CN113128744A - Distribution planning method and device - Google Patents

Abstract

The invention discloses a distribution planning method and device, and relates to the technical field of computers. The method includes: constructing a distribution network model according to the order information to be distributed; wherein, the distribution network model consists of nodes and edges between the nodes; the nodes are used to represent the distribution points of the order, and the nodes between the nodes are used for The edge is used to represent the connection relationship between the order distribution points; the nodes in the distribution network model are clustered to obtain multiple clusters; the range covered by each of the multiple clusters is taken as a Delivery area to get multiple delivery areas. Through the above steps, the delivery areas can be dynamically and reasonably divided according to the order information to be delivered, so that the quantity of delivery orders in each delivery area tends to be balanced, thereby helping to improve the delivery efficiency as a whole.

Description

Delivery planning method and apparatus

technical field

The invention relates to the field of computer technology, and in particular, to a distribution planning method and device.

Background technique

In the logistics distribution scenario, it is necessary to divide the distribution area, and assign corresponding distribution personnel to each distribution area. In the prior art, the distribution area is often kept fixed after being divided, and the courier sorts and distributes the goods according to the assigned distribution area.

In the process of realizing the present invention, the inventor found that there are at least the following problems in the prior art: First, since the number of orders in each distribution area changes dynamically, it is very likely that the number of orders and the time of delivery in different distribution areas will appear. In extremely unbalanced situations, even some couriers have a 2 to 3 hour difference in delivery time. Second, in the current delivery process, couriers often determine the delivery route based on experience. When the distribution range is small, the distribution according to the experience may have little effect on the distribution efficiency. However, when the distribution range becomes larger, problems such as unreasonable distribution path planning and low distribution efficiency will occur when distribution is carried out according to experience.

SUMMARY OF THE INVENTION

In view of this, the present invention provides a distribution planning method and device, which can dynamically and reasonably divide distribution areas according to the order information to be distributed, so that the amount of distribution orders in each distribution area tends to be balanced, thereby contributing to the overall Improve delivery efficiency. Further, the path planning in the divided distribution area based on the heuristic algorithm can further improve the distribution efficiency.

To achieve the above object, according to one aspect of the present invention, a distribution planning method is provided.

The distribution planning method of the present invention includes: constructing a distribution network model according to the order information to be distributed; wherein, the distribution network model consists of nodes and edges between nodes; the nodes are used to represent the distribution points of the order, and the The edges between the nodes are used to represent the connection relationship between the order distribution points; the nodes in the distribution network model are clustered to obtain multiple clusters; each of the multiple clusters is covered by The range is used as a delivery area to get multiple delivery areas.

Optionally, the constructing a distribution network model according to the order information to be distributed includes: converting the coordinates of the distribution points of the order into nodes in the distribution network model, and converting the connection relationships between the order distribution points into edges between nodes, The comprehensive score of logistics distribution difficulty between order distribution points is converted into the weight of edges between nodes.

Optionally, the clustering of nodes in the distribution network model to obtain multiple clusters includes: determining the initial positions of K cluster center points; calculating the relationship between each node and each node in the distribution network model. the distance of the cluster center point, and assign the node to the cluster with the smallest distance to realize the cluster update; calculate the position of the updated cluster center point until the iteration stop condition is met; wherein, K is an integer greater than 1.

Optionally, the calculating the distance between each node and each cluster center point in the distribution network model includes: according to the weight of each edge between a node and a cluster center point in the distribution network model, And the actual path length corresponding to each edge, calculate the distance from the node to the center point of the cluster.

Optionally, the method includes: after obtaining multiple delivery areas, planning an order delivery path in the delivery area according to a heuristic algorithm, and returning the planned order delivery path to the user terminal.

Optionally, the planning of the order delivery route in the delivery area according to the heuristic algorithm includes: determining a candidate order delivery route in the delivery area, and according to the total dispatch cost and total dispatch cost corresponding to the candidate order delivery route The travel cost calculates the total delivery cost of the candidate delivery route; taking the minimum total delivery cost as the objective function, the candidate order delivery route is optimized until the planned order delivery route is obtained.

Optionally, the method includes: determining a comprehensive score of logistics distribution difficulty between the order distribution points according to at least one of the following influencing factors: the actual path length between the order distribution points, the road conditions between the order distribution points, the order Parking difficulty between delivery points, weight of on-board cargo between order delivery points.

To achieve the above object, according to another aspect of the present invention, a delivery planning device is provided.

The distribution device of the present invention includes: a building module for constructing a distribution network model according to the order information to be distributed; wherein, the distribution network model is composed of nodes and edges between nodes; the nodes are used to represent the distribution of orders point, the edges between the nodes are used to represent the connection relationship between the order distribution points; the clustering module is used to cluster the nodes in the distribution network model to obtain multiple clusters; also used for The range covered by each of the plurality of clusters is taken as a delivery area to obtain a plurality of delivery areas.

