein, the lowest additional cost is the shortest sum of the paths of each product to be put into storage to its placement location;

[0088] The remaining products of the products to be put into storage are allocated to a second transport device until all products to be put into storage are allocated.

[0089] In one embodiment, the number of transport equipment units for transporting the products to be stored can be determined based on the capacity of the transport equipment and the quantity of the products to be stored. The shortest transport route can be planned for each transport equipment based on the distance between the storage location of the products to be stored and the warehouse entrance / exit location. Alternatively, the route with the fewest turns can be planned based on the location of the storage location and the distance between storage locations; these are not further limited here. Different transport equipment corresponds to different transport routes. A first transport equipment is assigned to the products whose storage location is furthest from the warehouse entrance / exit location, and the corresponding route of the first transport equipment is obtained. The route locations of the first transport equipment are determined based on its corresponding route. Other products in the route locations are added to the corresponding route of the first transport equipment. Other products with the lowest additional cost are also added to the corresponding route of the first transport equipment until the first transport equipment reaches its capacity limit. The lowest additional cost is defined as the shortest sum of the paths from each product to its storage location. A second transport equipment is assigned to the remaining products to be stored until all products to be stored have been allocated.

[0090] This solution determines the number of transport equipment needed to transport the products to be stored based on the capacity of the transport equipment and the quantity of the products to be stored. Corresponding routes are planned for each transport equipment, and the products to be stored are allocated to the corresponding transport equipment according to the planned routes. This minimizes the total moving distance when products are stored and improves the efficiency of product storage.

[0091] The technical solution provided in this application embodiment obtains the correlation between products and their popularity among the products to be put into storage using a clustering data mining algorithm based on the product data; determines the storage location of the products to be put into storage based on the correlation between products and their popularity; obtains the storage location data of the constructed warehouse; and determines the storage route of the products to be put into storage based on the storage location data and the storage location of the products to be put into storage. The storage location data includes: storage location, warehouse entrance / exit location, and distance between storage locations. This product warehousing method solves the problems of unreasonable product storage location allocation and low order picking efficiency. By using a clustering data mining algorithm to obtain the correlation between products and their popularity among the products to be put into storage based on the product data, and determining the storage location of the products to be put into storage based on the storage location data and the storage location, the method achieves the goal of allocating product storage locations according to product popularity and correlation, improving the rationality of product storage location allocation and thus improving the efficiency of order picking for inbound products.

[0092] Example 2

[0093] Figure 2 This is a flowchart illustrating the product warehousing method provided in Embodiment 2 of this application. Figure 2 As shown, the specific steps include the following:

[0094] S201, Obtain historical sales orders for the products to be put into storage, and determine the product data of the products to be put into storage based on the historical sales orders;

[0095] S202, convert the product data into binary to obtain a vector set of the product data;

[0096] In one embodiment, the product data can be converted into binary to obtain binary vectors for each product, thereby obtaining a vector set of the product data.

[0097] S203, cluster the vector set of the products to be put into the warehouse to obtain product similarity items of the products to be put into the warehouse, and determine the association relationship between each product in the products to be put into the warehouse based on the product similarity items;

[0098] The product similarity item can be a similarity attribute of the products in the product data. For example, product category.

[0099] In one embodiment, the MiniBatch K-Means algorithm can be used to cluster the vector set of products to be added to the database, obtain product similarity items, and determine the association between products in the database based on the product similarity items. The MiniBatch K-Means algorithm is an optimized variant of the K-Means algorithm, which uses a small subset of data (the dataset used for each training iteration is a subset of data randomly selected during algorithm training) to reduce computation time, while attempting to optimize the objective function.

[0100] S204, calculate the entries of each centroid vector in the cluster, and perform an up rounding operation on the entries of the centroid vector to obtain the candidate items of the frequent itemset in the product data; wherein, the entries of the centroid vector are the frequency of the products that make up the cluster in the cluster.

[0101] Here, the centroid can be the average of the (binary) vectors assigned to its corresponding cluster. The entries in the centroid vectors can be the frequency of the products that make up the cluster within that cluster. The frequent itemset can be the itemset in the vector set of the product data that satisfies a minimum support threshold.

[0102] In one embodiment, entries for each centroid vector in the cluster can be calculated based on the vector set of the product data, and the entries for the centroid vectors can be rounded up according to a pre-set rounding threshold to obtain candidate itemsets for the frequent itemset in the product data.

