Logistics distribution route planning method and system based on big data analysis

Abstract

The invention relates to the technical field of intelligent logistics, and discloses a logistics distribution route planning method and system based on big data analysis, and the method comprises the steps: constructing a logistics vertex map based on Q logistics connection points and an initial planning route, determining W intermediate planning routes based on the logistics vertex map, and determining a logistics distribution route based on the W intermediate planning routes; the method comprises the following steps of: selecting W intermediate planning paths according to distribution demand information, screening out P target planning paths from the W intermediate planning paths according to the distribution demand information, calculating a passenger-carrying completion degree value and a distribution completion degree value corresponding to each target planning path, and finally optimizing the P target planning paths based on the passenger-carrying completion degree values, the distribution completion degree values and a preset intelligent optimization algorithm. According to the method, the rural passenger vehicles and the logistics distribution are combined, the optimal path is screened out based on the logistics vertex map and the distribution demand information, and comprehensive evaluation is performed through the passenger-carrying completion degree value and the distribution completion degree value, so that the accuracy of path planning and the resource utilization efficiency are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of smart logistics technology, and more specifically, to a logistics distribution route planning method and system based on big data analysis. Background Art

[0002] With the vigorous development of the e-commerce industry, its influence and coverage continue to expand. Due to the convenience of online shopping and the attractiveness of prices, the consumer group of online shopping is not limited to urban residents. The shopping needs and consumption willingness of rural residents are also gradually increasing, which makes the closeness of rural logistics and residents' lives continue to deepen. However, many rural areas are still facing problems such as poor service quality, high distribution costs, low efficiency and lagging information level, which makes the "last mile" distribution a prominent problem in rural logistics. Although some technologies have been tried to manage and optimize rural logistics, there are still many challenges.

[0003] For example, the Chinese patent application with publication number CN116258429A provides a vehicle-cargo matching method for rural logistics terminal delivery. The application obtains the information of delivery personnel and goods, publishes tasks and enables delivery personnel to grab orders, screens qualified carriers and builds a vehicle-cargo matching model, and uses the GA-C algorithm to optimize the objective function, ultimately achieving the vehicle-cargo matching result with the lowest delivery cost.

[0004] Although existing technologies have attempted to optimize the delivery routes of rural logistics through algorithms, they still rely on specialized delivery vehicles and logistics personnel. No matter how they are optimized, it is still difficult to solve the problems of high delivery costs and low efficiency. In addition, existing technologies rarely involve innovative ways to combine passenger vehicles in rural areas with logistics distribution, resulting in the inability to effectively improve the flexibility and delivery efficiency of rural logistics.

[0005] In view of this, the present invention proposes a logistics distribution route planning method and system based on big data analysis to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a logistics distribution route planning method and system based on big data analysis.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] First, a logistics distribution route planning method based on big data analysis is provided, including:

[0009] Obtain Q logistics connection points in the area to be delivered, and obtain the initial planned path of the vehicle to be delivered, build a logistics vertex graph based on the Q logistics connection points and the initial planned path, and determine W intermediate planned paths based on the logistics vertex graph, wherein the vehicle to be delivered is a passenger vehicle in the area to be delivered, and the initial planned path is a passenger path in the area to be delivered;

[0010] Obtain the delivery demand information of the area to be delivered, select P target planning paths from W intermediate planning paths according to the delivery demand information, and calculate the passenger completion value and delivery completion value corresponding to each target planning path, where P≤W;

[0011] Based on the passenger completion value, delivery completion value, and the preset intelligent optimization algorithm, P target planning paths are optimized to obtain the optimal planning path.

[0012] Furthermore, the method for constructing a logistics vertex graph based on Q logistics connection points and the initial planning path includes:

[0013] The average passenger flow corresponding to Q logistics connection points is obtained, and the Q logistics connection points are used as vertices of the logistics vertex graph. The path distance and target passenger flow between two adjacent logistics connection points are determined, and the inverse of the target passenger flow and the path distance are weighted and summed to obtain the path weight value. The path weight value is used as the weight of the edge between two adjacent logistics connection points to construct a logistics vertex graph. The target passenger flow is the sum of the average passenger flow between two adjacent logistics connection points.