To achieve the above object, according to yet another aspect of the present invention, an electronic device is provided.

The electronic device of the present invention includes: one or more processors; and a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, all the programs are executed. The one or more processors implement the delivery planning method of the present invention.

To achieve the above object, according to yet another aspect of the present invention, a computer-readable medium is provided.

The computer-readable medium of the present invention has a computer program stored thereon, and when the program is executed by the processor, the delivery planning method of the present invention is implemented.

One embodiment of the above invention has the following advantages or beneficial effects: by constructing a distribution network model according to the order information to be distributed, clustering the nodes in the distribution network model to obtain multiple clusters, The range covered by each of the clusters is used as a delivery area to obtain multiple delivery areas. These steps can dynamically and reasonably divide delivery areas according to the order information to be delivered, so that the volume of delivery orders in each delivery area tends to be balance, which in turn helps to improve the overall efficiency of distribution.

Further effects of the above non-conventional alternatives will be described below in conjunction with specific embodiments.

Description of drawings

The accompanying drawings are used for better understanding of the present invention and do not constitute an improper limitation of the present invention. in:

Fig. 1 is the main flow chart of the distribution planning method according to the first embodiment of the present invention;

Fig. 2 is the main flow chart of the distribution planning method according to the second embodiment of the present invention;

3 is a schematic structural diagram of a distribution network model constructed according to an embodiment of the present invention;

4 is a schematic diagram of the positional relationship between a node and a cluster center point according to an embodiment of the present invention;

5 is a schematic diagram of the main modules of a distribution planning device according to a third embodiment of the present invention;

6 is a schematic diagram of the main modules of a distribution planning device according to a fourth embodiment of the present invention;

FIG. 7 is an exemplary system architecture diagram to which an embodiment of the present invention may be applied;

FIG. 8 is a schematic structural diagram of a computer system suitable for implementing an electronic device according to an embodiment of the present invention.

Detailed ways

Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, which include various details of the embodiments of the present invention to facilitate understanding and should be considered as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.

FIG. 1 is a schematic flow chart of a distribution planning method according to the first embodiment of the present invention. As shown in FIG. 1, the distribution planning method of the embodiment of the present invention includes:

Step S101 , constructing a distribution network model according to the order information to be distributed.

Wherein, the distribution network model consists of nodes and edges between nodes; the nodes are used to represent the distribution points of orders (the order distribution points may also be referred to as "order receiving locations" or "express delivery points"). Location", etc.), the edges between the nodes are used to represent the connection relationship between the order distribution points. In addition, the edges between the nodes may also be provided with corresponding weight values.

In one example, the distribution network model can be expressed as G=(V,E). Among them, V represents the set of nodes in the distribution network model, and E represents the set of edges between nodes in the distribution network model.

In another example, the distribution network model can also be represented by an adjacency matrix A for the convenience of calculation. In the adjacency matrix A, the value of the element A _ij is 1 or 0. Among them, the value of A _ij is 1, indicating that there is a connection between node i and node j (that is, there is an edge between node i and node j), and the value of A _ij is 0, indicating that there is no connection between node i and node j relationship (that is, there is no edge between node i and node j).

In yet another example, for the convenience of calculation, the distribution network model can also be represented by a weighted adjacency matrix A'. In the weighted adjacency matrix A', the value of the element A' _ij is the weight value ω _ij or 0. Among them, when the value of A _ij is the weight value, it means that there is an edge between node i and node j, and the weight value of this edge is ω _ij , and the value of A _ij is 0, which means that there is no connection between node i and node j (that is, there is no edge between node i and node j).

When building a distribution network model, it is theoretically possible to connect each order distribution point. In specific implementation, in order to simplify the network model, for order distribution points in the same community or in the same area, the nearest n (n can be set according to requirements, such as 2 or 3) order distribution points can be selected. Points are connected, and the connection is made between two cells or two areas. For example, two order delivery points with the shortest distance between the two areas can be selected for connection.

Step S102: Cluster the nodes in the distribution network model to obtain multiple clusters; take the range covered by each of the multiple clusters as a distribution area to obtain multiple distribution areas.

Exemplarily, k-means (k-means) clustering algorithm or other clustering algorithms can be used to cluster the nodes in the distribution network model.

In an optional embodiment, clustering the nodes in the distribution network model by using a k-means clustering algorithm to obtain multiple clusters includes: determining the initial positions of K cluster center points; calculating the distribution The distance between each node and each cluster center point in the network model, and assign the node to the cluster with the smallest distance to realize the update of the cluster; calculate the position of the updated cluster center point until The iteration stop condition is satisfied. Wherein, K is an integer greater than 1. During specific implementation, the value of K can be flexibly set. For example, the value of K can be determined according to the total amount of orders to be delivered and the average value of historical regional delivery volumes.

