An item shelving method, device, terminal device, and storage medium

Abstract

Embodiments of the present application disclose an article shelving method and device, a terminal device and a storage medium, wherein the method comprises: clustering each incoming box according to the coincidence degree of the articles in each incoming box to obtain a clustering result until a cycle stop condition is met; the coincidence degree represents the number of the same article numbers; the clustering result includes a preset number of sub-piles; based on a target clustering condition, a target clustering result is determined from the clustering result corresponding to each round of cycle; the target clustering condition includes that the number of the deduplicated article numbers of the articles in each sub-pile in the clustering result meets a preset condition; based on the warehouse storage information and the article numbers of the articles in each sub-pile in the target clustering result, the storage location of each article is determined; and based on the location information of each storage location, the articles in each sub-pile are combined in a flow direction to perform shelving of the articles in each sub-pile according to the flow direction combination result. The article shelving efficiency can be improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of logistics technology, and in particular to a method, apparatus, terminal device and storage medium for shelving items. Background Art

[0002] In the prior art, after items are put into storage, each entry order is usually used as a set of shelving tasks to allocate storage locations for the items. Afterwards, the corresponding devices can be controlled to put the items on the shelves according to the allocation results.

[0003] In the process of realizing the present invention, the inventors found that there are at least the following technical problems in the prior art: in the face of a large number of inventory receipts, the existing shelving method has a large amount of invalid movement distance, repeated shelving operations of items with the same number, etc., resulting in extremely low efficiency in shelving items. Summary of the Invention

[0004] The embodiments of the present invention provide a method, apparatus, terminal device and storage medium for putting items on shelves, which can greatly improve the efficiency of putting items on shelves.

[0005] In a first aspect, an embodiment of the present invention provides a method for putting items on shelves, comprising:

[0006] Clustering the incoming boxes according to the overlap of the items in the boxes to obtain clustering results until a loop stop condition is met; the overlap represents the number of items with the same serial number; and the clustering results include a preset number of piles;

[0007] Determining a target clustering result from the clustering results corresponding to each round of cycles based on a target clustering condition; the target clustering condition includes that the number of duplicate item numbers of items in each pile in the clustering result meets a preset condition;

[0008] Determining the storage location of each item according to the warehouse storage information and the item number of each item in the target clustering result;

[0009] The flow directions of the articles in the various piles are merged according to the position information of the various storage locations, so that the articles in the various piles are shelved according to the flow merging result.

[0010] Optionally, each cycle process includes:

[0011] Determining the first incoming box of each of the preset number of stacks from the incoming boxes;

[0012] Determine the incoming cargo boxes to be currently stacked from the incoming cargo boxes that have not been divided into the various stacks;

[0013] Determining a target sub-stack from the sub-stacks according to the overlap between the items in the current incoming cargo box to be stacked and the items in the incoming cargo boxes of the sub-stacks;

[0014] The incoming cargo boxes currently to be stacked are divided into the target stacks until the division of the incoming cargo boxes is completed.

[0015] Optionally, before the loop clusters the incoming boxes according to the overlap of the items in the incoming boxes, the method further includes:

[0016] The preset quantity is determined based on the quantity of articles in the incoming cargo box per unit time and the preset production capacity quantity.

[0017] Optionally, the cycle stop condition includes at least one of the following: the number of cycles reaches a preset number; the cycle duration reaches a preset duration.

[0018] Optionally, the target clustering conditions include:

[0019] When the number of duplicated item numbers of the items in each sub-pile meets the first balance condition and the number of items in each sub-pile meets the second balance condition, the total number of duplicated item numbers of the items in each sub-pile is the smallest.

[0020] Optionally, determining the storage location of each item according to the warehouse storage information and the item number of each pile of items in the target clustering result includes:

[0021] Determining, from warehouse storage information, an initial storage location corresponding to each of the items in each pile according to the item number of the item in the target clustering result;

[0022] The storage location of the corresponding item is determined according to the storage information of each initial storage location.

[0023] Optionally, determining the storage location of the corresponding item according to the storage information of each initial storage location includes:

[0024] Determining the remaining capacity of the corresponding items according to the remaining space of each initial storage location;

[0025] When the quantity of the corresponding items is less than or equal to the remaining storage quantity, the initial storage location is used as the storage location for the corresponding items;

[0026] When the number of the corresponding items is greater than the remaining capacity, the initial storage location is used as the storage location for the corresponding items of the remaining capacity, and the empty storage location closest to the initial storage location is used as the storage location for the corresponding items other than the remaining capacity.

[0027] In a second aspect, an embodiment of the present invention provides an item shelving device, comprising:

[0028] a cyclic clustering module for cyclically clustering the incoming boxes according to the overlap of the items in the boxes to obtain clustering results until a cyclic stopping condition is satisfied; the overlap represents the number of items with the same serial number; and the clustering results include a preset number of sub-piles;

[0029] A cluster determination module, configured to determine a target clustering result from the clustering results corresponding to each round of cycles based on a target clustering condition; the target clustering condition includes that the number of duplicate item numbers of items in each pile in the clustering result meets a preset condition;

[0030] A storage location determination module, configured to determine the storage location of each item according to the warehouse storage information and the item number of each item in the target clustering result;

[0031] The shelving module is used to merge the flow directions of the items in the various piles according to the position information of each storage location, so as to shelve the items in the various piles according to the flow merging result.

[0032] In a third aspect, an embodiment of the present invention provides a terminal device, including:

[0033] one or more processors;

[0034] a memory for storing one or more programs;

[0035] When the one or more programs are executed by the one or more processors, the one or more processors implement the item shelving method as described in any embodiment of the present invention.

[0036] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for shelving items as described in any embodiment of the present invention.

[0037] An embodiment of the present invention provides a method, apparatus, terminal device and storage medium for shelving items, the method comprising: cyclically clustering each incoming cargo box according to the degree of overlap of items in each incoming cargo box to obtain a clustering result until a loop stop condition is met; the degree of overlap represents the number of identical item numbers; the clustering result comprises a preset number of sub-piles; based on a target clustering condition, determining a target clustering result from the clustering results corresponding to each round of cycles; the target clustering condition comprises that the number of deduplicated item numbers of items in each sub-pile in the clustering result meets a preset condition; determining the storage location of each item based on warehouse storage information and the item number of each sub-pile in the target clustering result; merging the flow direction of the items in each sub-pile based on the location information of each storage location, so as to shelve the items in each sub-pile based on the flow direction merging result.