[0014] Furthermore, the method for determining W intermediate planning paths based on the logistics vertex graph includes:

[0015] Obtain the total number of edges corresponding to the logistics vertex graph, determine the corresponding path search algorithm based on the total number of edges, determine the planned path set corresponding to the logistics vertex graph based on the path search algorithm, and use the first W to-be-selected planned paths in the planned path set as W intermediate planned paths. The to-be-selected planned paths in the planned path set are arranged in descending order according to the sum of the path weight values.

[0016] Furthermore, the method of selecting P target planning paths from W intermediate planning paths according to the distribution demand information includes:

[0017] The delivery quantity corresponding to each logistics connection point is determined according to the delivery demand information, and the actual delivery number corresponding to each intermediate planning path is calculated according to the delivery quantity. The intermediate planning paths whose actual delivery number is less than the preset delivery number threshold are eliminated to screen out P target planning paths.

[0018] Furthermore, the method for calculating the delivery completion value corresponding to each target planning path includes:

[0019] Calculate the sum of the delivery quantities corresponding to each logistics connection point to obtain the total number of deliveries, calculate the ratio of the actual number of deliveries corresponding to each target planning path to the total number of deliveries to obtain the actual delivery ratio, and use the actual delivery ratio as the delivery completion value corresponding to each target planning path.

[0020] Furthermore, the method for calculating the passenger completion value corresponding to each target planning path includes:

[0021] Predict the future passenger flow corresponding to each logistics connection point, calculate the sum of the future passenger flow of all predicted logistics connection points, obtain the total passenger flow, and calculate the actual passenger flow corresponding to each target planning path, calculate the ratio of the actual passenger flow corresponding to each target planning path to the total passenger flow, and obtain the actual passenger load ratio. The actual passenger load ratio is used as the passenger load completion value corresponding to each target planning path. The actual passenger flow is the sum of the future actual passenger flow of the logistics connection points in the target planning path.

[0022] Furthermore, the method for predicting the future passenger flow corresponding to each logistics connection point includes:

[0023] The arrival time period corresponding to the logistics connection point is obtained, and the arrival time period is input into the pre-built passenger flow prediction model to obtain the corresponding future passenger flow. The arrival time period is the time period for passenger vehicles to arrive at the logistics connection point.

[0024] Furthermore, the intelligent optimization algorithm is a genetic algorithm, and the method for obtaining the optimal planning path includes:

[0025] S301: Taking P target planning paths as the initial population, and taking the inverse of the sum of the passenger completion value and the delivery completion value as the fitness function, the fitness value of each individual in the population is calculated;

[0026] S302: Adopting the tournament selection strategy, randomly select 4 individuals from the population, compare the fitness values ​​between the individuals, and select the individual with the smallest fitness value as the parent individual;

[0027] S303: Repeat the selection process of S302 until N parent individuals are selected, and then proceed to S304;

[0028] S304: Select a crossover point on the path of each pair of parent individuals, use the single-point crossover method to operate on all parent individuals, exchange the parts of the parent individuals after the crossover point, and generate two new child individuals;

[0029] S305: Randomly select two nodes for each child individual and exchange the positions of the two nodes, form a new population with all the child individuals, and replace the original population to ensure that the size of the new population is still N;

[0030] S306: The convergence threshold of the preset fitness value is CT. If the fitness value of the best individual in the population of consecutive K generations changes less than CT, the genetic algorithm terminates. When the algorithm terminates, the sub-individual with the smallest fitness value in the population is the optimal planning path.

[0031] In a second aspect, a logistics distribution route planning system based on big data analysis is provided, which is used to implement the above-mentioned logistics distribution route planning method based on big data analysis, including:

[0032] Path planning module: used to obtain Q logistics connection points in the area to be delivered, and to obtain the initial planned path of the vehicle to be delivered, to build a logistics vertex graph based on the Q logistics connection points and the initial planned path, and to determine W intermediate planned paths based on the logistics vertex graph. The vehicle to be delivered is a passenger vehicle in the area to be delivered, and the initial planned path is a passenger path in the area to be delivered;

[0033] Path screening module: used to obtain the delivery demand information of the delivery area, screen P target planning paths from W intermediate planning paths according to the delivery demand information, and calculate the passenger completion value and delivery completion value corresponding to each target planning path, where P≤W;

