Cargo transportation path planning method and device, computer device and storage medium
By splitting and optimizing cargo order data, and combining route optimization algorithms and loading verification, an executable optimal transportation route was generated, solving the problem of route infeasibility in traditional methods and achieving more efficient route planning.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ZHEJIANG GEELY HLDG GRP CO LTD
- Filing Date
- 2026-03-20
- Publication Date
- 2026-06-16
Smart Images
Figure CN122222157A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of route optimization technology, and in particular to a method, apparatus, computer equipment, and storage medium for cargo transportation route planning. Background Technology
[0002] In the field of freight transportation, route planning is a key technology for optimizing transportation costs and improving efficiency. Its basic goal is to generate transportation route plans based on order data, while meeting physical constraints such as vehicle load capacity and volume.
[0003] Traditional route planning methods typically input raw order data directly into a route optimization algorithm, which then automatically combines orders and generates routes. However, traditional methods generally suffer from insufficient physical executability. When faced with scenarios where the total amount of goods from a single supplier exceeds the carrying capacity of a single vehicle, or when the combination of goods from multiple suppliers exceeds the vehicle's physical constraints, the algorithm cannot reasonably adjust and adapt the orders, resulting in the generated route plan being unexecutable in practice. Therefore, traditional methods struggle to guarantee the feasibility of the final solution. Summary of the Invention
[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, and storage medium for cargo transportation route planning that can achieve optimal route and feasible loading, in order to address the above-mentioned technical problems.
[0005] Firstly, this application provides a cargo transportation route planning method, including: Obtain the original order data, which includes pickup order data from at least one supplier, and the pickup order data includes goods information; The pickup order data to be split is determined based on the cargo information of at least one supplier and the loading capacity of the vehicle to be allocated, and the pickup order data to be split is split to determine the split order data of the original order data. An initial transportation plan is generated based on the split order data. The initial transportation plan includes a set of pickup routes, which includes the pickup routes from each supplier in the original order data. The initial transportation plan is iteratively processed according to a pre-set path optimization algorithm to obtain at least one candidate plan, which includes at least one candidate path. Loading verification is performed based on the loading capacity of the vehicle to be assigned and the cargo information corresponding to the candidate route; The planned cargo transportation route is determined based on the verified candidate solutions.
[0006] In one embodiment, the vehicles to be allocated include multiple vehicles. The pickup order data to be split is determined based on the cargo information of at least one supplier and the loading capacity of the vehicles to be allocated. The pickup order data to be split is then split to determine the split order data from the original order data, including: The baseline vehicle volume is determined based on the loading capacity of the vehicles to be allocated. The baseline vehicle volume is the largest loading capacity among the loading capacities of the vehicles to be allocated. Determine the total volume of goods from the current supplier based on the current supplier's goods information; If the total volume of goods from the current supplier exceeds the baseline vehicle capacity, the current supplier's pickup order data is determined as pickup order data to be split. The current supplier's pickup order data is split based on the baseline vehicle volume and the current supplier's total cargo volume; Each pickup order data to be split is split sequentially to determine the split order data from the original order data.
[0007] In one embodiment, the cargo transportation route planning method further includes: When the total volume of the current supplier's goods is less than or equal to the baseline vehicle volume, obtain the pre-set rotation strategy, which includes a state of rotating at a preset angle and a state of not rotating. Based on the baseline vehicle volume, the current supplier's cargo information is loaded and verified under various states of the rotation strategy. If the current supplier's goods information fails to be loaded and verified in all states of the rotation strategy, the current supplier's pickup order data is determined to be pickup order data to be split.
[0008] In one embodiment, before generating an initial transportation plan based on the split order data, the cargo transportation route planning method further includes: Extract the pickup time window corresponding to each pickup order in the split pickup order data; Retrieve pickup order data from the split pickup order data that belong to the same supplier and have overlapping pickup time windows, and merge them; When the total volume of goods corresponding to the merged pickup order data is less than or equal to the benchmark vehicle volume, the data after preprocessing the original order data is determined based on the merged pickup order data. An initial shipping plan is generated based on the split order data, including: An initial shipping plan is generated based on the preprocessed data from the original order data.
[0009] In one embodiment, the path optimization algorithm is a genetic algorithm, which iteratively operates on the initial transportation plan according to a pre-set path optimization algorithm to obtain at least one candidate plan, including: An initial population is constructed using an initial transportation scheme based on a genetic algorithm; The initial population is subjected to selection, crossover, and mutation operations to perform iterative operations and obtain a new population. The next iteration is performed on the new population until the maximum number of iterations is reached, resulting in at least one candidate solution. The candidate solution is an individual in the new population obtained when the maximum number of iterations is reached.
[0010] In one embodiment, determining the planned cargo transportation route based on the validated candidate solutions includes: Based on the cargo information corresponding to each candidate path of the verified candidate solution, determine the loading rate of each candidate path of the verified candidate solution, and calculate the average loading rate of the candidate solution. Obtain the number of vehicles used for candidate solutions, and determine the target candidate solution based on the number of vehicles used and the average loading rate of the candidate solutions; The planned cargo transportation route is determined based on the target candidate scheme.
[0011] In one embodiment, determining the planned cargo transportation route based on the target candidate scheme includes: Obtain the candidate path with the lowest load rate among the target candidate solutions; The pickup order data of each supplier in the candidate path with the lowest loading rate are assigned to other candidate paths in the target candidate scheme, and the loading information of the goods in each assigned path is verified. When all the pickup order data of all suppliers in the candidate path with the lowest loading rate are assigned to other candidate paths in the target candidate scheme, and the loading verification of the cargo information of each assigned path is passed, the first adjustment scheme is obtained. The planned cargo transportation routes will be determined based on the first adjustment plan.
[0012] In one embodiment, the cargo transportation route planning method further includes: When the pickup order data of some suppliers in the candidate path with the lowest loading rate are allocated to other candidate paths in the target candidate scheme, and the loading verification of the cargo information of each path after allocation is passed, the second adjustment scheme is obtained. Calculate the values of key indicators for the second adjustment plan and the target candidate plan respectively. Key indicators include one or more of the following: number of vehicles used, average loading rate, and transportation cost. The planned cargo transportation routes are determined from the second adjustment plan and the target candidate plan based on the values of key indicators.
