Logistics transportation route planning method and system based on artificial intelligence

Abstract

The invention relates to a logistics transportation route planning method and system based on artificial intelligence, and the method comprises the steps: obtaining the original path information of a logistics transportation vehicle, and the original path information comprises the steps: setting a plurality of nodes according to an original path sequence route, and the plurality of nodes comprise a logistics starting point, a plurality of logistics stations, and a logistics terminal point; when the logistics transportation vehicles need to arrive at the temporary logistics station in the driving process from the logistics starting point to the logistics station, the temporary logistics station and the current driving position are both set as nodes, and the driving route sequence of the logistics transportation vehicles is determined according to the current driving point and the driving distance between the temporary logistics node and the adjacent nodes of the logistics station; and updating the original path information according to the driving path sequence, obtaining current path information, selecting a drivable path of the driving path sequence in the current path information by using an ant colony algorithm, and outputting an optimal driving path.

Description

Technical Field

[0001] The present invention relates to the technical field of transportation route planning, and in particular to a logistics transportation route planning method and system based on artificial intelligence. Background Art

[0002] Logistics and transportation route planning refers to determining the best transportation route and plan in the process of logistics and transportation, based on the starting point, end point and transportation requirements of the goods, through reasonable path selection and scheduling arrangements. Logistics and transportation route planning can reduce transportation distance and time and improve transportation efficiency by optimizing route selection and scheduling arrangements. Reasonable route planning can avoid unnecessary detours and congestion, reduce the transportation time of goods, and improve the speed and efficiency of logistics and transportation.

[0003] However, traditional route planning solutions usually make decisions based on human experience and intuition, lacking scientific data support and analysis. This subjective decision-making method may not fully consider the combined impact of multiple factors, such as the distance and congestion of logistics routes, resulting in inaccurate optimization of route selection, thereby affecting the transportation efficiency and quality of logistics products.

[0004] Therefore, there is an urgent need for an artificial intelligence-based logistics transportation route planning method and system to accurately optimize route selection and improve the transportation efficiency and quality of logistics products. Summary of the invention

[0005] In order to solve the problems existing in the above-mentioned prior art, the purpose of the present invention is to provide a logistics transportation route planning method and system based on artificial intelligence to accurately optimize route selection and improve the transportation efficiency and transportation quality of logistics products.

[0006] To achieve the above object, the present invention provides the following solutions:

[0007] A logistics transportation route planning method based on artificial intelligence, comprising:

[0008] Acquire original path information of the logistics transport vehicle, the original path information includes: setting a plurality of nodes according to the original path sequence route, the plurality of nodes including: a logistics starting point, a plurality of logistics sites and a logistics end point;

[0009] When the logistics transport vehicle needs to reach a temporary logistics site while traveling from the logistics starting point to the logistics site, the temporary logistics site and the current driving position are set as nodes, and the driving route sequence of the logistics transport vehicle is determined according to the driving distance between the current driving point, the temporary logistics node and the adjacent nodes of the logistics site;

[0010] According to the driving route sequence, the original route information is updated to obtain current route information, and an ant colony algorithm is used to select a drivable route in the driving route sequence in the current route information to output an optimal driving route.

[0011] Optionally, determining the driving route sequence of the logistics transport vehicle includes:

[0012] Determine the maximum driving time between adjacent nodes in the original path information according to the driving distance and driving speed between the current driving point, the temporary logistics node and the adjacent nodes between the logistics site;

[0013] Determine, according to the maximum driving time and the driving distance, a drivable geographical range corresponding to adjacent nodes in the original path information;

[0014] A drivable geographical range with the most drivable paths between adjacent nodes is selected and combined with the peak time period as the priority principle for the logistics transport vehicles to determine the driving order of the logistics transport vehicles.

[0015] Optionally, determining the drivable geographical range corresponding to adjacent nodes in the original path information includes:

[0016] According to the maximum driving time and using the driving speed, calculating the corresponding long axis between adjacent nodes;

[0017] Using the travel distance between adjacent nodes in the original path information as the corresponding focal distance between adjacent nodes;

[0018] According to the corresponding major axis between the adjacent nodes and the focal distance between every two adjacent nodes, the corresponding ellipse range is determined, and the ellipse range is used as the drivable geographical range corresponding to every two adjacent nodes.