[0103] In a feasible embodiment, optionally, the entries of the centroid vector are rounded up using a rounding formula, wherein the rounding formula is:

[0104] ;

[0105] in, This is the rounding threshold; The centroid of the cluster is defined as follows; Represents a given centroid vector The item;

[0106] Accordingly, the step of rounding up the entries of the centroid vector to obtain candidate itemsets for the frequent itemset in the product data includes:

[0107] The centroid vector entries are rounded up using a rounding formula, and each rounded vector obtained from the rounding up operation is determined as a candidate for the frequent itemset in the product data.

[0108] In one embodiment, the entries of the centroid vector can be rounded up using a rounding formula, which is:

[0109] ;

[0110] in, This is the rounding threshold; The centroid of the cluster is defined as follows; Represents a given centroid vector The item.

[0111] In one embodiment, the entries of the centroid vector can be rounded up using a rounding formula, and each rounded vector obtained from the rounding up operation can be identified as a candidate for the frequent itemset in the product data.

[0112] This solution improves the efficiency of preliminary screening of frequent itemsets in product data by using a rounding formula to round up the entries of the centroid vector and determining each rounded vector as a candidate for the frequent itemset in the product data.

[0113] S205, trim the candidate items of the frequent itemset according to the preset minimum support threshold to obtain the product popularity of the product to be included in the database;

[0114] In one embodiment, the candidate items of the frequent itemset can be pruned according to a preset minimum support threshold to obtain the frequent itemset in the product data. The sales data such as the historical sales volume and historical sales speed of the product to be added to the warehouse can be determined according to the frequent itemset. The popularity of the product to be added to the warehouse can be determined according to at least one of the sales data such as the historical sales volume and historical sales speed.

[0115] In one feasible embodiment, optionally, the step of pruning the candidates in the frequent itemset according to a preset minimum support threshold to obtain the product popularity of the product to be added to the database includes:

[0116] The candidate items in the frequent itemset are compared with the preset minimum support to identify whether the candidate items are greater than the preset minimum support.

[0117] If so, the candidate items with a support greater than the preset minimum support in the comparison results will be directly added to the pre-built frequent itemset list;

[0118] If not, the maximum frequent itemset in the candidate itemset is extracted using the MAFIA algorithm, and the maximum frequent itemset is added to the pre-constructed frequent itemset list;

[0119] The popularity of the products to be added to the warehouse is determined based on the sales data of each product in the frequent itemset list.

[0120] MAFIA (Merging of adaptive interval approach to spatial datamining) is an efficient and scalable subspace clustering algorithm applicable to high-dimensional and large datasets. MAFIA proposes an adaptive grid for fast subspace clustering and introduces a scalable parallel architecture on a shared-nothing architecture to handle massive datasets. It introduces parallelism to achieve a highly scalable clustering algorithm for large datasets and proposes an adaptive interval size that partitions dimensions based on the data distribution within those dimensions, thereby improving the quality of the clustering results.

[0121] In one embodiment, the candidates in the frequent itemset can be compared with the preset minimum support to identify whether the candidate is greater than the preset minimum support. If so, the candidates with support greater than the preset minimum support are directly added to a pre-built frequent itemset list; otherwise, the maximum frequent itemset among the candidates is extracted using the MAFIA algorithm, and the maximum frequent itemset is added to the pre-built frequent itemset list. The popularity of the products to be added to the warehouse is determined based on the sales data of each product in the frequent itemset list.

[0122] This solution prunes the candidate itemsets of frequent itemsets using a preset minimum support, thereby adding the largest frequent itemset from the candidates to a pre-built frequent itemset list. Then, based on the sales data of each product in the frequent itemset list, the popularity of the products to be added to the warehouse can be determined, which can improve the reliability of determining the popularity of the products and thus improve the reliability of the warehouse location allocation for the products to be added to the warehouse.

[0123] S206, determine the storage location of the products to be stored based on the relationship between the products and their popularity.

[0124] S207, Obtain the storage location data of the constructed warehouse, and determine the storage route of the products to be stored based on the storage location data and the storage location of the products to be stored; wherein, the storage location data includes: storage location, warehouse entrance and exit location, and distance between storage locations.