[0034] Path optimization module: used to optimize P target planning paths based on passenger completion value, delivery completion value, and preset intelligent optimization algorithm to obtain the optimal planning path.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] The present invention first constructs a logistics vertex graph based on Q logistics connection points and an initial planned path, determines W intermediate planned paths based on the logistics vertex graph, then obtains the distribution demand information of the area to be distributed, and selects P target planned paths from the W intermediate planned paths according to the distribution demand information, calculates the passenger completion value and the distribution completion value corresponding to each target planned path, and finally optimizes the P target planned paths based on the passenger completion value, the distribution completion value, and a preset intelligent optimization algorithm to obtain the optimal planned path. The present invention combines rural passenger vehicles with logistics distribution, selects the optimal path based on the logistics vertex graph and distribution demand information, and conducts a comprehensive evaluation through the passenger completion value and the distribution completion value, and then uses the intelligent optimization algorithm to optimize the path, thereby effectively improving the accuracy of path planning and the efficiency of resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a flow chart of the logistics distribution route planning method based on big data analysis in the present invention;

[0038] Figure 2It is a structural schematic diagram of the logistics distribution route planning system based on big data analysis in the present invention;

[0039] Figure 3 A schematic diagram of the initial planned path, fixed sites and road nodes in the present invention;

[0040] Figure 4 It is a flowchart of the method for determining W intermediate planning paths based on the logistics vertex graph in the present invention. DETAILED DESCRIPTION

[0041] 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.

[0042] Example 1

[0043] See also Figure 1 As shown, this embodiment discloses a logistics distribution route planning method based on big data analysis, including:

[0044] S10: obtaining Q logistics connection points in the area to be delivered, and obtaining the initial planned path of the vehicle to be delivered, constructing a logistics vertex graph based on the Q logistics connection points and the initial planned path, and determining W intermediate planned paths based on the logistics vertex graph, wherein the vehicle to be delivered is a passenger vehicle in the area to be delivered, and the initial planned path is a passenger path in the area to be delivered;

[0045] In this embodiment, the area to be delivered refers to the rural area or township area where logistics delivery is required, and the vehicle to be delivered is a passenger vehicle in the area to be delivered. The passenger vehicle can be a bus. It can be understood that for most residents in rural areas of my country, public transportation is the main mode of transportation. However, due to the spatial and temporal uncertainty and dispersion of rural residents' travel needs, rural passenger services cannot obtain stable economic returns and are difficult to operate. Therefore, in this embodiment, rural passenger transportation is combined with rural logistics, which effectively utilizes the transportation capacity of rural passenger vehicles, reduces the vehicle investment cost of logistics distribution, and improves the utilization efficiency of rural passenger vehicles, providing additional economic benefits for its operation. By integrating passenger and logistics resources, the flexibility and economy of logistics distribution can be improved while meeting the travel needs of rural residents.

[0046] It should be noted that the logistics connection point can be a fixed station where passenger vehicles stop during driving, or it can be an important road node for rural residents to travel. For example, Figure 3 As shown, Figure 3 The initial planned path 10, the first fixed site 20, the second fixed site 30, the third fixed site 40, the fourth fixed site 50 and the fifth fixed site 60 are shown. Figure 3 Also shown are the first road node 21 and the second road node 41, etc. Figure 3 It can be seen that, taking the first fixed station 20 as an example, when the passenger vehicle travels along the initial planned path 10, there will be two path choices when it arrives at the first fixed station 20. The first is to continue along the initial planned path 10 and arrive at the second fixed station 30. The second is to first arrive at the first road node 21 and then go to the second fixed station 30. It can be understood that when the express delivery demand of residents near the first road node 21 is large, the second path should be selected.

[0047] In some optional embodiments, Q logistics connection points can be pre-set according to demand. For example, each fixed site is first set as a logistics connection point, or each fixed site is set as a logistics connection point at intervals. The fixed sites set as logistics connection points are marked, and the road nodes near the marked fixed sites are determined. According to the distance or delivery demand, the road nodes near the fixed sites are set as logistics connection points.

[0048] The method of constructing a logistics vertex graph based on Q logistics connection points and the initial planning path includes:

[0049] The average passenger flow corresponding to Q logistics connection points is obtained, and the Q logistics connection points are used as vertices of the logistics vertex graph. The path distance and target passenger flow between two adjacent logistics connection points are determined, and the inverse of the target passenger flow and the path distance are weighted and summed to obtain the path weight value. The path weight value is used as the weight of the edge between two adjacent logistics connection points to construct a logistics vertex graph. The target passenger flow is the sum of the average passenger flow between two adjacent logistics connection points.

