WO2019242520A1

WO2019242520A1 - Logistics distribution station planning method, and server

Info

Publication number: WO2019242520A1
Application number: PCT/CN2019/090509
Authority: WO
Inventors: 张晓莹; 徐宗敏
Original assignee: 菜鸟智能物流控股有限公司
Priority date: 2018-06-20
Filing date: 2019-06-10
Publication date: 2019-12-26
Also published as: CN110619412B; CN110619412A

Abstract

Embodiments of the present description provide a logistics distribution station planning method, and a server. The method comprises: receiving a logistics distribution station planning parameter, the logistics distribution station planning parameter comprising a geographic area identifier; dividing nodes in a designated geographic area into multiple class clusters by taking the geographic locations corresponding to distribution addresses as the nodes, the designated geographic area being a geographic area identified by the geographic area identifier; and planning a plurality of logistics distribution stations in the designated geographic area on the basis of the divided class clusters.

Description

Logistics distribution site planning method and server

This application claims priority from a Chinese patent application filed on June 20, 2018 with application number 201810637029.9 and the invention name is "Logistics Distribution Site Planning Method and Server", the entire contents of which are incorporated herein by reference.

Technical field

The embodiments of the present specification relate to the field of computer technology, and in particular, to a method and server for planning a logistics distribution site.

Background technique

With the rapid development of e-commerce, in order to timely deliver distribution resources to users, logistics companies usually need to plan and build logistics distribution sites within geographical areas. In the prior art, planners of logistics companies usually use their experience to decide how to plan a logistics distribution site based on the density distribution of distribution orders. This method of planning logistics distribution sites based on experience usually results in irrational distribution of logistics distribution sites, resulting in higher distribution costs and lower timeliness of distribution.

Summary of the Invention

The purpose of the embodiments of the present specification is to provide a logistics distribution site planning method and server, so as to reduce the distribution cost and improve the timeliness of distribution.

To achieve the above objective, an embodiment of the present specification provides a method for planning a logistics distribution site, including: receiving a planning parameter of the logistics distribution site; the planning parameter of the logistics distribution site includes a geographical area identifier; The nodes in the designated geographic area are divided into multiple clusters; the designated geographic area is the geographic area identified by the geographic area identifier; and based on the divided clusters, multiple logistics distribution sites are planned in the designated geographic area.

In order to achieve the above purpose, an embodiment of the present specification provides a server, including: a receiving unit configured to receive planning parameters of a logistics distribution site; the planning parameters of the logistics distribution site include a geographic area identifier; and a dividing unit configured to correspond to a distribution address The geographical position is a node, and the nodes in the specified geographical area are divided into multiple clusters; the specified geographical area is a geographical area identified by the geographical area identifier; a planning unit is configured to: Plan multiple logistics distribution sites within a specified geographic area.

In order to achieve the above purpose, an embodiment of the present specification provides a server including: a memory for storing computer instructions; a processor for executing the computer instructions to implement the following steps: receiving planning parameters of a logistics distribution site; and the logistics distribution site The planning parameters include a geographical area identifier; the geographical location corresponding to the delivery address is used as a node to divide the nodes in the specified geographical area into multiple clusters; the specified geographical area is the geographical area identified by the geographical area identifier; based on the division Multiple clusters in the designated geographic area.

It can be seen from the technical solutions provided by the embodiments of the present specification that, in the embodiments of the present specification, the server can receive the planning parameters of the logistics distribution site, and the planning parameters of the logistics distribution site may include the geographic area identifier; the geographic location corresponding to the distribution address may be used as the node To divide the nodes in a specified geographic area into multiple clusters, and the specified geographic area is the geographic area identified by the geographic area identifier; based on the divided clusters, multiple logistics can be planned in the specified geographic area Distribution site. The method for planning a logistics distribution site in the embodiment of the present specification avoids the influence of manual experience, and makes the distribution of the planned logistics distribution site in the specified geographic area more reasonable, thereby reducing the distribution cost and improving the timeliness of distribution.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly explain the embodiments of the present specification or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are merely These are some of the embodiments described in this specification. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without paying creative labor.

FIG. 1 is a flowchart of a logistics distribution site planning method according to an embodiment of the present specification; FIG.

2 is a flowchart of a K-MEANS clustering algorithm according to an embodiment of the present specification;

3 is a flowchart of a proximity classification algorithm according to an embodiment of the present specification;

4 is a flowchart of a method for planning a logistics distribution site according to an embodiment of the present specification;

5 is a schematic diagram of a parameter input interface according to an embodiment of the present specification;

6 is a schematic diagram of a planning result according to an embodiment of the present specification;

7 is a schematic diagram of a functional structure of a server according to an embodiment of the present specification;

FIG. 8 is a schematic diagram of a functional structure of a server according to an embodiment of the present specification.

detailed description

In the following, the technical solutions in the embodiments of the present specification will be clearly and completely described with reference to the drawings in the embodiments of the present specification. Obviously, the described embodiments are only a part of the embodiments of the present specification, but not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by a person of ordinary skill in the art without creative efforts should fall within the protection scope of this specification.

