Three-dimensional warehouse type sorting frame matching method based on big data

Abstract

The invention relates to the field of sorting frame matching, in particular to a three-dimensional warehouse type sorting frame matching method based on big data. The method comprises the steps of obtaining size information of plates after cutting of each batch of order plates in history, and performing size clustering on the plates according to the size information to obtain a size clustering result; according to the size clustering result, order clustering is carried out on the historical orders, an order clustering result is obtained, and the types of the sorting frames and the number of the sorting frames are obtained; and the plates in the order needing to be matched are matched based on the types of the sorting frames and the number of the sorting frames, and when the mismatching degree of the plates is minimum, matching of the sorting frames is completed. By means of the technical scheme, the accuracy of the plate matching result of the sorting frame can be improved, and then the labor cost can be reduced.

Description

Technical Field

[0001] The present invention relates to the field of sorting rack matching. More specifically, the present invention relates to a method for matching vertical warehouse sorting racks based on big data. Background Art

[0002] The vertical warehouse sorting rack system is a key component in modern logistics and warehousing management, and is widely used in e-commerce, manufacturing, retail and other fields. This system can significantly improve logistics efficiency, reduce labor costs, and enhance the flexibility and responsiveness of overall operations through automated sorting and storage technology. With the development of big data technology, massive amounts of logistics data can be collected and analyzed, providing new solutions for logistics management. Through in-depth mining of logistics data, inventory management can be optimized, demand changes can be predicted, and sorting efficiency can be improved, thereby achieving more intelligent and personalized logistics services. In the vertical warehouse sorting rack system, how to achieve efficient shelf matching and cargo distribution based on the characteristics and sorting requirements of the goods is a complex and challenging problem.

[0003] The existing Chinese patent application document with publication number CN106485300A discloses a plate sorting and processing method and system. The method performs image recognition on the plate label to obtain the plate label information on the plate; performs matching retrieval in the component information library according to the plate label information to obtain the component information to which the plate belongs; the plates are sorted through the sorting channel and stored in the warehouse, and the storage status of the plates is monitored and recorded; if the monitoring record shows that the plates belonging to the same component are already assembled in the warehouse, the assembled plates are assembled and output through the sorting channel.

[0004] However, when there are unlabeled plates that need to be sorted, re-labeling and matching will be required, which will result in low plate matching efficiency. Summary of the invention

[0005] In order to solve the problem of low matching efficiency of plates, the present invention proposes a matching method for vertical warehouse sorting racks based on big data.

[0006] The present invention discloses a method for matching vertical warehouse sorting racks based on big data, comprising: obtaining size information of plates after cutting of plates in each batch of orders in history, clustering the plates according to the size information, and obtaining size clustering results; clustering the historical orders according to the size clustering results, obtaining the order clustering results, and obtaining the type of sorting racks and the number of sorting racks; matching the plates in the order to be matched based on the type of sorting racks and the number of sorting racks, and completing the sorting rack matching when the mismatch degree of the plates is the smallest; the mismatch degree of the plates satisfies the relationship: ,in, Indicates the mismatch of the plate. Indicates the number of types of panels in the order. Indicates the order The number of types of panels, Indicates The number of sorting racks corresponding to the order clusters, Indicates The order clusters correspond to the sorting rack storage The number of types of plates.

[0007] Through size clustering analysis, the plates in historical orders are classified according to size specifications, thus simplifying the inventory management of plates. The size clustering results are used to further cluster the orders, which not only helps to identify groups of orders with similar needs, but also predicts the type and quantity requirements of sorting racks based on order characteristics. Through this clustering method, orders and sorting rack resources can be accurately matched to achieve efficient sorting and storage of plates.

[0008] Preferably, the size clustering comprises: the size information comprises length and width, the size clustering center is calculated, and the size clustering is performed according to the length and width of the plate and the size clustering center; the size clustering formula satisfies the relationship: ,in, Indicates the plate and Plates The distance between and Respectively represent the plate Length and Plate Length, and Respectively represent the plate Length and Plate Width.

[0009] By calculating the cluster center of the plate size, the typical representative value of each size category can be determined, and these central values ​​summarize the main distribution characteristics of the plate size. This improves the efficiency of plate storage and retrieval, and also helps to optimize production planning and reduce material waste.

[0010] Preferably, the size clustering centers include: ,in, The length of the plate representing the center of the size cluster, Indicates the size of the cluster. The number of types of panels, Indicates the size of the cluster. The length of the type of plate.

[0011] Similarly, the plate width of the size clustering center is obtained; the calculated plate length and plate width are used as the size clustering center.

[0012] This ensures that the size cluster center can accurately reflect the size characteristics of the plates within the size cluster. This method not only simplifies the management of the diversity of plate sizes, but also provides a standardized reference for the classification, storage and retrieval of plates. Through the size cluster center, the commonalities of various types of plates can be quickly identified, thereby optimizing inventory management and production planning, and improving material utilization and production efficiency.

[0013] Preferably, the order clustering comprises: calculating the order clustering center, clustering the orders according to the size clustering result and the order clustering center; the order clustering formula satisfies the relationship: ,in, Indicates order and Orders The distance between Indicates order Middle The probability of the occurrence of similar plates, Indicates order Middle The probability of the occurrence of similar plates.

