Article sorting and warehouse-out method and device
By applying the order optimization method based on hierarchical clustering algorithm and item distribution wall technology in supermarket business, the problem of low efficiency in order production outbound processes is solved, efficient picking outbound products and reducing labor costs and error rates.
Patent Information
- Application Number
- CN202311550166.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-11-20
- Publication Date
- 2025-05-20
Smart Images
Figure CN120020841A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of warehousing logistics, and in particular, to a method and device for sorting and shipping out items. Background Art
[0002] In current supermarket business, the demand for production management of orders is becoming more and more refined. After a user places an order, the order information is sent to the warehousing management system, and it needs to go through the following links: inventory pre-occupation, order collection, picking, packing, merging, shipping, etc. This process can be collectively referred to as the order production and shipping process. Currently, algorithms such as order collection by road area and order collection by delivery route are adopted for the combined order generation method. Hardware devices such as merging walls and hanging chains are used for the merging method. Small stores adopt an integrated picking mode and do not need to merge orders.
[0003] In the process of implementing the present invention, the inventors found that there are at least the following problems in the prior art:
[0004] With the development and growth of the business, there is a bottleneck in improving the efficiency of the supermarket business format. When collecting orders by road area, the order collection rate is low, and the pickers pick goods almost according to each order, with a long picking path and low production efficiency. Order collection by delivery route will lead to an increase in the time for manual secondary sorting, greater difficulty, and customer complaints caused by errors. Manual sorting has the disadvantages of high labor intensity and high labor cost; during peak periods, the number of orders that need to be rechecked is relatively large, or the number of items in each order is relatively large, etc. If not reasonably arranged, it will make the operation of the staff too cumbersome, increasing the work intensity and the error rate of order recheck. Summary of the Invention
[0005] In view of this, embodiments of the present invention provide a method and device for sorting and shipping out items, which can better meet the order sorting and rechecking work, reasonably allocate on-site resources, optimize the picking route, improve the picking and shipping efficiency, save labor costs, reduce the work intensity and operation complexity of store staff, and reduce the error rate of order recheck.
[0006] To achieve the above object, according to one aspect of the embodiments of the present invention, a method for sorting and shipping out items is provided, including:
[0007] Based on the hierarchical clustering algorithm, perform order collection according to the correlation degree between orders in the order set to be sorted, and obtain at least one combined order;
[0008] For each combined order, generate at least one picking task according to the storage locations of the items included in the combined order;
[0009] In response to detecting that the picking task has been completed, a split-order outbound instruction is generated. The split-order outbound instruction is used to sort the items corresponding to the picking tasks included in the combined order to the compartments of the split-order verification table corresponding to the orders to which the items belong by using an item sorting wall for item sorting and outbound.
[0010] Optionally, based on the hierarchical clustering algorithm, order grouping is performed according to the association degree between orders in the order set to be sorted, and no less than one combined order is obtained, including: obtaining the order set to be sorted, and calculating the association degree between each two orders in the order set to be sorted; based on the hierarchical clustering algorithm, taking each order in the order set to be sorted as a cluster, and using the association degree between each two orders as the inter-class distance, performing iterative clustering between the clusters until the obtained clustering clusters meet the combined order generation condition, and obtaining no less than one combined order.
[0011] Optionally, based on the hierarchical clustering algorithm, order grouping is performed according to the association degree between orders in the order set to be sorted, and no less than one combined order is obtained, including: obtaining the order set to be sorted, and calculating the association degree between each two orders in the order set to be sorted; based on the hierarchical clustering algorithm, performing hierarchical clustering according to the association degree between each two orders to construct a clustering tree; performing a hierarchical traversal on the clustering tree to select target nodes that meet the combined order generation condition from the clustering tree; generating combined orders according to the orders included in the target nodes.
[0012] Optionally, calculating the association degree between each two orders in the order set to be sorted includes: for a first order and a second order in the order set to be sorted, respectively obtaining the items included in the first order and the items included in the second order; for each item included in the first order, respectively calculating the item association degree between the item and each item included in the second order, and taking the maximum value among the item association degrees between the item and each item included in the second order as the association degree between the item and the second order, so as to obtain the association degree between each item included in the first order and the second order; for each item included in the second order, respectively calculating the item association degree between the item and each item included in the first order, and taking the maximum value among the item association degrees between the item and each item included in the first order as the association degree between the item and the first order, so as to obtain the association degree between each item included in the second order and the first order; obtaining the association degree between the first order and the second order according to the association degree between each item included in the first order and the second order and the association degree between each item included in the second order and the first order.
[0013] Optionally, the item correlation degree between two items is calculated based on the number of times each of the two items appears in the entire store shelves, the number of times the two items appear on the same shelf, and the probability that the two items appear simultaneously given the presence of one item.
[0014] Optionally, calculating the correlation degree between every two orders in the to-be-sorted order set includes: for a first order and a second order in the to-be-sorted order set, respectively obtaining the items included in the first order and the items included in the second order; calculating the physical distance between each item included in the first order and each item included in the second order in no less than one attribute to generate a distance matrix; according to the distance matrix, calculating the Cartesian product between each item included in the first order and each item included in the second order, and calculating the mean value of the Cartesian product to obtain the correlation degree between the first order and the second order.
[0015] Optionally, the set order generation conditions include: the number of items in the set order does not exceed the set item upper limit; the number of orders in the set order cannot exceed the order upper limit; the current time is within the distribution time interval of the set order.
[0016] According to another aspect of the embodiments of the present invention, there is provided an apparatus for sorting and warehousing items, including:
[0017] A set order processing module, configured to perform set order based on the hierarchical clustering algorithm according to the correlation degree between orders in the to-be-sorted order set to obtain no less than one set order;
[0018] A picking task generation module, configured to generate no less than one picking task for each set order according to the storage locations of the items included in the set order;
[0019] A sorting and warehousing module, configured to generate a split order warehousing instruction in response to detecting that the picking task has been completed, where the split order warehousing instruction is used to sort the items corresponding to the picking tasks included in the set order to the compartments of the split order verification table corresponding to the orders to which the items belong by using an item sorting wall for item sorting and warehousing.