Please refer to FIGS. 1, 2, 3, 4, 5, and 6 together. The embodiments of the present specification provide a method for planning a logistics distribution site. The logistics distribution site planning method uses a server as an execution subject. The server may be one server; or, it may be a server cluster including multiple servers. The logistics distribution site planning method may include the following steps.

Step S10: Receive the planning parameters of the logistics distribution site.

In this embodiment, the logistics distribution site planning parameters may be used to plan a logistics distribution site that is capable of distributing distribution resources to one or more distribution addresses. The distribution resource may be any type of resource, for example, it may be commodities, goods, or takeaway. The delivery address may be a delivery address of the user, and may be, for example, XXX village, XXX town, XXX city, XXX province, or the like. The logistics distribution site planning parameter may include a geographic area identifier. The geographic area identifier may be used to identify a geographic area, for example, it may be a name or a code of the geographic area. The size of the geographic area can be flexibly set according to business needs, for example, it can be a street, a business circle, a city, a country, or an area composed of multiple countries.

In an implementation manner of this embodiment, the planning parameters of the logistics distribution site may further include the number of logistics distribution sites. The number of the logistics distribution sites can be any size, for example, it can be 10, 15, or 30.

In an implementation manner of this embodiment, in order to prevent the planned number of distribution addresses covered by the logistics distribution site from being too large and thereby affecting the timeliness of distribution, the planning parameters of the logistics distribution site may further include the maximum number of distribution addresses covered by the logistics distribution site. The maximum number of delivery addresses covered by the logistics distribution site can be any size, for example, it can be 100, 102, or 150.

In an implementation manner of this embodiment, in order to prevent the planned number of distribution addresses covered by the logistics distribution site from being too small, thereby affecting the distribution cost, the planning parameters of the logistics distribution site may further include the minimum number of distribution addresses covered by the logistics distribution site. The minimum number of delivery addresses covered by the logistics distribution site can be any size, for example, it can be 10, 12, or 15 and so on.

In an implementation manner of this embodiment, in order to prevent the planned distribution distance covered by the logistics distribution site from being too large and thereby affecting the distribution cost, the planning parameters of the logistics distribution site may further include a maximum distribution distance covered by the logistics distribution site. The maximum delivery distance covered by the logistics distribution site can be any size, for example, it can be 50 kilometers, 75 kilometers, or 80 kilometers.

In this embodiment, the user may directly input the logistics distribution site planning parameters on the server, and the server may receive the logistics distribution site planning parameters input by the user. For example, the server may provide a parameter input interface, and the user may input the logistics distribution site planning parameters on the parameter input interface, and the server may receive the logistics distribution site planning parameters input by the user. Alternatively, the user may also input the logistics distribution site planning parameters on a terminal device, the terminal device may receive and send the logistics distribution site planning parameters to a server, and the server may receive the logistics distribution site planning parameters. The terminal device may be a smart phone, a tablet electronic device, a portable computer, a personal digital assistant (PDA), a server, an industrial control computer (industrial control computer), a personal computer (PC), or an all-in-one computer.

Step S12: Use the geographic location corresponding to the delivery address as a node to divide the nodes in the designated geographic area into multiple clusters; the designated geographic area is the geographic area identified by the geographic area identifier.

In this embodiment, the server may use the geographic area identified by the geographic area identifier as the designated geographic area; may obtain multiple delivery addresses within the designated geographic area; and use the geographic location corresponding to the delivery address as a node, The nodes within the specified geographic area may be divided into multiple clusters. Each cluster may include at least one node. Specifically, the server may provide a delivery address set, and the delivery address set may include multiple delivery addresses. The server may obtain a plurality of delivery addresses in the specified geographic area from the delivery address set. The server can convert each delivery address into latitude and longitude data; the converted latitude and longitude data can be used as the latitude and longitude data of the node.

In this embodiment, the server may use a preset algorithm to divide the nodes in the specified geographic area into multiple clusters. The preset algorithm may include a clustering algorithm. The clustering algorithm may include a K-Means clustering algorithm, a DBSAN (Density-Based Spatial Clustering of Applications with Noise) clustering algorithm, a hierarchical clustering algorithm, and the like. Specifically, the server may determine the number of clusters; the preset algorithm may be used to divide the nodes in the specified geographic area into multiple clusters. The number of divided clusters may be equal to the number of clusters.