[0125] The technical solution provided in this application converts product data into binary to obtain a vector set of product data. Then, it performs clustering, rounding up, and pruning operations on the vector set to determine the relationships between products and their popularity among the products to be put into storage. This improves the reliability of determining the relationships between products and their popularity, thereby improving the reliability of determining the storage location of the products to be put into storage.

[0126] Example 3

[0127] Figure 3 This is a flowchart illustrating the product warehousing method provided in Embodiment 3 of this application. Figure 3 As shown, the specific steps include the following:

[0128] S301, set up the warehouse according to the number of shelves and the storage space on the shelves;

[0129] S302, Generate a comprehensive order history;

[0130] S303, using clustering-based data mining algorithms to extract product associations and determine product popularity;

[0131] S304, using a mathematical programming model to perform product warehousing operations.

[0132] Figure 4 This is a schematic diagram of the warehouse structure provided in the embodiments of this application.

[0133] like Figure 4 As shown, the warehouse layout is as follows: each warehouse has M vertical shelves. Each shelf has M uniformly sized discrete pick-up locations on both sides. Each location can only store one unit of product. There is an I / O point in the lower left corner of the warehouse, and each inbound process will begin from the I / O point. There are end aisles at both ends of the shelves to allow pickers to move from one shelf to another.

[0134] Furthermore, each record in the comprehensive order history includes data such as product category, quantity, and size.

[0135] Furthermore, based on the comprehensive order history, a clustering-based data mining algorithm is used to find the maximum frequent set, and the popularity of products is determined based on the frequency of product occurrence in the orders.

[0136] Furthermore, in order to formulate the warehouse location allocation problem as a mathematical programming model, we first define a set of p items to be warehoused, where In addition, there is a set of empty spaces in the warehouse that can be used to store items, defined as follows: We assume This ensures sufficient space for storing arriving items. The location of the warehouse's I / O point is denoted as location 0. For item i stored next to another item, there exists an association strength. It measures the relationship between item i and the item at location k based on whether the relationship between them is classified as a strong relationship extracted by an association rule mining algorithm. If item i is assigned to location j, then... Defined as a fitness metric, where . The value is calculated based on the following factors: First, the distance between position j and the I / O entry point (position 0), defined as... Second, the strength of the association between a project and its neighboring projects, which means assigning the project to a location close to other projects with strong associations. To define the neighbors of location j, we find all locations within a predetermined straight-line distance of location j and define the set of these locations as... We further determine the association strength of item i, as stored in The correlation strength of all items at position k in the middle. The sum of . Finally, the importance of product i based on the ABC classification method is defined as . , The value can be determined from past sales records according to the Pareto principle.

[0137] Furthermore, based on the adaptability metric, the optimal storage location for all items to be received during replenishment can be determined. This is further defined by defining binary decision variables. ,in:

[0138] ;

[0139] The mathematical programming formula for the product location allocation problem is as follows:

[0140] ;

[0141] ;

[0142] ;

[0143] When assigning item i to position j, we define two values. and The importance weights are respectively assigned to association strength and weighted travel distance. The fitness value can be determined by the following formula:

[0144] ;

[0145] Where: k is defined as the position adjacent to position j; and These are the weights assigned to the correlation strength factor and the weighted distance factor, respectively. If importance is weighted... If product i is assigned to be stored at location j, then It is the reciprocal of the weighted distance traveled.

[0146] Weighted distance components The value recommendation is to define popular products (defined as...) Category A items (with higher fitness values) are assigned to locations closer to the I / O entry point than Category C items. Even for locations with the same travel distance from the I / O entry point, Category A items have a higher fitness value than Category C items. The position j of the value is considered more suitable for storing item i. and The value is used to normalize the influence of the two fitness components. When When set to 0, the product will be assigned to the location closest to the I / O entry point. This setting simulates the nearest open location method. Conversely, if If set to 0, we only consider the association between items and adjacent items to store related items together, without considering the distance to the I / O entry point. Initialization and One possible way to set the values ​​is to set both parameters to values ​​such that they are assigned to the location closest to the warehouse (i.e., the distance). Location Item i (where item i is not associated with any adjacent items) has a significant weight. The fitness value and the distance assigned The farthest position Items i with the same fitness value have the same fitness value and have the highest possible association with their neighbors, i.e. Under these conditions, the following formula can be used to determine... and Value:

[0147] ;

[0148] .