[0014] The difference in the distribution of sheet material categories between different orders is measured, where the distance formula reflects the comparison between the probability of sheet material categories within an order and the probability of the order cluster center. This method effectively captures the similarities and differences between orders, allowing orders with similar sheet material demand patterns to be clustered together.

[0015] Preferably, the formula for order clustering further includes: taking the order as a multi-dimensional vector, each dimension representing a type of plate; and taking the similarity between two orders as the distance between the two orders.

[0016] Preferably, the order cluster center satisfies the relationship: ,in, Indicates The order cluster Order clustering center for plate-like products, Indicates Orders in clusters Middle The number of types of panels, Indicates the total number of orders.

[0017] Quickly identify the types of plates with concentrated demand, so as to make more accurate decisions in inventory management. This helps to improve production efficiency, reduce inventory backlogs, speed up order response, and ultimately improve customer satisfaction and the market competitiveness of enterprises.

[0018] Preferably, obtaining the type and number of sorting racks includes: the type of sorting racks is equal to the order plate distribution corresponding to the order cluster center; the ratio of the number of each sorting rack is equal to the ratio of the number of orders in each order cluster.

[0019] Preferably, completing the sorting rack matching further comprises: matching plates on a sorting rack to obtain the best match; and in response to there still being unmatched plates in the order, re-matching the remaining plates.

[0020] Beneficial effects of the present invention: 1. Through the designed data analysis and clustering technology, the plate storage and sorting process is deeply optimized. First, the size information of the plates in the historical orders is carefully clustered to ensure that the plates are classified in order according to specifications. Then, the size clustering results are used to intelligently cluster the orders, so as to accurately grasp the characteristics and requirements of different orders. By calculating the mismatch of the plates, the type and quantity of the sorting racks can be dynamically adjusted to achieve accurate matching with the order requirements, minimize the mismatch, improve the matching efficiency of the plates, and thus improve the storage efficiency and retrieval speed.

[0021] 2. The automated matching process not only reduces manual operations and errors caused by human factors, but also significantly improves the efficiency and accuracy of sorting rack matching. The present invention ensures that the sorting rack configuration can be quickly adjusted to meet changes in production needs when facing orders of different types and quantities. Real-time updated clustering results and matching calculations enable the system to quickly respond to real-time changes in orders, achieve instant matching, and improve response speed and service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 It is a flow chart of a method for matching vertical warehouse sorting racks based on big data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0024] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0025] The present invention provides a method for matching vertical warehouse sorting racks based on big data. Figure 1 As shown, the big data-based method for matching vertical warehouse sorting racks includes steps S1 to S3, which are described in detail below.

[0026] S1, obtaining the size information of the plates after cutting for each batch of orders in the history, clustering the plates according to the size information, and obtaining the size clustering results.

[0027] In one embodiment, in the process of plate processing and production management, it is crucial to accurately record and analyze the dimensional information of each batch of order plates, which not only helps to optimize the production process, but also improves material utilization and product quality.

[0028] Specifically, the size information of the plates after cutting is collected for each batch of orders in the history. The size information includes length and width. Because the thickness of the plates is generally consistent, the thickness of the plates is not considered as size information.

[0029] For those irregularly shaped plates, the size of its minimum circumscribed rectangle is used instead, that is, the length and width of this minimum circumscribed rectangle are measured and recorded.

[0030] The size clustering of the plates is performed according to the size information, including: selecting a preset number of initial center points, selecting a plate, and calculating the distance between the plate and each initial center point. The size clustering formula satisfies the relationship: ,in, Indicates the plate and Plates The distance between and Respectively represent the plate Length and Plate Length, and Respectively represent the plate Length and Plate Width.

[0031] The selected plate is constructed into a size cluster with the initial center point with the shortest distance.

[0032] Update the size cluster center to satisfy the relationship: ,in, The length of the plate representing the center of the size cluster, Indicates the size of the cluster. The number of types of panels, Indicates the size of the cluster. The length of the type of plate.

[0033] Similarly, the plate width of the size clustering center is obtained; the calculated plate length and plate width are used as the size clustering center.

[0034] Then select a new plate to calculate the distance from the three center points, which include an updated size cluster center and two initial center points. Traverse all plates to complete size clustering. After clustering, use the silhouette coefficient method to select the best clustering result as the size clustering result.

[0035] In one embodiment, the plates are clustered using a K-means clustering algorithm.

[0036] S2, clustering historical orders according to the size clustering results, obtaining the order clustering results, and obtaining the type and number of sorting racks.

[0037] In one embodiment, historical orders are clustered according to the size clustering result obtained in step S1 to determine the number of different types of plates in the order, and then the type and number of sorting racks are obtained.

[0038] Specifically, according to the clustering process of step S1, the orders are clustered, wherein the order clustering formula satisfies the relationship: ,in, Indicates order and Orders The distance between Indicates order Middle The probability of the occurrence of similar plates, Indicates order Middle The probability of the occurrence of similar plates.