In an implementation manner of this embodiment, the logistics distribution site planning parameters may include the number of logistics distribution sites. In this way, the server may use the number of logistics distribution sites in the logistics distribution site planning parameters as the number of clusters.

In an implementation manner of this embodiment, the server may calculate the number of clusters based on the number of nodes in the specified geographic area. For example, the server can be based on a formula

To calculate the number of clusters; K can represent the number of clusters; ALL can represent the number of nodes in the specified geographic area; U can represent the maximum number of distribution addresses covered by the logistics distribution site; L can represent the minimum coverage of the logistics distribution site The number of shipping addresses; [] can represent the round-up operator. Here, the size of U may be preset by a developer on the server. Alternatively, the logistics distribution site planning parameters may include the maximum number of distribution addresses covered by the logistics distribution site. In this way, the server may assign U to the maximum number of delivery addresses in the logistics delivery site planning parameters. Similarly, the size of L here can be preset by the developer on the server. Alternatively, the logistics distribution site planning parameters may include a minimum number of distribution addresses covered by the logistics distribution site. In this way, the server may assign L to the minimum number of delivery addresses in the logistics delivery site planning parameters. Those skilled in the art should be able to understand that the above formula for calculating the number of clusters is merely an example. In practice, there may be other formulas or methods for calculating the number of clusters.

The following uses the K-Means clustering algorithm as an example to describe in detail the process in which the server divides the nodes in the specified geographic area into multiple clusters. Those skilled in the art should be able to understand that the server may also use other clustering algorithms to divide the nodes in the specified geographic area into multiple clusters. In addition, the K-Means clustering algorithm here is only an example. In practice, the K-Means clustering algorithm may have other deformations or changes. The process in which the server divides the nodes in the specified geographic area into multiple clusters may include the following steps.

Step S120: Determine K cluster centers.

The K may represent the number of clusters, and the K cluster centers may correspond to K clusters. Specifically, the server may arbitrarily select K nodes from the nodes in the specified geographic area as K cluster centers. Those skilled in the art should be able to understand that, in practice, the server may also determine K cluster centers in other ways.

Step S122: For each node in the specified geographic area, calculate the geographic distance between the node and the K cluster centers; and divide the node into the cluster corresponding to the cluster center with the smallest geographic distance. .

For each node in the specified geographic area, the server can calculate the geographic distance between the node and the K cluster centers; it can select the cluster center corresponding to the smallest geographic distance; it can divide the node To the class cluster corresponding to the selected cluster center. Specifically, the server may be based on the formula D (x ₁ , y ₁ , x ₂ , y ₂ ) = R * arccos (sin (x ₁ ) * sin (x ₂ ) + cos (x ₁ ) * cos (x ₂ ) * cos (y ₁ -y ₂ )) to calculate the geographical distance between the node and the cluster center; D can represent the geographical distance; x ₁ can represent the dimensional data of the node; y ₁ can represent the longitude data of the node; x ₂ Can represent the dimensional data of the cluster center; y ₂ can represent the longitude data of the cluster center; R can represent the radius of the earth. Those skilled in the art should be able to understand that the above formula for calculating geographical distance is merely an example, and in practice, there may be other formulas or methods for calculating geographical distance. For example, the server may also be based on a formula:

D (x ₁ , y ₁ , x ₂ , y ₂ ) = R * arccos (sin (x ₁ ) * sin (x ₂ ) + cos (x ₁ ) * cos (x ₂ ) * cos (y ₁ -y ₂ )) +

R * arccos (sin (x ₁ ) * sin (cw) + cos (x ₁ ) * cos (cw) * cos (y ₁ -cj))

To calculate the geographical distance between the node and the cluster center; cw can represent the dimensional data of the overall center, and cj can represent the longitude data of the overall center, where the overall center can be understood as the center of each node in the specified geographic area. For example, cw may be an average value of dimensional data of each node in the specified geographic area; cj may be an average value of longitude data of each node in the specified geographic area.

Step S124: Determine the clustering centers of the K clusters again.

For each of the K clusters, the server may re-determine the cluster center of the cluster based on the nodes in the cluster. Specifically, the server may calculate the average value of the longitude data of each node in the cluster as the longitude data of the cluster center of the cluster; and may calculate the average value of the dimensional data of each node in the cluster as the cluster. The dimensional data of the cluster center of the cluster can be re-determined based on the calculated longitude data and dimensional data. Those skilled in the art should be able to understand that, in practice, the server may also use other methods to re-determine the clustering center of the cluster.

Step S126: Determine whether the iteration termination condition is satisfied. If it is satisfied, the K-Means clustering algorithm is terminated; if not, it returns to step S122.