[0050] It should be noted that the average passenger flow corresponding to a logistics connection point refers to the average number of passengers carried by passenger vehicles passing through the logistics connection point within a specific time period. The average passenger flow reflects the degree of passenger demand at the logistics connection point and is one of the important parameters for measuring the importance of the site and the path weight. It can be understood that although the road node is not a major fixed passenger site, the passenger flow of the road node can be estimated through the passenger flow correlation relationship with the fixed site and the logistics distribution demand. For example, the passenger flow between the road node and the adjacent fixed site has a certain correlation. The average passenger flow of the fixed site can be proportionally allocated to infer the potential passenger flow of the road node. Of course, data can also be collected in advance through experiments, and this embodiment will not go into details.

[0051] like Figure 4 As shown, the method for determining W intermediate planning paths based on the logistics vertex graph includes:

[0052] Obtain the total number of edges corresponding to the logistics vertex graph, determine the corresponding path search algorithm based on the total number of edges, determine the planned path set corresponding to the logistics vertex graph based on the path search algorithm, and use the first W to-be-selected planned paths in the planned path set as W intermediate planned paths. The to-be-selected planned paths in the planned path set are arranged in descending order according to the sum of the path weight values.

[0053] It should be noted that the total number of edges refers to the number of edges between all adjacent logistics connection points in the logistics vertex graph. The path search algorithm takes the Dijkstra algorithm and the A* algorithm as examples. When the total number of edges is less than the preset edge number threshold, the Dijkstra algorithm is selected. On the contrary, when the total number of edges is not less than the preset edge number threshold, the A* algorithm should be selected. The purpose of this selection is to improve the computational efficiency of path search while ensuring the accuracy of path search results, and to adapt to logistics vertex graphs of different sizes. It can be understood that in small-scale graphs, the computational complexity of the Dijkstra algorithm is low and it can run efficiently. In large-scale graphs, the A* algorithm has more advantages than the Dijkstra algorithm because it can reduce the search time while ensuring that the results are close to the optimal.

[0054] It should be added that each of the above-mentioned candidate planning paths corresponds to a sum of path weight values, and the sum of path weight values ​​refers to the sum of the weight values ​​of all edges on the candidate planning path, that is, the cumulative sum of the weight values ​​of the edges between all adjacent logistics connection points passed by the path.

[0055] In this embodiment, by gradually constructing a vertex graph, flexibly selecting a path search algorithm, and optimizing the screening path with weight values, the computational efficiency, path planning accuracy, and resource utilization of rural logistics distribution are effectively improved, meeting the actual application environment of combining rural regional logistics with passenger transportation.

[0056] S20: Obtaining the delivery demand information of the area to be delivered, selecting P target planning paths from W intermediate planning paths according to the delivery demand information, and calculating the passenger completion value and the delivery completion value corresponding to each target planning path, where P≤W;

[0057] In this embodiment, the delivery demand information includes at least demand location information and delivery time information. The demand location information refers to the goods delivery location information specified by the user, and the delivery time information refers to the time window specified by the user within which the goods need to be delivered. For example, the user can specify the logistics connection point closest to him / her as the demand location information.

[0058] Methods for selecting P target planning paths from W intermediate planning paths according to distribution demand information include:

[0059] The delivery quantity corresponding to each logistics connection point is determined according to the delivery demand information, and the actual delivery number corresponding to each intermediate planning path is calculated according to the delivery quantity. The intermediate planning paths whose actual delivery number is less than the preset delivery number threshold are eliminated to screen out P target planning paths.

[0060] It can be understood that the present application first determines the delivery quantity corresponding to each logistics connection point based on the demand location information and delivery time information in the delivery demand information. The delivery quantity refers to the quantity of goods that need to be delivered when the bus arrives at the logistics connection point in each transportation mission. For example, the quantity of goods that need to be delivered to the logistics connection point within the specified time in each transportation mission can be determined according to the bus schedule and the delivery time window.

[0061] The method for calculating the delivery completion value corresponding to each target planning path includes:

[0062] Calculate the sum of the delivery quantities corresponding to each logistics connection point to obtain the total number of deliveries, calculate the ratio of the actual number of deliveries corresponding to each target planning path to the total number of deliveries to obtain the actual delivery ratio, and use the actual delivery ratio as the delivery completion value corresponding to each target planning path.

