Intelligent logistics transportation path optimization method and device, equipment and medium

Abstract

The invention provides an intelligent logistics transportation path optimization method and device, equipment and a medium, and the method comprises the steps: determining transportation vehicles according to cargo information and vehicle information, and enabling the number of used vehicles to be minimum; according to a cargo transportation starting point, a cargo transportation ending point, a transfer station, preset transportation starting time and cargo unloading / loading time of each station, determining an initial target path to enable the path between the points to be shortest, and predicting transportation starting time and ending time of each initial target path according to the initial target path so as to obtain an initial transportation path and arrival time; according to the initial target path transportation departure time and end time, acquiring traffic accident data of each initial target path in the corresponding time period to determine the accident occurrence frequency; and when the accident occurrence frequency of the initial transportation path exceeds a first preset probability value, abandoning the initial transportation path and re-planning the transportation path through the transportation path planning step and the accident condition analysis step until the accident occurrence frequency of the transportation path does not exceed the first preset probability value.

Description

Technical Field

[0001] The present invention relates to the field of strategy formulation technology, and in particular to a method, device, equipment and medium for optimizing intelligent logistics transportation routes. Background Art

[0002] With the rapid development of social economy and the continuous rise and growth of the Internet e-commerce industry, most of the necessities of people's daily life are purchased through the Internet. As people's purchasing power continues to expand, the pressure of transporting the purchased goods is also extremely huge.

[0003] In the existing intelligent logistics distribution route design process, the location of each warehouse / transfer station is taken into consideration, and the shortest transportation route is customized after considering the remaining cargo capacity of the warehouse / transfer station or the cargo carrying capacity of the truck (or the remaining cargo loading capacity of the truck). Most of the route selection strategies are implemented and optimized during the transportation process. However, some sections of the road are prone to accidents at certain times. Therefore, the impact of road section accidents on transportation is not analyzed and predicted before the transport vehicle departs, resulting in unreasonable transportation routes. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present disclosure provides a smart logistics transportation path optimization method, device, equipment and medium to solve the problem in the related art that the impact of road accidents on transportation is not analyzed and predicted before the departure of the transport vehicle, resulting in unreasonable transportation routes.

[0005] One or more embodiments of this specification provide a method for optimizing a smart logistics transportation path, including the following steps:

[0006] A1, Determine the transport vehicle: Determine the transport vehicle based on the cargo information and vehicle information to minimize the number of vehicles used;

[0007] A2, transportation route planning: According to the cargo transportation starting point, end point, transfer station, preset transportation start time and cargo unloading / loading time of each transfer station, determine the initial target path so that the path between each point is the shortest, and estimate the initial arrival time and departure time of the vehicle at each station according to the initial target path, so as to obtain the initial transportation route and arrival time;

[0008] A3, accident situation analysis: according to the preset transportation start time and the initial arrival time of each station determined in the transportation vehicle route planning step, the traffic accident data of each initial target path in the corresponding time period is obtained, and the traffic accident data is input into the preset clustering algorithm for clustering analysis to obtain the accident information of the initial transportation path, wherein the accident information includes the number of accidents occurring on the initial transportation path; and

[0009] A4, route optimization and adjustment: according to the analysis results of the accident situation analysis step, when the number of accidents on the initial transport path exceeds the first preset probability value, the initial transport path is abandoned and the transport path is replanned through the transport path planning step and the accident situation analysis step until the number of accidents on the transport path does not exceed the first preset probability value, thereby determining the final transport path and the arrival time of each station.

[0010] Another smart logistics transportation path optimization method provided by one or more embodiments of this specification includes the following steps:

[0011] B1, transport vehicle determination: Determine the transport vehicle based on the cargo information and vehicle information to minimize the number of vehicles used;

[0012] B2, transportation route planning: According to the cargo transportation starting point, end point, transfer station, preset transportation start time and cargo unloading / loading time of each transfer station, determine the initial target path so that the path between each point is the shortest, and estimate the initial arrival time and departure time of the vehicle at each station according to the initial target path, so as to obtain the initial transportation route and arrival time;

[0013] B3, accident situation analysis: according to the preset transportation start time and the initial arrival time of each station determined in the transportation vehicle route planning step, the traffic accident data of each initial target path in the corresponding time period is obtained, and the traffic accident data is input into the preset clustering algorithm for clustering analysis to obtain the accident information, wherein the accident information includes the accident level, and the accident level includes minor accident, general accident, major accident and serious accident; and

[0014] B4, route optimization and adjustment: Based on the analysis results of the accident situation analysis step, if a major accident or a serious accident occurs on the initial target path within the corresponding time period determined in step B3, the initial target path is abandoned, and the replacement target path is replanned through steps B2-B3 until no major accident or serious accident occurs within the corresponding time period of the replacement target path, thereby determining the target path, the final transportation path and the arrival time of each station.

[0015] Another smart logistics transportation path optimization method provided by one or more embodiments of this specification includes the following steps:

[0016] C1, transport vehicle determination: Determine the transport vehicle based on the cargo information and vehicle information to minimize the number of vehicles used;

[0017] C2, transportation route planning: According to the cargo transportation starting point, end point, transfer station, preset transportation start time and cargo unloading / loading time of each transfer station, determine the initial target path so that the path between each point is the shortest, and estimate the initial arrival time and departure time of the vehicle at each station according to the initial target path, so as to obtain the initial transportation route and arrival time;

[0018] C3, accident situation analysis: according to the preset transportation start time and the initial arrival time of each station determined in the transportation vehicle route planning step, the traffic accident data of each initial target path in the corresponding time period is obtained, and the traffic accident data is input into the preset clustering algorithm for clustering analysis to obtain accident information, wherein the accident information includes the probability of accident occurrence; and

[0019] C4, route optimization and adjustment: according to the analysis results of the accident situation analysis step, if the probability of an accident occurring on the initial target path in the corresponding time period determined based on step C3 is greater than the preset accident probability threshold, the initial target path is abandoned, and the replacement target path is replanned through steps C2-C3 until the probability of an accident occurring on the replacement target path in the corresponding time period is not greater than the preset accident probability threshold, and the target path, final transportation path and arrival time of each station are obtained.