[0013] Secondly, this application provides a cargo transportation route planning device, comprising: The acquisition module is used to acquire original order data, which includes pickup order data from at least one supplier, and the pickup order data includes goods information. The splitting module is used to determine the pickup order data to be split based on the goods information of at least one supplier and the loading volume of the vehicle to be allocated, and to split the pickup order data to be split in order to determine the split order data of the original order data. The generation module is used to generate an initial transportation plan based on the split order data. The initial transportation plan includes a set of pickup routes, which includes the pickup routes from each supplier in the original order data. The iteration module is used to perform iterative operations on the initial transportation plan according to a pre-set path optimization algorithm to obtain at least one candidate plan, and the candidate plan includes at least one candidate path. The verification module is used to verify the loading based on the loading volume of the vehicle to be assigned and the cargo information corresponding to the candidate route; The determination module is used to determine the planned cargo transportation route based on the verified candidate solutions.
[0014] In a third aspect, this application provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the cargo transportation route planning method provided in any embodiment of the first aspect of this application.
[0015] In a fourth aspect, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the cargo transportation route planning method provided in any embodiment of the first aspect of this application.
[0016] The aforementioned cargo transportation route planning method, apparatus, computer equipment, and storage medium first identify and split pickup order data based on supplier cargo information and vehicle parameters to be allocated. After splitting, the orders can be accurately matched with vehicle loading capacity. Subsequently, the route optimization algorithm is iteratively solved based on the split order data, which can expand the feasible solution space of the algorithm and increase the number of effective feasible solutions. Furthermore, the candidate solutions output by the algorithm are loaded and verified based on the loading volume of the vehicle to be allocated and cargo information, thereby obtaining a more accurate physically executable and optimal cargo transportation route solution. Attached Figure Description
[0017] Figure 1 This is a flowchart illustrating the cargo transportation route planning method in some embodiments; Figure 2 This is a flowchart illustrating the process of splitting pickup order data to be split in some embodiments; Figure 3 This is a schematic diagram of the data preprocessing process in some embodiments; Figure 4 Here are some structural block diagrams of the cargo transportation route planning device in some embodiments; Figure 5 This is a diagram showing the internal structure of a computer device in some embodiments. Detailed Implementation
[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0019] In a first aspect, this application provides a method for planning cargo transportation routes, such as Figure 1 As shown, the method is applied to a server as an example, and includes the following steps: Step S11: Obtain the original order data, which includes pickup order data from at least one supplier and includes goods information.
[0020] The original order data refers to the collection of all pickup order data obtained before route planning, without any processing. It includes pickup order data corresponding to at least one supplier and serves as the original input for route planning. Specifically, the original order data may include information on at least one supplier and pickup order data corresponding to each supplier.
[0021] The supplier's pickup order data may include order identifier, pickup time window, and goods information, where the supplier refers to the entity that provides the goods to be transported.
[0022] Goods information refers to key data related to goods in a pickup order, including information such as weight, volume, category, and quantity of goods.
[0023] Specifically, in one embodiment, the original order data can be as shown in Table 1 below: Table 1 The original order data in Table 1 includes three suppliers: Supplier A, Supplier B, and Supplier C. It also includes the pickup order data for each supplier. Each supplier corresponds to one order, and each order has corresponding pickup order data. Each pickup order data includes specific goods information, such as the quantity and size of the goods.
[0024] Step S12: Determine the pickup order data to be split based on the cargo information of at least one supplier and the loading capacity of the vehicle to be allocated, and split the pickup order data to be split to determine the split order data of the original order data.
[0025] The loading volume of the vehicle to be allocated refers to the effective usable internal space volume of the vehicle to be allocated for loading goods.
[0026] Pickup order data to be split refers to pickup order data where, after assessment, the total weight or volume of the corresponding goods exceeds the carrying capacity of a single vehicle and cannot be directly adapted to a vehicle.
[0027] Splitting refers to the operation of dividing pickup order data into multiple sub-order data that can be independently adapted to a single vehicle, based on vehicle load or volume constraints. Specifically, one order can be split into two orders, or one order data can be split into two order data.
[0028] The order data after splitting the original order data refers to the set of all sub-order data that can be adapted to the carrying capacity of a single vehicle after the original order data has been split. This includes qualified orders that have not been split and sub-orders that have been split.
[0029] Specifically, taking Table 1 above as an example, assuming that pickup order data A is the pickup order data to be split, the split order data after splitting the original order data can be shown in Table 2 below: Table 2 Table 2 has been split compared to Table 1, adding a sub-order and a new data record. The original node "Supplier A" has been split into Supplier A-1 and Supplier A-2, resulting in two nodes on the path.
[0030] Step S13: Generate an initial transportation plan based on the split order data. The initial transportation plan includes a set of pickup routes, which includes the pickup routes from each supplier in the original order data.
[0031] The initial transportation plan refers to a preliminary route and loading execution plan generated based on the split order data and basic vehicle constraints. It includes at least one pickup route from the corresponding supplier to meet basic pickup requirements and vehicle compatibility.
[0032] In this application, the initial transportation plan includes a set of pickup routes, the vehicles and cargo placement methods suitable for each pickup route, etc., wherein the path nodes in the pickup route set need to include all suppliers in the original order data.
[0033] For example, suppose the original order data includes supplier A, supplier B, supplier C, and supplier D. Then the initial shipping plan can be specifically as follows: Path 1: Node 0 - Supplier A - Supplier B - Node 0, corresponding to vehicle 1 allocation Path 2: Node 0 - Supplier C - Supplier D - Node 0, corresponding to vehicle allocation 2 The initial transportation plan includes two pickup routes: Path 1 and Path 2. Path 1 means that vehicle 1 departs from node 0 (e.g., the warehouse), picks up goods via supplier A, then picks up goods from supplier B, and returns to node 0. Path 2 means that vehicle 2 departs from node 0, picks up goods via supplier C, then picks up goods from supplier D, and returns to node 0. Both paths need to include all suppliers from the original order data.