[0149] Furthermore, the steps for the inbound operation are as follows:

[0150] Through the following simple equation Determine the number of handcarts needed to perform the inbound operation for all products, where p is the number of products to be inbound and c is the unit capacity of the handcart. Assume the size of the products is unique. We now have m handcarts available to perform the inbound operation.

[0151] Determine the product location furthest from the I / O point and assign it to the first travel route. Initialize the remaining m-1 trolley routes to zero travel distance;

[0152] For each of the m cart routes, determine the optimal position to insert the item with the minimum additional cost into the current cart route. If the cart is full, stop considering that cart and proceed with further item insertion.

[0153] The cart route that yields the lowest additional cost required to insert a product wins the bid; then the product is assigned to that cart.

[0154] Repeat the above steps until all products are allocated. Set up the warehouses according to the number of shelves and the storage space on those shelves. Specifically, each warehouse has M vertical shelves, each shelf with M uniformly sized discrete pick positions on both sides, and each pick position can only store one unit of product. There is an I / O point in the lower left corner of the warehouse, and each inbound process will begin from this I / O point. There are end aisles at both ends of the shelves to allow pickers to move from one shelf to another.

[0155] Generate a comprehensive order history. This history is also used to determine product popularity based on the frequency of items appearing in orders. Understanding product popularity aims to identify the most frequently ordered products and allocate them to strategic locations—close to I / O entry points—to minimize storage and order retrieval distances.

[0156] This invention extracts product associations and determines product popularity by comprehensively analyzing order history. It uses a clustering-based data mining algorithm to find the maximum frequent set and determines product popularity based on the frequency of product occurrences in orders. The specific implementation of the clustering-based data mining algorithm is as follows:

[0157] Step 1: Data Representation. Our first step is to create a binary representation of the dataset. For this, we represent each transaction with a binary vector, where each entry indicates whether the item exists within the transaction in question. Now that we have a set of real vectors, we can proceed to the next step.

[0158] Step 2: Efficient Clustering. The MiniBatch K-Means algorithm is used to cluster the obtained vector set. Clustering is applied to discover similar items in a large dataset.

[0159] Step 3: Find the representative for each cluster. After applying clustering to the dataset, we are left with k centroids. Each centroid is the average of the (binary) vectors assigned to that cluster. Therefore, the entries for these centroids are intervals. The numbers in the text. Let Let represent the i-th term given the centroid vector c. Therefore, in a certain sense, This represents the frequency of the i-th item in the transaction set represented by c. In other words, The smaller the value, the less likely item i is to appear in these transactions. The larger the value, the greater the probability that item i will appear in these transactions. Next, we round the entries of the centroid vector as follows:

[0160] ;

[0161] in, This is the rounding threshold; The centroid of the cluster is defined as follows; Represents a given centroid vector The After running the MiniBatch K-Means algorithm and rounding the centroid vector, each rounded vector can be considered as a candidate for the frequent itemset.

[0162] Step 4: Pruning. To validate these candidates, we need to consider a minimum support level. As a threshold, we scan the dataset to find the support count for each candidate. Now, we have two possibilities:

[0163] Candidates who meet the minimum support criteria are added directly to the previously found list of frequent itemsets in this example.

[0164] The candidate did not meet the minimum support criteria. In this case, we run MAFIA on this candidate to extract the largest frequent itemsets, and then add them to the previously found frequent itemsets.

[0165] A mathematical programming model is used to execute product receiving operations. Based on an adaptability metric, the optimal storage location for all items to be received during replenishment can be determined. Binary decision variables are further defined. ,in:

[0166] ;

[0167] The mathematical programming formula for the product location allocation problem is as follows:

[0168] ;

[0169] ;

[0170] ;

[0171] When assigning item i to position j, we define two values. and The importance weights are respectively assigned to association strength and weighted travel distance. The fitness value can be determined by the following formula:

[0172] ;

[0173] Where: k is defined as the position adjacent to position j; and These are the weights assigned to the correlation strength factor and the weighted distance factor, respectively. If importance is weighted... If product i is assigned to be stored at location j, then It is the reciprocal of the weighted distance traveled.

