A shipment management method and system for matching vehicles with orders in a TMS system

Abstract

The application provides a kind of TMS system vehicle and order matching shipment management method and system, it is related to data processing technical field, the method comprises: obtaining the set of orders to be matched and the set of available vehicles;Order set contains the weight of goods, goods volume, destination and time limit of each order;Vehicle set contains the approved load of each vehicle, approved volume, current location and dynamically updated allocated order cumulative weight and cumulative volume;Based on the destination of the order and the current location of the vehicle, calculate the spatial distance between the destination of the order and the current location of each vehicle, pre-screen a set of geographically feasible candidate vehicles for each order by setting a distance threshold, and convert the order and vehicle data into a set of data points to construct a feature plane.The application improves the efficiency of vehicle order matching and the utilization rate of transport capacity.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a shipping management method and system for matching vehicles with orders in a TMS system. Background Technology

[0002] Currently, the dispatch management of matching vehicles and orders in TMS systems mostly relies on manual experience or a single dimension for matching, which makes it difficult to cope with the complex coupling needs of multiple order attributes and dynamic vehicle capacity in logistics scenarios. Especially in scenarios with concentrated orders and high time requirements, such as e-commerce promotions and fresh food cold chain, problems such as low capacity utilization and order delays often occur.

[0003] For example, during the Double Eleven shopping festival, a regional e-commerce warehousing center needed to process 300 pending orders for home appliances. With 15 available vehicles, the existing system, using a distance-first matching principle, assigned a 7-ton / 4.2m³ order with a distant destination but urgent delivery to the nearest vehicle, which already had a cumulative load of 5 tons. This resulted in the vehicle having only 5 tons of remaining capacity, unable to carry the order, forcing it to be split into two shipments, incurring an additional 25% transportation cost. Simultaneously, three vehicles were repeatedly assigned orders exceeding their capacity due to the system not updating the cumulative volume of assigned orders in real time, requiring manual rescheduling. Ultimately, this resulted in 12 delayed orders, an overall capacity utilization rate of only 62%, and an increase in manual scheduling costs of 18,000 yuan. This case highlights the technical flaws of the existing method: it fails to dynamically integrate real-time cumulative vehicle capacity with multiple order attributes for comprehensive matching; single-dimensional filtering easily leads to capacity waste and order delays; and its reliance on manual intervention results in low efficiency and high costs. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method and system for dispatch management of matching vehicles and orders in a TMS system, which improves the efficiency of vehicle order matching and the utilization rate of transportation capacity.

[0005] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0006] Firstly, a method for shipment management in a TMS system that matches vehicles with orders, the method comprising:

[0007] Step 1: Obtain the set of orders to be matched and the set of available vehicles; the order set includes the weight, volume, destination and time requirements of each order; the vehicle set includes the rated load capacity, rated volume, current location and dynamically updated cumulative weight and volume of assigned orders for each vehicle.

[0008] Step 2: Based on the order destination and the current location of the vehicle, calculate the spatial distance between the order destination and the current location of each vehicle. By setting a distance threshold, pre-screen a set of geographically feasible candidate vehicles for each order, and convert the order and vehicle data into a set of data points to construct a feature plane.

[0009] Step 3: Determine the reference region on the feature plane, partition the reference region according to the distribution characteristics of the data point set, and obtain the optimization coefficients; adjust the candidate vehicle set through the optimization coefficients to obtain the adjusted candidate vehicle set.

[0010] Step 4: Based on the adjusted candidate vehicle set, calculate the vehicle's remaining load capacity and remaining volume capacity by deducting the cumulative weight and volume of allocated orders from the vehicle's approved load capacity and approved volume.

[0011] Step 5: Calculate the matching degree between the order's cargo weight and volume and the vehicle's remaining load capacity and volume capacity to obtain a comprehensive matching degree score.

[0012] Step 6: Based on the comprehensive matching score, assign the final matching vehicle to the order from the candidate vehicle set, and update the vehicle capacity information of the assigned order's cumulative weight and cumulative volume for the final matching vehicle;

[0013] Step 7: Based on the updated vehicle capacity information, iteratively match the remaining orders until all orders have been assigned vehicles or there are no matching vehicles.

[0014] Furthermore, based on the order destination and the current location of the vehicle, the spatial distance between the order destination and the current location of each vehicle is calculated. By setting a distance threshold, a set of geographically feasible candidate vehicles is pre-filtered for each order. The order and vehicle data are then transformed into a set of data points to construct a feature plane, including:

[0015] Step 2.1: Based on the destination information of the order and the current location information of each vehicle in the available vehicle set, calculate the spatial distance between the order destination and the current location of each vehicle, thereby generating a set of spatial distances corresponding to all vehicles for each order.

[0016] Step 2.2: Compare each distance value in the spatial distance set with a predefined distance threshold, and filter out vehicles whose distance values ​​are less than or equal to the distance threshold to obtain a geographically feasible candidate vehicle set for the order;

[0017] Step 2.3: The candidate vehicle set and corresponding order data obtained after filtering and associated with all orders are transformed into a set of data points in a multi-dimensional feature space, thereby constructing a feature plane.

[0018] Furthermore, a baseline region is determined on the feature plane, and the baseline region is partitioned according to the distribution characteristics of the data point set to obtain optimization coefficients; the candidate vehicle set is adjusted using the optimization coefficients to obtain the adjusted candidate vehicle set, including:

[0019] Step 3.1: Perform a distribution density analysis on the data point set in the feature plane to obtain the analysis results; based on the analysis results, determine one or more core regions in the feature plane as reference regions;

[0020] Step 3.2: Based on the distribution density of the data point set within the benchmark area, divide the benchmark area into multiple sub-partitions;

[0021] Step 3.3: For each sub-partition, an optimization coefficient is calculated based on the number of data points, attribute characteristics, and their relationship with the overall set of data points within the sub-partition. This coefficient is used to evaluate the matching priority.

[0022] Step 3.4: Map the optimization coefficients back to the original data, and adjust the priority or weight of the vehicles in the generated candidate vehicle set accordingly to obtain the adjusted candidate vehicle set.

[0023] Furthermore, based on the adjusted candidate vehicle set, and deducting the cumulative weight and volume of allocated orders from the vehicle's approved load capacity and approved volume, the remaining load capacity and remaining volume capacity of the vehicle are calculated, including:

[0024] Step 4.1: Based on the obtained adjusted candidate vehicle set, read the approved load capacity, approved volume, and real-time updated cumulative weight and cumulative volume of allocated orders for each vehicle in the candidate vehicle set;

[0025] Step 4.2: For each vehicle in the adjusted candidate vehicle set, calculate the vehicle's remaining load capacity by subtracting the cumulative weight of allocated orders from the approved load capacity; at the same time, calculate the vehicle's remaining volume capacity by subtracting the cumulative volume of allocated orders from the approved volume.