[0034] Step S14: Iterate the initial transportation plan according to the pre-set path optimization algorithm to obtain at least one candidate plan, which includes at least one candidate path.
[0035] Among them, the route optimization algorithm refers to a class of algorithms that, under the condition of satisfying preset constraints, take route length, travel time, transportation cost and energy consumption as optimization objectives, and select the optimal or better travel route from the set of pickup routes through calculation and optimization.
[0036] Iterative operation refers to the process of repeatedly updating the route based on the pickup route in the initial transportation plan, according to a preset route optimization algorithm. By continuously adjusting and optimizing the route, multiple candidate routes are generated. Specifically, the iterative operation adjusts the order of the suppliers in the route to obtain multiple candidate routes.
[0037] Candidate solutions refer to transportation plans generated during the iterative process. Candidate paths refer to the routes taken by individual vehicles within a candidate solution.
[0038] Specifically, this application allows setting the objective function, constraints, and iteration count parameters for the path optimization algorithm. An initial transportation plan is input into the path optimization algorithm, which iteratively adjusts the path through multiple rounds of iteration. After each iteration, at least one candidate plan is output, and each candidate plan contains at least one optimized candidate path.
[0039] Step S15: Perform loading verification based on the loading volume of the vehicle to be assigned and the cargo information corresponding to the candidate route.
[0040] Loading verification refers to the verification operation that checks whether the total weight or volume of goods corresponding to the candidate path meets the vehicle's carrying capacity based on the load or volume constraints of the vehicle to be assigned. The core is to ensure the physical executability of the solution. Loading verification is performed after the iterative operation is completed. Specifically, it is used to verify the loading rationality of the goods corresponding to the candidate path, verifying whether the goods of each supplier can be placed and determining how to place them.
[0041] Specifically, this application can extract the cargo information corresponding to each candidate path and the cargo box size information of the vehicle to be assigned for each candidate scheme. Based on the cargo information of each candidate path and the cargo box size information of the vehicle, it can determine whether each piece of cargo corresponding to each candidate path has passed the loading verification.
[0042] Specifically, this application can determine whether each shipment has passed the loading verification based on the following constraints: Constraint 1: There is no spatial overlap between any two goods.
[0043] Constraint 2: The support area of each item is greater than or equal to the minimum support area.
[0044] Constraint 3: The placement of each item must satisfy the pre-defined stacking constraints.
[0045] The loading verification of a cargo is considered successful when each cargo simultaneously meets all three constraints mentioned above. The verification process ensuring no spatial overlap between any two cargoes may include: First, establish a coordinate origin, for example, a vertex on the bottom of the vehicle's cargo box. Establish a spatial coordinate system based on this origin. For each candidate path in each candidate solution, obtain information about each item on that path, such as weight, length, width, and height. Determine the placement position of the items, determine their coordinates within the cargo box based on their placement, determine the space they occupy based on their placement and dimensions, and determine if there is any spatial overlap between any two items based on their occupied space. The formula for determining the occupied space based on the placement and dimensions of the items is: ; in, Let i be the volume occupied by the goods. , , The three-dimensional coordinates of the goods within the vehicle. , , Let be the length, width, and height of cargo i, respectively.
[0046] Furthermore, the verification process for ensuring that the support area of each item is greater than or equal to the minimum support area may include: Calculate the area of the cargo's bottom surface based on its length and width, where the bottom surface refers to the side of the cargo closest to the floor of the carriage. Calculate the minimum supporting area for the cargo based on the area of its bottom surface.
[0047] Obtain the next layer of goods in contact with the current goods, denoted as the target goods. Calculate the contact area between the current goods and the target goods based on the coordinates and dimensions of the current goods and the target goods. When there are multiple target goods, calculate the sum of the contact areas between the current goods and each target goods. If the sum of the contact areas between the current goods and each target goods is greater than or equal to the minimum support area of the current goods, it is determined that the current goods meet constraint condition two.
[0048] The formula for calculating the area of the bottom surface of the current cargo is as follows: ; in, The area of the bottom surface of the goods. and These are the length and width of the bottom surface of cargo i, respectively.
[0049] The formula for calculating the minimum support area of the current cargo is: ; in, Let be the minimum support area for cargo i. Let be the area of the base of cargo i. is a coefficient.
[0050] The formula for calculating the contact area between current cargo i and target cargo j is: ; in, Let be the contact area between cargo i and cargo j below it. , , Let i be the three-dimensional coordinates of the cargo i within the vehicle. , , Let be the length, width, and height of cargo i, respectively.
[0051] The formula for calculating the total contact area between the current cargo and each target cargo is: ; in, Let i be the total contact area between cargo i and all potential supporting cargo below it. Let i be the set of all potential supporting goods below i.
[0052] Furthermore, the process of determining whether the placement of each item satisfies the pre-defined stacking constraints may include: pre-setting a stacking matrix, which includes the stacking rules between each item and other items; during loading verification, the placement of each item needs to be matched with the rules defined in the stacking matrix to determine whether all requirements are met; when the requirements are met, the current item is determined to satisfy constraint condition three.
[0053] Furthermore, other embodiments may also include weight constraints and size constraints, such as heavy goods not pressing on light goods, and large goods not pressing on small goods.
[0054] Step S16: Determine the planned cargo transportation route based on the verified candidate solutions.
[0055] Among them, the planned cargo transportation route refers to the optimal transportation route plan that has been determined after loading verification and can finally be implemented. It is the final output of route planning.
[0056] Specifically, this application may use the candidate routes from the verified candidate schemes as the planned cargo transportation routes.
[0057] This application can also be further adjusted based on the verified candidate schemes to obtain the planned cargo transportation route.