The iteration termination condition may include convergence of a standard measure function. Specifically, the server may calculate a standard measurement function; and may terminate the K-Means clustering algorithm when the standard measurement function converges. The standard measurement function may be, for example,

ALL can indicate the number of nodes in the specified geographic area; K can indicate the number of clusters; when the nth node belongs to the kth class cluster, the size of r _nk can be 1; the nth node does not belong For the k-th cluster, the size of r _nk can be 0; u _k can represent the cluster center of the k-th cluster. Of course, in practice, the iteration termination condition may also include other forms. For example, the iteration termination condition may further include that the cluster center of each cluster in the K clusters no longer changes; or that the change in the cluster center of each cluster in the K clusters is less than or Equal to a preset threshold. Here, the change amount of the cluster center can be understood as the geographic distance between the cluster center of the current iteration process and the cluster center of the previous iteration process, and the size of the preset threshold can be flexibly set according to actual needs.

Step S16: Based on the divided clusters, plan a plurality of logistics distribution sites in the designated geographic area.

In this embodiment, for each class cluster that is divided, the server may use the cluster center of the class cluster as the geographic location of the logistics distribution site, and may use the distribution address corresponding to the node in the class cluster as the logistics distribution site. Covered shipping address. In this way, the server can implement planning of multiple logistics distribution sites within the designated geographic area.

In an implementation manner of this embodiment, considering that it is inconvenient to distribute the distribution resources across geographic barriers (such as mountains, rivers, etc.), in order to avoid that the distribution address covered by the planned logistics distribution site crosses the geographic barrier, the The server may divide multiple delivery addresses in the specified geographic area into multiple business groups, and each business group may include multiple delivery addresses. Distribution addresses within a business group usually do not cross a geographic barrier (for example, on one side of the geographical barrier); distribution addresses between business groups can cross a geographic barrier. In this way, taking the geographical location corresponding to the delivery address as a node, the server can divide the nodes in each business group into multiple clusters. It should be noted that in this embodiment, according to the formula:

When calculating the geographical distance between a node and a cluster center, the overall center can be understood as the center of each node in the business group.

In an implementation manner of this embodiment, the server may be a server cluster including multiple servers. In this way, the process of dividing the nodes in the specified geographic area into multiple clusters can be performed on the server cluster, so that distributed computing can be implemented, and computing efficiency is improved.

In an implementation of this embodiment, the server may use a set formed by nodes in the specified geographic area as a node set; may identify noise points from the node set; and may remove the node set Nodes other than the noise point are divided into multiple clusters.

In this embodiment, considering that for a certain node, if the geographical distance between the node and the node is less than a preset distance, the number of nodes is less than a preset value, the node can be considered as an isolated point. As a kind of noise point, the existence of outliers will affect the planning of logistics distribution sites. In this way, for each node in the node set, the server may select a node from the node set whose geographic distance to the node is less than or equal to a first preset value; the number of selected nodes is less than or When equal to the preset number, the node can be identified as a noise point. The size of the first preset value and the preset number may be flexibly set according to actual needs.

Alternatively, in this embodiment, the designated geographic area may include multiple sub-geographical areas. For example, the designated geographic area may be Hangzhou, China, and the multiple sub-geographical areas may include West Lake District, Binjiang District, Xiaoshan District, Xiacheng District, Jianggan District, and the like. During the process of converting the shipping address to latitude and longitude data, errors may occur. The node corresponding to the wrong latitude and longitude data is a kind of noise point, and its existence will affect the planning of the logistics distribution site. In this way, for each node in the node set, the server may select a node with a geographic distance from the node set that is less than or equal to a second preset value from the node set; The set is the first sub-node set; the sub-geographic area with the largest number of corresponding nodes in the first sub-node set can be selected; when the selected sub-geographic area is different from the sub-geographic area to which the node belongs, the node can be identified Is the noise point. The size of the second preset value described herein can be flexibly set according to actual needs.