[0038] In the technical solution of the embodiment of the present invention, by cyclically clustering and stacking each incoming cargo box according to the degree of overlap of the items in each incoming cargo box, and determining the optimal target clustering result based on the target clustering condition, it is possible to ensure that the number of duplicate item numbers in each stack in the target clustering result meets the preset conditions, and the shelving efficiency of the items in each stack can be improved. By allocating storage locations for the items in each stack according to the warehouse storage information and the item number, it is possible to ensure that the positions of items with the same item number are the same or adjacent to each other, thereby reducing the number of shelving operations for the items. By diverting according to the location information of each storage location (such as the storage area, lane, shelf and other spatial locations to which the storage location belongs), items in adjacent positions can be transported in a unified manner, thereby reducing the invalid moving distance. In summary, the efficiency of shelving items can be greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 A flowchart of a method for putting items on shelves provided by an embodiment of the present invention is shown;

[0041] Figure 2 A schematic diagram showing the distribution of warehouse storage locations in a method for shelving items provided by an embodiment of the present invention is shown;

[0042] Figure 3 A flowchart of a method for putting items on shelves provided by an embodiment of the present invention is shown;

[0043] Figure 4 A flowchart of an algorithm for determining target clustering results in a method for shelving items provided by an embodiment of the present invention is shown;

[0044] Figure 5 A flowchart of a method for putting items on shelves provided by an embodiment of the present invention is shown;

[0045] Figure 6 A flowchart of an algorithm for determining a flow direction merging result in a method for shelving items provided by an embodiment of the present invention is shown;

[0046] Figure 7 A schematic structural diagram of an article shelving device provided by an embodiment of the present invention is shown;

[0047] Figure 8 A schematic diagram of the hardware structure of a terminal device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described through implementation methods with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In the following embodiments, each embodiment provides optional features and examples at the same time. The various features recorded in the embodiments can be combined to form multiple optional solutions. Each numbered embodiment should not be regarded as just one technical solution. The acquisition, storage, use, processing, etc. of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0049] Figure 1 A flowchart illustrating a method for shelving items provided in an embodiment of the present invention is provided. The method is applicable to shelving items after they enter a warehouse in a container. This method can be performed by an item shelving device, which is implemented using software and / or hardware and is preferably configured in a terminal device, such as a computer.

[0050] like Figure 1 As shown, the method for putting items on shelves provided in the embodiment of the present invention may include the following steps:

[0051] S110 , clustering each incoming cargo box according to the overlap of the items in each incoming cargo box in a loop to obtain a clustering result until a loop stop condition is met.

[0052] In embodiments of the present invention, shelving may include, but is not limited to, sorting incoming warehouse items, loading the sorted items into containers, transporting the containers to corresponding shelf locations within the warehouse, and placing the items in the containers onto corresponding shelf locations. The shelving method provided in embodiments of the present invention describes the item sorting step in detail.

[0053] Large quantities of items typically enter warehouses in boxes. In embodiments of the present invention, the boxes containing items upon entry can be referred to as incoming boxes. Each incoming box may contain items with different item numbers, and different incoming boxes may contain items with the same item number, meaning that items in different incoming boxes may have overlapping item numbers. Each item number can consist of at least one of letters, numbers, and symbols, and uniquely identifies an item. In some implementations, item numbers can be represented by stock keeping units (SKUs).

[0054] Before executing the item shelving method provided in this embodiment, relevant information about each incoming box can be obtained in advance. This relevant information may include, but is not limited to, the box number of each incoming box, the item numbers of the items in each incoming box, the number of items corresponding to each item number, the size of each item, and other information. Furthermore, the number of items in each incoming box with identical item numbers can be determined, and then the degree of overlap of items in each incoming box can be determined based on the number of identical item numbers.

[0055] The number of identical item numbers and the degree of overlap can be positively correlated. For example, the number of identical item numbers between items in each incoming box can be directly used as the degree of overlap of items in each incoming box. In another example, the number of identical item numbers between items in each incoming box can be multiplied by a preset positive correlation coefficient to obtain the degree of overlap of items in each incoming box. It can be considered that the degree of overlap can represent the number of identical item numbers, and the higher the degree of overlap, the greater the number of identical item numbers. In addition, other methods of determining the degree of overlap based on the number of identical item numbers can also be applied here, and are not exhaustive here.

[0056] In an embodiment of the present invention, sorting items may first include clustering each incoming container, i.e., dividing each incoming container into stacks. Accordingly, the resulting clustering results may include a preset number of stacks, each of which may include at least one incoming container. The preset number may represent a desired number of stacks and may be set based on the actual application scenario.

[0057] Incoming bins can be clustered, specifically based on the overlap of items within them. For example, bins with an overlap within a first preset range can be grouped together, while bins with a relatively high overlap can be grouped together. This helps to minimize the duplication of identical items, thereby improving shelving efficiency.

[0058] In this embodiment, multiple rounds of clustering can be performed on each incoming cargo box. Each round of clustering can produce a clustering result. The cycle can be stopped when a stop condition is met, resulting in the clustering result corresponding to each round of clustering. Because the solution space for clustering results is large, obtaining the optimal clustering result requires a long time, which often does not meet the time feasibility of shelving items in the warehouse. By setting a stop condition, the time consumed can be controlled while obtaining a good clustering result for the incoming cargo boxes, thereby ensuring the time feasibility of shelving items.

[0059] In some implementations, satisfying the loop stop condition may include at least one of the following: the number of loops reaching a preset number; the loop duration reaching a preset duration. In these implementations, the preset number of loops and the preset duration can be set based on the actual application scenario to control the duration of the loop clustering process while achieving good clustering results. Furthermore, the loop stop condition may include other conditions, such as terminating the loop upon determining the optimal clustering result within the solution space. This article does not provide an exhaustive list of loop stop conditions.