[0026] Furthermore, the order's cargo weight and volume are matched with the vehicle's remaining load capacity and volumetric capacity to calculate a comprehensive matching score, including:

[0027] Step 5.1: Obtain the weight and volume of the goods in the order to be matched, and read the remaining load capacity and volume capacity of each vehicle in the adjusted candidate vehicle set.

[0028] Step 5.2: For each vehicle in the adjusted candidate vehicle set, calculate the load matching degree between the order's cargo weight and the vehicle's remaining load capacity, and the volume matching degree between the order's cargo volume and the vehicle's remaining volume capacity.

[0029] Step 5.3: Based on the timeliness requirements of the order, evaluate the feasibility of each candidate vehicle in meeting the timeliness requirements, and generate a timeliness matching degree evaluation result.

[0030] Step 5.4: Based on the evaluation results of load matching degree, volume matching degree and timeliness matching degree, perform fusion calculation according to the preset weight rules to obtain a comprehensive matching degree score for the final vehicle decision.

[0031] Furthermore, based on the comprehensive matching score, final matching vehicles are assigned to orders from the candidate vehicle set, and the vehicle capacity information of the final matching vehicles, including the cumulative weight and volume of the assigned orders, is updated, including:

[0032] Step 6.1: Receive the comprehensive matching score generated for each candidate vehicle, and sort all candidate vehicles according to the score to obtain an ordered list of candidate vehicles.

[0033] Step 6.2: From the ordered list of candidate vehicles, select the vehicle with the highest overall matching score, determine the vehicle with the highest matching score as the final matching vehicle for the current order to be matched, and generate a vehicle allocation instruction.

[0034] Step 6.3: Based on the vehicle allocation instruction, immediately update the vehicle capacity information of the finally matched vehicle after the vehicle allocation is completed. That is, add the weight of the goods in the order to the cumulative weight of the vehicle's allocated orders, and add the volume of the goods in the order to the cumulative volume of the vehicle's allocated orders, so as to ensure the real-time and accuracy of the vehicle's remaining capacity information.

[0035] Furthermore, based on the updated vehicle capacity information, the remaining orders are iteratively matched until all orders have been assigned vehicles or no matching vehicles are available, including:

[0036] Step 7.1: After completing the vehicle allocation for an order and updating the vehicle capacity information, remove the successfully allocated current order from the set of orders to be matched to form a new set of remaining orders;

[0037] Step 7.2: Determine whether the new set of remaining orders is empty, or determine whether the remaining capacity of all available vehicles is insufficient to meet the basic requirements of any order in the set of remaining orders.

[0038] Step 7.3: If the remaining order set is not empty and there are matching vehicles, then the updated vehicle capacity information is used as the new input, and the steps of claims 2 to 6 are iteratively executed for the next order in the remaining order set to perform a new round of matching and allocation.

[0039] Step 7.4: Repeat the above iterative process until the remaining order set becomes empty or there are no matching vehicles, thus completing the shipment management of all orders in this round.

[0040] Secondly, a dispatch management system for matching vehicles and orders in a TMS system includes:

[0041] The acquisition module is used to acquire the order set to be matched and the available vehicle set; the order set includes the cargo weight, cargo volume, destination and time requirements of each order; the vehicle set includes the rated load capacity, rated volume, current location of each vehicle, and dynamically updated cumulative weight and volume of assigned orders;

[0042] The optimization module is used to calculate the spatial distance between the order destination and the current location of each vehicle based on the order destination and the current location of the vehicle. By setting a distance threshold, it pre-screens a set of geographically feasible candidate vehicles for each order and converts the order and vehicle data into a set of data points to construct a feature plane. A baseline region is determined on the feature plane, and the baseline region is partitioned according to the distribution characteristics of the data point set to obtain optimization coefficients. The candidate vehicle set is adjusted using the optimization coefficients to obtain the adjusted candidate vehicle set.

[0043] The calculation module is used to calculate the remaining load capacity and remaining volume capacity of a vehicle based on the adjusted candidate vehicle set, after deducting the cumulative weight and volume of the allocated orders from the vehicle's approved load capacity and approved volume. The module also calculates the matching degree between the order's cargo weight and cargo volume and the vehicle's remaining load capacity and remaining volume capacity to obtain a comprehensive matching degree score.

[0044] The processing module is used to allocate final matching vehicles to orders from the candidate vehicle set based on the comprehensive matching score, and update the vehicle capacity information of the allocated orders, including the cumulative weight and volume of the final matching vehicles; based on the updated vehicle capacity information, iterative matching is performed on the remaining orders until all orders have been allocated vehicles or there are no matching vehicles.

[0045] Thirdly, a computing device, comprising:

[0046] One or more processors;

[0047] A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the method.

[0048] Fourthly, a computer-readable storage medium storing a program that, when executed by a processor, implements the method.

[0049] The above-described solution of the present invention has at least the following beneficial effects:

[0050] By dynamically acquiring all attribute data of orders to be matched, including cargo weight, cargo volume, destination, timeliness requirements, and available vehicles, and verifying load capacity, volume, current location, and dynamically updated cumulative weight and volume of allocated orders, this system pre-screens geographically feasible candidate vehicles using geographical distance thresholds and constructs a multi-dimensional feature plane. Based on the distribution density of data points on the feature plane, it divides the baseline region and sub-regions, calculates optimization coefficients to adjust the priority of candidate vehicles, calculates remaining capacity by combining vehicle verification capacity and allocated cumulative capacity, and generates a comprehensive score by integrating load capacity, volume, and timeliness matching according to preset weights. After allocating the final vehicles based on the score, it updates capacity in real time and iteratively matches the remaining orders. This technical approach effectively overcomes the technical problems of existing TMS systems, which rely on manual experience or single-dimensional screening for vehicle-order matching, and fail to dynamically integrate real-time cumulative vehicle capacity with multiple order attributes for comprehensive matching. This leads to wasted capacity, order delays, and low efficiency and high cost of manual intervention. Ultimately, it achieves accurate, automated, and dynamic matching of vehicles and orders, improves the vehicle-order matching efficiency and overall capacity utilization of the TMS system, and reduces transportation costs and manual scheduling costs. Attached Figure Description

[0051] Figure 1 This is a flowchart illustrating a method for matching vehicles and orders in a TMS system, as provided in an embodiment of the present invention.

[0052] Figure 2 This is a schematic diagram of a vehicle-order matching dispatch management system in a TMS system provided by an embodiment of the present invention. Detailed Implementation

[0053] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0054] like Figure 1 As shown, an embodiment of the present invention proposes a shipment management method for matching vehicles and orders in a TMS system, the method comprising the following steps:

[0055] Step 1: Obtain the set of orders to be matched and the set of available vehicles; the order set includes the weight, volume, destination and time requirements of each order; the vehicle set includes the rated load capacity, rated volume, current location and dynamically updated cumulative weight and volume of assigned orders for each vehicle.