[0174] The technical solution provided in this application sets up warehouses based on the number of shelves and the storage space on the shelves, generates a comprehensive order history, uses a cluster-based data mining algorithm to extract product associations and determine the popularity of products, and uses a mathematical programming model to execute product warehousing operations. This achieves the goal of allocating product storage locations according to product popularity and the association between products, improving the rationality of product storage location allocation and thus improving the efficiency of picking inbound product orders.

[0175] Example 4

[0176] Figure 5 This is a schematic diagram of the product warehousing device provided in Embodiment 4 of this application. Figure 5 As shown, it specifically includes the following:

[0177] Product data acquisition module 501 is used to acquire historical sales orders of products to be put into storage, and determine product data of products to be put into storage based on the historical sales orders.

[0178] Product association acquisition module 502 is used to obtain the association relationship and product popularity among the products to be added to the warehouse based on the product data and a clustering data mining algorithm.

[0179] The placement location determination module 503 is used to determine the placement location of the products to be put into storage based on the relationship between the products and the popularity of the products.

[0180] The inbound route determination module 504 is used to acquire the storage location data of the constructed warehouse, and determine the inbound route of the product to be inbound based on the storage location data and the placement location of the product to be inbound; wherein, the storage location data includes: storage location, warehouse entrance and exit location and distance between storage locations.

[0181] Furthermore, the product association acquisition module 502 is specifically used for:

[0182] The product data is converted to binary to obtain a vector set of the product data;

[0183] Cluster the vector set of products to be added to the warehouse to obtain product similarity items, and determine the association between products in the products to be added to the warehouse based on the product similarity items.

[0184] Calculate the entries of each centroid vector in the cluster, and round up the entries of the centroid vector to obtain the candidate itemsets of the frequent itemset in the product data; wherein, the entries of the centroid vector are the frequency of the products that make up the cluster in the cluster;

[0185] The popularity of the products to be added to the database is obtained by pruning the candidates in the frequent itemset according to a preset minimum support threshold.

[0186] Furthermore, the product association acquisition module 502 is specifically used for:

[0187] The entries of the centroid vector are rounded up using a rounding formula, which is:

[0188] ;

[0189] in, This is the rounding threshold; The centroid of the cluster is defined as follows; Represents a given centroid vector The item;

[0190] The centroid vector entries are rounded up using a rounding formula, and each rounded vector obtained from the rounding up operation is determined as a candidate for the frequent itemset in the product data.

[0191] Furthermore, the product association acquisition module 502 is specifically used for:

[0192] The candidate items in the frequent itemset are compared with the preset minimum support to identify whether the candidate items are greater than the preset minimum support.

[0193] If so, the candidate items with a support greater than the preset minimum support in the comparison results will be directly added to the pre-built frequent itemset list;

[0194] If not, the maximum frequent itemset in the candidate itemset is extracted using the MAFIA algorithm, and the maximum frequent itemset is added to the pre-constructed frequent itemset list;

[0195] The popularity of the products to be added to the warehouse is determined based on the sales data of each product in the frequent itemset list.

[0196] Furthermore, the placement location determination module 503 is specifically used for:

[0197] Based on the correlation between products in the products to be put into the warehouse and the popularity of the products, weights are assigned to the correlation strength and weighted travel distance of each product in the products to be put into the warehouse.

[0198] The suitability value of each product in the products to be put into storage is calculated according to the weight, and the storage location with the largest suitability value is selected as the current storage location for the products to be put into storage.

[0199] Furthermore, the placement location determination module 503 is specifically used for:

[0200] Based on the aforementioned weights, the suitability value of each product in the products to be put into storage is calculated in different storage locations using a suitability weighted formula. The suitability weighted formula is as follows:

[0201] ;

[0202] in, Let be the fit value of product i at storage location j. Let j be the distance between storage location j and the warehouse entrance / exit location; This is the set of all storage locations adjacent to storage location j within a predetermined straight-line distance; The strength of the association between product i and the product placed at storage location k; Let i represent the importance of product i; k represents the storage location adjacent to location j. and These are the weights assigned to the correlation strength and the weighted travel distance, respectively.

[0203] Furthermore, the inbound route determination module 504 is specifically used for:

[0204] The number of transport equipment to transport the products to be stored is determined based on the capacity of the transport equipment and the quantity of the products to be stored, and corresponding routes are planned for the transport equipment based on the storage location data and the storage location of the products to be stored.