[0060] S120. Determine a target clustering result from the clustering results corresponding to each round of cycles based on a target clustering condition; the target clustering condition includes that the number of duplicated item numbers of items in each pile in the clustering result meets a preset condition.

[0061] By deduplicating the item numbers of the items in the cargo boxes of each sub-pile, the deduplicated item numbers of the items in each sub-pile can be obtained. In this embodiment, the target clustering condition may include that the number of deduplicated item numbers of the items in each sub-pile in the clustering result meets a preset condition. Among them, the preset condition may include, for example, that the number of deduplicated item numbers of the items in each sub-pile reaches a minimum, so that the number of deduplicated item numbers of the items in each sub-pile can be minimized to minimize the number of times the items in each sub-pile are put on the shelves; for example, it may include that the number of deduplicated item numbers of the items in each sub-pile meets a second preset numerical range, etc., so that the deduplicated item numbers of the items in each sub-pile can be balanced and small, so as to ensure that the shelving workload of each sub-pile is balanced on the basis of reducing the number of times the items in each sub-pile are put on the shelves.

[0062] Among them, preset conditions can be set according to actual application requirements, in the hope that through the target clustering conditions, the best target clustering results that meet the requirements can be screened out from the clustering results corresponding to each round of cycles.

[0063] S130: Determine the storage location of each item based on the warehouse storage information and the item number of each pile in the target clustering result.

[0064] In an embodiment of the present invention, sorting items may also include matching items to storage locations. Current warehouse storage information may be obtained from a warehouse management system (WMS). This warehouse storage information may include, but is not limited to, information about the distribution of warehouse storage locations and information about items stored in each location.

[0065] For example, Figure 2 A schematic diagram showing the distribution of warehouse storage locations in a method for shelving items provided by an embodiment of the present invention is shown. Figure 2 , the warehouse storage location distribution can be as follows: the warehouse can contain multiple logical areas (for example, Figure 2 Each logical area can be divided into multiple storage areas according to certain rules (for example Figure 2 The clothing area can include Area A, Area B, and so on). Each storage area can contain multiple rows of shelves, and the passages formed by adjacent rows of shelves are called lanes. Each lane can contain multiple shelves on both sides, each shelf can contain multiple shelf layers, and each shelf layer can contain multiple storage locations. Each storage location can be associated with unique location information to represent its spatial location in the warehouse. Accordingly, warehouse storage location distribution information can include the location information of each storage location in the warehouse.

[0066] The information about the items stored in each storage location may include, but is not limited to, the size of each storage location, the item number of the items stored in each storage location, the number and size of the items corresponding to the stored item number, and other information.

[0067] After determining the target clustering results and obtaining the current warehouse storage information, the storage locations of the items in each stack can be determined based on the warehouse storage location distribution information and the information about the items stored in each storage location in the warehouse storage information. The process of determining the storage location of an item can be performed by prioritizing the storage location of each item from closest to farthest from the storage location of stored items with the same item code. For example, the prioritization from closest to farthest can include, for example, prioritizing the same storage location as the first priority, the same lane as the second priority, and the same storage area as the third priority. This allows items with the same item number to be stored in the same or adjacent storage locations, which not only helps reduce repeated shelving operations for the same item and improves item shelving efficiency, but also improves storage utilization and facilitates warehouse management.

[0068] Furthermore, when determining the storage location of items, other information about the item (such as brand and model number) can be combined to determine the storage location. This ensures that items of the same brand are placed in adjacent locations, while items of different models are placed in adjacent locations, rather than in the same location. After determining the storage location of each stacked item, the warehouse storage information can be updated to implement pre-occupancy and avoid the situation where the same storage location is allocated multiple times.

[0069] S140: Merging the flow directions of the items in each sub-pile according to the location information of each storage location, and putting the items in each sub-pile on the shelves according to the flow merging result.

[0070] In an embodiment of the present invention, sorting items may also include merging the flow directions of items assigned to storage locations. The storage location information may be sequentially composed of area identifiers, ranging from large to small. For example, it may be sequentially composed of logical area identifiers, storage area identifiers, aisle identifiers, shelf identifiers, layer identifiers, and storage location identifiers. The storage location information can be used to represent the flow direction of the corresponding items, which can be considered the direction in which the items are transported to the corresponding storage location.

[0071] Among them, the location information can be split according to the splicing rules of the area identifiers in the location information. For example, assuming that the location information of the storage location is "64L232", the split result may include 6 for the logical area identifier, 4 for the storage area identifier, L for the lane identifier, 23 for the shelf identifier, and 2 for the layer identifier. Afterwards, for each sub-stack, the flow directions of the items in the same position can be merged according to the order of the area identifiers from small range to large range in the split location information. For example, for each sub-stack, the flow directions of the items in the same layer can be merged first, and then the flow directions of the items on the same shelf can be merged, and then the flow directions of the items in the same lane can be merged. Similarly, the flow directions of the items in the same storage area and the same logical area can be merged later.

[0072] In actual applications, sorted items must be placed into individual containers for subsequent shelving. Due to the size limitations of each container, the flow merging process can be a cyclic merging process. Each cyclic merging round may include: for each stack, when the number of items after the flow merging reaches the maximum capacity of the container, merging stops, resulting in a separate stream of items, each of which can be placed into a container; then, the flow merging can be repeated for items that have not been merged, until the diversion of the items in the current stack is complete. Accordingly, the flow merging result can include the separate items.

[0073] Once the flow merge results are obtained, the item sorting step is considered complete. Afterward, the corresponding equipment can be controlled to perform a series of operations, including loading the sorted items into containers, transporting the containers to the corresponding shelves within the warehouse, and placing the items in the containers on the corresponding storage locations on the shelves, thereby completing the shelving of the sorted items.

[0074] In traditional shelving methods, items with the same item number may originate from different carriers' incoming orders, different owners' incoming orders, or even different incoming orders for the same owner. This inevitably leads to scattered distribution of items with the same item number. If each incoming order is used as a shelving task to allocate storage space, items with the same item number would need to be transported to the shelf multiple times and repeatedly shelved to complete the task, resulting in extremely low shelving efficiency.