[0020] One or more embodiments of this specification provide a smart logistics transportation path optimization device, including:

[0021] The transport vehicle determination module is used to determine the transport vehicle according to the cargo information and vehicle information so as to minimize the number of vehicles used;

[0022] The transport route planning module is used to determine the initial target route so that the route between each point is the shortest according to the starting point, end point, transfer station, preset transport start time and cargo unloading / loading time of each transfer station, and estimate the initial arrival time and departure time of vehicles at each station according to the initial target route, so as to obtain the initial transport route and arrival time;

[0023] The accident situation analysis module is used to obtain the traffic accident data of each initial target path in the corresponding time period according to the preset transportation start time and the initial arrival time of each station determined in the transportation vehicle path planning step, and input the traffic accident data into the preset clustering algorithm for clustering analysis to obtain accident information, wherein the accident information includes the number of accidents occurring on the initial transportation path;

[0024] The first path optimization and adjustment module is used to abandon the initial transportation path and re-plan the transportation path through the transportation path planning module and the accident situation analysis module according to the analysis results of the accident situation analysis module until the number of accidents on the initial transportation path does not exceed the first preset probability value, thereby determining the final transportation path and the arrival time of each station.

[0025] Another intelligent logistics transportation path optimization device provided by one or more embodiments of this specification includes:

[0026] The transport vehicle determination module is used to determine the transport vehicle according to the cargo information and vehicle information so as to minimize the number of vehicles used;

[0027] The transport route planning module is used to determine the initial target route so that the route between each point is the shortest according to the starting point, end point, transfer station, preset transport start time and cargo unloading / loading time of each transfer station, and estimate the initial arrival time and departure time of vehicles at each station according to the initial target route, so as to obtain the initial transport route and arrival time;

[0028] An accident situation analysis module, which is used to obtain traffic accident data of each initial target path within a corresponding time period according to the preset transportation start time and the initial arrival time of each station determined in the transportation vehicle path planning step, and input the traffic accident data into a preset clustering algorithm for clustering analysis to obtain accident information, wherein the accident information includes accident levels, and the accident levels include minor accidents, general accidents, major accidents and serious accidents; and

[0029] The second path optimization and adjustment module is used to abandon the initial target path according to the analysis results of the accident situation analysis module when a major accident or serious accident occurs on the initial target path within the corresponding time period, and re-plan the replacement target path through the transportation path planning module and the accident situation analysis module until no major accident or serious accident occurs on the replacement target path within the corresponding time period, thereby determining the target path, the final transportation path and the arrival time of each station.

[0030] Another intelligent logistics transportation route optimization device provided by one or more embodiments of this specification includes: a transportation vehicle determination module, which is used to determine the transportation vehicle according to the cargo information and the vehicle information, so as to minimize the number of vehicles used;

[0031] The transport route planning module is used to determine the initial target route so that the route between each point is the shortest according to the starting point, end point, transfer station, preset transport start time and cargo unloading / loading time of each transfer station, and estimate the initial arrival time and departure time of vehicles at each station according to the initial target route, so as to obtain the initial transport route and arrival time;

[0032] The accident situation analysis module is used to obtain the traffic accident data of each initial target path in the corresponding time period according to the preset transportation start time and the initial arrival time of each station determined in the transportation vehicle path planning step, and input the traffic accident data into the preset clustering algorithm for clustering analysis to obtain accident information, wherein the accident information includes the probability of accident occurrence;

[0033] The third path optimization and adjustment module, based on the analysis results of the accident situation analysis module, if the probability of an accident occurring on the initial target path within the corresponding time period is greater than the preset accident probability threshold, then the initial target path is abandoned, and the replacement target path is replanned through steps C2-C3 until the probability of an accident occurring on the replacement target path within the corresponding time period is not greater than the preset accident probability threshold, thereby obtaining the target path, the final transportation path and the arrival time of each station.

[0034] One or more embodiments of the present specification provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the smart logistics transportation path optimization method as described in any one of the above items when executing the computer program.

[0035] One or more embodiments of the present specification provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for optimizing the intelligent logistics transportation path as described in any one of the above items is implemented.

[0036] The present invention provides a method, device, equipment and medium for optimizing the transportation path of smart logistics. The advantages are that the preliminary transportation path and the initial arrival time of each station are determined according to the cargo information and vehicle information, and the historical traffic accident data of the preliminary transportation path is obtained. The accident situation of each initial target path in the corresponding time period is determined by the cluster analysis algorithm. When the accident frequency of the entire path is too high, or a major accident occurs on the initial target path or the probability of an accident is too high, the transportation route will be optimized and planned, thereby realizing accurate analysis and optimization planning of the transportation path, and cooperating with the path planning during the transportation process to provide more reliable path planning for smart logistics transportation, so that shoppers can have a better experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 A flow chart of a smart logistics transportation path optimization method provided for one or more embodiments of this specification;

[0039] Figure 2 A flowchart of another intelligent logistics transportation route optimization method provided for one or more embodiments of this specification;

[0040] Figure 3 A flowchart of another intelligent logistics transportation route optimization method provided for one or more embodiments of this specification;

[0041] Figure 4 A block diagram of a smart logistics transportation route optimization device provided for one or more embodiments of this specification;

[0042] Figure 5 A block diagram of another intelligent logistics transportation route optimization device provided for one or more embodiments of this specification;

[0043] Figure 6 A block diagram of another intelligent logistics transportation route optimization device provided for one or more embodiments of this specification;

[0044] as well as

[0045] Figure 7 A schematic diagram of the structure of a computer device provided for one or more embodiments of this specification. DETAILED DESCRIPTION

[0046] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0047] The present invention is described in detail below in conjunction with specific implementation methods and the accompanying drawings.

[0048] Method Example 1

[0049] According to an embodiment of the present invention, a method for optimizing a smart logistics transportation path is provided. Figure 1 As shown, it is a flow chart of the intelligent logistics transportation path optimization method provided in this embodiment. The intelligent logistics transportation path optimization method according to the embodiment of the present invention includes the following steps:

[0050] Step A1, transport vehicle determination: Determine the transport vehicle based on the cargo information and vehicle information so as to minimize the number of vehicles used, wherein the cargo information includes cargo type, cargo quantity, cargo volume, remarks, cargo transportation starting point and end point, and the vehicle information includes vehicle type, vehicle loading capacity, etc., wherein the determination of the transport vehicle needs to be based on the cargo transportation starting point and cargo transportation end point as a prerequisite, and determine the vehicle suitable for transportation based on the acquired cargo type, such as fresh food, clothing, large pieces and fragile, etc. For example, if 2,000 pieces of fresh milk need to be transported to the destination, a cold chain truck that can accommodate 2,000 pieces of fresh milk is preferably selected. Alternatively, the transport vehicle can be determined based on the total cargo volume for the same type of cargo.