[0020] Optionally, the set order processing module is further configured to: obtain the to-be-sorted order set, and calculate the correlation degree between every two orders in the to-be-sorted order set; based on the hierarchical clustering algorithm, take each order in the to-be-sorted order set as a cluster, use the correlation degree between every two orders as the inter-cluster distance, and perform iterative clustering between the clusters until the obtained clustering clusters meet the set order generation conditions to obtain no less than one set order.
[0021] Optionally, the order set processing module is further configured to: obtain an order set to be sorted, and calculate the correlation degree between every two orders in the order set to be sorted; based on the hierarchical clustering algorithm, perform hierarchical clustering according to the correlation degree between every two orders to construct a clustering tree; perform hierarchical traversal on the clustering tree to select target nodes that meet the set order generation conditions from the clustering tree; and generate set orders according to the orders included in the target nodes.
[0022] Optionally, the order set processing module is further configured to: for a first order and a second order in the order set to be sorted, respectively obtain the items included in the first order and the items included in the second order; for each item included in the first order, calculate the item correlation degree between the item and each item included in the second order, and use the maximum value among the item correlation degrees between the item and each item included in the second order as the correlation degree between the item and the second order, so as to obtain the correlation degree between each item included in the first order and the second order; for each item included in the second order, calculate the item correlation degree between the item and each item included in the first order, and use the maximum value among the item correlation degrees between the item and each item included in the first order as the correlation degree between the item and the first order, so as to obtain the correlation degree between each item included in the second order and the first order; and obtain the correlation degree between the first order and the second order according to the correlation degree between each item included in the first order and the second order and the correlation degree between each item included in the second order and the first order.
[0023] Optionally, the item correlation degree between two items is calculated based on the number of times the two items appear in the entire store shelves respectively, the number of times the two items appear on the same shelf, and the probability that the two items appear simultaneously under the condition that one item appears.
[0024] Optionally, the order set processing module is further configured to: for a first order and a second order in the order set to be sorted, respectively obtain the items included in the first order and the items included in the second order; calculate the physical distance between each item included in the first order and each item included in the second order in no less than one attribute to generate a distance matrix; according to the distance matrix, calculate the Cartesian product between each item included in the first order and each item included in the second order, and calculate the mean value of the Cartesian product to obtain the correlation degree between the first order and the second order.
[0025] Optionally, the set order generation conditions include: the number of items in the set order does not exceed the set item upper limit; the number of orders in the set order cannot exceed the order upper limit; and the current time is within the set order issuance time interval.
[0026] According to another aspect of the embodiments of the present invention, a system for sorting and warehousing items is provided, including a server, an item sorting wall, and a sorting and verification table. Among them, the server is configured to: based on the hierarchical clustering algorithm, perform order aggregation according to the correlation degree between orders in the order set to be sorted, and obtain at least one aggregated order; for each aggregated order, generate at least one picking task according to the storage location of the items included in the aggregated order; in response to detecting that the picking task has been completed, generate a disaggregated warehousing instruction, and the disaggregated warehousing instruction is used to use the item sorting wall to sort the items corresponding to the picking tasks included in the aggregated order to the compartments of the sorting and verification table corresponding to the orders to which the items belong for item sorting and warehousing; the item sorting wall is configured to: sort the items to the compartments of the sorting and verification table corresponding to the orders to which the items belong; the sorting and verification table is configured to: perform sorting and verification according to the items and the orders to which the items belong.
[0027] According to another aspect of the embodiments of the present invention, an electronic device is provided, including: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method for sorting and warehousing items provided by the embodiments of the present invention.
[0028] According to still another aspect of the embodiments of the present invention, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method for sorting and warehousing items provided by the embodiments of the present invention is implemented.
[0029] One embodiment of the above invention has the following advantages or beneficial effects: By performing order aggregation based on the hierarchical clustering algorithm according to the correlation degree between orders in the order set to be sorted, at least one aggregated order is obtained; for each aggregated order, at least one picking task is generated according to the storage location of the items included in the aggregated order; in response to detecting that the picking task has been completed, a disaggregated warehousing instruction is generated, and the disaggregated warehousing instruction is used to use the item sorting wall to sort the items corresponding to the picking tasks included in the aggregated order to the compartments of the sorting and verification table corresponding to the orders to which the items belong for item sorting and warehousing. The technical solution adopts an order aggregation optimization algorithm based on hierarchical clustering to generate aggregated orders, and introduces a sorting wall hardware device for order sorting, which can better meet the order sorting and verification work, reasonably allocate on-site resources, optimize the picking route, improve the picking and warehousing efficiency, save labor costs, reduce the work intensity and operation complexity of store staff, and reduce the error rate of order verification.
[0030] The further effects of the above non-conventional optional methods will be described in conjunction with specific embodiments below. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation to the present invention. Among them:
[0032] Figure 1 is a schematic diagram of the main steps of the method for sorting and shipping out items according to an embodiment of the present invention;
[0033] Figure 2 is a schematic diagram of the implementation process for sorting and shipping out items according to an embodiment of the present invention;
[0034] Figure 3 is a schematic diagram of the main modules of the device for sorting and shipping out items according to an embodiment of the present invention;
[0035] Figure 4 is a schematic diagram of the shipping out process of the item sorting and shipping out system according to an embodiment of the present invention;
[0036] Figure 5 is an exemplary system architecture diagram to which an embodiment of the present invention can be applied;
[0037] Figure 6 is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. Detailed Embodiments
[0038] The following describes exemplary embodiments of the present invention with reference to the accompanying drawings. Various details of the embodiments of the present invention are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, descriptions of well-known functions and structures are omitted below for clarity and conciseness.