[0063] It should be noted that in each transportation mission, the bus will only deliver goods according to one target planned path. Therefore, there may be a situation where the actual number of deliveries is less than the total number of deliveries. The ratio of the actual number of deliveries to the total number of deliveries is used to measure the delivery completion of the current target planned path, which reflects the path execution effect. The larger the delivery completion value, the closer the current target planned path is to meeting the delivery needs, and the better the overall execution effect.

[0064] The method for calculating the passenger completion value corresponding to each target planning path includes:

[0065] Predict the future passenger flow corresponding to each logistics connection point, calculate the sum of the future passenger flow of all predicted logistics connection points, obtain the total passenger flow, and calculate the actual passenger flow corresponding to each target planning path, calculate the ratio of the actual passenger flow corresponding to each target planning path to the total passenger flow, and obtain the actual passenger load ratio. The actual passenger load ratio is used as the passenger load completion value corresponding to each target planning path. The actual passenger flow is the sum of the future actual passenger flow of the logistics connection points in the target planning path.

[0066] Methods for predicting future passenger flow at each logistics connection point include:

[0067] The arrival time period corresponding to the logistics connection point is obtained, and the arrival time period is input into the pre-built passenger flow prediction model to obtain the corresponding future passenger flow. The arrival time period is the time period for passenger vehicles to arrive at the logistics connection point.

[0068] The construction method of the passenger flow prediction model includes:

[0069] Obtain a training set, which includes historical arrival time periods and historical passenger flow, preset sliding steps and sliding window lengths; convert the training set into multiple training samples using a sliding window method, use the training samples as input of a regressor, predict the historical passenger flow after the sliding step as output, use the subsequent historical passenger flow of each training sample as a prediction target, and use the prediction accuracy as a training target to train the regressor; generate a passenger flow prediction model that predicts future passenger flow based on the arrival time period, wherein the regressor is an LSTM model;

[0070] It should be noted that the sliding window method is a conventional technical means of the LSTM model, and the present invention will not be further explained in principle here; however, in order to facilitate the implementation of the present invention, the present invention provides the following example of the sliding window method:

[0071] Assume that we want to use historical data [1,2,3,4,5,6] to train an LSTM model. In this embodiment, we take the prediction time step as 1 as an example, set the sliding step to 1, and set the sliding window length to 3; then three groups of training samples and corresponding prediction target data are generated: [1,2,3], [2,3,4], and [3,4,5] as training samples, and [4], [5], and [6] as prediction targets respectively;

[0072] The prediction accuracy can be measured using mean square error or mean absolute error as the loss function, and the weights and biases of the model are updated through the back-propagation algorithm to generate a passenger flow prediction model.

[0073] In this embodiment, W intermediate planning paths are first determined through path construction and weight screening, and then P target planning paths are further screened out through actual distribution demand information, ultimately achieving accuracy, practicality and resource optimization in path planning, which is in line with the actual application environment of combining rural logistics with passenger transport.

[0074] S30: Optimize P target planning paths based on the passenger completion value, the delivery completion value, and a preset intelligent optimization algorithm to obtain the optimal planning path.

[0075] The preset intelligent optimization algorithm may be a genetic algorithm, and the method for obtaining the optimal planning path includes:

[0076] S301: Taking P target planning paths as the initial population, and taking the inverse of the sum of the passenger completion value and the delivery completion value as the fitness function, the fitness value of each individual in the population is calculated;

[0077] It should be noted that, in this embodiment, the P target planning paths obtained by screening are used as the initial population of the genetic algorithm to ensure that the initial solution of the algorithm has a certain feasibility, and the "inverse of the sum of the passenger completion value and the delivery completion value" is used as the fitness function to measure the quality of each target planning path. The smaller the fitness value, the higher the passenger completion and delivery completion of the target planning path.

[0078] S302: Adopting the tournament selection strategy, randomly select 4 individuals from the population, compare the fitness values ​​between the individuals, and select the individual with the smallest fitness value as the parent individual;

[0079] Among them, through the tournament selection strategy, excellent individuals with smaller fitness values ​​are retained, ensuring that individuals with higher fitness have a better chance of passing their characteristics to the next generation.