[0056] Step 2: Based on the order destination and the current location of the vehicle, calculate the spatial distance between the order destination and the current location of each vehicle. By setting a distance threshold, pre-screen a set of geographically feasible candidate vehicles for each order, and convert the order and vehicle data into a set of data points to construct a feature plane.

[0057] Step 3: Determine the reference region on the feature plane, partition the reference region according to the distribution characteristics of the data point set, and obtain the optimization coefficients; adjust the candidate vehicle set through the optimization coefficients to obtain the adjusted candidate vehicle set.

[0058] Step 4: Based on the adjusted candidate vehicle set, calculate the vehicle's remaining load capacity and remaining volume capacity by deducting the cumulative weight and volume of allocated orders from the vehicle's approved load capacity and approved volume.

[0059] Step 5: Calculate the matching degree between the order's cargo weight and volume and the vehicle's remaining load capacity and volume capacity to obtain a comprehensive matching degree score.

[0060] Step 6: Based on the comprehensive matching score, assign the final matching vehicle to the order from the candidate vehicle set, and update the vehicle capacity information of the assigned order's cumulative weight and cumulative volume for the final matching vehicle;

[0061] Step 7: Based on the updated vehicle capacity information, iteratively match the remaining orders until all orders have been assigned vehicles or there are no matching vehicles.

[0062] In this embodiment of the invention, by dynamically acquiring the set of orders to be matched and the set of available vehicles, calculating the spatial distance between the order destination and the current location of the vehicle, pre-screening the set of geographically feasible candidate vehicles using a distance threshold, and constructing a feature plane, after determining the benchmark area on the feature plane, calculating optimization coefficients according to the data point distribution characteristics to adjust the candidate vehicle set, and combining the vehicle's approved load capacity and volume with the cumulative weight and volume of the allocated orders to calculate the remaining load capacity and volume capacity, a comprehensive matching score is generated by calculating the load and volume matching degree between orders and vehicles and assessing the feasibility of delivery, and the final vehicles are allocated based on the score, and the vehicle capacity information is updated in real time and the remaining orders are iteratively matched. Therefore, this method effectively overcomes the technical problems in the existing TMS system, such as the lack of multi-dimensional collaborative consideration in vehicle and order matching, the failure to dynamically track the cumulative capacity of the allocated orders, resulting in low matching accuracy, wasted capacity, order fulfillment delays, and low efficiency of manual intervention in scheduling. Thus, it achieves automated, accurate, and dynamic matching of vehicles and orders, improves the matching efficiency and overall capacity utilization of the TMS system's dispatch management, reduces manual scheduling costs, and ensures timely order fulfillment.

[0063] In a preferred embodiment of the present invention, step 1 above may include:

[0064] Step 1.1: Receive the set of orders to be matched in real time. Each order's data packet contains the order's cargo weight, cargo volume, destination information, and timeliness requirements. Specifically, this includes: establishing a real-time data transmission channel with the order management subsystem to immediately receive the data packet corresponding to the order after it is created, ensuring no delay in order data acquisition; for each received order data packet, extracting the recorded actual weight, actual measured volume, detailed destination information, and specific timeliness requirements, and associating and recording the above data for each order according to the order number to form the basic data pool of orders to be matched.

[0065] Step 1.2: Simultaneously, obtain the set of available vehicles in real time from the vehicle dispatch management subsystem. The dynamic data packet for each vehicle includes the vehicle's rated load capacity, rated volume, real-time updated current location information, and the cumulative weight and volume of currently assigned orders. Specifically, the system maintains real-time data interaction with the vehicle dispatch management subsystem, periodically sending requests to the subsystem to obtain available vehicle data, and simultaneously receiving vehicle status change data actively pushed by the subsystem, such as vehicle location updates and changes in assigned orders. For each obtained dynamic data packet of an available vehicle, first extract the vehicle's rated load capacity and rated volume from the vehicle's basic file, then obtain the real-time updated current location information from a GPS positioning device, accurate to latitude and longitude or specific road location, and finally extract the cumulative weight and volume of goods currently accepted by the vehicle from the assigned order management. The above data is then linked and integrated according to the vehicle number to form a dynamic data pool of available vehicles.

[0066] Step 1.3 involves integrating and verifying the received order set data and the acquired vehicle set data to construct a unified data structure for matching calculations, comprising the order set to be matched and the available vehicle set. Specifically, this includes: first, integrating the formed basic order data pool and the formed dynamic vehicle data pool; then, according to a preset unified data structure standard, converting weight units in the order data to tons and volume units to cubic meters; standardizing destination information to a province-city-district-street hierarchical format; and converting the vehicle's current location information to coordinates or address format matching the order destination information; subsequently, data verification is performed to check... For each order, check for missing weight, volume, destination, or timeliness requirements. For each vehicle, check for missing rated load capacity, rated volume, current location, or cumulative weight and volume of assigned orders. Simultaneously, verify that the vehicle's rated load capacity and volume comply with relevant national vehicle standards, and verify that the order weight and volume are within reasonable transportation limits. For data that passes verification, classify it into the order set to be matched and the available vehicle set according to a unified structure. For data that fails verification, mark it as abnormal data and feed it back to the corresponding subsystem for data completion or correction until a complete, accurate, and structurally unified order set to be matched and available vehicle set are formed.

[0067] In this embodiment of the invention, by employing the technical means of receiving the set of orders to be matched in real time, obtaining the set of available vehicles in real time from the vehicle dispatch management subsystem, and integrating and verifying the order and vehicle data to construct a unified data structure for the set of orders to be matched and the set of available vehicles, the technical problems of delayed acquisition of order and vehicle data, scattered data sources and inconsistent structures, and lack of data verification in the existing TMS system are effectively overcome. This ensures the real-time performance, integrity and standardization of the order and vehicle data to be matched, and improves the reliability of the data foundation of the overall shipping management process.

[0068] In a preferred embodiment of the present invention, step 2 above may include:

[0069] Step 2.1: Based on the destination information of the order and the current location information of each vehicle in the available vehicle set, calculate the spatial distance between the order's destination and the current location of each vehicle. This generates a spatial distance set corresponding to all vehicles for each order. Specifically, this includes: first, extracting the destination information of each order in the order set to be matched, and converting this destination information into precise latitude and longitude coordinates using a geographic information service; simultaneously, extracting the real-time current location information of each vehicle in the available vehicle set, and similarly converting it into corresponding latitude and longitude coordinates. For each order, the system calls the spatial distance calculation method one by one to calculate the latitude and longitude coordinates of the order's destination and the current location of each vehicle in the available vehicle set, obtaining the actual transportation spatial distance between the order's destination and the current location of each vehicle. After completing the distance calculation for all vehicles and the order, the system associates the distance value corresponding to each vehicle with the order according to the vehicle number, forming a spatial distance set with the order as the core and including the corresponding distances of all available vehicles. The above operation is repeated for all orders to be matched, generating a unique spatial distance set for each order.