[0039] To solve the technical problems existing in the prior art, the present invention provides a method and device for sorting and warehousing articles. The main implementation method is as follows: The system uses the order consolidation algorithm of hierarchical clustering to consolidate orders with the highest similarity of commodity categories, so as to generate a picking list with the shortest picking route. After the picker completes picking, the articles are sorted and warehoused according to the orders to which the articles belong. Specifically, a sorting wall can be used for automatic order sorting. After the picker completes picking, the order corresponding to the picking container is bound to the grid of the sorting and verification table. Among them, the commodities in the picking container correspond to multiple orders, and the orders with the same flow direction are bound to the same grid. In response to the operation of the user scanning the goods placed in the picking container, the expected sorting quantity of this kind of goods in each grid is determined according to the order information bound to the grid, and then a prompt information for indicating the expected sorting quantity of this kind of goods in each grid is generated. After the user sorts this kind of goods to each grid according to the prompt information, the actual sorting quantity of this kind of goods in each grid is determined. According to the actual sorting quantity of this kind of goods in each grid, the verification quantity of this kind of goods in the order bound to the grid is determined. Through the above steps, the work efficiency of article sorting and warehousing can be improved.
[0040] In an embodiment of the present invention, in terms of the order consolidation method, the specific implementation of the order set optimization algorithm of the present invention is as follows: First, each order is regarded as an object, and the association degree of the commodities in the order is used as the inter-class distance to construct a difference matrix. Then, the two objects with the largest order association degree are merged, and finally the difference matrix is updated. The above two processes are looped until the termination condition is met and stopped, and the order group with the largest association degree is obtained for combined picking.
[0041] In another embodiment of the present invention, multiple candidate orders are extracted from the order pool, and hierarchical clustering is performed on the multiple candidate orders to construct a clustering tree; the clustering tree is traversed hierarchically to select target nodes that meet the preset conditions from the clustering tree; a set order is generated using all the candidate orders included in the target nodes. The order consolidation algorithm uses hierarchical clustering, and the main clustering idea is similar to the greedy algorithm. By calculating the similarity between set orders, the two most similar set orders among all set orders are combined, and this process is iteratively repeated. Simply put, the merging algorithm of hierarchical clustering determines the similarity between them by calculating the distance between each set order and all set orders. The smaller the distance, the higher the similarity. And the two set orders with the closest distance are combined to generate a clustering tree.
[0042] The present invention adopts an optimized set order generation algorithm and introduces a sorting wall hardware device for order sorting, which can better meet the order sorting and verification work, reasonably allocate on-site resources, optimize the picking route, and reduce the complexity and error rate of the operations of store staff.
[0043] Figure 1It is a schematic diagram of the main steps of the method for sorting and warehousing items according to an embodiment of the present invention. As Figure 1 shown, the method for sorting and warehousing items according to an embodiment of the present invention mainly includes the following steps S101 to S103.
[0044] Step S101: Based on the hierarchical clustering algorithm, order consolidation is performed according to the correlation degree between orders in the order set to be sorted, and at least one consolidated order is obtained. In the embodiments of the present invention, the items mentioned are illustrated by taking commodities as an example.
[0045] According to an embodiment of the present invention, based on the hierarchical clustering algorithm, order consolidation is performed according to the correlation degree between orders in the order set to be sorted, and at least one consolidated order is obtained, which may specifically include: obtaining the order set to be sorted, and calculating the correlation degree between each two orders in the order set to be sorted; based on the hierarchical clustering algorithm, taking each order in the order set to be sorted as a cluster, and using the correlation degree between each two orders as the inter-class distance, iterative clustering between clusters is performed until the obtained clustering clusters meet the consolidated order generation condition, and at least one consolidated order is obtained.
[0046] According to another embodiment of the present invention, based on the hierarchical clustering algorithm, order consolidation is performed according to the correlation degree between orders in the order set to be sorted, and at least one consolidated order is obtained, which may specifically include: obtaining the order set to be sorted, and calculating the correlation degree between each two orders in the order set to be sorted; based on the hierarchical clustering algorithm, hierarchical clustering is performed according to the correlation degree between each two orders to construct a clustering tree; the clustering tree is traversed hierarchically to select target nodes that meet the consolidated order generation condition from the clustering tree; consolidated orders are generated according to the orders included in the target nodes.
[0047] In an embodiment of the present invention, calculating the correlation degree between every two orders in the order set to be sorted may specifically include: for a first order and a second order in the order set to be sorted, respectively obtaining the items included in the first order and the items included in the second order; for each item included in the first order, respectively calculating the item correlation degree between the item and each item included in the second order, and taking the maximum value among the item correlation degrees between the item and each item included in the second order as the correlation degree between the item and the second order, so as to obtain the correlation degree between each item included in the first order and the second order; for each item included in the second order, respectively calculating the item correlation degree between the item and each item included in the first order, and taking the maximum value among the item correlation degrees between the item and each item included in the first order as the correlation degree between the item and the first order, so as to obtain the correlation degree between each item included in the second order and the first order; according to the correlation degree between each item included in the first order and the second order, and the correlation degree between each item included in the second order and the first order, obtaining the correlation degree between the first order and the second order.
[0048] Wherein, the item correlation degree between two items is calculated based on the number of times the two items appear in the whole warehouse shelves respectively, the number of times the two items appear on the same shelf, and the probability that the two items appear simultaneously under the condition that one item appears.
[0049] In the optimization of picking order combination, the correlation degree of commodities is an important basis for order combination and also an important parameter in order grouping calculation. In the prior art, the association rule mining algorithm is generally used to determine the calculation method of commodity correlation degree. In the association rule mining algorithm, there are usually two parameters: support degree and confidence degree, which are used to represent the correlation degree between commodities. The support degree between commodity set A and commodity set B represents the probability that the two sets appear in all existing picking orders, that is, the probability that customers place orders for the commodities in the two sets at the same time. The confidence degree between commodity set A and commodity set B represents the probability that set B appears under the condition that set A appears, that is, the probability that customers continue to place orders for set B after placing orders for set A. However, representing the correlation degree between commodities only from the support degree and the confidence degree has certain limitations. For two completely non-overlapping orders, the correlation degree of commodities is 0, that is, the two orders are not related. Especially for the current situation of low overlap of order commodities in this e-commerce warehouse, this method is not advisable. Therefore, the correlation degree between commodity SKUs in this patent is calculated based on the distribution of commodities in the in-warehouse shelf inventory. In actual use, the inventory information is read in real time each time, and a certain correlation relationship can also be established for orders with no overlapping commodities, so as to improve the picking efficiency. The formula for calculating the correlation degree between commodity skui and commodity skuj is as follows:
[0050]
[0051] Among them, f i represents the number of times the product sku appears in all the shelves in the store, f i represents the number of times the product sku appears in all the shelves in the store, h j represents the number of times the product sku appears in all the shelves in the store, h j represents the number of times the product sku appears in all the shelves in the store, h ij represents the product sku i and the product sku j appear on the same shelf in the whole store. represents the product sku i Under the condition of appearance, the product sku i and the product sku j appear simultaneously. The probability is c ij represents the correlation value between any two products. The range of the correlation value between products is between 0 and 1. If they do not appear on the same shelf at all, it is 0. The correlation value between the same products is 1.