[0058] In one embodiment, please refer to Figure 2 The vehicles to be allocated include multiple vehicles. Based on the cargo information of at least one supplier and the loading capacity of the vehicles to be allocated, the pickup order data to be split is determined. This split pickup order data is then divided to determine the split order data from the original order data, including: Step S21: Determine the reference vehicle volume based on the loading volume of the vehicles to be allocated. The reference vehicle volume is the largest loading volume among the loading volumes of the vehicles to be allocated.
[0059] Step S22: Determine the total volume of goods of the current supplier based on the current supplier's goods information.
[0060] Step S23: When the total volume of goods of the current supplier is greater than the benchmark vehicle volume, determine the current supplier's pickup order data as pickup order data to be split.
[0061] Step S24: Split the current supplier's pickup order data based on the baseline vehicle volume and the current supplier's total cargo volume.
[0062] Step S25: Sequentially split each pickup order data to be split to determine the split order data of the original order data.
[0063] Among them, the baseline vehicle volume refers to the maximum value of the loading volume parameters of all vehicles in the set of vehicles to be allocated, which is the core volume constraint threshold for determining whether a single supplier order needs to be split.
[0064] The total volume of goods for a particular supplier refers to the cumulative value of the volume of all goods in the pickup order data corresponding to a specific supplier.
[0065] Specifically, this application can extract the loading volume parameter of each vehicle in the set of vehicles to be allocated, filter out the maximum value, and set this value as the baseline vehicle volume. A supplier is selected as the current supplier, and the volume of all goods in its pickup order data is calculated. The total volume of the supplier's goods is obtained by summing these volumes. The total volume of the current supplier's goods is compared with the baseline vehicle volume. If the former is greater than the latter, the current supplier's pickup order data is determined to be pickup order data to be split. Using the baseline vehicle volume as the splitting constraint, combined with the current supplier's total volume of goods, the supplier's pickup order is split into multiple sub-orders, where the total volume of goods corresponding to each sub-order does not exceed the baseline vehicle volume.
[0066] Following the steps above, the volume of each supplier's pickup order data is compared, split, and split in turn. Finally, all unsplit orders and split sub-orders are integrated to form the split order data of the original order data.
[0067] The beneficial effect of this embodiment is that, based on the maximum loading volume of the vehicle to be allocated, a unified order splitting judgment threshold is established. The total volume of goods in each sub-order after splitting does not exceed the benchmark vehicle volume, ensuring that the sub-order can be matched with at least one of the vehicles to be allocated, thus laying the foundation for the subsequent generation of an executable transportation plan.
[0068] In one embodiment, the cargo transportation route planning method may further include: when the total volume of the current supplier's cargo is less than or equal to the baseline vehicle volume, obtaining a pre-set rotation strategy, the rotation strategy including a state of rotating at a preset angle and a non-rotation state, verifying the loading of the current supplier's cargo information in each state of the rotation strategy according to the baseline vehicle volume, and if the loading verification of the current supplier's cargo information fails in each state of the rotation strategy, determining that the current supplier's pickup order data is pickup order data to be split.
[0069] Among them, the rotation strategy is a set of strategies for making decisions on the orientation of goods. Its core objective is to maximize the utilization of vehicle loading space and complete the loading feasibility verification by selecting a placement state in which the goods are not rotated or rotated at a preset angle.
[0070] The preset rotation angle refers to rotating the goods by a preset angle, swapping their original length and width, to attempt to adapt to the dimensions of the cargo compartment for loading. The preset angle can be set to 90 degrees.
[0071] The non-rotation state refers to the state in which no angle rotation is performed, which is the default initial state for the placement of goods.
[0072] Specifically, this application can first calculate the total volume of goods of the current supplier. If the total volume is less than or equal to the benchmark vehicle volume, it will enter the loading verification process based on the rotation strategy; otherwise, it will be directly split according to the original rules.
[0073] Furthermore, a rotation strategy is obtained, which defines two states: a state of no rotation and a state of rotating by a preset angle, such as 90 degrees.
[0074] Furthermore, the supplier's goods are verified in a non-rotating state. Based on the original dimensions of the goods and the dimensions of the carriage, a loading verification is performed to determine whether loading can be completed within the carriage.
[0075] Furthermore, the current supplier's goods are verified while in a rotating state. Based on the dimensions after rotation, the above loading verification process is repeated to perform loading verification.
[0076] If the loading verification fails in both states, meaning that neither placement method can load all of the current supplier's goods into the compartment corresponding to the baseline volume, then the current supplier's pickup order data will be determined as pickup order data to be split.
[0077] The beneficial effect of this embodiment is that when the total volume meets the constraints, the goods of each supplier are further verified based on the rotation strategy. If the verification fails, the goods are also determined to be pickup order data to be split, so that the splitting granularity is finer and the split pickup order data is more in line with physical executability.
[0078] In one embodiment, before generating an initial transportation plan based on the split order data, the cargo transportation route planning method further includes: extracting the pickup time window corresponding to each pickup order data in the split pickup order data, obtaining pickup order data belonging to the same supplier in the split pickup order data and whose pickup time windows overlap, and merging them; when the total volume of the goods corresponding to the merged pickup order data is less than or equal to the benchmark vehicle volume, determining the data after preprocessing the original order data based on the merged pickup order data, and generating an initial transportation plan based on the split order data, including: generating an initial transportation plan based on the data after preprocessing the original order data.
[0079] Among them, the pickup time window corresponding to each order data refers to the time period specified for a single order to complete the pickup operation, which usually includes two boundary values: the earliest pickup time and the latest pickup time.
[0080] Overlapping pickup time windows refer to the overlapping pickup time periods of multiple orders from the same supplier. Consolidation refers to combining multiple orders from the same supplier with overlapping pickup time windows into a single unified order, used to reduce the number of pickups from the same supplier and optimize vehicle scheduling.
[0081] The data after preprocessing of the original order data refers to the data obtained after performing a series of preprocessing operations on the original order data. Specifically, the original order data is first cleaned, then supplier matching, equipment matching, data splitting and data merging are performed, and finally the pickup order data is obtained.
[0082] Each data merging process requires verification that the merged pickup order data meets the conditions for loading feasibility. Specifically, the total volume of the goods in the merged pickup order data is compared with the baseline loading volume. If it is less than or equal to the baseline loading volume, the merging operation is performed.