In an implementation manner of this embodiment, the planning parameters of the logistics distribution site may further include a maximum number of distribution addresses covered by the logistics distribution site. In this way, in the process of dividing the nodes in the specified geographic area into multiple clusters, the server may limit the number of nodes in each cluster so that the number of nodes in the divided clusters is less than or equal to The maximum number of delivery addresses in the logistics delivery site planning parameters. Taking the K-Means clustering algorithm as an example, in step S122, for each node in the specified geographic area, the server may calculate the geographical distance between the node and the K cluster centers; A clustering center (hereinafter referred to as a first clustering center) corresponding to the smallest geographical distance is selected. When the number of nodes in the cluster corresponding to the first cluster center is less than or equal to the maximum number of distribution addresses in the planning parameters of the logistics distribution site, the server may divide the node into the first cluster center Corresponding class cluster. When the number of nodes in the cluster corresponding to the first cluster center is greater than the maximum number of delivery addresses in the logistics distribution site planning parameter, the server may divide the node into other clusters. For example, the server may select a cluster center (hereinafter referred to as a second cluster center) corresponding to the smallest geographic distance from other cluster centers except the first cluster center, and When the number of nodes in the cluster corresponding to the center is less than or equal to the maximum number of delivery addresses in the planning parameters of the logistics distribution site, the node may be divided into the cluster corresponding to the second cluster center. Of course, when the number of nodes in the cluster corresponding to the second cluster center is greater than the maximum number of delivery addresses in the logistics distribution site planning parameter, the server may continue to remove the first cluster center and the Among other cluster centers other than the second cluster center, a cluster center corresponding to the smallest geographical distance is selected.

Further, in this embodiment, in the process of dividing the nodes in the specified geographic area into multiple clusters, the number of nodes in some clusters may preferentially reach the maximum of the logistics distribution site planning parameters. The number of delivery addresses makes it impossible for some nodes to be divided into appropriate clusters. In this way, in the process of dividing the nodes in the specified geographic area into multiple clusters, the server may according to the formula:

To calculate the geographical distance between the node and the cluster center. In this way, nodes with a small geographic distance from the overall center can be preferentially divided into appropriate clusters, thereby making the division of clusters more reasonable overall.

In an implementation manner of this embodiment, the planning parameters of the logistics distribution site may further include a minimum number of distribution addresses covered by the logistics distribution site. In the class cluster divided in step S12, there may be a class cluster whose number of nodes is less than the minimum number of delivery addresses in the planning parameters of the logistics distribution site. In the subsequent process, if a logistics distribution site is planned for this cluster, the distribution cost will be affected. In this way, the server may select a class cluster containing the number of nodes less than or equal to the minimum number of delivery addresses in the planning parameters of the logistics distribution site from the classified class clusters as the first target class cluster; The nodes in the target cluster are divided into clusters other than the first target cluster.

In this embodiment, the server may use a classification algorithm to divide the nodes in the first target class cluster into clusters other than the first target class cluster. The classification algorithm may include a neighbor classification algorithm (K-NearestNeighbor, KNN), a support vector machine classification algorithm (Support Vector Machine, SVM), a convolutional neural network classification algorithm (Convolutional Neural Networks, CNN), and the like. The following uses a proximity classification algorithm as an example to describe in detail the process in which the server divides the nodes in the first target cluster into clusters other than the target cluster. Those skilled in the art should be able to understand that the server may also use other classification algorithms to divide the nodes in the first target class cluster into clusters other than the first target class cluster. In addition, the proximity classification algorithm here is only an example. In practice, the proximity classification algorithm may have other deformations or changes. Specifically, for each node in the first target cluster, the server may calculate a geographic distance between the node and each node in each cluster other than the first target cluster; the geographic Nodes whose distance is less than or equal to the third preset value; the set formed by the selected nodes may be used as the second sub-node set; corresponding nodes in the second sub-node set may be selected except the first target class cluster The largest number of clusters; this node can be divided into the selected clusters.

Further, in this embodiment, the server may be a server cluster including multiple servers. The server cluster may include a management server and a plurality of working servers. In order to implement distributed computing to improve computing efficiency, the management server may divide nodes in clusters other than the first target cluster into multiple first data units, and each first data unit may include at least For one node, the number of segmented first data units may be the same as the number of working servers in the server cluster. The management server may distribute a first data unit and the first target class cluster to each working server, respectively. Each working server can calculate the geographical distance between each node in the first target class cluster and each node in its first data unit.

Each working server may divide a node in the first target class cluster into a plurality of second data units, and each second data unit may include at least one node and may correspond to a data unit identifier. The management server may summarize the second data units corresponding to each data unit identifier on each work server to obtain a new second data unit corresponding to the data unit identifier. For each node in each new second data unit, the management server may select a preset number of nodes with the smallest geographic distance from the node; the set consisting of the selected nodes may be used as the second child node Set; the class cluster with the largest number of corresponding nodes in the second sub-node set except the first target class cluster may be selected; the node may be divided into the selected class cluster.

In an implementation manner of this embodiment, the planning parameters of the logistics distribution site may further include a maximum distribution distance covered by the logistics distribution site. There may be a cluster with a radius greater than the maximum distribution distance in the planning parameters of the logistics distribution site among the clusters divided in step S12. If a logistics distribution site is planned for this cluster in the subsequent process, the distribution cost will be affected. In this way, the server can determine the radius of each class cluster that is divided; it can select a class cluster with a radius greater than or equal to the maximum distribution distance in the planning parameters of the logistics distribution site; it can be based on other class clusters other than the selected class cluster, A plurality of logistics and distribution sites are planned in the designated geographic area. Specifically, for each class cluster that is divided, the server may calculate the geographic distance between each node in the class cluster and the cluster center of the class cluster; the maximum geographic distance may be used as the radius of the class cluster.