[0052] In addition to the product correlation, there is also an order correlation algorithm implementation based on the maximum product correlation, that is, a set of mutually correlated products exists in different orders, so that different orders also have a certain degree of correlation. Take the product sku in order A i and the maximum correlation value of all products in order B as the correlation of this product sku i with order B. The correlation between two orders depends on the correlation of all products with another order. The calculation method of the correlation between order A(a1, a2,..., am) and order B(b1, b2,..., bn) is as follows:
[0053]
[0054] Among them, c ij ∈[0,1] represents the correlation matrix between the product sku i and the product sku j which can be obtained through the product correlation algorithm in the above text. S AB represents the correlation value between two orders. m is the number of products in order A, and n is the number of products in order B.
[0055] In addition, in other embodiments of the present invention, the order correlation calculation based on the product correlation can also adopt the following algorithm:
[0056]
[0057] Among them, c ij ∈[0,1] represents the product skui and the product SKU j The correlation matrix between them can be obtained through the product correlation algorithm in the above text. S AB represents the correlation value between two orders.
[0058] The order combination strategy based on the hierarchical clustering idea is essentially an order grouping strategy that combines the order maximum correlation algorithm and the agglomerative hierarchical clustering idea. According to the distribution of products in the storage locations and the category similarity, the correlation between products is obtained, and then the correlation between orders containing these products is calculated based on the product correlation. Based on the hierarchical clustering idea, first, each order is regarded as a cluster, and the order correlation value calculated above is selected as the inter-class distance. Then, orders or order combinations with a correlation greater than a certain value between these orders are merged into larger and larger clusters, and the iteration is repeated until the set single generation condition for order grouping is reached, and the merging behavior stops. At this time, the merged order group is used as a set single, which will be uniformly sent to the production center module to generate a picking task.
[0059] In another embodiment of the present invention, calculating the correlation between every two orders in the order set to be sorted may specifically include: for the first order and the second order in the order set to be sorted, respectively obtain the items included in the first order and the items included in the second order; calculate the physical distance between each item included in the first order and each item included in the second order in at least one attribute to generate a distance matrix; according to the distance matrix, calculate the Cartesian product between each item included in the first order and each item included in the second order, and calculate the mean value of the Cartesian product to obtain the correlation between the first order and the second order.
[0060] In this embodiment, the correlation between orders can be represented by the distance between orders, and the distance calculation method can be calculated using the center of mass chain. The center of mass chain is a physical concept used to describe the change in the position of the center of mass of an object during motion. The center of mass is a virtual point that represents the average position of all parts of the object and the mass distribution of the whole object. Combining with the embodiment of the present invention, the center of mass is the attributes such as the storage area and category to which the products in the order belong. In the actual offline retail scenario, the center of mass chain is used to optimize warehouse management and generate set singles; the core idea of the center of mass chain is to calculate the similarity between set singles according to the attributes such as the storage location, category, and skuId of the products in the order.
[0061] In an embodiment of the present invention, it is possible to first calculate three dimensions: the physical distances between all the storage locations or storage areas to which the goods in the currently to-be-sorted order set belong, the similarity between the categories to which the goods belong, and the similarity between the product identification skuIds. Three fixed distances are respectively set, and a distance matrix is generated. Then, the dissimilarity between the centroid of set order a and the centroid of set order b is calculated, where the centroid of a set order refers to the average value of the goods in the set order in each attribute. For example, if the goods under a set order include attributes such as the skuId, storage area, and category of the goods, then the centroid is the average value of these attributes. For multiple set orders, their centroids can be calculated, and then the distance between these two centroids can be calculated, and this distance can be used to measure the similarity between the two set orders. If the centroid distance between two sets is small, then these two sets are relatively similar, otherwise they are not very similar. Among them, when calculating the centroid distance, it can be specifically calculated by finding the average Cartesian product.
[0062] The average Cartesian product of two set orders can be regarded as the average result of the combination of the product elements in the two set orders, and can be used to measure the similarity between the two set orders. A new set order C is formed by combining each element in a set order A with each element in set order B. For example, set order A contains products A1, A2, A3, and set order B contains products B1, B2, B3. Then, the Cartesian product of set order A and set order B is {A1,B1},{A1,B2},{A1,B3},{A2,B1},{A2,B2},{A2,B3},{A3,B1},{A3,B2},{A3,B3}, a total of 9 combinations. After the average Cartesian product of the two set orders, the similarities of the attributes such as the skuId, category, and storage area of the product combinations under the set order are obtained. The specific implementation steps are as follows:
[0063] 1. For each order in set order A, combine the categories to which all its products belong with the categories to which each order product in set order B belongs to obtain a new category combination. For each new category combination, calculate its average category similarity;
[0064] 2. For each order in set order A, combine the storage areas to which all its products belong with the storage areas to which each order product in set order B belongs to obtain a new storage area combination. For each new storage area combination, calculate its average storage area similarity;
[0065] 3. For each order in set order A, combine the skuIds of all its products with the skuIds of each order product in set order B to obtain a new skuId combination. For each skuId combination, calculate its average skuId similarity;
[0066] 4. Calculate the average similarity of categories for all new category combinations, the average similarity of storage areas for all new storage area combinations, and the average similarity of skuIds for all new skuId combinations, and then calculate the average value to obtain the similarity between the centroids of set single A and set single B. That is: the correlation degree between set single A and set single B.