[0070] Step 2.2 compares each distance value in the spatial distance set with a predefined distance threshold, filtering out vehicles with distance values ​​less than or equal to the threshold to obtain a geographically feasible candidate vehicle set for the order. Specifically, this involves: first, considering the current logistics business scenario, such as the e-commerce promotion scenario mentioned in the background, balancing transportation efficiency and cost by predefining a distance threshold. The threshold setting should refer to the normal transportation radius within the region, the average vehicle transportation speed, and the order's timeliness requirements. For example, a reasonable distance range for short-distance transportation within the region can be set as the distance threshold, such as 100 kilometers, to avoid situations where orders with distant destinations are assigned to nearby vehicles but suffer from insufficient capacity, as in the background. Then, for each order's spatial distance set, the distance value corresponding to each vehicle in the set is compared with the predefined distance threshold, filtering out vehicles with distance values ​​less than or equal to the threshold. These vehicles represent candidates that can efficiently handle the order within the geographical range without requiring long-distance transportation. The filtered vehicles are then categorized by order number, forming a candidate vehicle set for each order containing only geographically feasible vehicles.

[0071] Step 2.3 transforms the candidate vehicle set associated with all orders and their corresponding order data, obtained after filtering, into a set of data points in a multi-dimensional feature space. This constructs a feature plane. Specifically, this involves determining the core feature dimensions required to construct the multi-dimensional feature space. These dimensions must cover the key matching attributes between orders and candidate vehicles, including the order's cargo weight, cargo volume, and timeliness requirements, as well as the candidate vehicle's approved load capacity, approved volume, cumulative weight of allocated orders, cumulative volume of allocated orders, and calculated spatial distance. Then, for each order and its corresponding set of geographically feasible candidate vehicles, the system associates the order's cargo weight, cargo volume, and timeliness requirements with the approved load capacity, approved volume, cumulative weight of allocated orders, cumulative volume of allocated orders, and spatial distance of each vehicle in the candidate vehicle set, forming a combination containing all the aforementioned feature dimensions. The system treats each such combination as an independent data point. All data points formed by orders and their corresponding candidate vehicles together constitute the set of data points in the multi-dimensional feature space. The data points are distributed in the multi-dimensional space according to the attributes of the feature dimensions, ultimately constructing the feature plane for optimization analysis.

[0072] In this embodiment of the invention, a spatial distance is calculated based on the destination information of the order and the current location information of each vehicle in the available vehicle set to generate a spatial distance set for each order. Each distance value in the spatial distance set is compared with a predefined distance threshold to filter out a set of geographically feasible candidate vehicles. The filtered candidate vehicle sets associated with all orders and the corresponding order data are then combined to form a set of multi-dimensional feature spatial data points to construct a feature plane. This overcomes the technical problems in existing TMS systems where vehicle and order matching does not exclude geographically distant invalid vehicles in advance, resulting in redundant computation, chaotic matching range, and unstructured data integration that makes it difficult to support subsequent accurate optimization. Consequently, it is easy for distant vehicles to participate in the matching ineffectively, wasting computational resources and resulting in low matching efficiency. This achieves the goal of reducing the computational amount of invalid matching, narrowing the vehicle range for order matching to improve basic matching efficiency, and simultaneously realizing the structured sorting of order and vehicle data by constructing a feature plane.

[0073] In a preferred embodiment of the present invention, step 3 above may include:

[0074] Step 3.1: Perform a distribution density analysis on the data point set in the feature plane to obtain the analysis results. Based on the analysis results, determine one or more core regions within the feature plane as reference regions. Specifically, this includes: firstly, using a grid division method to uniformly divide the feature plane into multiple equal-area grids, and then counting the number of data points contained in each grid to quantify the data point distribution density in different regions of the feature plane, forming density analysis results. In the analysis results, select high-density grids with a significantly higher number of data points than other grids. The order and vehicle attributes corresponding to the data points in these grids, such as the order cargo weight and the vehicle's remaining load capacity, and the order cargo volume and the vehicle's remaining capacity, have a higher degree of fit and are more likely to form effective matches. Integrate these high-density grids according to their spatial location to form one or more continuous core regions, avoiding matching that only focuses on a single dimension and ignores attribute adaptability, and reducing the situation where vehicles with insufficient load capacity are assigned orders in the background.

[0075] Step 3.2: Based on the density distribution of data points within the baseline region, the baseline region is divided into multiple sub-regions. Specifically, this includes: first, setting a density threshold for the baseline region, which is determined based on the average density of all data points within the baseline region; then, traversing each grid within the baseline region, comparing the density of the grid data points with the threshold, and classifying grids with densities higher than the threshold as dense sub-regions. In these sub-regions, the demand for matching orders with vehicles is more concentrated, such as the area where a large number of home appliance orders and matching heavy-duty vehicles are concentrated during e-commerce promotions in the background; and classifying grids with densities lower than the threshold as sparse sub-regions. In these sub-regions, the matching demand is relatively dispersed. In this way, the baseline region is divided into multiple sub-regions with clearly defined characteristics.

[0076] Step 3.3: For each sub-partition, an optimization coefficient for evaluating matching priority is calculated based on the number of data points, attribute characteristics, and relationship with the overall data point set within the sub-partition. Specifically, this includes: First, counting the total number of data points within each sub-partition; a larger number of data points indicates a richer combination of orders to be matched and candidate vehicles in that area, resulting in a higher base value for the optimization coefficient. Next, analyzing the attribute characteristics of the data points within the sub-partition; if the order corresponding to a data point has an urgent time requirement (e.g., orders requiring delivery within 72 hours in the background), a smaller difference between the vehicle's remaining load capacity and the order's cargo weight, or a smaller difference between the vehicle's remaining volume and the order's cargo volume, then an additional adjustment is added to the base value of the sub-partition's optimization coefficient. Finally, comparing the relationship between the sub-partition and the overall data point set; if the proportion of urgent orders and the proportion of compatible vehicles within the sub-partition are higher than the corresponding proportions in the overall data point set, a supplementary adjustment is added to the optimization coefficient. Combining the base value and various adjustments, the optimization coefficient for each sub-partition is calculated, ensuring that the coefficient reflects the matching priority.

[0077] Step 3.4 involves mapping the optimization coefficients back to the original data. Based on this, the priority or weight of vehicles in the generated candidate vehicle set is adjusted to obtain the adjusted candidate vehicle set. Specifically, this includes: first, establishing a mapping relationship between feature plane data points and original order and vehicle data, clarifying the specific order number and vehicle number corresponding to each data point; then, assigning the optimization coefficient of each sub-partition to the vehicles corresponding to all data points within that partition; then, extracting the information of these vehicles from the candidate vehicle set, and sorting the vehicles from high to low according to the optimization coefficient, with higher-level vehicles having higher priority; for vehicles with the same optimization coefficient, further fine-tuning the sorting based on the remaining cumulative weight and volume of the vehicle's assigned orders to ensure that the priority better matches the actual matching requirements. After sorting, the adjusted candidate vehicle set is formed.