In an implementation manner of this embodiment, some nodes may not be classified into appropriate clusters, and the nodes may be considered as outliers. The existence of outliers will affect the planning of logistics distribution sites. For example, the clusters divided in step S12 may include clusters A, B. The geographical distance between a node in class cluster A and the cluster center of class cluster A is greater than the geographic distance between the cluster center of class cluster A and the cluster center of class cluster B. Then, the node can be considered as an outlier. In this way, the server may use a set formed by nodes in the specified geographic area as a node set; may identify at least one outlier from the set of nodes; and for each identified outlier, may The outlier is divided into clusters other than the cluster to which the outlier belongs. Specifically, for each node in the node set, the server may use a class cluster to which the node belongs as a second target class cluster; between the node and the cluster center of the second target class cluster When the geographic distance is greater than the geographic distance from the cluster center of any cluster other than the second target cluster, the node may be identified as an outlier. It should be noted that the process of dividing an outlier into clusters other than the cluster to which the outlier belongs can refer to the classification algorithm in the foregoing embodiment, and details are not described herein again.

Please refer to FIGS. 1, 4, 5 and 6 together. An example of a scenario in the embodiment of the present specification is described below. The main body of this scenario example may include a terminal device and a server.

In this scenario example, the terminal device may provide a parameter input interface. The user can input the logistics distribution site planning parameters on the parameter input interface. The logistics distribution site planning parameters may include geographic area identification, the maximum number of distribution addresses covered by the logistics distribution site, the minimum number of distribution addresses covered by the logistics distribution site, and the maximum distribution distance covered by the logistics distribution site. The terminal device may receive and send the logistics distribution site planning parameters to a server, and the server may receive the logistics distribution site planning parameters.

In this scenario example, the server may use the geographic area identified by the geographic area identifier as the designated geographic area; may obtain multiple delivery addresses within the designated geographic area; and may use the geographic location corresponding to the delivery address as a node ; A set formed by nodes in the specified geographic area may be a node set; a noise point may be identified from the node set; and other nodes except the noise point in the node set may be divided into a plurality of nodes Class cluster. The number of nodes in the divided cluster is less than or equal to the maximum number of delivery addresses in the planning parameters of the logistics distribution site.

In the example of this scenario, the server may select a class cluster containing the number of nodes less than or equal to the minimum number of delivery addresses in the planning parameters of the logistics distribution site from the divided class clusters as the target class cluster; The nodes in the target cluster are divided into clusters other than the target cluster. In addition, the server may also identify at least one outlier from the set of nodes; for each identified outlier, the outlier may be divided into groups other than the cluster to which the outlier belongs. Other clusters.

In the example of this scenario, the server may determine the radius of each class cluster that is divided; it may select a class cluster with a radius greater than or equal to the maximum distribution distance in the planning parameters of the logistics distribution site; it may be based on removing the selected class clusters Other types of clusters, planning multiple logistics distribution sites within the specified geographic area.

In this embodiment, the server may receive logistics distribution site planning parameters, and the logistics distribution site planning parameters may include geographic area identifiers; the geographic location corresponding to the distribution address may be used as a node, and the nodes within the designated geographic area may be divided It is a plurality of clusters, and the designated geographic area is the geographic area identified by the geographic area identifier. Based on the divided clusters, multiple logistics distribution sites can be planned in the designated geographic area. The method for planning a logistics distribution site in this embodiment avoids the influence of human experience, so that the planned distribution of the logistics distribution sites in the specified geographic area is more reasonable, thereby reducing distribution costs and improving timeliness of distribution.

See Figure 7. The embodiment of the present specification also provides a server. The server may include the following units.

The receiving unit 70 is configured to receive logistics distribution site planning parameters, where the logistics distribution site planning parameters include a geographic area identifier;

A dividing unit 72, configured to divide the nodes in a specified geographical area into multiple clusters by using the geographical location corresponding to the delivery address as a node; the specified geographical area is a geographical area identified by the geographical area identifier;

The planning unit 74 is configured to plan a plurality of logistics distribution sites in the specified geographic area based on the divided clusters.

See Figure 8. The embodiment of the present specification also provides a server. The server may include a memory and a processor.

In this embodiment, in this embodiment, the memory includes, but is not limited to, dynamic random access memory (Dynamic Random Access Memory, DRAM), static random access memory (Static Random Access Memory, SRAM), and the like. The memory may be used to store computer instructions.