In the embodiment of the present invention, by constructing a distribution network model according to the order information to be distributed, the nodes in the distribution network model are clustered to obtain multiple clusters, and each of the multiple clusters is The covered area is used as a distribution area to obtain multiple distribution areas. These steps can dynamically and reasonably divide the distribution areas according to the order information to be distributed, so that the amount of distribution orders in each distribution area tends to be balanced, which in turn helps Improve overall delivery efficiency.

FIG. 2 is a schematic flow chart of a distribution planning method according to a second embodiment of the present invention. As shown in FIG. 2 , the distribution planning method according to the embodiment of the present invention includes:

Step S201 , constructing a distribution network model according to the order information to be distributed.

As shown in FIG. 3 , the distribution network model constructed in the embodiment of the present invention is composed of nodes and edges between nodes. The nodes are used to represent the delivery points of the order, and the edges between the nodes are used to represent the connection relationship between the delivery points of the order. In addition, the edges between the nodes may also be provided with corresponding weight values.

Further, for the convenience of calculation, the distribution network model can be represented by a weighted adjacency matrix A'. In the weighted adjacency matrix A', the value of the element A' _ij is the weight value ω _ij or 0. Among them, when the value of A _ij is the weight value, it means that there is an edge between node i and node j, and the weight value of this edge is ω _ij , and the value of A _ij is 0, which means that there is no connection between node i and node j (that is, there is no edge between node i and node j).

When building a distribution network model, it is theoretically possible to connect each order distribution point. In specific implementation, in order to simplify the network model, for order distribution points in the same community or in the same area, the nearest n (n can be set according to requirements, such as 2 or 3) order distribution points can be selected. Points are connected, and the connection is made between two cells or two areas. For example, two order delivery points with the shortest distance between the two areas can be selected for connection.

In an optional example, step S201 may specifically include: converting the coordinates of the distribution points of the order into nodes in the distribution network model, converting the connection relationship between the order distribution points into edges between nodes, and converting the order distribution points into nodes in the distribution network model. The comprehensive score of logistics distribution difficulty between nodes is converted into the weight of edges between nodes.

Wherein, the comprehensive score of the logistics distribution difficulty between the order distribution points may be determined according to at least one of the following influencing factors: the actual path length between the order distribution points, the road conditions between the order distribution points, and the parking between the order distribution points. Difficulty, weight of on-board cargo between order delivery points. For example, in a specific example, the actual path length between the order delivery points, the road conditions between the order delivery points, the difficulty of parking between the order delivery points, and the on-board cargo between the order delivery points The four influencing factors of weight determine the comprehensive score of logistics distribution difficulty between order distribution points. Table 1 shows the scores of these four influencing factors.

Table 1

每个影响因素的评分为c_i(i＝1,3,5)，进而，订单配送点i与订单配送点j之间的物流配送难度综合评分为

具体实施时，这四种影响因素的权重的取值可根据应用场景灵活设置。Further, in this specific example, the weights of these four influencing factors are respectively _wi (i=1, 2, 3, 4), and

The score of each influencing factor is c _i (i=1,3,5), and further, the comprehensive score of logistics distribution difficulty between order distribution point i and order distribution point j is

During specific implementation, the values of the weights of the four influencing factors can be flexibly set according to application scenarios.

Step S202: Cluster the nodes in the distribution network model to obtain multiple clusters; take the range covered by each of the multiple clusters as a distribution area to obtain multiple distribution areas.

In an optional example, step S202 specifically includes: step 1 to step 3.

Step 1. Determine the initial positions of the K cluster center points.

In this step, K points can be randomly selected from the order delivery point set X={x _i | _xi ∈R,i=1,2,...,N} as the cluster center points z ₁ , z ₂ ,...,z _k , these K clusters can be written as W ₁ ,W ₂ ,...,W _k . Wherein, K is an integer greater than 1. During specific implementation, the value of K can be flexibly set. For example, the value of K can be determined according to the total amount of orders to be delivered and the average value of historical regional delivery volumes. In addition, after determining the initial positions of the K cluster center points, the m order distribution points closest to the cluster center point can be selected (the value of m can be set as required, such as 2 or 3) and the cluster center point. Connect the cluster center points.

Step 2: Calculate the distance between each node in the distribution network model and the center point of each cluster, and assign the node to the cluster with the smallest distance, so as to update the cluster.

Exemplarily, in this step, according to the weight of each edge between a node and a cluster center point in the distribution network model, and the actual path length corresponding to each edge, calculate the distance from the node to the cluster. Distance between cluster center points.