[0083] Specifically, this application can extract the pickup time windows of all split pickup orders; filter out all pickup order data from the same supplier whose pickup time windows overlap. For the filtered orders, merge their corresponding goods information, pickup time windows, and supplier information to form merged pickup order data, wherein the pickup time window can be the overlapping interval of the merged time window.
[0084] Furthermore, verify the total volume of goods corresponding to the merged order to determine if it is less than or equal to the baseline vehicle volume. If it meets the requirement, retain the merged order; otherwise, retain the original order. Complete the above merging and verification process for all supplier orders. Integrate all verified merged pickup order data with the split pickup order data that did not meet the merging conditions into the preprocessed data corresponding to the original order data.
[0085] For example, in the original data, orders with different pickup time windows are recorded in two separate data records. For instance, orders from supplier A during the 9:00-11:00 pickup time window constitute one sub-order, corresponding to one pickup order record. Orders from supplier A during the 10:00-12:00 pickup time window also constitute one sub-order, corresponding to one pickup order record. Since the pickup time windows of these two sub-orders overlap, the pickup data records corresponding to these two sub-orders can be merged. Before merging, it is necessary to determine whether the total volume of the goods corresponding to the merged order is less than or equal to the baseline vehicle capacity.
[0086] In one embodiment, please refer to Figure 3 Before splitting the pickup order data to be split, this application may also include data cleaning of the original order data. Specifically, this includes uniformly processing the cargo information, quantity, weight, time window, supplier information, and vehicle model restriction information contained in the original order data. Through unit conversion, field completion, and outlier correction, it ensures that all order data meets the calculation requirements in terms of expression format and numerical range, providing a consistent data foundation for subsequent 3D loading analysis.
[0087] Furthermore, during the data standardization process, supplier matching verification is performed based on the supplier information in the pickup order data. When it is detected that the supplier information corresponding to the order is missing or inconsistent in the local supplier database, the latest supplier data is obtained from the external business system through interface calls and updated to the supplier database to ensure the real-time and accuracy of the supplier information.
[0088] Simultaneously, based on the cargo's dimensions, weight, and packaging attributes, equipment matching is performed in the standard equipment library. When equipment matching failure is detected, the system triggers an equipment information update mechanism to supplement or correct the standard equipment library, ensuring the validity of the equipment data used in subsequent loading analyses.
[0089] The beneficial effects of this embodiment are that by cleaning the data, a consistent data foundation is provided for subsequent loading verification analysis; by matching suppliers and equipment, the real-time and accuracy of supplier information and the validity of the equipment data used are ensured; and the order data, supplier information, and equipment constraints are kept consistent at the structural and semantic levels. By merging orders with overlapping pickup time windows from the same supplier, multiple pickups by the same supplier are avoided, the number of merged orders is reduced, the complexity of generating the initial transportation plan is reduced, and the processing efficiency of route planning is improved.
[0090] In one embodiment, the path optimization algorithm is a genetic algorithm. The algorithm iteratively processes the initial transportation plan according to a pre-set path optimization algorithm to obtain at least one candidate plan. This includes: constructing an initial population using the initial transportation plan based on the genetic algorithm; performing selection, crossover, and mutation operations on the initial population; and iteratively obtaining a new population. The next iteration is performed on the new population until the maximum number of iterations is reached, resulting in at least one candidate solution. The candidate solution is an individual in the new population obtained when the maximum number of iterations is reached.
[0091] Genetic algorithms, designed based on the evolutionary laws of organisms in nature, are computational models that simulate the biological evolutionary process of natural selection and genetic mechanisms in Darwin's theory of evolution. They are methods for searching for optimal solutions by simulating natural evolution. This algorithm uses mathematical methods and computer simulations to transform the problem-solving process into processes similar to the crossover and mutation of chromosomes and genes in biological evolution. When solving complex combinatorial optimization problems, compared to some conventional path optimization algorithms, this algorithm can usually obtain better optimization results faster.
[0092] The initial population is the starting point for the genetic algorithm iteration, and is a set of feasible solutions generated by mapping the initial transportation scheme; each individual corresponds to a complete transportation scheme.
[0093] Selection is one of the core operations of genetic algorithms. It involves evaluating the quality of individuals in the population according to a preset fitness function, such as the lowest transportation cost or the shortest distance, and selecting high-quality individuals to enter the next generation of the population.
[0094] Crossover is one of the core operations of genetic algorithms. It is the process of recombining genes of two selected high-quality individuals according to preset crossover rules, such as path segment exchange and order allocation exchange, to generate new offspring individuals.
[0095] Mutation is one of the core operations of genetic algorithms. It involves randomly modifying some of the genes of individuals in the population according to a preset mutation probability, such as randomly adjusting the order of pickup points on a certain path or changing the vehicle assigned to an order, to avoid the algorithm getting stuck in local optima.
[0096] An individual in the population refers to the basic unit of the genetic algorithm population, corresponding to a complete and feasible transportation scheme.
[0097] Specifically, this application allows for the pre-setting of core parameters of the genetic algorithm, such as population size, maximum number of iterations, and fitness function.
[0098] Furthermore, the initial transportation plan is randomly fine-tuned, such as adjusting the order of picking up goods from suppliers, to generate an initial population that meets the population size requirements, where each individual corresponds to a complete transportation plan.
[0099] Furthermore, the fitness value of each individual is calculated using a fitness function, and individuals with high fitness are selected to form the parent population. Individuals in the parent population are paired according to a pre-set crossover probability, and gene recombination is performed according to preset rules, such as path segmented crossover, to generate offspring individuals.
[0100] Furthermore, based on a pre-set mutation probability, the generated offspring individuals undergo random genetic modification, such as adjusting the order of goods pickup along a certain path.
[0101] Furthermore, individuals from the parent population are integrated with the mutated offspring individuals to form a new population. This new population serves as the initial population for the next iteration, and the selection, crossover, and mutation processes are repeated until the preset maximum number of iterations is reached, at which point iteration stops. All individuals in the new population at the maximum number of iterations are considered as candidate solutions, with each candidate solution corresponding to one or more candidate paths.