[0075] The embodiment of the present invention provides a method for shelving items. By cyclically clustering and stacking each incoming cargo box according to the degree of overlap of the items in each incoming cargo box, and determining the optimal target clustering result based on the target clustering condition, it is possible to ensure that the number of duplicate item numbers in each stack in the target clustering result meets the preset conditions, thereby improving the shelving efficiency of the items in each stack. By allocating storage locations for the items in each stack according to the warehouse storage information and the item number, it is possible to ensure that the positions of items with the same item number are the same or adjacent to each other, thereby reducing the number of shelving operations for the items. By diverting according to the location information of each storage location (such as the storage area, lane, shelf, and other spatial locations to which the storage location belongs), items in adjacent positions can be transported in a unified manner, thereby reducing the invalid movement distance. In summary, the efficiency of shelving items can be greatly improved.

[0076] Based on the above embodiment, this embodiment describes in detail the cyclic clustering steps and the steps of determining the target clustering results. By determining the preset number of cluster piles according to the preset production capacity, it is beneficial to put items on the shelves based on the actual production capacity, thereby improving the universality of the item shelving method. By randomly generating cluster centers, different clustering results corresponding to each cycle can be obtained. By setting target clustering conditions including the balance of the number of duplicate item numbers, the balance of the number of items, and the minimum number of duplicate item numbers, it is possible to ensure that the same items are divided into the same piles as much as possible to improve the shelving efficiency, and it is also possible to ensure that the workload of each pile is balanced to match the actual production capacity, thereby ensuring the availability of the item shelving method.

[0077] Figure 3 A flowchart of a method for putting items on shelves provided by an embodiment of the present invention is shown. Figure 3 The method for putting items on shelves provided in this embodiment may include the following steps:

[0078] S310: Determine a preset quantity based on the number of items in the incoming cargo box per unit time and the preset production capacity.

[0079] The unit time can be, for example, every four hours, every day, or other values, and can be set according to the specific application scenario. The preset production capacity can be, for example, the average number of items put on the shelves in the warehouse per unit time, or the average number of items put on the shelves by each item shelving device in the warehouse per unit time, and can also be set according to the specific application scenario. The preset quantity can be obtained by dividing the number of items in the incoming cargo box per unit time by the preset production capacity and rounding up or down to the nearest integer.

[0080] For example, assuming that the unit time is one day and the preset production capacity is 8,000 pieces per day, if the number of items in the incoming cargo box per unit time is 24,000 pieces, then the preset quantity n=24,000 / 8,000=3.

[0081] By determining the preset number of clustering and stacking based on the actual preset production capacity of the warehouse, it is possible to sort the items that can be put on the shelves in a unit time in the warehouse, and the item shelving method can be applied to different warehouses, thereby improving the universality of the method.

[0082] S320: Determine the first incoming box of each of the preset number of sub-stacks from the incoming boxes.

[0083] In this embodiment, during each round of clustering, a preset number of incoming boxes are randomly selected as the first incoming box in each of the preset number of sub-stacks. Thus, each sub-stack can be clustered with the first incoming box as the cluster center. By randomly generating cluster centers, different clustering results can be obtained for each round of the cycle.

[0084] S330: Determine the incoming cargo box to be currently stacked from the incoming cargo boxes that have not been divided into the various stacks.

[0085] Among them, the current incoming boxes to be stacked can be randomly determined from the undivided incoming boxes, or can be determined from the undivided incoming boxes according to at least one information such as the box number, arrival time, etc., and no exhaustive list is given here.

[0086] S340: Determine a target sub-stack from each sub-stack according to the degree of overlap between the items in the incoming cargo box currently to be sub-stacked and the items in the incoming cargo boxes of each sub-stack.

[0087] The overlap represents the number of identical item numbers. For each stack, the sub-overlap between the items in the incoming bin to be stacked and the items in each incoming bin in the current stack can be determined. Based on each sub-overlap, the total overlap between the incoming bin to be stacked and the current stack can be determined. For example, the sum or average of the sub-overlaps can be used as the total overlap. The stack with the highest total overlap can then be selected as the target stack for the incoming bin to be stacked.

[0088] S350: sort the incoming cargo boxes currently to be sorted into target stacks until all incoming cargo boxes are sorted.

[0089] When all incoming cargo boxes are divided, the current round of clustering is considered to be completed, and the clustering result of the current round can be obtained, and the clustering result includes a preset number of piles.

[0090] S360, determine whether the loop stop condition is met; if so, jump to S370, if not, jump to S320.

[0091] When the cycle stop condition is met, the subsequent target clustering result can be determined; when the cycle stop condition is not met, the first incoming cargo box of each stack can be determined again and clustered.

[0092] S370. Determine a target clustering result from the clustering results corresponding to each round of cycles based on a target clustering condition; the target clustering condition includes that the number of duplicated item numbers of items in each pile in the clustering result meets a preset condition.

[0093] In some optional implementations, the target clustering condition may include: when the number of excluding duplicate item numbers of items in each pile meets the first balance condition and the number of items in each pile meets the second balance condition, the total number of excluding duplicate item numbers of items in each pile is the smallest.

[0094] The first and second balance conditions can be set based on actual application scenarios. For example, assuming the preset number is 3, the total number of items in the incoming cargo box per unit time is 24,000, and the total number of duplicate item numbers is 1,500. To achieve a balanced number of duplicate item numbers and a balanced number of items in each pile, the number of duplicate item numbers in each pile is expected to be around 1,500 / 3 = 500, and the number of items in each pile is expected to be around 24,000 / 3 = 8,000.

[0095] At this time, the first balancing condition can be set to a numerical range including 500, for example, a small neighborhood interval range centered on 500; the second balancing condition can be set to a numerical range including 8000, for example, a small neighborhood interval range centered on 8000.