In an optional implementation of this example, when there is only one connected road between a node i and a cluster center point k (the connected road refers to a road composed of existing edges), then Calculate the distance from node i to the cluster center point k according to the following formula:

where d _ik is the distance from node i to the cluster center point k, l _r is the actual path length of the rth edge existing between node i and the cluster center point k, and C _r is the distance from node i to the cluster center point k The weight of the rth edge that exists between the cluster center points k. Further, when there are two or more connected roads between a node i and a cluster center point k, multiple distances can be calculated by the above formula, and the minimum value among the multiple distances can be used as the node. The distance from i to the cluster center point k.

After calculating the distance between each node and each cluster center point, the node can be assigned to the cluster with the smallest distance. For example, assuming there are three clusters a, b, c, the distance from node 1 to the center of cluster a is 35, the distance from node 1 to the center of cluster b is 25, and the distance from node 1 to the center of cluster c The distance of the points is 40, then the node 1 is divided into cluster b.

Step 3: Calculate the position of the updated cluster center point until the iteration stop condition is satisfied.

In this step, the position of the cluster center point can be calculated according to the updated coordinates of each node in the cluster, and the following formula can be used specifically:

Among them, z _k is the position of the cluster center point, n _k is the number of nodes included in the updated cluster, and x represents any node in the cluster W _k .

Wherein, the iterative stop condition can be flexibly set. For example, the iterative stop condition can be set as: no nodes are assigned to different cluster centers; the iteration stop condition can also be set as: the position of the cluster center point is unchanged or the error is smaller than a predetermined threshold, etc.

Step S203 , carrying out order delivery path planning in the delivery area according to a heuristic algorithm.

Exemplarily, the planning of the order delivery route in the delivery area according to the heuristic algorithm includes: determining a candidate order delivery route in the delivery area, and according to the total dispatch cost and total cost of the candidate order delivery route The travel cost calculates the total delivery cost of the candidate delivery route; taking the minimum total delivery cost as the objective function, the candidate order delivery route is optimized until the planned order delivery route is obtained. In specific implementation, heuristic algorithms such as simulated annealing algorithm and variable-domain distributed search algorithm can be used to plan the order distribution path.

In a practical application scenario, while the order is delivered, it is also necessary to meet the customer's return demand and shipping demand. When planning the distribution path for this practical application scenario, the following objective functions can be set:

Further, when planning the distribution path for this practical application scenario, the constraints shown in Table 2 can be set.

Table 2

The parameters involved in the objective function and constraints, and the meanings of constraints are described below. in,

V: Represents the point set of express delivery, V=V'∪{0}, V'=(1,2,...n).

i,j: Indicates the index of the order delivery point.

k: Indicates the index of the delivery vehicle.

K _t : a set representing the type t of delivery vehicles.

T: Represents a collection of delivery vehicles.

t: Indicates the index of the type of delivery vehicle.

Q _t : Indicates the vehicle capacity of the delivery vehicle type t.

Z _tk : Indicates the delivery cost of the k-th vehicle of the delivery vehicle type t.

e _ij : Indicates the driving cost of order delivery point i and order delivery point j.

p _i : Indicates the reverse demand of the customer corresponding to the order delivery point i (ie, the demand for return).

d _i : Indicates the delivery demand of customer i corresponding to the order delivery point i.

α _ijtk : Indicates that the k-th vehicle whose delivery vehicle type is t has delivered the order delivery point i and continues to go to the order delivery point j is 1, otherwise it is 0.

γ _itk : indicates that the k-th vehicle of the delivery vehicle type t is responsible for the order delivery point i is 1, otherwise it is 0.

ε _i : Indicates the pickup volume of the delivery vehicle at the order delivery point i and the order delivery point j.

：表示订单配送点i与订单配送点j的配送车送货量。

: Indicates the delivery volume of the delivery vehicle between the order delivery point i and the order delivery point j.

Among them, the objective function expresses the hope to obtain the order delivery route with the smallest sum of the regional dispatch cost and the travel cost. Constraint (1) is used to ensure that customers have delivery vehicle services; Constraint (2) is used to ensure that there is only one vehicle service between point i and point j; Constraint (3) is used to ensure that the delivery vehicle will not be overloaded; Constraints (4) and (5) are used to constrain the vehicle capacity of delivery and pickup; Constraint (6) is used to ensure that the distribution vehicle returns to the distribution center after completing the distribution task; Constraint (7) is used to Constraints on the total number of delivery vehicles; constraints (8) to (11) are used to represent the range of symbols.

Step S204, returning the planned order delivery route to the user terminal.

Exemplarily, the planned order delivery route may include: a sequence of orders to be delivered arranged in order of delivery. For example, assuming that there are 200 orders to be delivered in a delivery area and there are 4 delivery vehicles, the planned order sequence for each delivery vehicle and arranged in the order of delivery can be returned to the user terminal.

In specific implementation, when the courier completes the delivery task and returns to the terminal end point, or encounters the customer's rejection, etc., a trigger instruction can be input through the user terminal to perform step S203 again to re-plan the route.