[0078] In this embodiment of the invention, a core benchmark region is determined by performing distribution density analysis on the data point set within the feature plane. Sub-partitions are then divided based on the density characteristics of the data point distribution within the benchmark region. An optimization coefficient for evaluating the matching priority is calculated by combining the number of data points, attribute characteristics, and relationship with the overall data point set within each sub-partition. This optimization coefficient is then mapped back to the original data to adjust the priority or correct the weight of the candidate vehicle set. Therefore, this overcomes the technical problems in existing TMS systems where vehicle-order matching relies solely on a single dimension of screening and does not consider data distribution patterns and vehicle compatibility priorities. This results in highly compatible vehicles not being prioritized, matching decisions lacking specificity, and consequently, capacity mismatch and low order fulfillment efficiency. As a result, the ranking of the candidate vehicle set is made more aligned with actual matching needs, highlighting the priority of highly compatible vehicles, reducing invalid matching attempts, and further improving the accuracy and efficiency of vehicle-order matching.

[0079] In a preferred embodiment of the present invention, step 4 above may include:

[0080] Step 4.1: Based on the obtained adjusted candidate vehicle set, read the approved load capacity, approved volume, and real-time updated cumulative weight and volume of allocated orders for each vehicle in the candidate vehicle set. Specifically, this includes: first, locking the adjusted candidate vehicle set; for each candidate vehicle in the set, retrieving data from the vehicle dynamic information management system; first, reading the basic capacity parameters of each vehicle, i.e., the approved load capacity and approved volume of the vehicle's cargo hold as marked at the factory; then, reading the real-time capacity occupancy data of each vehicle, i.e., the cumulative weight and volume of all orders currently allocated to that vehicle. The cumulative data will be updated to the system immediately after each vehicle completes order allocation, ensuring that the cumulative weight and volume read at this time are the latest data reflecting the current actual capacity occupancy of the vehicle, avoiding the information lag problem caused by the failure to update the cumulative volume of allocated orders in real time, as mentioned in the background.

[0081] Step 4.2: For each vehicle in the adjusted candidate vehicle set, calculate the vehicle's remaining load capacity by subtracting the cumulative weight of allocated orders from the approved load capacity; simultaneously, calculate the vehicle's remaining volume capacity by subtracting the cumulative volume of allocated orders from the approved volume. Specifically, this includes: calculating for each vehicle in the adjusted candidate vehicle set one by one. For a single vehicle, first subtract the cumulative weight of currently allocated orders from the previously read vehicle's approved load capacity value to calculate the upper limit of the vehicle's current cargo weight that can still be carried, i.e., the remaining load capacity; at the same time, subtract the cumulative volume of currently allocated orders from the vehicle's approved volume value to calculate the upper limit of the vehicle's current cargo volume that can still be accommodated, i.e., the remaining volume capacity. By calculating the remaining capacity in terms of both load capacity and volume, the actual available transport capacity of each candidate vehicle can be accurately determined, avoiding matching errors caused by inaccurate transport capacity calculations, such as the case in the background where a vehicle with only 5 tons of remaining load capacity was assigned a 7-ton order.

[0082] In this embodiment of the invention, based on the adjusted candidate vehicle set, the approved load capacity, approved volume, and real-time updated cumulative weight and volume of allocated orders for each vehicle are read. The remaining load capacity is calculated by subtracting the cumulative weight of allocated orders from the vehicle's approved load capacity, and the remaining volume capacity is calculated by subtracting the cumulative volume of allocated orders from the approved volume. This overcomes the technical problem in existing TMS systems where the approved vehicle capacity is not linked to the cumulative capacity of allocated orders in real time, making it impossible to accurately grasp the actual carrying capacity of vehicles. This leads to vehicles being repeatedly assigned overloaded or over-capacity orders, or orders being assigned to vehicles with insufficient remaining capacity, such as assigning a 7-ton order to a vehicle with a cumulative load of 5 tons in the background. This achieves precise quantification of the current actual carrying capacity and volume limit of each candidate vehicle, avoiding problems such as order splitting and manual rescheduling due to capacity judgment errors, and reducing additional transportation and labor costs.

[0083] In a preferred embodiment of the present invention, step 5 above may include:

[0084] Step 5.1: Obtain the weight and volume of the goods in the orders to be matched, and read the remaining load capacity and volume capacity of each vehicle in the adjusted candidate vehicle set. Specifically, this includes: extracting the data of the orders to be matched that need to be calculated from the order set, focusing on obtaining the actual weighed weight and actual measured volume of the goods in the order to ensure that the data is consistent with the actual transportation needs of the order; at the same time, retrieving the adjusted candidate vehicle set data that has been calculated, and reading the remaining load capacity and volume capacity of each candidate vehicle. The data is the latest result calculated based on the vehicle's approved transport capacity and the cumulative transport capacity of the real-time allocated orders, avoiding matching judgment errors due to data lag.

[0085] Step 5.2: For each vehicle in the adjusted candidate vehicle set, calculate the load matching degree between the order's cargo weight and the vehicle's remaining load capacity, and the volume matching degree between the order's cargo volume and the vehicle's remaining volume capacity. Specifically, for each vehicle in the adjusted candidate vehicle set, first calculate the load matching degree by comparing the cargo weight of the order to be matched with the vehicle's remaining load capacity. If the order's cargo weight is less than or equal to the remaining load capacity, and the smaller the difference, the closer the vehicle's remaining load capacity is to the order weight, thus avoiding wasted transport capacity, the load matching degree is higher. If the order's cargo weight exceeds the remaining load capacity, the load matching degree is low, excluding the possibility of the vehicle carrying the order, avoiding the situation in the background where a 100-ton order is assigned to a vehicle with only 5 tons of remaining load capacity. Next, calculate the volume matching degree using the same comparison logic as the load matching degree, comparing the order's cargo volume with the vehicle's remaining volume capacity, and determining the volume matching degree based on the difference between the two, ensuring that the vehicle's volume can accommodate the order's cargo, and avoiding orders that cannot be loaded due to insufficient volume.

[0086] Step 5.3: Based on the timeliness requirements of the order, assess the feasibility of each candidate vehicle in meeting those requirements and generate a timeliness matching degree assessment result. This includes: first, extracting the timeliness requirements of the order to be matched, such as the specific time limit of 72 hours for delivery in the background; then, for each candidate vehicle, combining its current location information and the order destination information, calling the map navigation service to calculate the estimated total time for the vehicle to start from the current location, complete the loading, transportation to the destination, and unloading of goods; comparing the estimated total time with the order timeliness requirements, if the estimated total time is less than or equal to the timeliness requirements, and the larger the difference between the two, the more time the vehicle has to deal with unexpected situations during transportation, the higher the timeliness matching degree; if the estimated total time exceeds the timeliness requirements, the timeliness matching degree is low, thus obtaining a timeliness matching degree assessment result.