[0051] Step A2, transportation route planning: according to the cargo transportation starting point, end point, transfer site, preset transportation start time and cargo unloading / loading time of each transfer site, determine the initial target path so that the path between each point is the shortest, and estimate the transportation departure time and end time of each initial target path according to the initial target path, so as to obtain the initial transportation path and arrival time; in this embodiment, the initial transportation path is composed of each initial target path.

[0052] In this embodiment, determining the shortest initial target transportation path between each point, the preset transportation start time and the cargo unloading / loading time of each transfer station can be achieved through a path planning method composed of, for example, map data + rendering engine path finding algorithm, which will not be elaborated here.

[0053] Step A3, accident situation analysis: according to the departure time and end time of the initial target path transportation, the historical traffic accident data of the initial target path in the corresponding time period is obtained, and the historical traffic accident data is input into the preset clustering algorithm for clustering analysis to obtain accident information, wherein the accident information includes the number of accidents occurring on the initial transportation path.

[0054] Step A4, route optimization and adjustment: According to the analysis results of the accident situation analysis step, when the number of accidents on the initial transport path exceeds the first preset probability value, the initial transport path is abandoned and the transport path is replanned through steps S2-S3 until the number of accidents on the transport path does not exceed the first preset probability value, thereby determining the final transport path and the arrival time of each station.

[0055] Preferably, in this embodiment, the first preset probability value is ≥ 4 times.

[0056] The smart logistics transportation path optimization method provided in this embodiment determines the preliminary transportation path and the transportation departure time and end time according to the initial target path according to the cargo information and vehicle information, and then obtains the historical traffic accident data of the preliminary transportation path, and determines the accident occurrence of each initial target path in the corresponding time period through the cluster analysis algorithm. When the accident frequency of the entire path is too high, the transportation route will be optimized and planned, thereby realizing accurate analysis and optimization planning of the transportation path, and coordinating with the path planning during the transportation process to provide more reliable path planning for smart logistics transportation, so that shoppers can have a better experience.

[0057] In order to more accurately determine the initial arrival time of each station in step S3 in this embodiment, it is also necessary to determine the driver's driving habits by analyzing the driver's historical driving data based on the driver information of the transport vehicle, thereby determining the average driving speed of the corresponding driver. The initial arrival time of each station can be more accurately determined based on the average driving speed of the driver. The specific steps are as follows:

[0058] Step 11, obtaining the driver's historical cargo transportation data, and determining the average driving speed of the driver's vehicle through a data analysis method.

[0059] Step 12, based on the cargo transportation starting point, end point, transfer site, preset starting point transportation start time, cargo unloading / loading time at each transfer site and the average driving speed of the driver, the shortest initial target path between each point is determined through the path planning method, and the departure time and end time of each initial target path transportation are estimated, so as to obtain the initial transportation path.

[0060] This embodiment can determine the driving habits of each driver through the above steps, and determine the corresponding transportation arrival time in combination with the road type of the target path, so that the planned initial arrival time is more accurate.

[0061] In a preferred embodiment, the initial arrival time of each station is determined by the following steps:

[0062] Step 111, obtaining driving data of various types of roads during the driver's historical transportation process, and determining the driver's average driving speed on various types of roads through a data analysis method, wherein the road type is the corresponding road classification category, and includes expressways, urban roads, national roads, provincial roads, rural roads, etc.

[0063] Step 112, based on the cargo transportation starting point, end point, transfer site, preset transportation start time, cargo unloading / loading time at each transfer site, determine the shortest initial target path between each point through a path planning method, and estimate the transportation departure time and end time of each initial target path based on the road type of each initial target path and the average driving speed of the driver on each type of road, thereby obtaining the initial transportation path.

[0064] In this embodiment, during the entire logistics task transportation process, trucks or drivers may be replaced at various transfer stations, and for long-distance transportation, the transportation route will include various types of roads, and different drivers will have different driving speeds due to different driving habits. The above steps can be used to determine the driving habits of each driver respectively, and the corresponding transportation arrival time can be determined more accurately in combination with the road type of the target path, so that the planned initial arrival time is more accurate.

[0065] In step A3 of this embodiment, inputting the traffic accident data into a preset clustering algorithm for clustering analysis to obtain accident information specifically includes the following steps:

[0066] Step 1111, input the historical traffic accident data of each initial transport route determined in the above steps (steps 11-12 or steps 111-112) into a preset clustering algorithm for clustering analysis to obtain a set of accident-prone areas, and perform spatial clustering analysis on the accidents in the set of accident-prone areas to obtain spatial clustering results, so as to determine the accident hotspot range information through the spatial clustering results, thereby determining the accident information, wherein the accident information includes the number of accidents occurring on the initial transport path; wherein the preset clustering algorithm refers to an algorithm used for clustering analysis, such as the KANN-DSCAN algorithm, the HDBSCAN algorithm, and the OPTICS algorithm, and the spatial clustering algorithm may be a Getis-OrdGeneral G analysis algorithm.

[0067] In this embodiment, the path planning method can be implemented using existing mature ant colony algorithm, particle swarm algorithm and / or reinforcement learning, which are not specifically limited or described herein.

[0068] In this embodiment, the initial transportation path is optimized and adjusted through step A4. The impact of accidents on transportation in the corresponding time period and the initial transportation path is determined based on historical data analysis. However, the analysis is about the number of accidents in the entire transportation process, but the location and time of the corresponding accident are not associated with the arrival time of the transportation vehicle, resulting in inaccurate path optimization, which may make the target path not the optimal target path. Therefore, in order to improve the optimization accuracy,

[0069] In this embodiment, the accident information also includes the accident location, the time of occurrence, and the time when the accident handling is completed. Then step A4 also includes:

[0070] Step A41: According to the accident information determined in step A3, if the number of accidents on the initial transport path exceeds a first preset probability value, then the corresponding accident locations and occurrence times are determined.