[0019] Optionally, outputting the optimal driving path includes:

[0020] S1. Initialize parameters and construct a cost matrix of obstacle information according to the current path information;

[0021] S2, select a drivable path, add exploration ants, and effectively select the drivable path;

[0022] S3, updating of pheromones. For each drivable path, the path length and the corresponding pheromone increment are calculated respectively, and the pheromones of the corresponding points on the path are updated;

[0023] S4, the ant path generated at the next moment generates a new feasible path;

[0024] S5. If the upper limit of the number of searches is not reached, jump to step S2; otherwise, output the optimal driving path.

[0025] Optionally, the method of constructing the cost matrix of obstacle information is:

[0026] A=0 i=j

[0027] A=B ij There is no obstacle between nodes i and j i≠j

[0028] A=MAX There is no obstacle between nodes i and j i≠j

[0029] Among them, A is the cost from node i to node j. If there is an obstacle between the two points, the cost is MAX infinity, otherwise it is the Euclidean distance, B ij Represents the Euclidean distance between node i and node j.

[0030] To achieve the above objectives, the present invention also provides a logistics transportation route planning system based on artificial intelligence, comprising:

[0031] The original path acquisition module is used to acquire the original path information of the logistics transport vehicle, wherein the original path information includes: setting a plurality of nodes according to the original path sequence route, wherein the plurality of nodes include: a logistics starting point, a plurality of logistics sites and a logistics end point;

[0032] A path updating module is used for, when the logistics transport vehicle needs to arrive at a temporary logistics site during its journey from the logistics starting point to the logistics site, setting the temporary logistics site and the current driving position as nodes, determining the driving route sequence of the logistics transport vehicle according to the driving distance between the current driving point, the temporary logistics node and the adjacent nodes of the logistics site, and updating the original path information according to the driving route sequence to obtain the current path information;

[0033] The optimal path determination module is used to select a drivable path in the driving route sequence in the current path information by using an ant colony algorithm, and output an optimal driving path.

[0034] Optionally, the path updating module includes:

[0035] A driving range determination unit, used to determine the maximum driving time corresponding to the adjacent nodes in the original path information according to the driving distance and driving speed between the current driving point, the temporary logistics node and the adjacent nodes between the logistics site, and determine the drivable geographical range corresponding to the adjacent nodes in the original path information according to the maximum driving time and the driving distance;

[0036] A path updating unit is used to select a drivable geographical range with the most drivable paths between adjacent nodes and combine the current time period as a peak time period as the priority principle for the logistics transportation vehicles to arrive first, determine the driving route sequence of the logistics transportation vehicles, and update the original path information according to the driving route sequence to obtain the current path information.

[0037] Optionally, the driving range determination unit includes:

[0038] A driving time determination subunit is used to determine the maximum driving time corresponding to the adjacent nodes in the original path information according to the driving distance and driving speed of the adjacent nodes between the current driving point, the temporary logistics node and the logistics site;

[0039] The driving range determination subunit is used to calculate the corresponding major axis between adjacent nodes according to the maximum driving time and the driving speed; use the driving distance between adjacent nodes in the original path information as the corresponding focal distance between adjacent nodes; determine the corresponding elliptical range according to the corresponding major axis between adjacent nodes and the focal distance corresponding to every two adjacent nodes, and use the elliptical range as the drivable geographical range corresponding to every two adjacent nodes.

[0040] Optionally, the optimal path determination module includes:

[0041] The optimal path determination unit is used for:

[0042] S1. Initialize parameters and construct a cost matrix of obstacle information according to the current path information;

[0043] S2, select a drivable path, add exploration ants, and effectively select the drivable path;

[0044] S3, updating of pheromones. For each drivable path, the path length and the corresponding pheromone increment are calculated respectively, and the pheromones of the corresponding points on the path are updated;

[0045] S4, the ant path generated at the next moment generates a new feasible path;

[0046] S5. If the upper limit of the number of searches is not reached, jump to step S2; otherwise, output the optimal driving path.

[0047] The beneficial effects of the present invention are:

[0048] The present invention obtains original path information of logistics transport vehicles. When the logistics transport vehicle needs to arrive at a temporary logistics site during its travel from the logistics starting point to the logistics site, the temporary logistics site and the current driving position are both set as nodes. According to the driving distance between the current driving point, the temporary logistics node and the adjacent nodes between the logistics site, the drivable geographical range corresponding to the adjacent nodes in the original path information is determined. The drivable geographical range with the most drivable paths between adjacent nodes is selected, and combined with the current time period being a peak time period, the driving route sequence of the logistics transport vehicles is determined as the principle of priority arrival of the logistics transport vehicles. This enables more drivable path options to appear.