[0080] S303: Repeat the selection process of S302 until N parent individuals are selected, and then proceed to S304;

[0081] S304: Select a crossover point on the path of each pair of parent individuals, use the single-point crossover method to operate on all parent individuals, exchange the parts of the parent individuals after the crossover point, and generate two new child individuals;

[0082] Among them, this embodiment reorganizes some characteristics of parent individuals through a single-point crossover operation to generate child individuals with new path characteristics, thereby increasing the diversity of the population.

[0083] S305: Randomly select two nodes for each child individual and exchange the positions of the two nodes, form a new population with all the child individuals, and replace the original population to ensure that the size of the new population is still N;

[0084] S306: The convergence threshold of the preset fitness value is CT. If the fitness value of the best individual in the population of consecutive K generations changes less than CT, the genetic algorithm terminates. When the algorithm terminates, the sub-individual with the smallest fitness value in the population is the optimal planning path.

[0085] This embodiment first constructs a logistics vertex graph based on Q logistics connection points and the initial planned path, determines W intermediate planned paths based on the logistics vertex graph, then obtains the distribution demand information of the area to be distributed, and selects P target planned paths from the W intermediate planned paths according to the distribution demand information, calculates the passenger completion value and the delivery completion value corresponding to each target planned path, and finally optimizes the P target planned paths based on the passenger completion value, the delivery completion value, and the preset intelligent optimization algorithm to obtain the optimal planned path. This embodiment combines rural passenger vehicles with logistics distribution, selects the optimal path based on the logistics vertex graph and distribution demand information, and conducts a comprehensive evaluation through the passenger completion value and the delivery completion value, and then uses the intelligent optimization algorithm to optimize the path, thereby effectively improving the accuracy of path planning and the efficiency of resource utilization.

[0086] Example 2

[0087] See also Figure 2 As shown, based on the same inventive concept, this embodiment discloses a logistics distribution route planning system based on big data analysis. For details not provided in this embodiment, please refer to the description of the relevant parts in Embodiment 1. The system includes:

[0088] Path planning module: used to obtain Q logistics connection points in the area to be delivered, and to obtain the initial planned path of the vehicle to be delivered, to build a logistics vertex graph based on the Q logistics connection points and the initial planned path, and to determine W intermediate planned paths based on the logistics vertex graph. The vehicle to be delivered is a passenger vehicle in the area to be delivered, and the initial planned path is a passenger path in the area to be delivered;

[0089] In this embodiment, the area to be delivered refers to the rural area or township area where logistics delivery is required, and the vehicle to be delivered is a passenger vehicle in the area to be delivered. The passenger vehicle can be a bus. It can be understood that for most residents in rural areas of my country, public transportation is the main mode of transportation. However, due to the spatial and temporal uncertainty and dispersion of rural residents' travel needs, rural passenger services cannot obtain stable economic returns and are difficult to operate. Therefore, in this embodiment, rural passenger transportation is combined with rural logistics, which effectively utilizes the transportation capacity of rural passenger vehicles, reduces the vehicle investment cost of logistics distribution, and improves the utilization efficiency of rural passenger vehicles, providing additional economic benefits for its operation. By integrating passenger and logistics resources, the flexibility and economy of logistics distribution can be improved while meeting the travel needs of rural residents.

[0090] The method of constructing a logistics vertex graph based on Q logistics connection points and the initial planning path includes:

[0091] The average passenger flow corresponding to Q logistics connection points is obtained, and the Q logistics connection points are used as vertices of the logistics vertex graph. The path distance and target passenger flow between two adjacent logistics connection points are determined, and the inverse of the target passenger flow and the path distance are weighted and summed to obtain the path weight value. The path weight value is used as the weight of the edge between two adjacent logistics connection points to construct a logistics vertex graph. The target passenger flow is the sum of the average passenger flow between two adjacent logistics connection points.

[0092] The method for determining W intermediate planning paths based on the logistics vertex graph includes:

[0093] Obtain the total number of edges corresponding to the logistics vertex graph, determine the corresponding path search algorithm based on the total number of edges, determine the planned path set corresponding to the logistics vertex graph based on the path search algorithm, and use the first W to-be-selected planned paths in the planned path set as W intermediate planned paths. The to-be-selected planned paths in the planned path set are arranged in descending order according to the sum of the path weight values.