[0071] Step A42, calculate and determine the arrival time of the vehicle at the corresponding accident location based on the starting point of the initial transportation path, the road type determined in step 112, the average driving speed of the driver of the corresponding road type, and the departure time of the initial target path transportation.

[0072] Step A43: Determine an accident in which the time when the vehicle arrives at the corresponding accident point is earlier than the time when the accident occurs. The accident is not accumulated as the number of accident occurrences. If it is determined that the number of accident occurrences still exceeds the first preset probability value, the path optimization adjustment is implemented through steps A2-A4 to obtain the transportation path.

[0073] In the process of transport route planning, this embodiment determines the location and time of each accident based on the driver's driving speed, and determines whether the occurrence time is earlier than the arrival time of the vehicle to determine whether the route needs to be replanned. If it is later than the arrival time, the optimization process will definitely not be implemented, making the optimization planning process more accurate.

[0074] In this embodiment, in order to further optimize the planning of the initial target path and realize more accurate path planning, in step A43, when determining whether the arrival time is earlier than the time when the accident occurred, the accident handling completion time corresponding to the accident that occurred is considered as a judgment condition for whether the initial transportation path needs to be optimized and adjusted, specifically as follows:

[0075] Step A111, determining an accident in which the time when the vehicle arrives at the corresponding accident point is earlier than the time when the accident handling is completed, and the accident is not accumulated as the number of accident occurrences.

[0076] Method Example 2

[0077] like Figure 2 As shown, it is a flow chart of another intelligent logistics transportation path optimization method provided by this embodiment. Another intelligent logistics transportation path optimization method provided by this embodiment includes the steps of:

[0078] Step B1, transport vehicle determination: Determine the transport vehicle based on the cargo information and vehicle information so as to minimize the number of vehicles used, wherein the cargo information includes cargo type, cargo quantity, cargo volume, remarks information, cargo transportation starting point and end point, and the vehicle information includes vehicle type, vehicle loading capacity, etc.

[0079] Step B2, transportation route planning: according to the cargo transportation starting point, end point, transfer station, preset transportation start time and cargo unloading / loading time of each transfer station, determine the initial target path so that the path between each point is the shortest, and estimate the departure time and end time of each initial target path transportation according to the initial target path, so as to obtain the initial transportation path and arrival time.

[0080] Step B3, accident situation analysis: according to the departure time and end time of the initial target path transportation, obtain the historical traffic accident data of the initial target path in the corresponding time period, input the historical traffic accident data into the preset clustering algorithm for clustering analysis to obtain the accident information, wherein the accident information includes the accident location, occurrence time and accident handling completion time (road smooth time).

[0081] In this embodiment, the accident information also includes accident levels, such as minor accidents, general accidents, major accidents, and serious accidents. Accidents in a set of high-incidence accident areas are classified into levels 1, 2, 3, and 4, respectively, to facilitate subsequent route planning as a reference.

[0082] Step B4, route optimization and adjustment: Based on the analysis results of the accident situation analysis step, if a major accident or a serious accident occurs on the initial target path within the corresponding time period determined based on step B3, the initial target path is abandoned, and the replacement target path is replanned through steps B2-B3 until no major accident or serious accident occurs within the corresponding time period of the replacement target path, thereby determining the target path, the final transportation path and the arrival time of each station.

[0083] Compared with the first embodiment, the optimization accuracy of the path implemented in step A4 according to the number of accidents on the initial transport path as the optimization condition is lower. This is because the initial transport path is composed of multiple initial target paths. The number and probability of accidents on the initial transport path cannot indicate that some initial target paths are not suitable as target paths. Those initial target paths without accidents or with low accident rates are screened out as the shortest paths, resulting in poor path planning. Therefore, in order to achieve a more accurate and optimized route and avoid the uncertainty of delivery time caused by accident information encountered in the planned path, the present embodiment takes each initial target path as an optimization and adjustment object, and takes the historical accident data of the target path as the analysis object to obtain the accident information to implement path optimization and adjustment through the above steps, so that the adjustment target is smaller, the path optimization process is simple to execute, the optimization accuracy is higher, and computing resources are greatly saved.

[0084] In this embodiment, the initial target path is optimized and adjusted through step B4. The impact of the accident on the transportation of the initial target path in the corresponding time period is determined based on historical data analysis. However, the nature of the accident within a period of time is analyzed, but the location and time of the accident are not associated with the arrival time of the transport vehicle, resulting in inaccurate path optimization, which may make the target path not the optimal target path. Therefore, in order to improve the optimization accuracy, step B4 specifically includes the following steps:

[0085] Step B41: Based on the accident information determined in step B3, if a major accident or a serious accident occurs on the initial target path within the corresponding time period, determine the time and location of the major accident or the serious accident.

[0086] Step B42, based on the starting point and end point of the initial target path, and based on the road type determined in step 112 and the average driving speed of drivers of the corresponding road type and the starting time of transportation from the starting point, calculate and determine the time for the vehicle to arrive at the corresponding major accident or serious accident location.

[0087] Step B43: If it is determined that the vehicle arrival time is earlier than the accident occurrence time, the path optimization adjustment is implemented through steps C2-C4 to obtain the target path.

[0088] In the process of planning each target path, this embodiment determines whether the time when a major accident or a serious accident occurs is earlier than the arrival time based on the driver's driving speed, so as to determine whether the path needs to be replanned, so that the optimization conditions are minimized and optimized, making the planning process more accurate.

[0089] It should be noted that if a large accident or multiple major accident points occur on the initial target path, it is determined whether the initial target path needs to be optimized through steps B41 to B43 in sequence according to the direction of transportation.

[0090] In this embodiment, in order to further optimize the planning of the initial target path and realize more accurate path planning, in step B43, when judging whether the arrival time is earlier than the time when the accident occurred, the accident handling completion time corresponding to the accident that occurred is considered as a judgment condition for whether the initial target path needs to be optimized and adjusted, specifically as follows:

[0091] Step B111: If the vehicle arrival time is earlier than the accident handling completion time or the road smooth time, then the corresponding initial target path does not need to be optimized and adjusted.

[0092] This method not only considers the impact of accidents on path planning, but also combines historical data analysis with the driver's driving habits to more accurately determine the time to arrive at each node. The initial target path is taken as the minimum optimization object, and data analysis is combined to predict whether the vehicle arrival time can avoid the accident time, or the accident can be handled when the vehicle is planned to arrive at the accident point. In this way, the path planning achieved by combining multiple factors of the accident is more accurate, so that users can get a better experience.