[0067] After calculating the correlation degree between each two set singles, order clustering can be performed based on the hierarchical clustering algorithm. Specifically, there are mainly the following steps:
[0068] 1. Initialize all orders as set singles with one order per set.
[0069] 2. Calculate the correlation degree between set singles, which can be calculated using the correlation degree calculation method introduced in the foregoing embodiments or using the method of calculating the distance between set singles by centroid linkage.
[0070] 3. Find the two set singles with the highest correlation degree and merge them into one set single.
[0071] 4. Recalculate the correlation degree between the new set single and all the old set singles.
[0072] 5. Repeat steps 2 and 3 until finally merged into one set single, forming a tree, and each node is a clustering result.
[0073] When distributing set singles, the set singles can be traversed from top to bottom in this tree to determine whether the node meets the set single generation conditions. If it meets, the orders in all its child nodes are clustered into one set single for distribution, and other nodes are traversed; if it does not meet, its child nodes are traversed until the entire tree is traversed. Among them, the set single generation conditions include, for example: the number of items in the set single does not exceed the set item upper limit; the number of orders in the set single cannot exceed the order upper limit; the current time is within the distribution time interval of the set single. Among them, the calculation method for the estimated distribution time of the set single is the earliest start picking time of all orders in the set single minus the estimated picking time (60s + 10s * number of categories + 20s * number of regions), and the distribution time interval is [estimated distribution time - 90s, estimated distribution time], where s is the time unit of seconds.
[0074] Step S102: For each set single, generate at least one picking task according to the storage locations of the items included in the set single. After obtaining the set single, it is split according to the result of the set single to obtain at least one picking task, and the specific splitting rule is to split according to the storage locations of the items. For example: if the storage areas where the commodities under set single A belong include storage area 1, storage area 2, and storage area 3, then set single A will be split into three picking tasks according to the storage areas. The staff can perform picking according to the picking tasks, and the commodities corresponding to the picking tasks can be placed in the picking bag.
[0075] Step S103: In response to detecting that the picking task has been completed, a split order outbound instruction is generated. The split order outbound instruction is used to sort the items corresponding to the picking tasks included in the combined order to the compartments of the split order verification table corresponding to the orders to which the items belong by using an item sorting wall for item sorting and outbound. When all the picking tasks corresponding to the combined order are completed, split order outbound can be carried out. When carrying out split order outbound, it can be specifically implemented based on the sorting wall, a hardware device for small item sorting, by combining the combined order algorithm with the sorting hardware device, ensuring the efficiency of the order picking, packing, and outbound process.
[0076] The specific sorting method is as follows: The picker places the picking bag on the bag supply table. After the barcode is recognized by the scanning module at the equipment entrance, the sorting vehicle at the end of the conveyor belt will transport it to the corresponding compartment. After completing the sorting of the orders (one combined order) in one wave, the staff can remove the bin from the sorting rack and send it to the packing table. Through practice, the use of the automatic sorting wall has improved the picking efficiency by 200% compared with manual sorting, with a finer sorting granularity and an accuracy rate as high as 99.99%.
[0077] Figure 2 It is a schematic diagram of the implementation process of item sorting and outbound in an embodiment of the present invention. As Figure 2 shown, in an embodiment of the present invention, when carrying out item sorting and outbound, first, the commodity information included in each order in the order list is obtained, and it is judged whether all the commodities are in the category white list and whether there are any commodities in the black list; if all are in the category white list and there are no commodities in the black list, the correlation degree between two orders is calculated, and a pre-combined order node is generated according to the order correlation degree, where the pre-combined order node is used to store the orders for which combined orders will be generated. Then, it is judged whether the picking can be completed on time according to the planned picking time of each obtained order. If not, the order is taken as a separate combined order; if so, based on the hierarchical clustering algorithm, the orders in the pre-combined order node are divided to generate a tree-shaped clustering structure; then, the nodes of the tree are traversed, and it is judged whether the combined order generation condition is met; if so, a combined order is generated; otherwise, the order corresponding to the node is sent back to the order list.
[0078] Figure 3 It is a schematic diagram of the main modules of the item sorting and outbound device according to an embodiment of the present invention. As Figure 3 shown, the item sorting and outbound device 300 in the embodiment of the present invention mainly includes a combined order processing module 301, a picking task generation module 302, and a sorting and outbound module 303.
[0079] The combined order processing module 301 is used to perform combined order based on the hierarchical clustering algorithm according to the correlation degree between the orders in the order set to be sorted, and obtain at least one combined order;
[0080] The picking task generation module 302 is configured to generate at least one picking task for each collection list according to the storage locations of the items included in the collection list;
[0081] The sorting and outbound module 303 is configured to generate a sub - order outbound instruction in response to detecting that the picking task has been completed. The sub - order outbound instruction is used to sort the items corresponding to the picking tasks included in the collection list to the compartments of the sub - order verification table corresponding to the order to which the items belong by using an item sorting wall for item sorting and outbound.
[0082] According to an embodiment of the present invention, the collection list processing module 301 may further be configured to: obtain a set of orders to be sorted, and calculate the correlation degree between every two orders in the set of orders to be sorted; based on the hierarchical clustering algorithm, take each order in the set of orders to be sorted as a cluster, use the correlation degree between every two orders as the inter - cluster distance, and perform iterative clustering between the clusters until the obtained clustering clusters meet the collection list generation condition, so as to obtain at least one collection list.
[0083] According to another embodiment of the present invention, the collection list processing module 301 may further be configured to: obtain a set of orders to be sorted, and calculate the correlation degree between every two orders in the set of orders to be sorted; based on the hierarchical clustering algorithm, perform hierarchical clustering according to the correlation degree between every two orders to construct a clustering tree; perform a hierarchical traversal on the clustering tree to select target nodes that meet the collection list generation condition from the clustering tree; generate collection lists according to the orders included in the target nodes.