[0096] In some other implementations, the first equilibrium condition can also be defined as the formula MIN(sum(distinct(SKUNumPerBox))), where SKUNumPerBox is the number of duplicate item codes in each pile, distinct(.) is the difference between the numbers of duplicate item codes in each pile, sum(.) is the sum of the differences, and MIN(.) requires that the sum be minimized. The formula for the first equilibrium condition requires that the sum of the differences between the numbers of duplicate item codes in each pile be minimized, so that when the number of duplicate item codes in each pile is close to 500, an optimal solution that satisfies the first equilibrium condition can be obtained. Similarly, the second equilibrium condition can be defined as the formula MIN(sum(distinct(NumPerBox))), where NumPerBox is the number of items in each pile, and the rest can refer to the formula for the first equilibrium condition. The formula for the second equilibrium condition requires that the sum of the differences between the numbers of items in each pile be minimized, so that when the number of items in each pile is close to 8000, an optimal solution that satisfies the second equilibrium condition can be obtained. In addition, other first and second balancing conditions that can achieve a balanced number of duplicated item numbers and a balanced number of items in each pile can also be applied here, and are not exhaustively listed here.

[0097] Based on the balanced number of deduplicated item numbers and the balanced number of items in each sub-pile in the clustering results, the clustering result with the smallest number of deduplicated item numbers in each sub-pile can be used as the target clustering result. The total number of deduplicated item numbers in each sub-pile can be defined as MIN(sum(SKUNumPerBox)), where the meaning of each character can be found in the formula for the first balance condition.

[0098] By setting target clustering conditions including balanced number of duplicate item numbers, balanced number of items, and minimum number of duplicate item numbers, we can not only ensure that the same type of items are divided into the same piles as much as possible to improve the shelving efficiency, but also ensure that the workload of each pile is balanced to match the actual production capacity, thereby ensuring the availability of the item shelving method.

[0099] In some other implementations, after each round of cyclic clustering, the current target clustering result can be recorded based on the target clustering condition; the loop can be stopped when the loop stop condition is met, and the target clustering result recorded when the loop is stopped can be used as the final target clustering result.

[0100] For example, after the first round of cyclic clustering, the first round of clustering results can be recorded as the current target clustering results. After each subsequent round of cyclic clustering, the clustering results of the current round can be compared with the current target clustering results, and the clustering results that better meet the target clustering conditions can be selected to update the current target clustering results until the cycle is terminated. The current target clustering results recorded when the cycle is terminated can be used as the final target clustering results.

[0101] S380: Determine the storage location of each item based on the warehouse storage information and the item number of each pile in the target clustering result.

[0102] S390: Merge the flow directions of the items in each pile according to the location information of each storage location, and put the items in each pile on the shelf according to the flow merging result.

[0103] For example, Figure 4 The flowchart of the algorithm for determining the target clustering result in the method for putting items on shelves provided by an embodiment of the present invention is shown. Figure 4 Before performing cyclic clustering, some tables and methods can be defined in advance; the tables can be used to record the data required in cyclic clustering, and the methods can be used to process the data in cyclic clustering.

[0104] like Figure 4 The predefined tables may include, but are not limited to, a source data table (Source), a container renumbering table (Container), a degree of overlap table (Distance), a current round clustering result table (Box Center), a table showing the number of duplicate item codes for each pile in the current round (Box Center Distance), a table showing the number of duplicate item codes for each pile in the current round (BoxCenter Info), a current target clustering result table (Op Box Center), a table showing the number of duplicate item codes for each pile in the current target clustering result (Op Box Center Distance), a table showing the number of duplicate item codes for each pile in the current target clustering result (Op Box Center Info), a current target clustering result summary table (Result), and a final target clustering result summary table (OpResult). The Result table may summarize data from the Op Box Center table, the Op Box Center Distance table, and the Op Box Center Info table. The Op Result table stores the data in the Result table at the end of the cyclic clustering process.

[0105] like Figure 4The predefined methods may include but are not limited to a method for calculating the degree of overlap (Cal Distance), a method for initializing each pile (Create Box Center), a clustering method (Cluster Box), and a method for calculating duplicate item numbers (Cal SKU Num).

[0106] Accordingly, the algorithm process for determining the target clustering result may include:

[0107] Obtain the Source table, which contains information about each incoming box, such as the box number, item SKU, quantity of items corresponding to each SKU, and style number (which can be considered size information). Renumber the box numbers in the Source table, for example, replacing complex, multi-digit box numbers with simpler numbers like 1 or 2 to facilitate subsequent data recording. Store the renumbered information in the Container table. Use the Cal Distance method to calculate the number of identical item numbers between items in each incoming box in the Container table and record the result in the Distance table.

[0108] After that, you can start a round of clustering at regular intervals. For example, if each round of clustering takes about 450 seconds to complete, you can start a round every 500 seconds to avoid locking in the loop.

[0109] During each round of cyclic clustering, the Create Box Center method is first used to randomly select a preset number of incoming boxes from the Container table as the first incoming box in each sub-stack; the preset number is adjustable. Next, the Cluster Box method is used to determine the incoming box to be stacked from the unstacked incoming boxes in the Container table. The Distance table is queried for the sub-overlap between the incoming box to be stacked and the incoming boxes in each sub-stack. Based on the sub-overlap, the total overlap with each sub-stack is determined, and the target sub-stack is determined from each sub-stack based on the overlap. The incoming box to be stacked is then divided into the target sub-stack until all incoming boxes in the Container table are divided, resulting in the clustering results for the current round. The clustering results for the current round include, for example, the box numbers of the incoming boxes in each sub-stack, and the results for the current round can be stored in the Box Center table.

[0110] After each round of clustering, the Cal SKU Num method is used to calculate the number of duplicate item codes for each incoming box in each stack in the Box Center table. This number of duplicate item codes for each stack is stored in the Box Center Distance table. Based on the target clustering criteria, the Op Box Center table updates the incoming box number for each stack, the Op Box Center Distance table updates the number of duplicate item codes for each stack, and the Op Box Center Info table updates the item information corresponding to each duplicate item code. Simultaneously, the Result table is updated based on the updated Op Box Center, Op Box Center Distance, and Op Box Center Info tables.