[0049] The present application updates the original path information according to the driving route sequence, obtains the current path information, uses the ant colony algorithm to select the drivable path in the driving route sequence in the current path information, outputs the optimal driving route, accurately optimizes the route selection, and improves the transportation efficiency and quality of logistics products. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0051] Figure 1 This is a flow chart of a logistics transportation route planning method based on artificial intelligence according to an embodiment of the present invention;

[0052] Figure 2 A sequential flow chart of determining a travel route of a logistics transport vehicle according to an embodiment of the present invention;

[0053] Figure 3 A flow chart of determining the drivable geographical range corresponding to adjacent nodes in original path information according to an embodiment of the present invention;

[0054] Figure 4 This is a flow chart of outputting the optimal driving path according to an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0057] like Figure 1 As shown, this embodiment discloses a logistics transportation route planning method based on artificial intelligence, including: obtaining original path information of logistics transportation vehicles, the original path information including: setting multiple nodes according to the original route sequence, the multiple nodes including: a logistics starting point, several logistics sites and a logistics end point; when the logistics transportation vehicle needs to arrive at a temporary logistics site while traveling from the logistics starting point to the logistics site, the temporary logistics site and the current driving position are both set as nodes, and the driving route sequence of the logistics transportation vehicle is determined according to the driving distance between the current driving point, the temporary logistics node and the adjacent nodes between the logistics site; according to the driving route sequence, the original path information is updated to obtain the current path information, and the ant colony algorithm is used to select the drivable path in the driving route sequence in the current path information, and the optimal driving route is output.

[0058] like Figure 2 As shown, determining the driving route sequence of logistics transport vehicles includes: determining the maximum driving time corresponding to the adjacent nodes in the original path information according to the driving distance and driving speed between the current driving point, temporary logistics nodes and adjacent nodes between the logistics sites; determining the drivable geographical range corresponding to the adjacent nodes in the original path information according to the maximum driving time and driving distance; selecting the drivable geographical range with the most drivable paths between adjacent nodes and combining the current time period as the peak time period (that is, avoiding traffic jams during peak times) as the priority principle for logistics transport vehicles to determine the driving route sequence of logistics transport vehicles, or selecting the drivable geographical range with the least drivable paths between adjacent nodes and combining the current time period as the non-peak time period as the priority principle for logistics transport vehicles to determine the driving route sequence of logistics transport vehicles.

[0059] like Figure 3 As shown, determining the drivable geographical range corresponding to adjacent nodes in the original path information includes: calculating the corresponding long axis between adjacent nodes using the driving speed according to the maximum driving time; using the driving distance between adjacent nodes in the original path information as the corresponding focal distance between adjacent nodes; determining the corresponding elliptical range according to the corresponding long axis between adjacent nodes and the focal distance corresponding to every two adjacent nodes, and using the elliptical range as the drivable geographical range corresponding to every two adjacent nodes.

[0060] like Figure 4As shown, outputting the optimal driving path includes: S1, initializing parameters, constructing a cost matrix of obstacle information according to the current path information; S2, selecting a drivable path, adding exploration ants, and effectively selecting the drivable path; S3, updating pheromones, for each drivable path, calculating the path length and the corresponding pheromone increment respectively, and updating the pheromones of the corresponding points on the path; S4, the ant path generated at the next moment, generating a new feasible path; S5, if the upper limit of the search times is not reached, jump to step S2, otherwise, output the optimal driving path.

[0061] The method to construct the cost matrix of obstacle information is:

[0062] A=0 i=j

[0063] A=B ij There is no obstacle between nodes i and j i≠j

[0064] A=MAX There is no obstacle between nodes i and j i≠j

[0065] Among them, A is the cost from node i to node j. If there is an obstacle between the two points, the cost is MAX infinity, otherwise it is the Euclidean distance, B ij Represents the Euclidean distance between node i and node j.

[0066] The method of the pheromone update mechanism is:

[0067] C ij =P ij (1-P)+D ij +E ij

[0068] Among them, C ij is the amount of original pheromone on the road between node i and node j, P is the pheromone volatilization ratio, D ij is the amount of pheromone that all general ants need to add on the road between node i and node j after this round of search, is the amplification factor of the best path found for the first time, E ij The amount of pheromone added to the path between node i and node j by the optimal ant.

[0069] The method for selecting a drivable path is:

[0070] H=0j∈G

[0071]

[0072] Among them, H is the next point selected by the ant on node i, ω ij βis the road information between node i and node j, β is the role of road information in ant path selection, α is the role of pheromone in ant path selection, is the amount of pheromone between node i and node j, and G is the set of points that are not in the ant taboo table (pre-set condition).