[0205] Assign a first transport device to the products whose storage location is furthest from the warehouse entrance / exit location among the products to be put into the warehouse, and obtain the corresponding route of the first transport device;

[0206] Other products with the lowest additional cost among the products to be put into storage are added to the corresponding route of the first transportation equipment until the first transportation equipment reaches its capacity limit; wherein, the lowest additional cost is the shortest sum of the paths of each product to be put into storage to its placement location;

[0207] The remaining products of the products to be put into storage are allocated to a second transport device until all products to be put into storage are allocated.

[0208] The technical solution provided in this application includes a product data acquisition module for acquiring historical sales orders of products to be put into storage, and determining product data of the products to be put into storage based on the historical sales orders; a product association acquisition module for acquiring the association relationships and popularity of products among the products to be put into storage through clustering data mining algorithms based on the product data; a placement location determination module for determining the placement location of the products to be put into storage based on the association relationships and popularity of the products among the products to be put into storage; and an inbound route determination module for acquiring storage location data of the constructed warehouse, and determining the inbound route of the products to be put into storage based on the storage location data and the placement location of the products to be put into storage; wherein, the storage location data includes: storage location, warehouse entrance / exit location, and distance between storage locations. The aforementioned product warehousing device solves the problems of unreasonable product storage location allocation and low order picking efficiency. By using clustering data mining algorithms based on the product data to obtain the correlation between products to be warehoused and the popularity of products, the device determines the placement location of products to be warehoused. Based on the storage location data and placement location, the device determines the warehousing route of the products to be warehoused. This achieves the goal of allocating product storage locations according to product popularity and correlation between products, improving the rationality of product storage location allocation and thus improving the efficiency of order picking for warehoused products.

[0209] The product warehousing device in this application embodiment can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices can be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices can be servers, network-attached storage (NAS), personal computers (PCs), televisions (TVs), ATMs, or self-service machines, etc. This application embodiment does not impose specific limitations.

[0210] The product warehousing device in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit the specific operating system used.

[0211] The product warehousing device provided in this application embodiment can realize the various processes implemented in the above method embodiments. To avoid repetition, it will not be described again here.

[0212] Example 5

[0213] like Figure 6 As shown, this application embodiment also provides an electronic device 600, including a processor 601, a memory 602, and a program or instructions stored in the memory 602 and executable on the processor 601. When the program or instructions are executed by the processor 601, they implement the various processes of the above-described product warehousing device embodiment and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0214] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0215] Example 6

[0216] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described product warehousing device embodiments and achieve the same technical effects. To avoid repetition, these will not be described again here.

[0217] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0218] Example 7

[0219] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described product warehousing device embodiment and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0220] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0221] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0222] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0223] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

[0224] The above description is merely a preferred embodiment and the technical principles employed in this application. This application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions that can be made by those skilled in the art will not depart from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of this application, the scope of which is determined by the scope of the claims.

Claims

1. A product warehousing method, characterized in that, The method includes: Obtain historical sales orders for products to be put into storage, and determine product data for products to be put into storage based on the historical sales orders; The product data is converted to binary to obtain a vector set of the product data. The vector set of the products to be added to the warehouse is clustered to obtain product similarity items of the products to be added to the warehouse. The correlation between each product in the products to be added to the warehouse is determined based on the product similarity items. The entries of each centroid vector in the cluster are calculated, and the entries of the centroid vector are rounded up to obtain the candidate items of the frequent itemset in the product data. The entries of the centroid vector are the frequency of the products that make up the cluster in the cluster. The candidate items of the frequent itemset are pruned according to a preset minimum support threshold to obtain the product popularity of the products to be added to the warehouse. Based on the relationships between products in the products to be put into storage and the popularity of the products, weights are assigned to the relationship strength and weighted travel distance of each product in the products to be put into storage. Based on the weights, the suitability value of each product in the products to be put into storage in different storage locations is calculated, and the storage location with the largest suitability value is taken as the current storage location of the products to be put into storage. The fitness weighting formula is as follows: ； in, Let be the fit value of product i at storage location j. Let j be the distance between storage location j and the warehouse entrance / exit location. Let j be the set of all storage locations adjacent to storage location j within a predetermined straight-line distance. Let i be the strength of the association between product i and the product placed at storage location k. Let i represent the importance of product i, and k represent the storage location adjacent to location j. and These are the weights assigned to the correlation strength and the weighted travel distance, respectively. Obtain the storage location data of the constructed warehouse, and determine the storage route of the products to be stored based on the storage location data and the storage location of the products to be stored; wherein, the storage location data includes: storage location, warehouse entrance and exit location, and distance between storage locations.