[0102] The beneficial effect of this embodiment is that, through population iteration and random operations of the genetic algorithm, it can quickly search in the solution space, avoid getting trapped in local optima, and is easier to obtain a globally better transportation scheme compared with traditional methods.
[0103] In one embodiment, determining the planned cargo transportation route based on the verified candidate schemes includes: determining the loading rate of each candidate path of the verified candidate scheme based on the cargo information corresponding to each candidate path of the verified candidate scheme, calculating the average loading rate of the candidate scheme, obtaining the number of vehicles used for the candidate scheme, determining the target candidate scheme based on the number of vehicles used and the average loading rate of the candidate scheme, and determining the planned cargo transportation route based on the target candidate scheme.
[0104] Load factor refers to the ratio of the total amount of cargo actually loaded on a candidate route to the rated loading capacity of the vehicles used on that route, such as the vehicle's rated capacity. Load factor reflects the utilization rate of vehicle space on a single route.
[0105] The average load factor of the candidate scheme is the arithmetic mean of the load factors of all used paths in the candidate scheme, reflecting the overall space utilization level of the entire scheme.
[0106] The number of vehicles used in a candidate scheme refers to the total number of vehicles dispatched in that candidate scheme to complete all cargo transportation tasks.
[0107] The target candidate solution refers to the comprehensive optimal solution calculated using a preset evaluation function among all verified candidate solutions.
[0108] Specifically, this application can iterate through each candidate solution and perform the following operations for each candidate solution: For each subsequent path in the current candidate solution, extract the cargo information corresponding to the candidate path, such as the total weight or total volume of the cargo. Calculate the loading rate of the candidate path.
[0109] Count the total number of candidate paths in the current candidate scheme, i.e. the number of vehicles used.
[0110] The average load rate of the current candidate path is calculated by summing the load rates of all paths and dividing by the total number of candidate paths.
[0111] Furthermore, while ensuring that the average loading rate is greater than a threshold, the scheme with the fewest vehicle usages is selected as the target candidate scheme. The specific path sequences of the target candidate schemes are output as the final planned freight transportation routes.
[0112] The beneficial effects of this embodiment are as follows: This application selects target candidate schemes based on loading rate and number of vehicles used. By maximizing the average loading rate, it reduces invalid transportation mileage and vehicle idle space. By minimizing the number of vehicles used, it directly reduces scheduling costs. The combination of the two achieves the minimization of total logistics costs.
[0113] In one embodiment, determining the planned cargo transportation route based on the target candidate routes includes: obtaining the candidate route with the lowest loading rate among the target candidate routes. The pickup order data of each supplier in the candidate path with the lowest loading rate are assigned to other candidate paths in the target candidate scheme. The loading information of each assigned path is verified. When the pickup order data of all suppliers in the candidate path with the lowest loading rate are assigned to other candidate paths in the target candidate scheme, and the loading verification of the cargo information of each assigned path is passed, the first adjustment scheme is obtained. The planned cargo transportation path is determined according to the first adjustment scheme.
[0114] The first adjustment plan refers to removing the candidate path with the lowest loading rate from the target candidate plan, and allocating all the pickup order data of all suppliers on that path to other candidate paths within the plan. After the allocation, the cargo information of all paths is verified through loading, forming an optimized candidate plan.
[0115] Specifically, this application can select the candidate path P with the lowest loading rate from the set of target candidate paths.
[0116] Extract pickup order data for all suppliers on path P, including information such as goods weight, volume, and pickup point, and split these into independent order units based on the supplier. Iterate through the order data for each supplier and attempt to assign the order to other candidate paths in turn.
[0117] For each order unit assigned, the loading information of the goods along the assigned path is verified. If the assigned path verification fails, the system attempts to assign the order to the next path until a path that meets the constraints is found, or the order is determined to be unassignable.
[0118] When all supplier orders on path P have been compliantly allocated and all allocated paths have passed loading verification, a first adjustment plan is formed. In the first adjustment plan, path P is removed, while the other adjusted paths are retained.
[0119] Furthermore, the set of routes in the first adjustment plan will be used as the final planned cargo transportation routes.
[0120] The beneficial effects of this embodiment are: eliminating the inefficient routes with the lowest loading rates and distributing their orders to other routes, directly increasing the average loading rate of the entire solution, reducing vehicle space waste, and lowering the unit cargo transportation cost.
[0121] In one embodiment, the cargo transportation route planning method may further include: when the pickup order data of some suppliers in the candidate route with the lowest loading rate are allocated to other candidate routes in the target candidate scheme, and the loading verification corresponding to the cargo information of each route after allocation is passed, a second adjustment scheme is obtained; the values of key indicators of the second adjustment scheme and the target candidate scheme are calculated respectively; the key indicators include one or more of vehicle usage, average loading rate and transportation cost; and the planned cargo transportation route is determined from the second adjustment scheme and the target candidate scheme based on the values of the key indicators.
[0122] The second adjustment scheme is the scheme obtained by allocating the pickup order data of each supplier in the candidate path with the lowest loading rate to other candidate paths in sequence and performing loading verification. Only some suppliers' pickup order data are successfully allocated to other candidate paths if the loading verification is passed. The scheme obtained after allocating the pickup order data of these suppliers to other candidate paths is the second adjustment scheme.
[0123] Key performance indicators (KPIs) are core quantitative parameters used to quantitatively evaluate the merits of candidate solutions and support decision-making. Here, they specifically refer to one or more of the following: number of vehicles used, average load factor, and transportation cost. Among these, transportation cost is the total expenditure for completing the transportation task.
[0124] Specifically, this application can filter out the path P with the lowest loading rate from the target candidate routes, extract the pickup order data of all suppliers on path P and split it into independent units by supplier. It then iterates through the order units and attempts to assign them to other candidate paths.