[0073] The present embodiment also discloses a logistics transportation route planning system based on artificial intelligence, including: an original path acquisition module, used to obtain the original path information of the logistics transportation vehicle, the original path information includes: multiple nodes are set according to the original path sequence route, and the multiple nodes include: a logistics starting point, several logistics sites and a logistics end point; a path update module, used to set the temporary logistics site and the current driving position as nodes when the logistics transportation vehicle needs to reach a temporary logistics site during its travel from the logistics starting point to the logistics site, and determine the driving route sequence of the logistics transportation vehicle according to the current driving point, the driving distance between the temporary logistics node and the adjacent nodes between the logistics site, and update the original path information according to the driving route sequence to obtain the current path information; an optimal path determination module, used to use an ant colony algorithm to select a drivable path in the driving route sequence in the current path information, and output the optimal driving route.

[0074] The path update module includes: a driving range determination unit, which is used to determine the maximum driving time corresponding to the adjacent nodes in the original path information according to the driving distance and driving speed between the current driving point, the temporary logistics node and the adjacent nodes between the logistics site, and the driving speed, and determine the drivable geographical range corresponding to the adjacent nodes in the original path information according to the maximum driving time and the driving distance; a path update unit, which is used to select the drivable geographical range with the most drivable paths between adjacent nodes and combine the current time period as a peak time period as the principle of priority for logistics transportation vehicles to determine the driving route sequence of logistics transportation vehicles, update the original path information according to the driving route sequence, and obtain the current path information.

[0075] The driving range determination unit includes: a driving time determination subunit, which is used to determine the maximum driving time corresponding to the adjacent nodes in the original path information according to the driving distance between the adjacent nodes between the current driving point, the temporary logistics node and the logistics site, and the driving speed; a driving range determination subunit, which is used to calculate the corresponding major axis between the adjacent nodes according to the maximum driving time and the driving speed; the driving distance between the adjacent nodes in the original path information is used as the corresponding focal distance between the adjacent nodes; the corresponding elliptical range is determined according to the corresponding major axis between the adjacent nodes and the focal distance between every two adjacent nodes, and the elliptical range is used as the drivable geographical range corresponding to every two adjacent nodes.

[0076] The optimal path determination module includes: an optimal path determination unit, which is used to: S1, initialize parameters, and construct a cost matrix of obstacle information based on current path information; S2, select a drivable path, add exploration ants, and effectively select a drivable path; S3, update pheromones, for each drivable path, calculate the path length and the corresponding pheromone increment respectively, and update the pheromones of the corresponding points on the path; S4, generate an ant path at the next moment, and generate a new feasible path; S5, if the upper limit of the search times is not reached, jump to step S2, otherwise, output the optimal driving path.

[0077] The embodiments of the above methods are only descriptions of the preferred embodiments of the present invention, and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should fall within the protection scope determined by the claims of the present invention.

Claims

1. A logistics transportation route planning method based on artificial intelligence, characterized in that: include: Acquire original path information of the logistics transport vehicle, the original path information includes: setting a plurality of nodes according to the original path sequence route, the plurality of nodes including: a logistics starting point, a plurality of logistics sites and a logistics end point; When the logistics transport vehicle needs to reach a temporary logistics site while traveling from the logistics starting point to the logistics site, the temporary logistics site and the current driving position are set as nodes, and the driving route sequence of the logistics transport vehicle is determined according to the driving distance between the current driving point, the temporary logistics node and the adjacent nodes of the logistics site; According to the driving route sequence, the original route information is updated to obtain current route information, and an ant colony algorithm is used to select a drivable route in the driving route sequence in the current route information to output an optimal driving route.

2. The method for logistics transportation route planning based on artificial intelligence according to claim 1 is characterized in that: Determining the driving route sequence of the logistics transport vehicle includes: Determine the maximum driving time between adjacent nodes in the original path information according to the driving distance and driving speed between the current driving point, the temporary logistics node and the adjacent nodes between the logistics site; Determine, according to the maximum driving time and the driving distance, a drivable geographical range corresponding to adjacent nodes in the original path information; A drivable geographical range with the most drivable paths between adjacent nodes is selected and combined with the peak time period as the priority principle for the logistics transport vehicles to determine the driving order of the logistics transport vehicles.