[0094] Path screening module: used to obtain the delivery demand information of the delivery area, screen P target planning paths from W intermediate planning paths according to the delivery demand information, and calculate the passenger completion value and delivery completion value corresponding to each target planning path, where P≤W;

[0095] In this embodiment, the delivery demand information includes at least demand location information and delivery time information. The demand location information refers to the goods delivery location information specified by the user, and the delivery time information refers to the time window specified by the user within which the goods need to be delivered. For example, the user can specify the logistics connection point closest to him / her as the demand location information.

[0096] Methods for selecting P target planning paths from W intermediate planning paths according to distribution demand information include:

[0097] The delivery quantity corresponding to each logistics connection point is determined according to the delivery demand information, and the actual delivery number corresponding to each intermediate planning path is calculated according to the delivery quantity. The intermediate planning paths whose actual delivery number is less than the preset delivery number threshold are eliminated to screen out P target planning paths.

[0098] The method for calculating the delivery completion value corresponding to each target planning path includes:

[0099] Calculate the sum of the delivery quantities corresponding to each logistics connection point to obtain the total number of deliveries, calculate the ratio of the actual number of deliveries corresponding to each target planning path to the total number of deliveries to obtain the actual delivery ratio, and use the actual delivery ratio as the delivery completion value corresponding to each target planning path.

[0100] The method for calculating the passenger completion value corresponding to each target planning path includes:

[0101] Predict the future passenger flow corresponding to each logistics connection point, calculate the sum of the future passenger flow of all predicted logistics connection points, obtain the total passenger flow, and calculate the actual passenger flow corresponding to each target planning path, calculate the ratio of the actual passenger flow corresponding to each target planning path to the total passenger flow, and obtain the actual passenger load ratio. The actual passenger load ratio is used as the passenger load completion value corresponding to each target planning path. The actual passenger flow is the sum of the future actual passenger flow of the logistics connection points in the target planning path.

[0102] Methods for predicting future passenger flow at each logistics connection point include:

[0103] The arrival time period corresponding to the logistics connection point is obtained, and the arrival time period is input into the pre-built passenger flow prediction model to obtain the corresponding future passenger flow. The arrival time period is the time period for passenger vehicles to arrive at the logistics connection point.

[0104] Path optimization module: used to optimize P target planning paths based on passenger completion value, delivery completion value, and preset intelligent optimization algorithm to obtain the optimal planning path.

[0105] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0106] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD) or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0107] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0108] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0109] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0110] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0111] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0112] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

[0113] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A logistics distribution route planning method based on big data analysis, characterized in that: include: Obtain Q logistics connection points in the area to be delivered, and obtain the initial planned path of the vehicle to be delivered, build a logistics vertex graph based on the Q logistics connection points and the initial planned path, and determine W intermediate planned paths based on the logistics vertex graph, wherein the vehicle to be delivered is a passenger vehicle in the area to be delivered, and the initial planned path is a passenger path in the area to be delivered; Obtain the delivery demand information of the area to be delivered, select P target planning paths from W intermediate planning paths according to the delivery demand information, and calculate the passenger completion value and delivery completion value corresponding to each target planning path, where P≤W; Based on the passenger completion value, delivery completion value, and the preset intelligent optimization algorithm, P target planning paths are optimized to obtain the optimal planning path.

2. The logistics distribution route planning method based on big data analysis according to claim 1 is characterized in that: The method for constructing a logistics vertex graph based on Q logistics connection points and an initial planning path includes: The average passenger flow corresponding to Q logistics connection points is obtained, and the Q logistics connection points are used as vertices of the logistics vertex graph. The path distance and target passenger flow between two adjacent logistics connection points are determined, and the inverse of the target passenger flow and the path distance are weighted and summed to obtain the path weight value. The path weight value is used as the weight of the edge between two adjacent logistics connection points to construct a logistics vertex graph. The target passenger flow is the sum of the average passenger flow between two adjacent logistics connection points.

3. The logistics distribution route planning method based on big data analysis according to claim 2 is characterized in that: The method for determining W intermediate planning paths based on the logistics vertex graph includes: Obtain the total number of edges corresponding to the logistics vertex graph, determine the corresponding path search algorithm based on the total number of edges, determine the planned path set corresponding to the logistics vertex graph based on the path search algorithm, and use the first W to-be-selected planned paths in the planned path set as W intermediate planned paths. The to-be-selected planned paths in the planned path set are arranged in descending order according to the sum of the path weight values.