[0087] Step 5.4: Based on the evaluation results of load matching, volume matching, and timeliness matching, a comprehensive matching score for the final vehicle decision is obtained by fusion calculation according to preset weight rules. Specifically, this includes: first, preset weight rules according to the current logistics scenario. For example, in the e-commerce promotion scenario mentioned in the background, order timeliness requirements are high and home appliance orders have strict requirements for load and volume adaptability. Therefore, the weight of timeliness matching is set to 40%, the weight of load matching to 30%, and the weight of volume matching to 30%. Then, for each candidate vehicle, its load matching, volume matching, and timeliness matching are multiplied by the corresponding preset weights, and the three products are added together to obtain the comprehensive matching score between the vehicle and the current order to be matched. The higher the score, the stronger the vehicle's comprehensive capabilities in terms of weight adaptability, volume adaptability, and timeliness. A comprehensive matching score for the final vehicle decision is obtained.

[0088] In this embodiment of the invention, the weight and volume of the goods in the order to be matched are obtained, and the remaining load capacity and volume capacity of each vehicle in the adjusted candidate vehicle set are read. The load matching degree and volume matching degree between the order and the vehicle are calculated respectively. The feasibility of each candidate vehicle to meet the timeliness requirements of the order is evaluated to generate the timeliness matching degree. Then, the load matching degree, volume matching degree and timeliness matching degree are integrated according to the preset weight rules to obtain the comprehensive matching degree score. Therefore, this overcomes the technical means of existing TMS systems that rely only on a single dimension for vehicle and order matching and do not comprehensively consider order weight and volume capacity. By conducting multi-dimensional collaborative assessments of volume requirements, vehicle remaining capacity, and order timeliness requirements, technical issues such as mismatches between vehicle load capacity and order demand, delays caused by urgent orders not being prioritized by suitable vehicles, and inaccurate capacity utilization are identified. This approach provides multi-dimensional quantitative decision-making basis for vehicle allocation, achieving precise matching of orders and vehicles in terms of weight, volume, and timeliness. It prioritizes vehicles with the highest overall suitability, reducing order splitting and manual rescheduling caused by improper matching, improving order fulfillment timeliness and overall capacity utilization, and reducing additional transportation costs.

[0089] In a preferred embodiment of the present invention, step 6 above may include:

[0090] Step 6.1: Receive the comprehensive matching score generated for each candidate vehicle, and sort all candidate vehicles according to the score to obtain an ordered candidate vehicle list. Specifically, this includes: receiving the comprehensive matching score generated for each candidate vehicle in the adjusted candidate vehicle set, ensuring that the scores of all vehicles participating in the matching are included in the sorting scope without omission; then initiating the sorting mechanism, using the comprehensive matching score as the core basis, and arranging all candidate vehicles in descending order of score; if multiple candidate vehicles have the same comprehensive matching score, further consider the difference between the vehicle's remaining load capacity and the order's cargo weight, and the difference between the vehicle's remaining volume capacity and the order's cargo volume, prioritizing vehicles with smaller differences, i.e., those whose remaining capacity better matches the order's demand and avoids wasted capacity, and finally forming an ordered candidate vehicle list that clearly reflects the degree of vehicle suitability for the current order.

[0091] Step 6.2: From the ordered list of candidate vehicles, select the vehicle with the highest overall matching score. This vehicle is then designated as the final matching vehicle for the current order and a vehicle allocation instruction is generated. Specifically, this involves extracting the vehicle at the top of the generated list of candidate vehicles; this vehicle has the highest overall matching score. To ensure accurate matching, the vehicle undergoes a second verification process. This verifies whether its remaining load capacity is greater than or equal to the weight of the goods in the current order, whether its remaining volume capacity is greater than or equal to the volume of the goods, and whether its estimated transit time meets the order's timeliness requirements. This avoids misselection due to errors in previous data, such as the situation in the background where a vehicle with insufficient load capacity was assigned an order. After successful verification, the vehicle is officially designated as the final matching vehicle for the current order, and a vehicle allocation instruction containing key information such as the order number, vehicle number, loading location, loading time, order destination, and timeliness requirements is generated.

[0092] Step 6.3: Based on the vehicle allocation instruction, immediately update the vehicle capacity information of the finally matched vehicle after vehicle allocation is completed. This involves adding the order's cargo weight to the vehicle's cumulative weight of allocated orders and adding the order's cargo volume to the vehicle's cumulative volume of allocated orders. This ensures the real-time and accuracy of the vehicle's remaining capacity information. Specifically, this includes: immediately triggering the vehicle capacity information update process after the vehicle allocation instruction is generated and confirmed to have been transmitted to the execution stage, such as the vehicle dispatcher or onboard terminal; extracting the cargo weight and cargo volume from the current order data to be matched; directly adding the cargo weight value to the cumulative weight of allocated orders of the finally matched vehicle to obtain the updated cumulative weight of allocated orders; and simultaneously, directly adding the cargo volume value to the cumulative volume of allocated orders of the vehicle to obtain the updated cumulative volume of allocated orders. After completing the accumulation calculation, the latest vehicle capacity occupancy status can be obtained, avoiding the problem of duplicate allocation of over-capacity orders due to the failure to update the cumulative volume of allocated orders in the background, thus ensuring that the vehicle's remaining capacity information is always real-time and accurate.

[0093] In this embodiment of the invention, the comprehensive matching score of each candidate vehicle is received and sorted according to the score to form an ordered candidate vehicle list. The vehicle with the highest score is selected from the list as the final matched vehicle for the current order, and a vehicle allocation instruction is generated. After the allocation is completed, the weight of the goods in the order is immediately added to the cumulative weight of the vehicle's allocated orders, and the volume of the goods is added to the cumulative volume to update the vehicle's transport capacity information. Therefore, this effectively overcomes the technical problems in the existing TMS system, such as the inability to select the vehicle with the best comprehensive suitability due to single-dimensional screening, the lag in updating the cumulative transport capacity information of the vehicle's allocated orders leading to duplicate allocation of overloaded and over-capacity orders, and the low efficiency and high cost of manual rescheduling. This ensures that the vehicle with the best comprehensive suitability is accurately matched for the order, avoids order splitting or delays due to improper matching, and ensures the real-time and accuracy of vehicle transport capacity information, reduces the frequency of manual intervention, lowers the cost of manual scheduling, and improves the overall efficiency of dispatch management and transport capacity utilization.

[0094] In a preferred embodiment of the present invention, step 7 above may include:

[0095] Step 7.1: After completing vehicle allocation for an order and updating vehicle capacity information, remove the successfully allocated current order from the set of orders to be matched, forming a new set of remaining orders. Specifically, after the current order to be matched is allocated a vehicle and the cumulative weight and volume of the allocated orders for the finally matched vehicle have been updated, immediately locate and remove the successfully allocated order from the set of orders to be matched. The order is accurately identified by the order number to ensure that the removal operation is accurate and avoids accidentally deleting other unallocated orders. After removal, the original set of orders to be matched is automatically updated to a new set of remaining orders containing only unallocated orders, ensuring that the remaining order set can reflect the actual situation of the orders to be processed in real time.