[0093] Method Example 3

[0094] like Figure 3As shown, it is a flow chart of another intelligent logistics transportation path optimization method provided by this embodiment. Another intelligent logistics transportation path optimization method provided by this embodiment includes the steps of:

[0095] Step C1, transport vehicle determination: Determine the transport vehicle based on the cargo information and vehicle information to minimize the number of vehicles used, wherein the cargo information includes cargo type, cargo quantity, cargo volume, remarks information, cargo transportation starting point and end point, and the vehicle information includes vehicle type, vehicle loading capacity, etc.

[0096] Step C2, transportation route planning: according to the cargo transportation starting point, end point, transfer station, preset transportation start time and cargo unloading / loading time of each transfer station, determine the initial target path so that the path between each point is the shortest, and estimate the departure time and end time of each initial target path transportation according to the initial target path, so as to obtain the initial transportation path and arrival time.

[0097] Step C3, accident situation analysis: according to the departure time and end time of the initial target path transportation, the historical traffic accident data of the initial target path in the corresponding time period is obtained, and the historical traffic accident data is input into the preset clustering algorithm for clustering analysis to obtain the accident information, wherein the accident information includes the accident location, occurrence time, accident probability of each accident location and the completion time of the accident handling.

[0098] Step C4, path optimization and adjustment: according to the analysis results of the accident situation analysis step, if the probability of an accident occurring on the initial target path in the corresponding time period determined based on step C3 is greater than the preset accident probability threshold, the initial target path is discarded, and the replacement target path is replanned through steps C2-C3 until the probability of an accident occurring on the replacement target path in the corresponding time period is not greater than the preset accident probability threshold, and the target path is obtained.

[0099] In this embodiment, the preset accident probability threshold may be 50% to 80%, and the preferred preset accident probability threshold may be 50%.

[0100] In one embodiment, in order to improve the optimization accuracy, step C4 specifically includes the following steps:

[0101] Step C41: Based on the accident information determined in step C3, if the probability of an accident occurring on the initial target path within the corresponding time period is greater than a preset accident probability threshold, the time and location of the corresponding accident are determined.

[0102] Step C42, based on the starting point and end point of the initial target path, the road type determined in step 112 and the average driving speed of the driver of the corresponding road type and the starting time of the starting point transportation, calculate and determine the time for the vehicle to arrive at the corresponding accident location.

[0103] Step C43: If it is determined that the time when the vehicle arrives at the accident site is earlier than the time when the accident occurs, the path optimization adjustment is implemented through steps C2-C4 to obtain the target path.

[0104] It should be noted that if there are multiple accident points on the initial target path where the probability of an accident occurring is greater than a preset accident probability threshold, it is determined whether the initial target path needs to be optimized through steps C41 to C43 in sequence according to the direction of transport.

[0105] In this embodiment, it is also necessary to execute step B111 in the second embodiment of the above method to further optimize the planning of the initial target path and achieve more accurate path planning.

[0106] Device Example 4

[0107] According to an embodiment of the present invention, a smart logistics transportation path optimization device is provided. Figure 4 As shown, it is a block diagram of the intelligent logistics transportation path optimization device provided in this embodiment. The intelligent logistics transportation path optimization device according to the embodiment of the present invention includes:

[0108] The transport vehicle determination module 10 is used to determine the transport vehicle based on the cargo information and vehicle information so as to minimize the number of vehicles used, wherein the cargo information includes cargo type, cargo quantity, cargo volume, remarks information, cargo transportation starting point and end point, and the vehicle information includes vehicle type, vehicle loading capacity, etc.

[0109] The transport path planning module 20 is used to determine the initial target path so that the path between each point is the shortest according to the starting point, end point, transfer site, preset transport start time and cargo unloading / loading time of each transfer site, and estimate the departure time and end time of each initial target path according to the initial target path, so as to obtain the initial transport path and arrival time; in this embodiment, the initial transport path is composed of each initial target path.

[0110] In this embodiment, determining the shortest initial target transportation path between each point, the preset transportation start time and the cargo unloading / loading time of each transfer station can be achieved through a path planning method composed of, for example, map data + rendering engine path finding algorithm, which will not be elaborated here.

[0111] The accident situation analysis module 30 is used to obtain the historical traffic accident data of the initial target path within the corresponding time period according to the departure time and end time of the initial target path transportation, and input the historical traffic accident data into a preset clustering algorithm for clustering analysis to obtain accident information, wherein the accident information includes the number of accidents occurring on the initial transportation path.

[0112] The first path optimization and adjustment module 40 is used to abandon the initial transportation path and re-plan the transportation path through the transportation path planning module 20 and the accident situation analysis module 30 until the number of accidents on the initial transportation path does not exceed the first preset probability value according to the analysis result of the accident situation analysis module 30, thereby determining the final transportation path and the arrival time of each station.

[0113] The smart logistics transportation path optimization device provided in this embodiment firstly determines the preliminary transportation path and the initial arrival time of each station according to the cargo information and the vehicle information by the transportation path planning module 20, then the accident situation analysis module 30 obtains the historical traffic accident data of the initial transportation path, and determines the accident situation of each initial target path in the corresponding time period through the cluster analysis algorithm. The first path optimization adjustment module 40 determines that when the accident frequency of the entire path is too high, the transportation will be optimized and planned, thereby realizing accurate analysis and optimization planning of the transportation path, cooperating with the path planning during the transportation process, and providing more reliable path planning for smart logistics transportation, so that shoppers can have a better experience.

[0114] In this embodiment, in order for the accident situation analysis module 30 to more accurately determine the initial arrival time of each station, it is also necessary to determine the driver information of the transport vehicle, and determine the driver's driving habits by analyzing the driver's historical driving data, thereby determining the average driving speed of the corresponding driver driving the vehicle. According to the average driving speed of the driver, the initial arrival time of each station can be more accurately determined. Specifically, the following modules are set:

[0115] The driving data analysis module 101 is used to obtain the driver's historical cargo transportation data and determine the average driving speed of the driver's vehicle through a data analysis method.