3. The method for logistics transportation route planning based on artificial intelligence according to claim 2 is characterized in that: Determining the drivable geographical range corresponding to adjacent nodes in the original path information includes: According to the maximum driving time and using the driving speed, calculating the corresponding long axis between adjacent nodes; Using the travel distance between adjacent nodes in the original path information as the corresponding focal distance between adjacent nodes; According to the corresponding major axis between the adjacent nodes and the focal distance between every two adjacent nodes, the corresponding ellipse range is determined, and the ellipse range is used as the drivable geographical range corresponding to every two adjacent nodes.

4. The method for logistics transportation route planning based on artificial intelligence according to claim 1 is characterized in that: The output optimal driving path includes: S1. Initialize parameters and construct a cost matrix of obstacle information according to the current path information; S2, select a drivable path, add exploration ants, and effectively select the drivable path; S3, updating of pheromones. For each drivable path, the path length and the corresponding pheromone increment are calculated respectively, and the pheromones of the corresponding points on the path are updated; S4, the ant path generated at the next moment generates a new feasible path; S5. If the upper limit of the number of searches is not reached, jump to step S2; otherwise, output the optimal driving path.

5. The method for logistics transportation route planning based on artificial intelligence according to claim 4 is characterized in that: The method to construct the cost matrix of obstacle information is: A=0i=j A=B ij There is no obstacle between nodes i and j i≠j A=MAX There is no obstacle between nodes i and j i≠j Among them, A is the cost from node i to node j. If there is an obstacle between the two points, the cost is MAX infinity, otherwise it is the Euclidean distance, B ij Represents the Euclidean distance between node i and node j.

6. A logistics transportation route planning system based on artificial intelligence, which adopts the route planning method according to any one of claims 1 to 5 for route planning, characterized in that: include: The original path acquisition module is used to acquire the original path information of the logistics transport vehicle, wherein the original path information includes: setting a plurality of nodes according to the original path sequence route, wherein the plurality of nodes include: a logistics starting point, a plurality of logistics sites and a logistics end point; A path updating module is used for, when the logistics transport vehicle needs to arrive at a temporary logistics site during its journey from the logistics starting point to the logistics site, setting the temporary logistics site and the current driving position as nodes, determining the driving route sequence of the logistics transport vehicle according to the driving distance between the current driving point, the temporary logistics node and the adjacent nodes of the logistics site, and updating the original path information according to the driving route sequence to obtain the current path information; The optimal path determination module is used to select a drivable path in the driving route sequence in the current path information by using an ant colony algorithm, and output an optimal driving path.

7. The artificial intelligence-based logistics transportation route planning system according to claim 6 is characterized in that: The path updating module comprises: A driving range determination unit, used to determine the maximum driving time corresponding to the adjacent nodes in the original path information according to the driving distance and driving speed between the current driving point, the temporary logistics node and the adjacent nodes between the logistics site, and determine the drivable geographical range corresponding to the adjacent nodes in the original path information according to the maximum driving time and the driving distance; A path updating unit is used to select a drivable geographical range with the most drivable paths between adjacent nodes and combine the current time period as a peak time period as the priority principle for the logistics transportation vehicles to arrive first, determine the driving route sequence of the logistics transportation vehicles, and update the original path information according to the driving route sequence to obtain the current path information.

8. The artificial intelligence-based logistics transportation route planning system according to claim 7 is characterized in that: The driving range determination unit includes: A driving time determination subunit is used to determine the maximum driving time corresponding to the adjacent nodes in the original path information according to the driving distance and driving speed of the adjacent nodes between the current driving point, the temporary logistics node and the logistics site; The driving range determination subunit is used to calculate the corresponding major axis between adjacent nodes according to the maximum driving time and the driving speed; use the driving distance between adjacent nodes in the original path information as the corresponding focal distance between adjacent nodes; determine the corresponding elliptical range according to the corresponding major axis between adjacent nodes and the focal distance corresponding to every two adjacent nodes, and use the elliptical range as the drivable geographical range corresponding to every two adjacent nodes.

9. The artificial intelligence-based logistics transportation route planning system according to claim 6 is characterized in that: The optimal path determination module comprises: The optimal path determination unit is used for: S1. Initialize parameters and construct a cost matrix of obstacle information according to the current path information; S2, select a drivable path, add exploration ants, and effectively select the drivable path; S3, updating of pheromones. For each drivable path, the path length and the corresponding pheromone increment are calculated respectively, and the pheromones of the corresponding points on the path are updated; S4, the ant path generated at the next moment generates a new feasible path; S5. If the upper limit of the number of searches is not reached, jump to step S2; otherwise, output the optimal driving path.

Images