[0096] Step 7.2: Determine whether the new remaining order set is empty, or whether the remaining capacity of all available vehicles is insufficient to meet the basic requirements of any order in the remaining order set. This includes: first, checking the newly generated remaining order set and counting the number of orders it contains. If the number is zero, the remaining order set is considered empty, meaning all orders have been allocated. If the remaining order set is not empty, further check the remaining capacity of all available vehicles, comparing the remaining load capacity of each available vehicle with the weight of goods in each order in the remaining order set, and the remaining volume capacity with the volume of goods in each order, to determine whether there is at least one vehicle whose remaining load capacity is greater than or equal to the weight of goods in a certain order and whose remaining volume capacity is greater than or equal to the volume of goods in that order. If the remaining capacity of all vehicles is insufficient to meet the basic weight and volume requirements of any order in the remaining order set, then no matching vehicle is found.

[0097] Step 7.3: If the remaining order set is not empty and there are matching vehicles, then the updated vehicle capacity information is used as the new input. For the next order in the remaining order set, the steps of claims 2 to 6 are iteratively executed to perform a new round of matching and allocation. Specifically, this includes: when the remaining order set is not empty and there are matching vehicles, the updated capacity information of all available vehicles, including the cumulative weight and volume of the allocated orders and the remaining load and volume calculated therefrom, are used as the latest data input; the next order to be matched is selected from the remaining order set, which can be selected according to preset rules such as order creation time and time urgency. For example, orders with urgent time in the background are given priority. The complete process of steps 2 to 6 is re-executed for the order: calculating the spatial distance to the vehicle and filtering the set of geographically feasible candidate vehicles, constructing a feature plane and adjusting the set of candidate vehicles, calculating the remaining vehicle capacity, evaluating the multi-dimensional matching degree and generating a comprehensive score, allocating the final vehicle and updating the capacity, ensuring that each round of matching is based on the latest vehicle capacity status.

[0098] Step 7.4: Repeat the above iterative process until the remaining order set becomes empty or there are no matching vehicles, thus completing the shipment management of all orders in this round. Specifically, this includes: repeating the operations from Step 7.1 to Step 7.3; after each remaining order is assigned, remove the order and update the remaining order set; check the status of the remaining orders and vehicle capacity; if there are still matching orders and vehicles, continue to execute the complete matching process for the next order. The iterative process continues until the remaining order set becomes empty or it is determined that the remaining capacity of all available vehicles cannot meet the basic requirements of the remaining orders. At this point, the matching process is terminated, and the allocation results of all orders in this round are output, including the correspondence between successfully assigned orders and vehicles, the list of unassigned orders and the reasons, thus completing the full-process shipment management of batch orders such as 300 home appliance orders in the background, achieving automated processing and reducing manual intervention.

[0099] In this embodiment of the invention, because it employs a technical means that after completing the vehicle allocation and updating the capacity information for an order, the allocated orders are removed from the unmatched order set to form a remaining order set, and it is determined whether the remaining order set is empty or whether the remaining capacity of all available vehicles cannot meet the basic requirements of the remaining orders, if the remaining order set is not empty and there are matching vehicles, then steps 2 to 6 are executed iteratively for the next remaining order using the updated capacity as input, and the above process is repeated until there are no remaining orders or no matching vehicles, thus effectively overcoming the lack of an automated iterative mechanism for batch order matching in existing TMS systems. The previous approach addressed the technical issues of manually tracking the allocation progress of remaining orders and real-time changes in vehicle capacity, which could lead to missed order matching or subsequent matching errors due to failure to reuse updated capacity. This resulted in low efficiency and long order processing cycles due to reliance on manual intervention. The solution achieves automated closed-loop matching of batch orders from the first order to the last, ensuring that each remaining order can be accurately matched based on the latest vehicle capacity information without manual intervention. This improves the overall shipping management efficiency in scenarios with concentrated orders, such as e-commerce promotions, avoids order omissions, reduces order fulfillment delays caused by lag in manual intervention, and maximizes the utilization of available vehicle capacity.

[0100] like Figure 2 As shown, embodiments of the present invention also provide a vehicle-order matching dispatch management system in a TMS system, comprising:

[0101] The acquisition module is used to acquire the order set to be matched and the available vehicle set; the order set includes the cargo weight, cargo volume, destination and time requirements of each order; the vehicle set includes the rated load capacity, rated volume, current location of each vehicle, and dynamically updated cumulative weight and volume of assigned orders;

[0102] The optimization module is used to calculate the spatial distance between the order destination and the current location of each vehicle based on the order destination and the current location of the vehicle. By setting a distance threshold, it pre-screens a set of geographically feasible candidate vehicles for each order and converts the order and vehicle data into a set of data points to construct a feature plane. A baseline region is determined on the feature plane, and the baseline region is partitioned according to the distribution characteristics of the data point set to obtain optimization coefficients. The candidate vehicle set is adjusted using the optimization coefficients to obtain the adjusted candidate vehicle set.

[0103] The calculation module is used to calculate the remaining load capacity and remaining volume capacity of a vehicle based on the adjusted candidate vehicle set, after deducting the cumulative weight and volume of the allocated orders from the vehicle's approved load capacity and approved volume. The module also calculates the matching degree between the order's cargo weight and cargo volume and the vehicle's remaining load capacity and remaining volume capacity to obtain a comprehensive matching degree score.

[0104] The processing module is used to allocate final matching vehicles to orders from the candidate vehicle set based on the comprehensive matching score, and update the vehicle capacity information of the allocated orders, including the cumulative weight and volume of the final matching vehicles; based on the updated vehicle capacity information, iterative matching is performed on the remaining orders until all orders have been allocated vehicles or there are no matching vehicles.