In the embodiment of the present invention, the above steps can dynamically and reasonably divide the delivery area according to the order information to be delivered, so that the quantity of delivery orders in each delivery area tends to be balanced, thereby helping to improve the delivery efficiency as a whole. Further, the path planning in the divided distribution area based on the heuristic algorithm can further improve the distribution efficiency.

FIG. 4 is a schematic diagram of a positional relationship between a node and a cluster center point according to an embodiment of the present invention. The following describes in detail how to calculate the distance between the node and the cluster center point with reference to FIG. 4 .

As shown in Figure 4, there are two connected roads between node 3 in the distribution network model and the cluster center point shown in the figure, one connecting channel routes the edge between node 3 and node 1, node 1 and the cluster center It is composed of the edge between the nodes, and another connected channel is composed of the edge between the node 3 and the node 2, and the edge between the node 2 and the cluster center point. When calculating the distance between node 3 and the cluster center point, the following formula can be used:

d _3z =min{l ₃₁ ·C ₃₁ +l _1z ·C _1z ,l ₃₂ ·C ₃₂ +l _2z ·C _2z }

Among them, d _3z represents the distance between node 3 and the center point of the cluster, l ₃₁ represents the true path length of the edge between node 3 and node 1, C ₃₁ represents the weight of the edge between node 3 and node 1, and l _1z represents the real path length of the edge between node 1 and the cluster center point, C _1z represents the weight of the edge between node 1 and the cluster center point, l ₃₂ represents the real path length of the edge between node 3 and node 2, C ₃₂ represents the weight of the edge between node 3 and node 2, l _2z represents the real path length of the edge between node 2 and the center point of the cluster, and C _2z represents the weight of the edge between node 2 and the center point of the cluster. The above formula expresses; the minimum distance in the two connected roads is taken as the distance d _3z between node 3 and the cluster center point.

FIG. 5 is a schematic diagram of main modules of a distribution planning apparatus according to a third embodiment of the present invention. As shown in FIG. 5 , the distribution planning apparatus 500 according to the embodiment of the present invention includes: a building module 501 and a clustering module 502 .

The building module 501 is used to build a delivery network model according to the order information to be delivered.

Wherein, the distribution network model consists of nodes and edges between nodes; the nodes are used to represent the distribution points of orders (the order distribution points may also be referred to as "order receiving locations" or "express delivery points"). Location", etc.), the edges between the nodes are used to represent the connection relationship between the order distribution points. In addition, the edges between the nodes may also be provided with corresponding weight values.

In one example, the distribution network model can be expressed as G=(V,E). Among them, V represents the set of nodes in the distribution network model, and E represents the set of edges between nodes in the distribution network model.

In another example, the distribution network model can also be represented by an adjacency matrix A for the convenience of calculation. In the adjacency matrix A, the value of the element A _ij is 1 or 0. Among them, the value of A _ij is 1, indicating that there is a connection between node i and node j (that is, there is an edge between node i and node j), and the value of A _ij is 0, indicating that there is no connection between node i and node j relationship (that is, there is no edge between node i and node j).

In yet another example, for the convenience of calculation, the distribution network model can also be represented by a weighted adjacency matrix A'. In the weighted adjacency matrix A', the value of the element A' _ij is the weight value ω _ij or 0. Among them, when the value of A _ij is the weight value, it means that there is an edge between node i and node j, and the weight value of this edge is ω _ij , and the value of A _ij is 0, which means that there is no connection between node i and node j (that is, there is no edge between node i and node j).

During specific implementation, in order to simplify the network model, for order distribution points in the same community or in the same area, the nearest n (n can be set according to requirements, such as 2 or 3) order distribution points can be selected. Connect, and connect between two cells or two areas. For example, you can select two order delivery points with the shortest distance between the two areas to connect.

The clustering module 502 is used to cluster the nodes in the distribution network model to obtain multiple clusters; the range covered by each of the multiple clusters is taken as a distribution area to obtain multiple clusters. delivery area.

Exemplarily, k-means (k-means) clustering algorithm or other clustering algorithms can be used to cluster the nodes in the distribution network model.

In an optional embodiment, the clustering module 502 uses a k-means clustering algorithm to cluster the nodes in the distribution network model to obtain multiple clusters. The clustering module 502 determines K cluster center points. The clustering module 502 calculates the distance between each node and the center point of each cluster in the distribution network model, and assigns the node to the cluster with the smallest distance, so as to realize the update of the cluster; The clustering module 502 calculates the updated position of the cluster center point until the iteration stop condition is satisfied. Wherein, K is an integer greater than 1. During specific implementation, the value of K can be flexibly set. For example, the value of K can be determined according to the total amount of orders to be delivered and the average value of historical regional delivery volumes.