In this embodiment, the processor may be implemented in any suitable manner. For example, the processor may take, for example, a microprocessor or processor and a computer-readable medium, logic gate, switch, dedicated integration storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor. Circuit (Application Specific Integrated Circuit, ASIC), programmable logic controller and embedded microcontroller form, etc. The processor may be configured to execute the computer instructions to implement the following steps: receiving logistics distribution site planning parameters; the logistics distribution site planning parameters including a geographic area identifier; and using a geographic location corresponding to a distribution address as a node, the designated geographic area will be designated The nodes are divided into multiple clusters; the designated geographic area is the geographic area identified by the geographic area identifier; and based on the divided clusters, multiple logistics distribution sites are planned in the designated geographic area.

It should be noted that each embodiment in the description of this application is described in a progressive manner, and the same and similar parts between the various embodiments may refer to each other. Each embodiment focuses on the differences from other embodiments. Office. In particular, for the server embodiment, since it is basically similar to the embodiment of the logistics and distribution site planning method, the description is relatively simple. For the related parts, refer to the description of the embodiment of the method of logistics and distribution site planning.

In addition, those skilled in the art should be able to understand that after reading the specification of this application, those skilled in the art may combine some or all of the embodiments listed in this application without creative labor, and these combinations are also described in this application. Within the scope of application disclosure and protection.

In the 1990s, for a technical improvement, it can be clearly distinguished whether it is an improvement in hardware (for example, the improvement of circuit structures such as diodes, transistors, switches, etc.) or an improvement in software (for the improvement of method flow). However, with the development of technology, the improvement of many methods and processes can be regarded as a direct improvement of the hardware circuit structure. Designers almost always get the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be realized by hardware entity modules. For example, a programmable logic device (Programmable Logic Device (PLD)) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. It is programmed by the designer to "integrate" a digital system on a PLD, without having to ask a chip manufacturer to design and make a dedicated integrated circuit chip 2. Moreover, nowadays, instead of making integrated circuit chips by hand, this programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used in program development and writing, but before compilation The original code must also be written in a specific programming language, which is called Hardware Description Language (HDL), and HDL is not only one, but there are many types, such as ABEL (Advanced Boolean ExpressionLanguage) , AHDL (Altera, Hardware, Description, Language), Confluence, CUPL (Cornell, University Programming, Language), HDCal, JHDL (Java, Hardware, Description, Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby, Hardware, Description), etc. It is VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog2. Those skilled in the art should also be clear that as long as the method flow is slightly logically programmed and integrated into the integrated circuit using the above-mentioned several hardware description languages, a hardware circuit that implements the logic method flow can be easily obtained.

The system, device, module, or unit described in the foregoing embodiments may be specifically implemented by a computer chip or entity, or a product with a certain function. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or A combination of any of these devices.

It can be known from the description of the foregoing embodiments that those skilled in the art can clearly understand that this specification can be implemented by means of software plus a necessary universal hardware platform. Based on such an understanding, the technical solution of this specification, in essence, or the part that contributes to the existing technology, can be embodied in the form of a software product, which can be stored in a storage medium, such as ROM / RAM, magnetic disk , Optical discs, etc., including a number of instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the methods described in various embodiments or portions of embodiments of this specification.

This manual can be used in many general-purpose or special-purpose computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, small computers, mainframe computers, including Distributed computing environment for any of the above systems or devices, etc.

This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

Although the specification is described through the embodiments, those skilled in the art know that there are many variations and changes in the specification without departing from the spirit of the specification, and it is expected that the appended claims include these modifications and changes without departing from the spirit of the specification.

Claims

A logistics distribution site planning method includes:

Receiving planning parameters of the logistics distribution site; the planning parameters of the logistics distribution site include a geographic area identifier;

Use the geographic location corresponding to the delivery address as a node to divide the nodes in the designated geographic area into multiple clusters; the designated geographic area is the geographic area identified by the geographic area identifier;

Based on the divided clusters, a plurality of logistics distribution sites are planned in the designated geographic area.
The method according to claim 1, wherein the distribution addresses in the designated geographic area belong to multiple business groups; correspondingly, the dividing the nodes in the designated geographic area into multiple clusters includes:

The nodes in each business group are divided into multiple clusters.
The method according to claim 1, wherein the dividing the nodes in a specified geographic area into a plurality of clusters comprises:

Use a set formed by nodes in a specified geographic area as a set of nodes to identify noise points from the set of nodes;

The nodes other than the noise point in the node set are divided into multiple class clusters.
The method according to claim 3, wherein identifying a noise point from the node set comprises:

For each node in the node set, select a node from the node set whose geographic distance to the node is less than or equal to a first preset value; when the number of selected nodes is less than or equal to a preset number, This node is identified as a noise point.
The method according to claim 3, wherein the designated geographic area comprises a plurality of sub-geographical areas; and correspondingly, identifying the noise point from the set of nodes comprises:

For each node in the node set, select a node with a geographic distance from the node set that is less than or equal to a second preset value from the node set; use the set formed by the selected nodes as the first child node set , Selecting the sub-geographic area with the largest number of corresponding nodes in the first sub-node set; identifying the node as a noise point when the selected sub-geographic area is different from the sub-geographic area to which the node belongs.
The method according to claim 1, wherein the dividing the nodes in a specified geographic area into a plurality of clusters comprises:

A preset algorithm is used to divide the nodes in a specified geographic area into multiple clusters; the preset algorithm includes a clustering algorithm.
The method according to claim 1, wherein the logistics distribution site planning parameters further include at least one of the following:

The number of logistics distribution sites;

The maximum number of distribution addresses covered by the logistics distribution site;

The minimum number of distribution addresses covered by the logistics distribution site;

The maximum delivery distance covered by the logistics distribution site.
The method according to claim 7, wherein in the step of dividing the nodes in the specified geographic area into a plurality of clusters, the number of clusters divided is equal to the number of logistics distribution sites in the logistics distribution site planning parameter.
The method according to claim 7, in the step of dividing the nodes in the specified geographic area into a plurality of clusters, the number of nodes in the divided clusters is less than or equal to a maximum distribution address in the planning parameters of the logistics distribution site Quantity.
The method according to claim 7, after dividing the nodes in the specified geographic area into a plurality of clusters, the method further comprises:

Selecting a class cluster including the number of nodes less than or equal to the minimum number of delivery addresses in the logistics distribution site planning parameters as the first target class cluster; dividing the nodes in the first target class cluster to remove the first target class Clusters other than clusters.
The method according to claim 10, wherein the dividing the nodes in the first target class cluster into clusters other than the first target class cluster comprises:

For each node in the first target cluster, calculate a geographic distance between the node and each node in each cluster except the first target cluster; select a geographic distance that is less than or equal to a third preset Value nodes; using the set formed by the selected nodes as the second child node set, selecting the class cluster with the largest number of corresponding nodes in the second child node set except the first target class cluster; dividing the node to The selected cluster.
The method according to claim 1, after dividing the nodes in the specified geographic area into a plurality of clusters, the method further comprises:

Using a set formed by nodes in a specified geographic area as a node set, and identifying outliers from the node set;

For the identified outlier, the outlier is divided into clusters other than the cluster to which the outlier belongs.
The method according to claim 12, wherein the identifying outliers from the set of nodes comprises:

For each node in the node set, the class cluster to which the node belongs is the second target class cluster; the geographical distance between the node and the cluster center of the second target class cluster is greater than and removed from When the geographic distance between the cluster centers of any other clusters other than the second target cluster is described, the node is identified as an outlier.
The method according to claim 7, wherein said planning a plurality of logistics distribution sites within said designated geographic area comprises:

Determine the radius of each cluster

Selecting a cluster with a radius greater than or equal to the maximum distribution distance in the planning parameters of the logistics distribution site;

Based on the clusters other than the selected clusters, a plurality of logistics distribution sites are planned in the specified geographic area.
The method according to claim 14, wherein said determining the radius of each cluster includes:

For each cluster, calculate the geographic distance between each node in the cluster and the cluster center of the cluster; select the maximum geographic distance as the radius of the cluster.
The method according to claim 1, in the step of planning a plurality of logistics distribution sites in the designated geographic area, the cluster center of the cluster is the geographic location of the logistics distribution site; the distribution address corresponding to the node in the cluster is The delivery address covered by the logistics delivery site.
A server including:

A receiving unit, configured to receive planning parameters of a logistics distribution site; the planning parameters of the logistics distribution site include a geographic area identifier;

A dividing unit, configured to divide the nodes in a specified geographical area into multiple clusters by using the geographical location corresponding to the delivery address as a node; the specified geographical area is a geographical area identified by the geographical area identifier;

A planning unit is configured to plan a plurality of logistics distribution sites in the specified geographic area based on the divided clusters.
A server including:

Memory for storing computer instructions;

A processor configured to execute the computer instructions to implement the following steps: receiving logistics distribution site planning parameters; the logistics distribution site planning parameters including a geographic area identifier; and taking a geographic location corresponding to a distribution address as a node, the nodes within the designated geographic area Divided into a plurality of clusters; the designated geographic area is a geographic area identified by the geographic area identifier; and based on the divided clusters, a plurality of logistics distribution sites are planned in the designated geographic area.