[0125] For each order assigned, the loading information of the goods on the assigned route is verified. If the verification is successful, the assignment is completed; otherwise, the next route is tried. When an order cannot be successfully assigned to any other candidate route, the order is kept on route P. Here, successful assignment means being assigned to another candidate route while meeting the loading verification requirements.
[0126] The assigned path P and other candidate paths are obtained to form a second adjustment scheme. In this scheme, the unassigned orders are retained in the assigned path P, and the orders from the original path P are added to the other candidate paths.
[0127] Furthermore, the key indicators of the second adjustment scheme and the target candidate scheme are calculated respectively; based on the preset evaluation rules, such as weighted scoring and threshold screening, the optimal scheme is selected from the two schemes, and the planned cargo transportation route is determined based on the selected optimal scheme.
[0128] The beneficial effects of this embodiment are: when it is impossible to complete the transfer of all orders, the average loading rate can be improved by allocating some orders; and by quantitatively comparing key indicators, the option with a higher average loading rate and lower transportation cost can be selected from the second adjustment option and the target candidate option.
[0129] In a second aspect, this application provides a cargo transportation route planning device, such as... Figure 4 As shown, the cargo transportation route planning device includes: an acquisition module 41, a splitting module 42, a generation module 43, an iteration module 44, a verification module 45, and a determination module 46, wherein: The acquisition module 41 is used to acquire original order data, which includes pickup order data from at least one supplier and includes goods information. The splitting module 42 is used to determine the pickup order data to be split based on the goods information of at least one supplier and the loading volume of the vehicle to be allocated, and to split the pickup order data to be split in order to determine the split order data of the original order data. The generation module 43 is used to generate an initial transportation plan based on the split order data. The initial transportation plan includes a set of pickup routes, which includes the pickup routes from each supplier in the original order data. The iteration module 44 is used to perform iterative operations on the initial transportation plan according to a pre-set path optimization algorithm to obtain at least one candidate plan, and the candidate plan includes at least one candidate path. The verification module 45 is used to perform loading verification based on the loading volume of the vehicle to be assigned and the cargo information corresponding to the candidate route; The determination module 46 is used to determine the planned cargo transportation route based on the verified candidate schemes.
[0130] In one embodiment, the vehicles to be allocated include multiple vehicles, and the splitting module 42 can... The baseline vehicle volume is determined based on the loading capacity of the vehicles to be allocated. The baseline vehicle volume is the largest loading capacity among the loading capacities of the vehicles to be allocated. The total volume of the current supplier's goods is determined based on the current supplier's goods information. If the total volume of the current supplier's goods is greater than the baseline vehicle volume, the current supplier's pickup order data is determined as pickup order data to be split. The current supplier's pickup order data is split based on the baseline vehicle volume and the current supplier's total volume of goods. Each pickup order data to be split is split sequentially to determine the split order data after splitting the original order data.
[0131] In one embodiment, the splitting module 42 can also obtain a pre-set rotation strategy when the total volume of the current supplier's goods is less than or equal to the base vehicle volume. The rotation strategy includes a state of rotating at a preset angle and a state of not rotating. The loading verification of the current supplier's goods information in each state of the rotation strategy is performed according to the base vehicle volume. If the loading verification of the current supplier's goods information fails in each state of the rotation strategy, the current supplier's pickup order data is determined to be pickup order data to be split.
[0132] In one embodiment, the splitting module 42 can also extract the pickup time window corresponding to each pickup order data in the split pickup order data, obtain the pickup order data belonging to the same supplier in the split pickup order data and whose pickup time windows overlap, and merge them. When the total volume of the goods corresponding to the merged pickup order data is less than or equal to the benchmark vehicle volume, the data after preprocessing the original order data is determined according to the merged pickup order data, and the generation module 43 can generate an initial transportation plan according to the data after preprocessing the original order data.
[0133] In one embodiment, the path optimization algorithm is a genetic algorithm. The iteration module 44 can construct an initial population based on the initial transportation scheme according to the genetic algorithm, perform selection, crossover and mutation operations on the initial population to carry out iterative operations, obtain a new population, and perform the next iteration operation on the new population until the maximum number of iterations is reached, and obtain at least one candidate scheme. The candidate scheme is an individual in the new population obtained when the maximum number of iterations is reached.
[0134] In one embodiment, the determining module 46 can determine the loading rate of each candidate path of the verified candidate scheme based on the cargo information corresponding to each candidate path of the verified candidate scheme, calculate the average loading rate of the candidate scheme, obtain the number of vehicles used in the candidate scheme, determine the target candidate scheme based on the number of vehicles used and the average loading rate of the candidate scheme, and determine the planned cargo transportation route based on the target candidate scheme.
[0135] In one embodiment, the determining module 46 can obtain the candidate path with the lowest loading rate in the target candidate scheme, allocate the pickup order data of each supplier in the candidate path with the lowest loading rate to other candidate paths in the target candidate scheme, and verify the loading of the goods information of each allocated path. When all the pickup order data of all suppliers in the candidate path with the lowest loading rate are allocated to other candidate paths in the target candidate scheme, and the loading verification of the goods information of each allocated path is passed, a first adjustment scheme is obtained, and the planned goods transportation path is determined according to the first adjustment scheme.
[0136] In one embodiment, the determining module 46 can further obtain a second adjustment scheme when the pickup order data of some suppliers in the candidate path with the lowest loading rate are allocated to other candidate paths in the target candidate scheme, and the loading verification corresponding to the cargo information of each allocated path passes. The module then calculates the values of key indicators for the second adjustment scheme and the target candidate scheme, whereby the key indicators include one or more of the following: number of vehicles used, average loading rate, and transportation cost. The planned cargo transportation routes are determined from the second adjustment plan and the target candidate plan based on the values of key indicators.
[0137] In a third aspect, this application provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the cargo transportation route planning method provided in any embodiment of the first aspect of this application.
[0138] In one embodiment, the computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a cargo transportation route planning method.
[0139] In a fourth aspect, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the cargo transportation route planning method provided in any embodiment of the first aspect of this application.
[0140] The computer-readable storage medium may be Figure 4The computer-readable storage medium in the computer device shown.