In the device of the embodiment of the present invention, a distribution network model is constructed according to the order information to be distributed by a building module, and nodes in the distribution network model are clustered by a clustering module to obtain a plurality of clusters, and the The range covered by each of the multiple clusters is used as a distribution area to obtain multiple distribution areas, which can dynamically and reasonably divide the distribution areas according to the order information to be distributed, so that the amount of distribution orders in each distribution area tends to balance , which in turn helps to improve the overall delivery efficiency.

FIG. 6 is a schematic diagram of main modules of a delivery planning apparatus according to a fourth embodiment of the present invention. As shown in FIG. 6 , the distribution planning apparatus 600 according to the embodiment of the present invention includes: a building module 601 , a clustering module 602 , and a path planning module 603 .

The building module 601 is used to build a delivery network model according to the order information to be delivered.

The distribution network model constructed by the embodiment of the present invention is composed of nodes and edges between the nodes. The nodes are used to represent the delivery points of the order, and the edges between the nodes are used to represent the connection relationship between the delivery points of the order. In addition, the edges between the nodes may also be provided with corresponding weight values.

Further, for the convenience of calculation, the distribution network model can be represented by a weighted adjacency matrix A'. In the weighted adjacency matrix A', the value of the element A' _ij is the weight value ω _ij or 0. Among them, when the value of A _ij is the weight value, it means that there is an edge between node i and node j, and the weight value of this edge is ω _ij , and the value of A _ij is 0, which means that there is no connection between node i and node j (that is, there is no edge between node i and node j).

When building a distribution network model, it is theoretically possible to connect each order distribution point. In specific implementation, in order to simplify the network model, for order distribution points in the same community or in the same area, the nearest n (n can be set according to requirements, such as 2 or 3) order distribution points can be selected. Points are connected, and the connection is made between two cells or two areas. For example, two order delivery points with the shortest distance between the two areas can be selected for connection.

In an optional example, the construction module 601 constructing a distribution network model according to the order information to be distributed may specifically include: the construction module 601 transforms the coordinates of the distribution point of the order into nodes in the distribution network model, The connection relationship between nodes is transformed into edges between nodes, and the comprehensive score of logistics distribution difficulty between order distribution points is transformed into the weight of edges between nodes.

Wherein, the comprehensive score of the logistics distribution difficulty between the order distribution points may be determined according to at least one of the following influencing factors: the actual path length between the order distribution points, the road conditions between the order distribution points, and the parking between the order distribution points. Difficulty, weight of on-board cargo between order delivery points. For example, in a specific example, the actual path length between the order delivery points, the road conditions between the order delivery points, the difficulty of parking between the order delivery points, and the on-board cargo between the order delivery points The four influencing factors of weight determine the comprehensive score of logistics distribution difficulty between order distribution points.

The clustering module 602 is used for clustering the nodes in the distribution network model to obtain a plurality of clusters; also used for taking the range covered by each of the plurality of clusters as a distribution area, to get multiple delivery areas.

In an optional example, the clustering module 602 performs clustering on the nodes in the distribution network model to obtain multiple clusters, which specifically includes: step 1 to step 3 .

Step 1. The clustering module 602 determines the initial positions of the K cluster center points.

In this step, the clustering module 602 can randomly select K points from the order delivery point set X={ _xi | _xi ∈R,i=1,2,...,N} as the cluster center point z ₁ , z ₂ ,...,z _k , these K clusters can be denoted as W ₁ , W ₂ ,...,W _k . Wherein, K is an integer greater than 1. During specific implementation, the value of K can be flexibly set. For example, the value of K can be determined according to the total amount of orders to be delivered and the average value of historical regional delivery volumes. In addition, after determining the initial positions of the K cluster center points, the m order distribution points closest to the cluster center point can be selected (the value of m can be set as required, such as 2 or 3) and the cluster center point. Connect the cluster center points.

Step 2: The clustering module 602 calculates the distance between each node in the distribution network model and the center point of each cluster, and assigns the node to the cluster with the smallest distance, so as to update the cluster.

Exemplarily, in this step, the clustering module 602 can calculate the weight of each edge between a node and a cluster center point in the distribution network model and the actual path length corresponding to each edge. The distance from the node to the center point of this cluster.

In an optional implementation of this example, when there is only one connected road between a certain node i and a cluster center point k (the connected road refers to a road composed of existing edges), the clustering The class module 602 can calculate the distance from node i to the cluster center point k according to the following formula:

where d _ik is the distance from node i to the cluster center point k, l _r is the actual path length of the rth edge existing between node i and the cluster center point k, and C _r is the distance from node i to the cluster center point k The weight of the rth edge that exists between the cluster center points k. Further, when there are two or more connected roads between a node i and a cluster center point k, the clustering module 602 can calculate a plurality of distances through the above formula, and calculate the distance among the distances. The minimum value is taken as the distance from node i to the cluster center point k.