[0116] The arrival time determination module 102 is used to determine the shortest initial target path between points through a path planning method according to the cargo transportation starting point, end point, transfer station, preset starting point transportation start time, cargo unloading / loading time at each transfer station and the average driving speed of the driver, and estimate the departure time and end time of each initial target path transportation, so as to obtain the initial transportation path.

[0117] In this embodiment, the driving data analysis module 101 and the arrival time determination module 102 are configured to perform the following steps:

[0118] Step 111, obtaining driving data of various types of roads during the driver's historical transportation process, and determining the driver's average driving speed on various types of roads through a data analysis method, wherein the road type is the corresponding road classification category, which may include expressways, urban roads, national roads, provincial roads, rural roads, etc.

[0119] Step 112, based on the cargo transportation starting point, end point, transfer site, preset transportation start time, cargo unloading / loading time at each transfer site, determine the shortest initial target path between each point through a path planning method, and estimate the transportation departure time and end time of each initial target path based on the road type of each initial target path and the average driving speed of the driver on each type of road, thereby obtaining the initial transportation path.

[0120] In this embodiment, the accident situation analysis module 30 inputs the traffic accident data into a preset clustering algorithm for clustering analysis to obtain accident information. The specific execution process is as follows:

[0121] Step 1111, input the historical traffic accident data of each initial transport route determined above into a preset clustering algorithm for clustering analysis to obtain a set of accident-prone areas, and perform spatial clustering analysis on the accidents in the set of accident-prone areas to obtain spatial clustering results, so as to determine the accident hotspot range information through the spatial clustering results, thereby determining the accident information, wherein the accident information includes the number of accidents occurring on the initial transport path; wherein the preset clustering algorithm refers to an algorithm used for clustering analysis, such as the KANN-DSCAN algorithm, the HDBSCAN algorithm, and the OPTICS algorithm, and the spatial clustering algorithm may be a Getis-OrdGeneral G analysis algorithm.

[0122] In this embodiment, the accident information further includes the accident location, the time of occurrence, and the time when the accident is handled. Then, the first path optimization and adjustment module 40 is configured to execute the following steps:

[0123] Step A41: According to the accident information determined by the accident situation analysis module 30, if the number of accidents on the initial transportation path exceeds a first preset probability value, the corresponding accident locations and occurrence times are determined.

[0124] Step A42, calculate and determine the arrival time of the vehicle at the corresponding accident location based on the starting point of the initial transportation path, the road type determined in step 112, the average driving speed of the driver of the corresponding road type, and the departure time of the initial target path transportation.

[0125] Step A43: Determine an accident in which the time when the vehicle arrives at the corresponding accident point is earlier than the time when the accident occurs. The accident is not accumulated as the number of accident occurrences. If it is determined that the number of accident occurrences still exceeds the first preset probability value, the path optimization adjustment is implemented through steps A2-A4 to obtain the transportation path.

[0126] In this embodiment, in order to further optimize the planning of the initial target path and realize more accurate path planning, in step A43, when determining whether the arrival time is earlier than the time when the accident occurred, the accident handling completion time corresponding to the accident that occurred is considered as a judgment condition for whether the initial transportation path needs to be optimized and adjusted, specifically as follows:

[0127] Step A111, determining an accident in which the time when the vehicle arrives at the corresponding accident point is earlier than the time when the accident handling is completed, and the accident is not accumulated as the number of accident occurrences.

[0128] Device Example 5

[0129] like Figure 5 As shown, it is a block diagram of another intelligent logistics transportation path optimization device provided by this embodiment. The intelligent logistics transportation path optimization device provided by this embodiment is different from the above-mentioned device embodiment 4 in that:

[0130] Accident information also includes accident levels, such as minor accidents, general accidents, major accidents, and serious accidents. Accidents in a set of high-incidence areas are classified into levels 1, 2, 3, and 4, respectively, to facilitate subsequent route planning as a reference.

[0131] According to the above accident information, the second path optimization and adjustment module 50 is configured to perform the following steps:

[0132] The second path optimization and adjustment module 50, based on the analysis results of the accident situation analysis step, if a large accident or a major accident occurs on the initial target path within the corresponding time period determined by the accident situation analysis module 30, the initial target path is abandoned, and the replacement target path is replanned through the transportation path planning module 20 and the accident situation analysis module 30 until no large accident or a major accident occurs within the corresponding time period of the replacement target path, thereby determining the target path, the final transportation path and the arrival time of each station.

[0133] In this embodiment, the second path optimization and adjustment module 50 is configured to execute the following steps:

[0134] Step B51, according to the accident information determined by the accident situation analysis module 30, if a major accident or a serious accident occurs on the initial target path within the corresponding time period, determine the time and place where the major accident or the serious accident occurs.

[0135] Step B52, based on the starting point and end point of the initial target path, and based on the road type determined in step 112 and the average driving speed of drivers of the corresponding road type and the starting time of transportation from the starting point, calculate and determine the time for the vehicle to arrive at the corresponding major accident or serious accident site.

[0136] Step B53: If it is determined that the vehicle arrival time is earlier than the accident occurrence time, the transport path planning module 20 and the accident situation analysis module 30 are used to optimize the path and thereby obtain the target path.

[0137] In the process of planning each target path, this embodiment determines whether the time when a major accident or a serious accident occurs is earlier than the arrival time based on the driver's driving speed, so as to determine whether the path needs to be replanned, so that the optimization conditions are minimized and optimized, making the planning process more accurate.

[0138] In this embodiment, in order to further optimize the planning of the initial target path and realize more accurate path planning, in step B53, when judging whether the arrival time is earlier than the time when the accident occurred, the accident handling completion time corresponding to the accident that occurred is considered as a judgment condition for whether the initial target path needs to be optimized and adjusted, specifically as follows:

[0139] Step B111: If the vehicle arrival time is earlier than the accident handling completion time or the road smooth time, then the corresponding initial target path does not need to be optimized and adjusted.

[0140] Device Example 6

[0141] like Figure 6 As shown, it is a block diagram of another intelligent logistics transportation path optimization device provided by this embodiment. The intelligent logistics transportation path optimization device provided by this embodiment is different from the fourth and fifth embodiments of the above-mentioned devices in that:

[0142] The accident information includes the accident location, the time of occurrence, the probability of accident occurrence at each accident location, and the time when the accident handling is completed.