[0141] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0142] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0143] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.
Claims
1. A method for planning cargo transportation routes, characterized in that, The method includes: Obtain original order data, which includes pickup order data from at least one supplier, and the pickup order data includes goods information; Based on the cargo information of the at least one supplier and the loading capacity of the vehicle to be allocated, the pickup order data to be split is determined, and the pickup order data to be split is split to determine the split order data of the original order data. An initial transportation plan is generated based on the split order data. The initial transportation plan includes a set of pickup paths, which includes paths for picking up goods from each of the suppliers in the original order data. The initial transportation plan is iteratively performed according to a pre-set path optimization algorithm to obtain at least one candidate plan, wherein the candidate plan includes at least one candidate path. Loading verification is performed based on the loading capacity of the vehicle to be assigned and the cargo information corresponding to the candidate route; The planned cargo transportation route is determined based on the verified candidate schemes.
2. The method according to claim 1, characterized in that, The vehicles to be allocated include multiple vehicles. The process involves determining the pickup order data to be split based on the cargo information of at least one supplier and the loading capacity of the vehicles to be allocated, and then splitting the pickup order data to determine the split order data from the original order data. This includes: The reference vehicle volume is determined based on the loading volume of the vehicles to be allocated, and the reference vehicle volume is the largest loading volume among the loading volumes of the vehicles to be allocated. The total volume of goods from the current supplier is determined based on the current supplier's goods information; When the total volume of goods from the current supplier is greater than the baseline vehicle volume, the current supplier's pickup order data is determined as the pickup order data to be split. The current supplier's pickup order data is split based on the baseline vehicle volume and the current supplier's total cargo volume; Each of the pickup order data to be split is split sequentially to determine the split order data of the original order data.
3. The method according to claim 2, characterized in that, The method further includes: When the total volume of goods of the current supplier is less than or equal to the reference vehicle volume, a pre-set rotation strategy is obtained, which includes a state of rotating at a preset angle and a state of not rotating. The current supplier's cargo information is loaded and verified based on the baseline vehicle volume under each state of the rotation strategy. If the loading verification of the current supplier's goods information fails in all states of the rotation strategy, the current supplier's pickup order data is determined to be the pickup order data to be split.
4. The method according to claim 2, characterized in that, Before generating the initial transportation plan based on the split order data, the method further includes: Extract the pickup time window corresponding to each pickup order data in the split pickup order data; Collect and merge pickup order data from the split pickup order data that belong to the same supplier and have overlapping pickup time windows; When the total volume of goods corresponding to the merged pickup order data is less than or equal to the baseline vehicle volume, the preprocessed data of the original order data is determined based on the merged pickup order data. The step of generating an initial transportation plan based on the split order data includes: The initial transportation plan is generated based on the preprocessed data of the original order data.
5. The method according to claim 1, characterized in that, The path optimization algorithm is a genetic algorithm. The step of iteratively optimizing the initial transportation plan according to a pre-set path optimization algorithm to obtain at least one candidate plan includes: An initial population is constructed using the initial transportation scheme based on the genetic algorithm described above; The initial population is subjected to selection, crossover, and mutation operations to perform the iterative operation and obtain a new population. The next iteration operation is performed on the new population until the maximum number of iterations is reached, to obtain at least one candidate scheme, wherein the candidate scheme is an individual in the new population obtained when the maximum number of iterations is reached.
6. The method according to claim 1, characterized in that, The step of determining the planned cargo transportation route based on the verified candidate solutions includes: Based on the cargo information corresponding to each candidate path of the verified candidate scheme, the loading rate of each candidate path of the verified candidate scheme is determined, and the average loading rate of the candidate scheme is calculated. Obtain the number of vehicles used for the candidate schemes, and determine the target candidate scheme based on the number of vehicles used for the candidate schemes and the average loading rate; The planned cargo transportation route is determined based on the target candidate scheme.
7. The method according to claim 6, characterized in that, Determining the planned cargo transportation route based on the target candidate scheme includes: Obtain the candidate path with the lowest load rate among the target candidate solutions; The pickup order data of each supplier in the candidate path with the lowest loading rate are respectively assigned to other candidate paths in the target candidate scheme, and the loading information of the goods in each assigned path is verified. When all the pickup order data of all suppliers in the candidate path with the lowest loading rate are allocated to other candidate paths in the target candidate scheme, and the loading verification of the goods information corresponding to each allocated path is passed, the first adjustment scheme is obtained. The planned cargo transportation route is determined based on the first adjustment scheme.
8. The method according to claim 7, characterized in that, The method further includes: When the pickup order data of some suppliers in the candidate path with the lowest loading rate are allocated to other candidate paths in the target candidate scheme, and the loading verification of the goods information corresponding to each allocated path passes, a second adjustment scheme is obtained. Calculate the values of key indicators for the second adjustment scheme and the target candidate scheme respectively. The key indicators include one or more of the following: number of vehicles used, average loading rate, and transportation cost. The planned cargo transportation route is determined from the second adjustment scheme and the target candidate scheme based on the value of the key indicator.
9. A cargo transportation route planning device, characterized in that, The device includes: The acquisition module is used to acquire original order data, which includes pickup order data from at least one supplier and includes goods information. The splitting module is used to determine the pickup order data to be split based on the goods information of the at least one supplier and the loading volume of the vehicle to be allocated, and to split the pickup order data to be split to determine the split order data of the original order data. A generation module is used to generate an initial transportation plan based on the split order data. The initial transportation plan includes a set of pickup paths, which includes paths for picking up goods from each of the suppliers in the original order data. An iteration module is used to iterate the initial transportation plan according to a pre-set path optimization algorithm to obtain at least one candidate plan, wherein the candidate plan includes at least one candidate path. The verification module is used to perform loading verification based on the loading volume of the vehicle to be assigned and the cargo information corresponding to the candidate route; The determination module is used to determine the planned cargo transportation route based on the verified candidate schemes.
10. 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, it implements the steps of the method according to any one of claims 1 to 8.
11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 8.