After calculating the distance between each node and each cluster center point, the node can be assigned to the cluster with the smallest distance. For example, assuming there are three clusters a, b, c, the distance from node 1 to the center of cluster a is 35, the distance from node 1 to the center of cluster b is 25, and the distance from node 1 to the center of cluster c The distance of the points is 40, then the node 1 is divided into cluster b.

Step 3: The clustering module 602 calculates the updated position of the cluster center point until the iteration stop condition is satisfied.

In this step, the clustering module 602 can calculate the position of the cluster center point according to the updated coordinates of each node in the cluster, and the following formula can be used specifically:

Among them, z _k is the position of the cluster center point, n _k is the number of nodes included in the updated cluster, and x represents any node in the cluster W _k .

Wherein, the iterative stop condition can be flexibly set. For example, the iterative stop condition can be set as: no nodes are assigned to different cluster centers; the iteration stop condition can also be set as: the position of the cluster center point is unchanged or the error is smaller than a predetermined threshold, etc.

The route planning module 603 is configured to plan the order delivery route in the delivery area according to the heuristic algorithm, and return the planned order delivery route to the user terminal.

Exemplarily, the path planning module 603 performs order delivery path planning in the delivery area according to a heuristic algorithm, including: the path planning module 603 determines a candidate order delivery path in the delivery area, and according to the corresponding order delivery path of the candidate order delivery path The total delivery cost of the candidate delivery route is calculated from the total dispatch cost and the total travel cost; the candidate order delivery route is optimized with the minimum total delivery cost as the objective function until the planned order delivery route is obtained. During specific implementation, the route planning module 603 may use heuristic algorithms such as simulated annealing algorithm, variable-domain distributed search algorithm, etc. to plan the order delivery route.

In the device of the embodiment of the present invention, the building module and the clustering module can dynamically and reasonably divide the delivery area according to the order information to be delivered, so that the quantity of delivery orders in each delivery area tends to be balanced, thereby helping to improve the overall Improve delivery efficiency. Further, the route planning module performs route planning in the divided delivery area based on the heuristic algorithm, which can further improve the delivery efficiency.

FIG. 7 shows an exemplary system architecture 700 to which a delivery planning method or a delivery planning apparatus according to an embodiment of the present invention may be applied.

As shown in FIG. 7 , the system architecture 700 may include terminal devices 701 , 702 , and 703 , a network 704 and a server 705 . The network 704 is the medium used to provide the communication link between the terminal devices 701 , 702 , 703 and the server 705 . Network 704 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user can use the terminal devices 701, 702, 703 to interact with the server 705 through the network 704 to receive or send messages and the like. Various communication client applications can be installed on the terminal devices 701 , 702 and 703 , such as logistics and distribution management applications, shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. .

The terminal devices 701, 702, 703 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

The server 705 may be a server that provides various services, such as a background management server that provides support for logistics and distribution management applications or websites browsed by the user using the terminal devices 701 , 702 , and 703 . The background management server can analyze and process the received distribution planning request and other data, and feed back the processing result (for example, the distribution area division result) to the terminal device.

It should be noted that the delivery planning method provided in the embodiment of the present invention is generally executed by the server 705 , and accordingly, the delivery planning apparatus is generally set in the server 705 .

It should be understood that the numbers of terminal devices, networks and servers in FIG. 7 are only illustrative. There can be any number of terminal devices, networks and servers according to implementation needs.

Referring next to FIG. 8 , it shows a schematic structural diagram of a computer system 800 suitable for implementing an electronic device according to an embodiment of the present invention. The computer system shown in FIG. 8 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present invention.

As shown in FIG. 8, a computer system 800 includes a central processing unit (CPU) 801, which can be loaded into a random access memory (RAM) 803 according to a program stored in a read only memory (ROM) 802 or a program from a storage section 808 Instead, various appropriate actions and processes are performed. In the RAM 803, various programs and data necessary for the operation of the system 800 are also stored. The CPU 801 , the ROM 802 , and the RAM 803 are connected to each other through a bus 804 . An input/output (I/O) interface 805 is also connected to bus 804 .

The following components are connected to the I/O interface 805: an input section 806 including a keyboard, a mouse, etc.; an output section 807 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 808 including a hard disk, etc. ; and a communication section 809 including a network interface card such as a LAN card, a modem, and the like. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I/O interface 805 as needed. A removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is mounted on the drive 810 as needed so that a computer program read therefrom is installed into the storage section 808 as needed.

In particular, the processes described above with reference to the flowcharts may be implemented as computer software programs in accordance with the disclosed embodiments of the present invention. For example, embodiments disclosed herein include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the method illustrated in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network via the communication portion 809, and/or installed from the removable medium 811. When the computer program is executed by the central processing unit (CPU) 801, the above-described functions defined in the system of the present invention are performed.