[0084] According to another embodiment of the present invention, when calculating the correlation degree between every two orders in the order set to be sorted, the order set processing module 301 may specifically be configured to: for a first order and a second order in the order set to be sorted, respectively obtain the items included in the first order and the items included in the second order; for each item included in the first order, respectively calculate the item correlation degree between the item and each item included in the second order, and use the maximum value among the item correlation degrees between the item and each item included in the second order as the correlation degree between the item and the second order, so as to obtain the correlation degree between each item included in the first order and the second order; for each item included in the second order, respectively calculate the item correlation degree between the item and each item included in the first order, and use the maximum value among the item correlation degrees between the item and each item included in the first order as the correlation degree between the item and the first order, so as to obtain the correlation degree between each item included in the second order and the first order; according to the correlation degree between each item included in the first order and the second order, and the correlation degree between each item included in the second order and the first order, obtain the correlation degree between the first order and the second order.
[0085] According to another embodiment of the present invention, the item correlation degree between two items is calculated based on the number of times the two items appear in the entire store shelves respectively, the number of times the two items appear on the same shelf, and the probability that the two items appear simultaneously under the condition that one item appears.
[0086] According to another embodiment of the present invention, when calculating the correlation degree between every two orders in the order set to be sorted, the order set processing module 301 may specifically be configured to: for a first order and a second order in the order set to be sorted, respectively obtain the items included in the first order and the items included in the second order; calculate the physical distance between each item included in the first order and each item included in the second order in no less than one attribute to generate a distance matrix; according to the distance matrix, calculate the Cartesian product between each item included in the first order and each item included in the second order, and calculate the mean value of the Cartesian product, so as to obtain the correlation degree between the first order and the second order.
[0087] According to another embodiment of the present invention, the set order generation conditions include: the number of items in the set order does not exceed the set item upper limit; the number of orders in the set order cannot exceed the order upper limit; the current time is within the distribution time range of the set order.
[0088] According to the technical solution of the embodiment of the present invention, by based on the hierarchical clustering algorithm, order grouping is performed according to the correlation degree between orders in the order set to be sorted, and at least one grouped order is obtained; for each grouped order, at least one picking task is generated according to the storage location of the items included in the grouped order; in response to detecting that the picking task has been completed, a split-order outbound instruction is generated, and the split-order outbound instruction is used to use the item sorting wall to sort the items corresponding to the picking tasks included in the grouped order to the compartments of the sorting and verification table corresponding to the orders to which the items belong for item sorting and outbound. The technical solution adopts the order grouping optimization algorithm based on hierarchical clustering to generate grouped orders, and introduces the hardware device of the sorting wall for order sorting, which can better meet the order sorting and verification work, reasonably allocate on-site resources, optimize the picking route, improve the picking and outbound efficiency, save labor costs, reduce the work intensity and operation complexity of store staff, and reduce the error rate of order verification.
[0089] According to another embodiment of the present invention, a system for item sorting and outbound is further provided, including a server, an item sorting wall, and a sorting and verification table. Among them, the server is used for: based on the hierarchical clustering algorithm, performing order grouping according to the correlation degree between orders in the order set to be sorted, and obtaining at least one grouped order; for each grouped order, generating at least one picking task according to the storage location of the items included in the grouped order; in response to detecting that the picking task has been completed, generating a split-order outbound instruction, and the split-order outbound instruction is used to use the item sorting wall to sort the items corresponding to the picking tasks included in the grouped order to the compartments of the sorting and verification table corresponding to the orders to which the items belong for item sorting and outbound; the item sorting wall is used for: sorting the items to the compartments of the sorting and verification table corresponding to the orders to which the items belong; the sorting and verification table is used for: performing sorting and verification according to the items and the orders to which the items belong. Specifically, the device for item sorting and outbound of the embodiment of the present invention is deployed on the server to generate a split-order outbound instruction according to the foregoing embodiments for item sorting and outbound.
[0090] Figure 4 It is a schematic diagram of the outbound process of the item sorting and outbound system of the embodiment of the present invention. As Figure 4As shown, in the embodiments of the present invention, when sorting and shipping items out of the warehouse, first, zonal general sorting can be performed (such as "1. Zonal General Sorting" in the figure). Specifically, it can be executed by the server in the item sorting and shipping out system, and the server realizes zonal general sorting through the item sorting and shipping out device deployed thereon to generate a sub - order shipping out instruction. Then, sub - order shipping out is carried out according to the sub - order shipping out instruction. Specifically, it can be realized based on the hardware device, the sorting wall, for small - item commodity sorting (such as "2. Automatic Sorting" in the figure). By combining the order - picking algorithm with the sorting hardware device, the efficiency of the order picking, packing, and shipping out process is ensured. The specific sorting method is as follows: The order - picker places the picking bag on the bag - supply table. After the barcode is recognized by the scanning module at the equipment entrance, the sorting vehicle at the end of the conveyor belt will transport it to the corresponding grid opening of the sorting and verification table. After completing the sorting of an order wave (a set order), the staff can conduct sorting and verification according to the items in the grid opening and the order. After the verification is completed, the bin is removed from the sorting rack (such as "3. Path Set Order Bin Retrieval") and shipped out (such as "4. Shipping Out"). Then, the delivery personnel, the rider, picks up and delivers the items (such as "5. Pick - up and Delivery"). Finally, the empty bin is put into the warehouse again, and the empty bin is replaced into the sorting wall (such as "6. Empty Bin Replacement into the Sorting Wall"). Through the above shipping - out process, item shipping out according to the item sorting and shipping out system of the embodiments of the present invention can be realized.
[0091] Figure 5 An exemplary system architecture 500 is shown that can apply the method or device for item sorting and shipping out of the embodiments of the present invention.
[0092] As Figure 5 shown, the system architecture 500 may include terminal devices 501, 502, 503, a network 504, and a server 505. The network 504 is used to provide a medium for communication links between the terminal devices 501, 502, 503 and the server 505. The network 504 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.