[0143] According to the above accident information, the third path optimization and adjustment module 60 is configured to perform the following steps:

[0144] The third path optimization and adjustment module 60, based on the analysis result of the accident situation analysis step, if the probability of an accident occurring on the initial target path in the corresponding time period determined by the accident situation analysis module 30 is greater than a preset accident probability threshold, then the initial target path is abandoned, and the replacement target path is replanned through the transport path planning module 20 and the accident situation analysis module 30 until the probability of an accident occurring on the replacement target path in the corresponding time period is not greater than the preset accident probability threshold, thereby determining the target path, the final transport path and the arrival time of each station.

[0145] In this embodiment, the preset accident probability threshold may be 50% to 80%, and the preferred preset accident probability threshold may be 50%.

[0146] In this embodiment, the third path optimization and adjustment module 60 is configured to execute the following steps:

[0147] Step C61: According to the accident information determined by the accident situation analysis module 30, if the probability of an accident occurring on the initial target path within the corresponding time period is greater than a preset accident probability threshold, the time and location of the corresponding accident are determined.

[0148] Step C62, based on the starting point and end point of the initial target path, the road type determined in step 112 and the average driving speed of the driver of the corresponding road type and the starting time of the starting point transportation, calculate and determine the time for the vehicle to arrive at the corresponding accident location.

[0149] Step C63: If it is determined that the time when the vehicle arrives at the accident site is earlier than the time when the accident occurred, the transport path planning module 20 and the accident situation analysis module 30 are used to optimize the path and thereby obtain the target path.

[0150] In the process of planning each target path, this embodiment determines whether the time when a major accident or a serious accident occurs is earlier than the arrival time based on the driver's driving speed, so as to determine whether the path needs to be replanned, so that the optimization conditions are minimized and optimized, making the planning process more accurate.

[0151] It should be noted that the device embodiments of the present invention are device embodiments corresponding one-to-one to the above-mentioned method embodiments. The specific operations of the processing steps of each module can be understood by referring to the description of the method embodiment, which will not be repeated here.

[0152] like Figure 7 As shown, the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, any one of the smart logistics transportation path optimization methods described in Embodiments 1 to 3 above is implemented.

[0153] The present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, any one of the smart logistics transportation path optimization methods described in Embodiments 1 to 3 above is implemented; or when the computer program is executed by a processor, any one of the smart logistics transportation path optimization methods described in Embodiments 1 to 3 above is implemented.

[0154] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0155] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0156] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and the contents not described in detail in the specification of the present invention belong to the common knowledge of those skilled in the art.

Claims

1. A smart logistics transportation path optimization method, characterized in that The following steps are involved: A1, Determine the transport vehicle: Determine the transport vehicle based on the cargo information and vehicle information to minimize the number of vehicles used; A2, transportation route planning: According to the cargo transportation starting point, end point, transfer station, preset transportation start time and cargo unloading / loading time of each transfer station, determine the initial target path so that the path between each point is the shortest, and estimate the transportation departure time and end time of each initial target path according to the initial target path, so as to obtain the initial transportation path and arrival time; A3, accident situation analysis: according to the departure time and end time of the initial target route, the historical traffic accident data of the initial target route in the corresponding time period is obtained, and the historical traffic accident data is input into the preset clustering algorithm for clustering analysis to obtain the accident information of the initial transport route, wherein the accident information includes the number of accidents occurring on the initial transport route; as well as A4, route optimization and adjustment: according to the analysis results of the accident situation analysis step, when the number of accidents on the initial transport path exceeds the first preset probability value, the initial transport path is abandoned and the transport path is replanned through the transport path planning step and the accident situation analysis step until the number of accidents on the transport path does not exceed the first preset probability value, thereby determining the final transport path and the arrival time of each station.

2. The intelligent logistics transportation path optimization method according to claim 1, characterized in that: The initial arrival time of each station is further estimated based on the driver information of the transport vehicle, which specifically includes the following steps: Obtain the driver's historical cargo transport data to determine the driver's average driving speed when driving the vehicle; and Based on the cargo transportation starting point, end point, transfer site, preset starting point transportation start time, cargo unloading / loading time at each transfer site and the average driving speed of the driver, the shortest initial target path between each point is determined, and the departure time and end time of each initial target path transportation are estimated to obtain the initial transportation path.

3. The intelligent logistics transportation path optimization method according to claim 1, characterized in that: The initial arrival time of each station is further estimated based on the driver information of the transport vehicle, which specifically includes the following steps: Acquire driving data of various types of roads during the driver's historical transportation process, and determine the driver's average driving speed on various types of roads, wherein the road type is a corresponding road classification category and includes expressways, urban roads, national roads, provincial roads, and rural roads; and According to the starting point, end point, transfer site, preset transportation start time, and cargo unloading / loading time of each transfer site, the shortest initial target path between each point is determined, and according to the road type of each initial target path and the average driving speed of the driver on each type of road, the departure time and end time of each initial target path are estimated to obtain the initial transportation path.

4. The intelligent logistics transportation path optimization method according to claim 3, characterized in that: The accident information also includes the accident location and time of occurrence, and the path optimization and adjustment step also includes: According to the accident information determined in step A3, if the number of accidents on the initial transport path exceeds a first preset probability value, then the corresponding accident locations and occurrence times are determined; Calculate and determine the time when the vehicle arrives at the corresponding accident point based on the starting point of the initial transport route, the determined road type, the average driving speed of the drivers on the corresponding road type, and the departure time of the initial target route transport; and If the time when the vehicle arrives at the corresponding accident point is earlier than the time when the accident occurred, the accident is not accumulated as the number of accident occurrences. If it is determined that the number of accident occurrences still exceeds the first preset probability value, the path optimization adjustment is implemented through steps A2 to A4 to obtain the transportation path.

5. The intelligent logistics transportation path optimization method according to claim 3, characterized in that: The accident information also includes the accident location, the time of occurrence and the time when the accident handling is completed, and the path optimization and adjustment step also includes: According to the accident information determined in step A3, if the number of accidents on the initial transport path exceeds a first preset probability value, then the corresponding accident locations, occurrence times, and accident handling completion times are determined; Calculate and determine the time for the vehicle to arrive at the corresponding accident location based on the starting point of the initial transportation route, the determined road type, the average driving speed of drivers on the corresponding road type, and the departure time of the initial target route transportation; and For an accident in which the time when the vehicle arrives at the corresponding accident point is earlier than the time when the accident handling is completed, the accident is not accumulated as the number of accident occurrences. If the number of accident occurrences still exceeds the first preset probability value, the path optimization adjustment is implemented through steps A2 to A4 to obtain the transportation path.