It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above 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 a combination of any of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), fiber optics, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. In the present invention, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device . Program code embodied on a computer readable medium may be transmitted using any suitable medium including, but not limited to, wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations 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 diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams or flowchart illustrations, and combinations of blocks in the block diagrams or flowchart illustrations, can be implemented in special purpose hardware-based systems that perform the specified functions or operations, or can be implemented using A combination of dedicated hardware and computer instructions is implemented.

The modules involved in the embodiments of the present invention may be implemented in a software manner, and may also be implemented in a hardware manner. The described modules can also be set in the processor, for example, it can be described as: a processor includes a building module and a clustering module. Wherein, the names of these modules do not constitute a limitation of the module itself under certain circumstances, for example, a building module can also be described as a "module for building a distribution network model".

As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or may exist alone without being assembled into the device. The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by a device, the device includes: constructing a distribution network model according to the order information to be distributed; wherein, the distribution network model It consists of nodes and edges between nodes; the nodes are used to represent the distribution points of the order, and the edges between the nodes are used to represent the connection relationship between the distribution points of the order; for the nodes in the distribution network model Clustering is performed to obtain multiple clusters; the range covered by each of the multiple clusters is taken as a delivery area to obtain multiple delivery areas.

According to the technical solution of the embodiment of the present invention, by constructing a distribution network model according to the order information to be distributed, the nodes in the distribution network model are clustered to obtain multiple clusters, and the nodes in the multiple clusters are clustered. Each covered area is used as a distribution area to obtain multiple distribution areas. These steps can dynamically and reasonably divide the distribution area according to the order information to be distributed, so that the amount of distribution orders in each distribution area tends to be balanced, and then there are Helps to improve overall delivery efficiency.

The above-mentioned specific embodiments do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims (10)

1. A distribution planning method, characterized in that the method comprises: A delivery network model is constructed according to the order information to be delivered; wherein, the delivery network model consists of nodes and edges between nodes; the nodes are used to represent the delivery points of the order, and the edges between the nodes are used to represent The connection relationship between the order distribution points; The nodes in the distribution network model are clustered to obtain multiple clusters; the range covered by each of the multiple clusters is taken as a distribution area to obtain multiple distribution areas. 2. The method according to claim 1, wherein the building a distribution network model according to the order information to be distributed comprises: Convert the coordinates of the distribution points of the order into nodes in the distribution network model, convert the connection relationship between the order distribution points into the edges between the nodes, and convert the comprehensive score of the logistics distribution difficulty between the order distribution points into the nodes between the nodes. edge weights. 3. The method according to claim 2, wherein the described nodes in the distribution network model are clustered to obtain a plurality of clusters comprising: Determine the initial positions of the K cluster center points; calculate the distance between each node and each cluster center point in the distribution network model, and assign the nodes to the cluster with the smallest distance to achieve clustering update; calculate the position of the updated cluster center point until the iteration stop condition is met; where K is an integer greater than 1. 4. method according to claim 3, is characterized in that, described calculating the distance of each node and each cluster center point in described distribution network model comprises: According to the weight of each edge between a node and a cluster center point in the distribution network model, and the actual path length corresponding to each edge, the distance between the node and the cluster center point is calculated. 5. The method of claim 1, wherein the method comprises: After a plurality of delivery areas are obtained, order delivery path planning is performed in the delivery area according to a heuristic algorithm, and the planned order delivery path is returned to the user terminal. 6. The method according to claim 5, wherein the planning of the order delivery path in the delivery area according to a heuristic algorithm comprises: Determine a candidate order delivery route in the delivery area, and calculate the total delivery cost of the candidate delivery route according to the total dispatch cost and total travel cost corresponding to the candidate order delivery route; take the minimum total delivery cost as the objective function, The candidate order delivery route is optimized until the planned order delivery route is obtained. 7. The method according to claim 2, wherein the method comprises: determining a comprehensive score of logistics distribution difficulty between the order distribution points according to at least one of the following influencing factors: the actual path length between the order distribution points , Road conditions between order distribution points, parking difficulty between order distribution points, and on-board cargo weight between order distribution points. 8. A distribution planning device, characterized in that the distribution planning device comprises: A building module is used to construct a distribution network model according to the order information to be distributed; wherein, the distribution network model is composed of nodes and edges between nodes; the nodes are used to represent the distribution points of the order, and the nodes between the nodes The edge of is used to represent the connection relationship between the order distribution points; The clustering module is used for clustering the nodes in the distribution network model to obtain multiple clusters; it is also used for taking the range covered by each of the multiple clusters as a distribution area, to Get multiple delivery areas. 9. An electronic device, characterized in that, comprising: one or more processors; storage means for storing one or more programs, The one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-7. 10. A computer-readable medium on which a computer program is stored, characterized in that, when the program is executed by a processor, the method according to any one of claims 1-7 is implemented.

Images