2. The product warehousing method according to claim 1, characterized in that, The entries of the centroid vector are rounded up using a rounding formula, which is: ； in, This is the rounding threshold; The centroid of the cluster is defined as follows; Represents a given centroid vector The item; Accordingly, the step of rounding up the entries of the centroid vector to obtain candidate itemsets for the frequent itemset in the product data includes: The centroid vector entries are rounded up using a rounding formula, and each rounded vector obtained from the rounding up operation is determined as a candidate for the frequent itemset in the product data.

3. The product warehousing method according to claim 1, characterized in that, The step of pruning the candidates in the frequent itemset according to a preset minimum support threshold to obtain the product popularity of the product to be added to the database includes: The candidate items in the frequent itemset are compared with the preset minimum support to identify whether the candidate items are greater than the preset minimum support. If so, the candidate items with a support greater than the preset minimum support in the comparison results will be directly added to the pre-built frequent itemset list; If not, the maximum frequent itemset in the candidate itemset is extracted using the MAFIA algorithm, and the maximum frequent itemset is added to the pre-constructed frequent itemset list; The popularity of the products to be added to the warehouse is determined based on the sales data of each product in the frequent itemset list.

4. The product warehousing method according to claim 1, characterized in that, The step of determining the warehousing route of the products to be received based on the storage location data and the storage location of the products to be received includes: The number of transport equipment to transport the products to be stored is determined based on the capacity of the transport equipment and the quantity of the products to be stored, and corresponding routes are planned for the transport equipment based on the storage location data and the storage location of the products to be stored. Assign a first transport device to the products whose storage location is furthest from the warehouse entrance / exit location among the products to be put into the warehouse, and obtain the corresponding route of the first transport device; Other products with the lowest additional cost among the products to be put into storage are added to the corresponding route of the first transportation equipment until the first transportation equipment reaches its capacity limit; wherein, the lowest additional cost is the shortest sum of the paths of each product to be put into storage to its placement location; The remaining products of the products to be put into storage are allocated to a second transport device until all products to be put into storage are allocated.

5. A product warehousing device, characterized in that, The device includes: The product data acquisition module is used to acquire the historical sales orders of products to be put into the warehouse, and to determine the product data of the products to be put into the warehouse based on the historical sales orders. The product association acquisition module is used to convert the product data into binary form to obtain a vector set of the product data, cluster the vector set of products to be added to the database to obtain product similarity items of the products to be added to the database, determine the association relationship between products in the products to be added to the database based on the product similarity items, calculate the entries of each centroid vector in the cluster, and perform an up rounding operation on the entries of the centroid vector to obtain the candidate items of the frequent itemset in the product data. The entries of the centroid vector represent the frequency of the products that make up the cluster in the cluster. The candidate items of the frequent itemset are pruned according to a preset minimum support threshold to obtain the product popularity of the products to be added to the database. The storage location determination module is used to assign weights to the correlation strength and weighted travel distance of each product in the product to be stored based on the correlation between the products and the popularity of the products. It then calculates the suitability value of each product in different storage locations based on these weights and selects the storage location with the highest suitability value as the current storage location for the product to be stored. The suitability weighting formula is as follows: ； in, Let be the fit value of product i at storage location j. Let j be the distance between storage location j and the warehouse entrance / exit location. Let j be the set of all storage locations adjacent to storage location j within a predetermined straight-line distance. Let i be the strength of the association between product i and the product placed at storage location k. Let i represent the importance of product i, and k represent the storage location adjacent to location j. and These are the weights assigned to the correlation strength and the weighted travel distance, respectively. The inbound route determination module is used to acquire the storage location data of the constructed warehouse, and determine the inbound route of the product to be inbound based on the storage location data and the storage location where the product to be inbound is placed; wherein, the storage location data includes: storage location, warehouse entrance and exit location, and distance between storage locations.

6. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the product warehousing method as described in any one of claims 1-4.

7. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the product warehousing method as described in any one of claims 1-4.

Images