6. A smart logistics transportation path optimization method, characterized in that The following steps are involved: B1, Determine the transport vehicle: Determine the transport vehicle based on the cargo information and vehicle information to minimize the number of vehicles used; B2, transportation route planning: According to the cargo transportation starting point, end point, transfer station, preset transportation start time and cargo unloading / loading time of each transfer station, determine the initial target path so that the path between each point is the shortest, and estimate the transportation departure time and end time of each initial target path according to the initial target path, so as to obtain the initial transportation path and arrival time; B3, accident situation analysis: according to the departure time and end time of the initial target route, the historical traffic accident data of the initial target route in the corresponding time period is obtained, and the historical traffic accident data is input into the clustering algorithm for clustering analysis to obtain the accident information, wherein the accident information includes the accident level, and the accident level includes minor accident, general accident, major accident and serious accident; as well as B4, route optimization and adjustment: Based on the analysis results of the accident situation analysis step, if a major accident or a serious accident occurs on the initial target path within the corresponding time period determined based on step B3, the initial target path is abandoned, and the replacement target path is replanned through steps B2-B3 until no major accident or serious accident occurs within the corresponding time period of the replacement target path, thereby determining the target path, the final transportation path and the arrival time of each station.

7. A smart logistics transportation path optimization method, characterized in that The following steps are involved: C1, transport vehicle determination: Determine the transport vehicle based on the cargo information and vehicle information to minimize the number of vehicles used; C2, transportation route planning: According to the starting point, end point, transfer station, preset transportation start time and cargo unloading / loading time of each transfer station, determine the initial target path so that the path between each point is the shortest, and estimate the departure time and end time of each initial target path according to the initial target path, so as to obtain the initial transportation path and arrival time; C3, accident situation analysis: according to the departure time and end time of the initial target route transportation, the historical traffic accident data of the initial target route in the corresponding time period is obtained, and the historical traffic accident data is input into the preset clustering algorithm for clustering analysis to obtain the accident information, wherein the accident information includes the probability of accident occurrence; as well as C4, path optimization and adjustment: According to the analysis results of the accident situation analysis step, if the probability of an accident occurring on the initial target path in the corresponding time period determined based on step C3 is greater than the preset accident probability threshold, the initial target path is abandoned, and the replacement target path is replanned through steps C2-C3 until the probability of an accident occurring on the replacement target path in the corresponding time period is not greater than the preset accident probability threshold, and the target path, final transportation path and arrival time of each station are obtained.

8. A smart logistics transportation route optimization device, characterized in that include: The transport vehicle determination module is used to determine the transport vehicle according to the cargo information and vehicle information so as to minimize the number of vehicles used; The transportation route planning module is used to determine the initial target route so that the route between each point is the shortest according to the starting point, end point, transfer station, preset transportation start time and cargo unloading / loading time of each transfer station, and estimate the departure time and end time of each initial target route according to the initial target route, so as to obtain the initial transportation route and arrival time; The accident situation analysis module is used to obtain the historical traffic accident data of the initial target path in the corresponding time period according to the departure time and end time of the initial target path transportation, and input the historical traffic accident data into a preset clustering algorithm for clustering analysis to obtain the accident information of the initial transportation path, wherein the accident information includes the number of accidents occurring on the initial transportation path; The first path optimization and adjustment module is used to abandon the initial transportation path and re-plan the transportation path through the transportation path planning module and the accident situation analysis module according to the analysis results of the accident situation analysis module until the number of accidents on the initial transportation path does not exceed the first preset probability value, thereby determining the final transportation path and the arrival time of each station.

9. A smart logistics transportation route optimization device, characterized in that include: The transport vehicle determination module is used to determine the transport vehicle according to the cargo information and vehicle information so as to minimize the number of vehicles used; The transportation route planning module is used to determine the initial target route so that the route between each point is the shortest according to the starting point, end point, transfer station, preset transportation start time and cargo unloading / loading time of each transfer station, and estimate the departure time and end time of each initial target route according to the initial target route, so as to obtain the initial transportation route and arrival time; The accident situation analysis module is used to obtain the historical traffic accident data of the initial target path within the corresponding time period according to the departure time and end time of the initial target path transportation, and input the historical traffic accident data into the clustering algorithm for clustering analysis to obtain the accident information, wherein the accident information includes the accident level, and the accident level includes minor accident, general accident, major accident and serious accident; as well as The second path optimization and adjustment module is used to abandon the initial target path according to the analysis results of the accident situation analysis module when a major accident or serious accident occurs on the initial target path within the corresponding time period, and re-plan the replacement target path through the transportation path planning module and the accident situation analysis module until no major accident or serious accident occurs on the replacement target path within the corresponding time period, thereby determining the target path, the final transportation path and the arrival time of each station.

10. A smart logistics transportation route optimization device, characterized in that include: The transport vehicle determination module is used to determine the transport vehicle according to the cargo information and vehicle information so as to minimize the number of vehicles used; The transport route planning module is used to determine the initial target route so that the route between each point is the shortest according to the starting point, end point, transfer station, preset transport start time and cargo unloading / loading time of each transfer station, and estimate the initial arrival time and departure time of vehicles at each station according to the initial target route, so as to obtain the initial transport route and arrival time; The accident situation analysis module is used to obtain the historical traffic accident data of the initial target path within the corresponding time period according to the departure time and end time of the initial target path transportation, and input the historical traffic accident data into the preset clustering algorithm for clustering analysis to obtain accident information, wherein the accident information includes the probability of accident occurrence; The third path optimization and adjustment module, based on the analysis results of the accident situation analysis module, if the probability of an accident occurring on the initial target path within the corresponding time period is greater than the preset accident probability threshold, then the initial target path is abandoned, and the replacement target path is replanned through steps C2-C3 until the probability of an accident occurring on the replacement target path within the corresponding time period is not greater than the preset accident probability threshold, thereby obtaining the target path, the final transportation path and the arrival time of each station.

11. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the intelligent logistics transportation path optimization method as described in any one of claims 1 to 7 is implemented.

12. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the intelligent logistics transportation path optimization method as described in any one of claims 1 to 7 is implemented.

Images