[0111] After each round of clustering, it can also be determined whether the loop stop condition is met; if so, the data in the Result table is copied to the Op Result table to obtain the final target clustering result; if not, a round of cyclic clustering can be started again after a certain interval.

[0112] Based on the above embodiment, the embodiment of the present invention provides a detailed description of the cyclic clustering steps and the steps of determining the target clustering results. By determining the preset number of cluster piles according to the preset production capacity, it is beneficial to shelve items based on actual production capacity, thereby improving the universality of the item shelving method. By randomly generating cluster centers, different clustering results corresponding to each cycle can be obtained. By setting target clustering conditions including a balanced number of deduplicated item numbers, a balanced number of items, and a minimum number of deduplicated item numbers, it is possible not only to ensure that the same type of items are divided into the same piles as much as possible to improve the shelving efficiency, but also to ensure that the workload of each pile is balanced to match the actual production capacity, thereby ensuring the availability of the item shelving method. In addition, the embodiment of the present invention and the item shelving method proposed in the above embodiment belong to the same inventive concept. The technical details that are not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0113] This embodiment, building on the previous one, details the determination of item storage locations and the merging of flows based on these locations. By determining the relevant initial storage locations from warehouse storage information based on the item number, storage location matching efficiency can be improved compared to matching the entire warehouse storage information. By determining the storage locations of corresponding items based on the remaining space in each initial storage location, similar items can be placed in the same location whenever possible, and placed in adjacent locations when insufficient space is available. This not only improves shelving efficiency but also ensures storage location utilization.

[0114] Figure 5A flowchart of a method for putting items on shelves provided by an embodiment of the present invention is shown. Figure 5 The method for putting items on shelves provided in this embodiment may include the following steps:

[0115] S510 , clustering each incoming cargo box according to the overlap of the items in each incoming cargo box in a loop to obtain a clustering result until a loop stop condition is met.

[0116] The overlap degree represents the number of identical item numbers; the clustering result includes a preset number of sub-piles.

[0117] S520. Determine a target clustering result from the clustering results corresponding to each round of cycles based on a target clustering condition; the target clustering condition includes that the number of duplicated item numbers of items in each pile in the clustering result meets a preset condition.

[0118] S530: According to the item numbers of the items in each pile in the target clustering result, determine the initial storage location corresponding to each item from the warehouse storage information.

[0119] In this embodiment, the storage location information of stored items with the same item code as each item can be extracted from the full warehouse storage information and used as the initial storage location for the corresponding item. Compared with reading the full warehouse storage information and matching storage locations according to item codes, this can speed up storage location matching and improve storage location matching efficiency.

[0120] S540: Determine the storage location of the corresponding item based on the storage information of each initial storage location.

[0121] The storage information of the initial storage location may include, but is not limited to, the item codes of the stored items, the quantity, size, and style of the items corresponding to each item code, and other information. Determining the corresponding storage location for the items based on the storage information of the initial storage location may include, but is not limited to, determining the storage location for each item based on a priority order from closest to farthest from the initial storage location. For example, the priority order from closest to farthest may include, for example, prioritizing items in the same storage location as first priority, items in the same lane as second priority, and items in the same storage area as third priority.

[0122] In some optional implementations, determining the storage location of the corresponding items based on the storage information of each initial storage location may include: determining the remaining capacity of the corresponding items based on the remaining space of each initial storage location; when the number of corresponding items is less than or equal to the remaining capacity, using the initial storage location as the storage location for the corresponding items; when the number of corresponding items is greater than the remaining capacity, using the initial storage location as the storage location for the corresponding items of the remaining capacity, and using the empty storage location closest to the initial storage location as the storage location for the corresponding items other than the remaining capacity.

[0123] The size information of each initial storage location can be obtained to determine the original space of each initial storage location. The occupied space of each initial storage location can be determined based on the size information of the items stored in each initial storage location. The remaining space of each initial storage location can be obtained by subtracting the occupied space from the original space. The space required for each corresponding item can then be determined based on the size information of the corresponding item. The remaining space can be divided by the required space and rounded down to obtain the remaining capacity of the corresponding item.

[0124] If the number of corresponding items is less than or equal to the remaining capacity, the initial storage location can be considered to be able to accommodate all of the corresponding items. In this case, the initial storage location can be used as the storage location for each corresponding item. If the number of corresponding items is greater than the remaining capacity, the initial storage location can be considered to be able to accommodate some of the corresponding items. In this case, the initial storage location can be used as the storage location for the corresponding items with the remaining capacity. At the same time, the empty storage location closest to the initial storage location can be used as the storage location for the corresponding items other than the remaining capacity.

[0125] In these optional implementations, by determining the storage locations of corresponding items based on the remaining space in each initial storage location, it is possible to place the same items in the same storage location as much as possible, and to place the same items in adjacent storage locations when the remaining space is insufficient. This not only improves the shelving efficiency, but also ensures storage location utilization.

[0126] S550: Merge the flow directions of the items in each pile according to the location information of each storage location, and put the items in each pile on the shelf according to the flow merging result.

[0127] For example, Figure 6 The flowchart of the algorithm for determining the flow direction merging result in a method for putting items on shelves provided by an embodiment of the present invention is shown. Figure 6 Before determining the storage location of items and merging the flow directions according to the storage location, some tables and methods can be defined in advance; the tables can be used to record the data required for determining the storage location of items and merging the flow directions, and the methods can be used to process the data in determining the storage location of items and merging the flow directions.

[0128] like Figure 6 The predefined tables may include but are not limited to the source data table (Source), the target clustering result summary table (Op Result), the aisle sequence table (Aisle Sequence), the WMS stock table (WMS stock), the WMS empty storage table (EmptyWMS stock), the model number rough classification table (Rough Sort Result Tab), the flow direction subdivision table (Classify Result Tab), and the initialized WMS stock table (Init WMS stock).

[0129] like Figure 6 The predefined methods may include but are not limited to the inventory reading method (Read WMS), the item number rough classification method (Rough Sort Result), the storage location subdivision method (Classify Result) and the flow direction merging method (AllocateSlip).