[0093] Users can use the terminal devices 501, 502, 503 to interact with the server 505 through the network 504 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 501, 502, 503, such as shopping - type applications, web browser applications, search - type applications, instant messaging tools, email clients, social platform software, etc. (only as examples).
[0094] The terminal devices 501, 502, 503 can be various electronic devices with a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, and desktop computers, etc.
[0095] The server 505 can be a server that provides various services. For example, it can be a back-end management server (only for example) that supports the websites browsed by users using the terminal devices 501, 502, and 503. The back-end management server can perform data such as item sorting and outbound requests based on a hierarchical clustering algorithm, group orders according to the correlation degree between orders in the order set to be sorted, and obtain at least one set order; for each set order, generate at least one picking task according to the storage location of the items included in the set order; in response to detecting that the picking task has been completed, generate a split order outbound instruction, which is used to sort the items corresponding to the picking tasks included in the set order to the compartments of the split sorting and verification table corresponding to the orders to which the items belong using an item distribution wall for item sorting and outbound processing, etc., and feedback the processing result (such as the sorting result - only for example) to the terminal device.
[0096] It should be noted that the method for item sorting and outbound provided by the embodiments of the present invention is generally executed by the server 505. Correspondingly, the device for item sorting and outbound is generally arranged in the server 505.
[0097] It should be understood that Figure 5 the numbers of the terminal devices, network, and server in
[0098] are merely illustrative. According to the implementation requirements, there can be any number of terminal devices, network, and server. Figure 6 is a schematic structural diagram of a computer system 600 suitable for implementing the terminal device or server of the embodiments of the present invention. Figure 6 The terminal device or server shown is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present invention.
[0099] As Figure 6 shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 602 or the program loaded from the storage section 608 into the random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other through a bus 604. The input / output (I / O) interface 605 is also connected to the bus 604.
[0100] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as required. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is installed on the drive 610 as required so that a computer program read out therefrom is installed into the storage section 608 as required.
[0101] Specifically, according to the embodiments disclosed by the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed by the present invention include a computer program product which includes a computer program carried on a computer-readable medium, and the computer program includes program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 609, and / or installed from the removable medium 611. When the computer program is executed by a central processing unit (CPU) 601, the above-described functions defined in the system of the present invention are executed.
[0102] It should be noted that the computer-readable medium shown in the present invention can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. In the present invention, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and this computer-readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.
[0103] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the above module, program segment, or 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 functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.
[0104] The units or modules involved in the embodiments of the present invention can be implemented in software or in hardware. The described units or modules can also be provided in a processor. For example, it can be described as: A processor includes a single order aggregation processing module, a picking task generation module, and a sorting and outbound module. Among them, the names of these units or modules do not constitute a limitation to the units or modules themselves in some cases. For example, the single order aggregation processing module can also be described as "a module for aggregating single orders based on a hierarchical clustering algorithm according to the association degree between orders in the order set to be sorted, and obtaining at least one aggregated order".
[0105] As another aspect, the present invention also provides a computer-readable medium. The computer-readable medium can be included in the device described in the above embodiments; or it can exist alone without being assembled into the device. The above computer-readable medium carries one or more programs. When the above one or more programs are executed by the device, the device includes: aggregating single orders based on a hierarchical clustering algorithm according to the association degree between orders in the order set to be sorted, and obtaining at least one aggregated order; for each aggregated order, generating at least one picking task according to the storage location of the items included in the aggregated order; in response to detecting that the picking task has been completed, generating a split order outbound instruction, where the split order outbound instruction is used to use an item distribution wall to sort the items corresponding to the picking tasks included in the aggregated order to the compartments of the distribution and verification table corresponding to the orders to which the items belong for item sorting and outbound.
[0106] According to the technical solution of the embodiments of the present invention, by aggregating single orders based on a hierarchical clustering algorithm according to the association degree between orders in the order set to be sorted, and obtaining at least one aggregated order; for each aggregated order, generating at least one picking task according to the storage location of the items included in the aggregated order; in response to detecting that the picking task has been completed, generating a split order outbound instruction, where the split order outbound instruction is used to use an item distribution wall to sort the items corresponding to the picking tasks included in the aggregated order to the compartments of the distribution and verification table corresponding to the orders to which the items belong for item sorting and outbound. The technical solution that adopts an aggregated order generation optimization algorithm based on hierarchical clustering and introduces a distribution wall hardware device for order distribution can better meet the order distribution and verification work, reasonably allocate on-site resources, optimize the picking movement route, improve the picking and outbound efficiency, save labor costs, reduce the work intensity and operation complexity of store staff, and reduce the error rate of order verification.
[0107] The above specific embodiments do not constitute a limitation to the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.
Claims
1. A method for sorting items out of a warehouse, characterized in that: include: Based on the hierarchical clustering algorithm, the orders are grouped according to the correlation between the orders in the order set to be sorted, and no less than one group order is obtained; For each collection list, generating at least one picking task according to the storage locations of the items included in the collection list; In response to detecting that the picking task has been completed, a split order outbound instruction is generated. The split order outbound instruction is used to sort the items corresponding to the picking tasks included in the collection order, using the item distribution wall, to the grid of the distribution review table corresponding to the order to which the items belong, so as to sort the items out of the warehouse.
2. The method according to claim 1, characterized in that Based on the hierarchical clustering algorithm, the orders are grouped according to the correlation between the orders in the order set to be sorted, and at least one group order is obtained, including: Obtain a set of orders to be sorted, and calculate the correlation between every two orders in the set of orders to be sorted; Based on the hierarchical clustering algorithm, each order in the to-be-sorted order set is regarded as a cluster, and the correlation between every two orders is used as the distance between clusters, and iterative clustering is performed between clusters until the obtained clusters meet the collection order generation conditions and obtain no less than one collection order.