4. The logistics distribution route planning method based on big data analysis according to claim 3 is characterized in that: The method of selecting P target planning paths from W intermediate planning paths according to the distribution demand information includes: The delivery quantity corresponding to each logistics connection point is determined according to the delivery demand information, and the actual delivery number corresponding to each intermediate planning path is calculated according to the delivery quantity. The intermediate planning paths whose actual delivery number is less than the preset delivery number threshold are eliminated to screen out P target planning paths.

5. The logistics distribution route planning method based on big data analysis according to claim 4 is characterized in that: The method for calculating the delivery completion value corresponding to each target planning path includes: Calculate the sum of the delivery quantities corresponding to each logistics connection point to obtain the total number of deliveries, calculate the ratio of the actual number of deliveries corresponding to each target planning path to the total number of deliveries to obtain the actual delivery ratio, and use the actual delivery ratio as the delivery completion value corresponding to each target planning path.

6. The logistics distribution route planning method based on big data analysis according to claim 4 is characterized in that: The method for calculating the passenger completion value corresponding to each target planning path includes: Predict the future passenger flow corresponding to each logistics connection point, calculate the sum of the future passenger flow of all predicted logistics connection points, obtain the total passenger flow, and calculate the actual passenger flow corresponding to each target planning path, calculate the ratio of the actual passenger flow corresponding to each target planning path to the total passenger flow, and obtain the actual passenger load ratio. The actual passenger load ratio is used as the passenger load completion value corresponding to each target planning path. The actual passenger flow is the sum of the future actual passenger flow of the logistics connection points in the target planning path.

7. The logistics distribution route planning method based on big data analysis according to claim 6 is characterized in that: The method for predicting the future passenger flow corresponding to each logistics connection point includes: The arrival time period corresponding to the logistics connection point is obtained, and the arrival time period is input into the pre-built passenger flow prediction model to obtain the corresponding future passenger flow. The arrival time period is the time period for passenger vehicles to arrive at the logistics connection point.

8. The logistics distribution route planning method based on big data analysis according to claim 4 is characterized in that: The intelligent optimization algorithm is a genetic algorithm, and the method for obtaining the optimal planning path includes: S301: Taking P target planning paths as the initial population, and taking the inverse of the sum of the passenger completion value and the delivery completion value as the fitness function, the fitness value of each individual in the population is calculated; S302: Adopting the tournament selection strategy, randomly select 4 individuals from the population, compare the fitness values ​​between the individuals, and select the individual with the smallest fitness value as the parent individual; S303: Repeat the selection process of S302 until N parent individuals are selected, and then proceed to S304; S304: Select a crossover point on the path of each pair of parent individuals, use the single-point crossover method to operate on all parent individuals, exchange the parts of the parent individuals after the crossover point, and generate two new child individuals; S305: Randomly select two nodes for each child individual and exchange the positions of the two nodes, form a new population with all the child individuals, and replace the original population to ensure that the size of the new population is still N; S306: The convergence threshold of the preset fitness value is CT. If the fitness value of the best individual in the population of consecutive K generations changes less than CT, the genetic algorithm terminates. When the algorithm terminates, the sub-individual with the smallest fitness value in the population is the optimal planning path.

9. A logistics distribution route planning system based on big data analysis, which is used to implement the logistics distribution route planning method based on big data analysis as described in any one of claims 1 to 8, characterized in that: include: Path planning module: used to obtain Q logistics connection points in the area to be delivered, and to obtain the initial planned path of the vehicle to be delivered, to build a logistics vertex graph based on the Q logistics connection points and the initial planned path, and to determine W intermediate planned paths based on the logistics vertex graph. The vehicle to be delivered is a passenger vehicle in the area to be delivered, and the initial planned path is a passenger path in the area to be delivered; Path screening module: used to obtain the delivery demand information of the delivery area, screen P target planning paths from W intermediate planning paths according to the delivery demand information, and calculate the passenger completion value and delivery completion value corresponding to each target planning path, where P≤W; Path optimization module: used to optimize P target planning paths based on passenger completion value, delivery completion value, and preset intelligent optimization algorithm to obtain the optimal planning path.

Images