[0130] Accordingly, the algorithm process for determining the flow merging result may include:

[0131] The Read WMS command reads the latest WMS inventory information and writes it to the WMS stock table. At the same time, the latest WMS inventory information can be backed up to the Init WMS stock table to improve disaster recovery when determining flow merge results.

[0132] Reorder the warehouse's aisles based on their spatial location and write the reordered aisle information into the Aisle Sequence table. Because aisles with adjacent aisle identifiers may not be spatially adjacent, redefining the aisle order based on their spatial location can help minimize wasted movement when items are put on shelves.

[0133] After obtaining data from the Op Result table, the Rough Sort Result Tab method can be used to update the box numbers of each incoming case in the Op Result table with the corresponding item numbers, the quantity of items corresponding to each item number, and the style number based on the data in the Source table. The information for each case can then be re-aggregated based on the item and style numbers and recorded in the Rough Sort Result Tab. Simultaneously, the information from the Rough Sort Result Tab can be written to the Classify Result Tab.

[0134] The Classify Result method allocates storage locations for each stack based on data from the WMS stock table and the Empty WMS stock table, and adds each item's storage location to the Classify Result Tab. The Allocate Slip method then merges the items corresponding to each item code in the Classify Result Tab, sequentially, based on data from the Aisle Sequence table. The maximum number of items in each split is 80. Finally, the merged flow results are added to the Classify Result Tab to create the final Classify Result Tab.

[0135] Furthermore, after determining the Classify Result Tab, the items in the same stream can be placed into a single container based on the data in the Classify Result Tab. Subsequently, the corresponding equipment can be controlled to transport each container to the corresponding shelf location within the warehouse and place the items in the container on the corresponding shelf storage location, thereby completing a series of operations to shelve the items in each stack.

[0136] This embodiment of the present invention, based on the above-described embodiment, improves storage location matching efficiency by determining the relevant initial storage location from warehouse storage information based on the item number, compared to matching the entire warehouse storage information. By determining the storage location of the corresponding item based on the remaining space in each initial storage location, it is possible to place similar items in the same storage location as much as possible, and to place similar items in adjacent storage locations when remaining space is insufficient. This not only improves shelving efficiency but also ensures storage location utilization. Furthermore, the item shelving methods proposed in this embodiment of the present invention and the above-described embodiment are based on the same inventive concept. For technical details not fully described in this embodiment, please refer to the above-described embodiment. This embodiment and the above-described embodiment have the same beneficial effects.

[0137] Figure 7 The schematic diagram of the structure of an item shelving device provided by an embodiment of the present invention is shown. This embodiment of the present invention is applicable to situations where items are shelved after entering a warehouse in a container. The item shelving device provided by the present invention can implement the item shelving method provided by the above embodiment.

[0138] like Figure 7 As shown, the article shelving device in the embodiment of the present invention may include:

[0139] A loop clustering module 710 is configured to cyclically cluster each incoming container based on the overlap of items in each container to obtain clustering results until a loop stop condition is satisfied; the overlap represents the number of items with the same ID; and the clustering results include a preset number of sub-piles.

[0140] The cluster determination module 720 is configured to determine a target clustering result from the clustering results corresponding to each round of cycles based on a target clustering condition; the target clustering condition includes that the number of duplicate item numbers of items in each pile in the clustering result meets a preset condition;

[0141] A storage location determination module 730 is configured to determine the storage location of each item based on the warehouse storage information and the item numbers of the items in each pile in the target clustering result;

[0142] The shelving module 740 is used to merge the flow directions of the items in each pile according to the location information of each storage location, so as to shelve the items in each pile according to the flow merging result.

[0143] In some optional implementations, the loop clustering module is configured to perform each loop process based on the following steps:

[0144] Determine the first incoming box in each of the preset number of stacks from each incoming box;

[0145] Determine the incoming cargo boxes to be currently stacked from the incoming cargo boxes that have not been divided into the various stacks;

[0146] Determine a target stack from each stack based on the degree of overlap between the items in the current incoming cargo box to be stacked and the items in the incoming cargo boxes of each stack;

[0147] The incoming boxes to be sorted are sorted into target piles until all the incoming boxes are sorted.

[0148] In some optional embodiments, the article shelving device further includes:

[0149] The preset quantity determination module is used to determine the preset quantity based on the number of items in the incoming boxes per unit time and the preset production capacity before cyclically clustering the incoming boxes according to the overlap of the items in the incoming boxes.

[0150] In some optional embodiments, the cycle stop condition is met, including at least one of the following: the number of cycles reaches a preset number; the cycle duration reaches a preset duration.

[0151] In some optional implementations, the target clustering conditions include:

[0152] When the number of duplicated item numbers of items in each sub-pile meets the first balance condition and the number of items in each sub-pile meets the second balance condition, the total number of duplicated item numbers of items in each sub-pile is the smallest.

[0153] In some optional implementations, the storage location determination module may be used to:

[0154] According to the item numbers of the items in each pile in the target clustering result, the initial storage location corresponding to each item is determined from the warehouse storage information;

[0155] According to the storage information of each initial storage location, the storage location of the corresponding item is determined.

[0156] In some optional implementations, the storage location determination module may be used to:

[0157] Determine the remaining capacity of the corresponding items based on the remaining space of each initial storage location;

[0158] When the number of corresponding items is less than or equal to the remaining storage capacity, the initial storage location is used as the storage location for the corresponding items;

[0159] When the number of corresponding items is greater than the remaining capacity, the initial storage location will be used as the storage location for the corresponding items of the remaining capacity, and the empty storage location closest to the initial storage location will be used as the storage location for the corresponding items other than the remaining capacity.

[0160] The item shelving device provided in the embodiment of the present invention belongs to the same inventive concept as the item shelving method provided in the above embodiment. Technical details not fully described in the embodiment of the present invention can be referred to the above embodiment, and the embodiment of the present invention has the same beneficial effects as the above embodiment.

[0161] Figure 8 The figure shows a hardware structure diagram of a terminal device provided by an embodiment of the present invention. The terminal device in the embodiment of the present invention may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 8 The terminal device 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.