[0039] Calculate the order cluster center, which satisfies the relationship: ,in, Indicates The order cluster Order clustering center for plate-like products, Indicates Orders in clusters Middle The number of types of panels, Indicates the total number of orders.

[0040] At this point, the order clustering results can be obtained.

[0041] The type of sorting rack is equal to the order plate distribution corresponding to the order cluster center; the ratio of the number of each sorting rack is equal to the ratio of the number of orders in each order cluster.

[0042] For example, the plate models are divided into extra-large plates, large plates, medium plates, small plates and extra-small plates. There are three types of order plates corresponding to the order clustering center: large plates, small plates and extra-small plates, so there are also three types of sorting racks; three order clusters are obtained when the orders are clustered, and the number of orders in each order cluster is 50, 40 and 70 respectively, so the ratio of the number of sorting racks should be 5:4:7.

[0043] In one embodiment, the formula for order clustering further includes: taking the order as a multi-dimensional vector, where each dimension is the number of a type of plate; and taking the similarity between two orders as the distance between the two orders.

[0044] S3, matching the plates in the order to be matched based on the type and number of the sorting racks, and completing the sorting rack matching when the mismatch of the plates is minimized.

[0045] In one embodiment, the size information of the plates in the order to be matched is obtained, and the size cluster to which each plate belongs is calculated. The plate distribution of the order to be matched is obtained, and the best combination of sorting racks is determined according to the plate distribution of the order to be matched and the number of plates that can be stored in different sorting racks, and the plate mismatch degree is calculated. The plate mismatch degree satisfies the relationship: ,in, Indicates the mismatch of the plate. Indicates the number of types of panels in the order. Indicates the order The number of types of panels, Indicates The number of sorting racks corresponding to the order clusters, Indicates The order clusters correspond to the sorting rack storage The number of types of plates.

[0046] When the mismatch of the plates is minimal, the best sorting rack combination is obtained and the sorting rack matching is completed.

[0047] In one embodiment, a sorting rack is matched with plates to obtain the best match; in response to there still being unmatched plates in the order, the remaining plates are re-matched.

[0048] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0049] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for matching vertical warehouse sorting racks based on big data, characterized in that: include: Obtain the size information of the plates after cutting for each batch of orders in the history, cluster the plates according to the size information, and obtain the size clustering results; Perform order clustering on historical orders according to the size clustering results, obtain order clustering results, and obtain the type and number of sorting racks; The plates in the order to be matched are matched based on the type and number of sorting racks. When the mismatch of the plates is minimized, the sorting rack matching is completed. The mismatch of the plate satisfies the relationship: ,in, Indicates the mismatch of the plate. Indicates the number of types of panels in the order. Indicates the order The number of types of panels, Indicates The number of sorting racks corresponding to the order clusters, Indicates The order clusters correspond to the sorting rack storage The number of types of plates.

2. The method for matching vertical warehouse sorting racks based on big data according to claim 1 is characterized in that: The size clustering comprises: The size information includes length and width, and the size cluster center is calculated. The size clustering is performed according to the length and width of the plate and the size cluster center; The formula for size clustering satisfies the relationship: ,in, Indicates the plate and Plates The distance between and Respectively represent the plate Length and Plate Length, and Respectively represent the plate Length and Plate Width.

3. The method for matching vertical warehouse sorting racks based on big data according to claim 2 is characterized in that: The size cluster centers include: ,in, The length of the plate representing the size cluster center, Indicates the size of the cluster. The number of types of panels, Indicates the size of the cluster. Length of the board type; Similarly, the width of the plate at the size cluster center is obtained; The calculated plate length and plate width are used as the size cluster centers.

4. The method for matching vertical warehouse sorting racks based on big data according to claim 1 is characterized in that: The order clustering comprises: Calculate the order clustering center and cluster the orders according to the size clustering results and the order clustering center; The formula for order clustering satisfies the relationship: ,in, Indicates order and Orders The distance between Indicates order Middle The probability of the occurrence of similar plates, Indicates order Middle The probability of the occurrence of similar plates.

5. The big data-based vertical warehouse sorting rack matching method according to claim 4 is characterized in that: The formula for order clustering also includes: The order is regarded as a multi-dimensional vector, each dimension represents a type of plate; The similarity between two orders is taken as the distance between the two orders.

6. The method for matching vertical warehouse sorting racks based on big data according to claim 4 is characterized in that: The order cluster center satisfies the relationship: ,in, Indicates The order cluster Order clustering center for plate-like products, Indicates Orders in clusters Middle The number of types of panels, Indicates the total number of orders.

7. The method for matching vertical warehouse sorting racks based on big data according to claim 1 is characterized in that: The method of obtaining the type of the sorting rack and the number of the sorting racks comprises: The type of sorting rack is equal to the order plate distribution corresponding to the order cluster center; The ratio of the number of each sorting rack is equal to the ratio of the number of orders in each order cluster.

8. The method for matching vertical warehouse sorting racks based on big data according to claim 1 is characterized in that: The completing the sorting rack matching also includes: Match the plates on a sorting rack to get the best match; In response to there still being unmatched plates in the order, the remaining plates are re-matched.

Images