3. The method according to claim 1, characterized in that Based on the hierarchical clustering algorithm, the orders are grouped according to the correlation between the orders in the order set to be sorted, and at least one group order is obtained, including: Obtain a set of orders to be sorted, and calculate the correlation between every two orders in the set of orders to be sorted; Based on a hierarchical clustering algorithm, hierarchical clustering is performed according to the correlation between each two orders to construct a clustering tree; Performing a hierarchical traversal on the clustering tree to select a target node that meets a set order generation condition from the clustering tree; A collection order is generated according to the orders included in the target node.
4. The method according to claim 2 or 3, characterized in that: Calculating the correlation between every two orders in the to-be-sorted order set, including: For the first order and the second order in the set of orders to be sorted, respectively obtaining items included in the first order and items included in the second order; For each item included in the first order, respectively calculate the item association degree between the item and each item included in the second order, and use the maximum value of the item association degrees between the item and each item included in the second order as the association degree between the item and the second order, so as to obtain the association degree between each item included in the first order and the second order; For each item included in the second order, respectively calculate the item association degree between the item and each item included in the first order, and use the maximum value of the item association degrees between the item and each item included in the first order as the association degree between the item and the first order, so as to obtain the association degree between each item included in the second order and the first order; The degree of association between the first order and the second order is obtained according to the degree of association between each item included in the first order and the second order, and the degree of association between each item included in the second order and the first order.
5. The method according to claim 4, characterized in that The item association between two items is calculated based on the number of times the two items appear in all shelves, the number of times the two items appear on the same shelf, and the probability of the two items appearing at the same time when one item appears.
6. The method according to claim 2 or 3, characterized in that: Calculating the correlation between every two orders in the to-be-sorted order set, including: For the first order and the second order in the set of orders to be sorted, respectively obtaining items included in the first order and items included in the second order; calculating a physical distance between at least one attribute of each item included in the first order and each item included in the second order to generate a distance matrix; According to the distance matrix, the Cartesian product between each item included in the first order and each item included in the second order is calculated, and the mean of the Cartesian products is calculated to obtain the association degree between the first order and the second order.
7. The method according to claim 2 or 3, characterized in that: The collection order generation conditions include: The number of items in the collection list does not exceed the set item limit; The number of orders in a collection order cannot exceed the order limit; The current time is within the time range for issuing the collection order.
8. A device for sorting out items from a warehouse, characterized in that: include: The order collection processing module is used to collect orders according to the correlation between the orders in the order collection to be sorted based on the hierarchical clustering algorithm to obtain no less than one collection order; A picking task generating module, used for generating at least one picking task for each collection list according to the storage locations of the items included in the collection list; The sorting and outbound module is used to generate a separate order outbound instruction in response to detecting that the picking task has been completed. The separate order outbound instruction is used to sort the items corresponding to the picking tasks included in the collection order to the grid of the distribution review table corresponding to the order to which the items belong, using the item distribution wall, for sorting and outbound delivery of the items.
9. The device according to claim 8, characterized in that The collection order processing module is also used for: Obtain a set of orders to be sorted, and calculate the correlation between every two orders in the set of orders to be sorted; Based on the hierarchical clustering algorithm, each order in the to-be-sorted order set is regarded as a cluster, and the correlation between every two orders is used as the distance between clusters, and iterative clustering is performed between clusters until the obtained clusters meet the collection order generation conditions and obtain no less than one collection order.
10. The device according to claim 8, characterized in that The collection order processing module is also used for: Obtain a set of orders to be sorted, and calculate the correlation between every two orders in the set of orders to be sorted; Based on a hierarchical clustering algorithm, hierarchical clustering is performed according to the correlation between each two orders to construct a clustering tree; Performing a hierarchical traversal on the clustering tree to select a target node that meets a set order generation condition from the clustering tree; A collection order is generated according to the orders included in the target node.
11. The device according to claim 9 or 10, characterized in that The collection order processing module is also used for: For the first order and the second order in the set of orders to be sorted, respectively obtaining items included in the first order and items included in the second order; For each item included in the first order, respectively calculate the item association degree between the item and each item included in the second order, and use the maximum value of the item association degrees between the item and each item included in the second order as the association degree between the item and the second order, so as to obtain the association degree between each item included in the first order and the second order; For each item included in the second order, respectively calculate the item association degree between the item and each item included in the first order, and use the maximum value of the item association degrees between the item and each item included in the first order as the association degree between the item and the first order, so as to obtain the association degree between each item included in the second order and the first order; The degree of association between the first order and the second order is obtained according to the degree of association between each item included in the first order and the second order, and the degree of association between each item included in the second order and the first order.
12. The device according to claim 11, characterized in that The item association between two items is calculated based on the number of times the two items appear in all shelves, the number of times the two items appear on the same shelf, and the probability of the two items appearing at the same time when one item appears.
13. The device according to claim 9 or 10, characterized in that The collection order processing module is also used for: For the first order and the second order in the set of orders to be sorted, respectively obtaining items included in the first order and items included in the second order; calculating a physical distance between at least one attribute of each item included in the first order and each item included in the second order to generate a distance matrix; According to the distance matrix, the Cartesian product between each item included in the first order and each item included in the second order is calculated, and the mean of the Cartesian products is calculated to obtain the association degree between the first order and the second order.
14. The device according to claim 9 or 10, characterized in that The collection order generation conditions include: The number of items in the collection list does not exceed the set item limit; The number of orders in a collection order cannot exceed the order limit; The current time is within the time range for issuing the collection order.
15. A system for sorting items out of a warehouse, characterized in that: It includes servers, item distribution walls and sorting review desks, among which: The server is used to: collect orders according to the correlation between orders in the to-be-sorted order set based on a hierarchical clustering algorithm to obtain at least one collection order; for each collection order, generate at least one picking task according to the storage location of the items included in the collection order; in response to detecting that the picking task has been completed, generate a separate order outbound instruction, the separate order outbound instruction is used to sort the items corresponding to the picking tasks included in the collection order to the grid of the distribution review station corresponding to the order to which the items belong using the item distribution wall for item sorting and outbound; The article distribution wall is used to: sort articles to the slots of the distribution and review station corresponding to the orders to which the articles belong; The distribution review station is used to: perform distribution review according to the items and the orders to which the items belong.
16. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.
17. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.