[0162] like Figure 8 As shown, the terminal device 800 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage device 808 into a random access memory (RAM) 803. Various programs and data required for the operation of the terminal device 800 are also stored in the RAM 803. The processing device 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0163] Typically, the following devices may be connected to the I / O interface 805: an input device 806 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 807 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 808 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 809. The communication device 809 may allow the terminal device 800 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 8 The terminal device 800 is shown as having various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0164] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for executing the methods illustrated in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 809, or installed from storage device 808, or installed from ROM 802. When executed by processing device 801, the computer program performs the functions described above in the item shelving method provided in or described in embodiments of the present invention.

[0165] The terminal provided in the embodiment of the present invention and the item shelving method provided in the above embodiment belong to the same inventive concept. For technical details not fully described in the embodiment of the present invention, please refer to the above embodiment. The embodiment of the present invention has the same beneficial effects as the above embodiment.

[0166] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for shelving items provided in the above embodiment or the like is implemented.

[0167] It should be noted that the computer-readable storage medium described above in the embodiments of the present invention may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having 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 (FLASH), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the embodiments of the present invention, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or component. In the embodiments of the present invention, the computer-readable signal medium may include a data signal transmitted in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can 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 suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0168] In some embodiments, the client and server can communicate using any currently known or future developed network protocol, such as HTTP (Hypertext Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0169] The computer-readable storage medium may be included in the terminal device, or may exist independently without being incorporated into the terminal device.

[0170] The terminal device stores and carries one or more programs. When the one or more programs are executed by the terminal device, the terminal device:

[0171] The loop clusters each incoming cargo box according to the overlap of the items in each incoming cargo box to obtain the clustering result until the loop stop condition is met; the overlap represents the number of identical item numbers; the clustering result includes a preset number of piles; based on the target clustering condition, the target clustering result is determined from the clustering results corresponding to each round of the loop; the target clustering condition includes that the number of duplicate item numbers of the items in each pile in the clustering result meets the preset condition; the storage location of each item is determined according to the warehouse storage information and the item number of the items in each pile in the target clustering result; the items in each pile are merged according to the location information of each storage location, so that the items in each pile are put on the shelf according to the flow merging result.

[0172] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0173] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the function pages marked in the box can occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0174] The units involved in the embodiments of the present invention may be implemented in software or hardware, wherein the name of a unit does not necessarily limit the unit itself.

[0175] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0176] Note that the above are only preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will appreciate that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments, and substitutions are possible for those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments and may include many other equivalent embodiments without departing from the scope of the present invention. The scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for putting items on shelves, characterized in that: include: Clustering the incoming boxes according to the overlap of the items in the boxes in a loop to obtain clustering results until a loop stop condition is met; The overlap degree represents the number of identical item numbers; the clustering result includes a preset number of sub-piles; Based on the target clustering condition, determining the target clustering result from the clustering results corresponding to each round of cycles; The target clustering condition includes that the number of duplicate item numbers of items in each pile in the clustering result meets a preset condition; Determining the storage location of each item according to the warehouse storage information and the item number of each item in the target clustering result; The flow directions of the articles in the various piles are merged according to the position information of the various storage locations, so that the articles in the various piles are shelved according to the flow merging result.

2. The method according to claim 1, characterized in that The process of each cycle includes: Determining the first incoming box of each of the preset number of stacks from the incoming boxes; Determine the incoming cargo boxes to be currently stacked from the incoming cargo boxes that have not been divided into the various stacks; Determining a target sub-stack from the sub-stacks according to the overlap between the items in the current incoming cargo box to be stacked and the items in the incoming cargo boxes of the sub-stacks; The incoming cargo boxes currently to be stacked are divided into the target stacks until the division of the incoming cargo boxes is completed.

3. The method according to claim 1, characterized in that Before the loop clusters the incoming boxes according to the overlap of the items in the incoming boxes, the method further includes: The preset quantity is determined based on the number of articles in the incoming cargo box per unit time and the preset production capacity quantity.

4. The method according to claim 1, wherein The cycle stop condition is satisfied, and includes at least one of the following: the number of cycles reaches a preset number; the cycle duration reaches a preset duration.

5. The method according to claim 1, characterized in that The target clustering conditions include: When the number of duplicated item numbers of the items in each sub-pile meets the first balance condition and the number of items in each sub-pile meets the second balance condition, the total number of duplicated item numbers of the items in each sub-pile is the smallest.

6. The method according to claim 1, characterized in that The determining of the storage location of each item according to the warehouse storage information and the item number of each pile of items in the target clustering result includes: Determining, from warehouse storage information, an initial storage location corresponding to each of the items in each pile according to the item number of the item in the target clustering result; The storage location of the corresponding item is determined according to the storage information of each initial storage location.

7. The method according to claim 6, characterized in that The step of determining the storage location of the corresponding item according to the storage information of each initial storage location includes: Determining the remaining capacity of the corresponding items according to the remaining space of each initial storage location; When the quantity of the corresponding items is less than or equal to the remaining storage quantity, the initial storage location is used as the storage location for the corresponding items; When the number of the corresponding items is greater than the remaining capacity, the initial storage location is used as the storage location for the corresponding items of the remaining capacity, and the empty storage location closest to the initial storage location is used as the storage location for the corresponding items other than the remaining capacity.

8. An article shelving device, characterized in that: include: A cyclic clustering module, configured to cyclically cluster the incoming boxes according to the overlap of the items in the boxes to obtain clustering results until a cyclic stopping condition is met; The overlap degree represents the number of identical item numbers; the clustering result includes a preset number of sub-piles; A cluster determination module, configured to determine a target clustering result from the clustering results corresponding to each round of cycles based on a target clustering condition; The target clustering condition includes that the number of duplicate item numbers of items in each pile in the clustering result meets a preset condition; A storage location determination module, configured to determine the storage location of each item according to the warehouse storage information and the item number of each item in the target clustering result; The shelving module is used to merge the flow directions of the items in the various piles according to the position information of each storage location, so as to shelve the items in the various piles according to the flow merging result.

9. A terminal device, characterized in that: The terminal includes: one or more processors; a memory 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 item shelving method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for shelving items as described in any one of claims 1 to 7 is implemented.

Images