[0105] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A shipment management method for matching vehicles and orders in a TMS system, characterized in that, The method includes: Step 1: Obtain the set of orders to be matched and the set of available vehicles; the order set includes the weight, volume, destination and time requirements of each order; the vehicle set includes the rated load capacity, rated volume, current location and dynamically updated cumulative weight and volume of assigned orders for each vehicle. Step 2: Based on the order destination and the current location of the vehicle, calculate the spatial distance between the order destination and the current location of each vehicle. By setting a distance threshold, pre-screen a set of geographically feasible candidate vehicles for each order, and convert the order and vehicle data into a set of data points to construct a feature plane. Step 3: Determine the baseline region on the feature plane. Divide the baseline region into sub-regions based on the distribution characteristics of the data point set to obtain optimization coefficients. Specifically, this includes: For each sub-region, first, count the total number of data points within the sub-region to obtain the base value of the optimization coefficient; then, analyze the attribute characteristics of the data points within the sub-region. The more urgent the order timeliness requirement, the smaller the difference between the vehicle's remaining load capacity and the order's cargo weight, and the smaller the difference between the vehicle's remaining volume and the order's cargo volume, the more adjustments are added to the base value of the sub-region's optimization coefficient. Finally, compare the relationship between the sub-region and the overall data point set. If the proportion of urgent orders and the proportion of compatible vehicles within the sub-region are higher than the corresponding proportions in the overall data point set, further adjustments are added to the optimization coefficient. Combining the above base values ​​and various adjustments, calculate the optimization coefficient for each sub-region. The optimization coefficients for each sub-partition are used to ensure that the coefficients reflect the matching priority. The candidate vehicle set is adjusted by optimizing the coefficients to obtain the adjusted candidate vehicle set. This includes: performing distribution density analysis on the data point set in the feature plane to obtain the analysis results; determining one or more core regions as benchmark regions in the feature plane based on the analysis results; dividing the benchmark region into multiple sub-partitions according to the distribution density characteristics of the data point set in the benchmark region; for each sub-partition, calculating an optimization coefficient for evaluating the matching priority based on the number of data points, attribute characteristics, and their relationship with the overall data point set; mapping the optimization coefficients back to the original data, and adjusting the priority or weight of vehicles in the generated candidate vehicle set accordingly to obtain the adjusted candidate vehicle set. Step 4: Based on the adjusted candidate vehicle set, calculate the vehicle's remaining load capacity and remaining volume capacity by deducting the cumulative weight and volume of allocated orders from the vehicle's approved load capacity and approved volume. Step 5: Calculate the matching degree between the order's cargo weight and volume and the vehicle's remaining load capacity and volume capacity to obtain a comprehensive matching degree score. Step 6: Based on the comprehensive matching score, assign the final matching vehicle to the order from the candidate vehicle set, and update the vehicle capacity information of the assigned order's cumulative weight and cumulative volume for the final matching vehicle; Step 7: Based on the updated vehicle capacity information, iteratively match the remaining orders until all orders have been assigned vehicles or there are no matching vehicles.

2. The method for dispatch management of vehicle-order matching in a TMS system according to claim 1, characterized in that, Based on the order destination and the current location of the vehicle, the spatial distance between the order destination and the current location of each vehicle is calculated. By setting a distance threshold, a set of geographically feasible candidate vehicles is pre-filtered for each order. The order and vehicle data are then transformed into a set of data points to construct a feature plane, including: Based on the destination information of the order and the current location information of each vehicle in the available vehicle set, the spatial distance between the order destination and the current location of each vehicle is calculated, thereby generating a set of spatial distances corresponding to all vehicles for each order. Each distance value in the spatial distance set is compared with a predefined distance threshold, and vehicles with distance values ​​less than or equal to the distance threshold are filtered out to obtain a geographically feasible candidate vehicle set for the order; The candidate vehicle set and corresponding order data obtained after filtering, which are associated with all orders, are transformed into a set of data points in a multi-dimensional feature space, thereby constructing a feature plane.

3. The method for dispatch management of matching vehicles and orders in a TMS system according to claim 2, characterized in that, Based on the adjusted candidate vehicle set, and deducting the cumulative weight and volume of allocated orders from the vehicle's approved load capacity and approved volume, the remaining load capacity and remaining volume capacity of the vehicles are calculated, including: Based on the obtained adjusted candidate vehicle set, the approved load capacity, approved volume, and real-time updated cumulative weight and cumulative volume of allocated orders for each vehicle in the candidate vehicle set are read. For each vehicle in the adjusted candidate vehicle set, the remaining load capacity of the vehicle is calculated by subtracting the cumulative weight of the allocated orders from the approved load capacity; at the same time, the remaining volume capacity of the vehicle is calculated by subtracting the cumulative volume of the allocated orders from the approved volume.

4. The method for dispatch management of vehicle-order matching in a TMS system according to claim 3, characterized in that, The matching degree between the order's cargo weight and volume and the vehicle's remaining load capacity and volumetric capacity is calculated to obtain a comprehensive matching degree score, including: Obtain the weight and volume of the goods in the order to be matched, and read the remaining load capacity and volume capacity of each vehicle in the adjusted candidate vehicle set. For each vehicle in the adjusted candidate vehicle set, calculate the load matching degree between the order's cargo weight and the vehicle's remaining load capacity, and the volume matching degree between the order's cargo volume and the vehicle's remaining volume capacity. Based on the timeliness requirements of the order, assess the feasibility of each candidate vehicle in meeting those requirements and generate a timeliness matching evaluation result. Based on the evaluation results of load matching degree, volume matching degree and time matching degree, a comprehensive matching degree score is obtained by fusion calculation according to the preset weight rules to obtain a final vehicle decision.

5. The method for dispatch management of vehicle-order matching in a TMS system according to claim 4, characterized in that, Based on the comprehensive matching score, final matching vehicles are assigned to orders from the candidate vehicle set, and the vehicle capacity information of the final matching vehicles, including the cumulative weight and cumulative volume of the assigned orders, is updated, including: Receive the comprehensive matching score generated for each candidate vehicle, and sort all candidate vehicles according to the score to obtain an ordered list of candidate vehicles. From the ordered list of candidate vehicles, select the vehicle with the highest overall matching score, determine the vehicle with the highest matching score as the final matching vehicle for the current order to be matched, and generate a vehicle allocation instruction; Based on the vehicle allocation instruction, after the vehicle allocation is completed, the vehicle capacity information of the finally matched vehicle is updated immediately. This means that the weight of the goods in the order is added to the cumulative weight of the vehicle's allocated orders, and the volume of the goods in the order is added to the cumulative volume of the vehicle's allocated orders, so as to ensure the real-time and accuracy of the vehicle's remaining capacity information.

6. The method for dispatch management of matching vehicles and orders in a TMS system according to claim 5, characterized in that, Based on the updated vehicle capacity information, the remaining orders are iteratively matched until all orders are assigned vehicles or no matching vehicles are available, including: After completing the vehicle allocation for an order and updating the vehicle capacity information, the successfully allocated current order is removed from the set of orders to be matched, forming a new set of remaining orders; Determine whether the new set of remaining orders is empty, or whether the remaining capacity of all available vehicles is insufficient to meet the basic requirements of any order in the set of remaining orders; If the remaining order set is not empty and there are matching vehicles, then the updated vehicle capacity information is used as the new input, and steps 2 to 6 are iteratively executed for the next order in the remaining order set to carry out a new round of matching and allocation. Repeat the above iterative process until the remaining order set becomes empty or there are no matching vehicles, thus completing the shipment management of all orders in this round.

7. A vehicle-order matching dispatch management system in a TMS system, the system implementing the method as described in any one of claims 1 to 6, characterized in that, include: The acquisition module is used to acquire the set of orders to be matched and the set of available vehicles; the order set includes the weight, volume, destination and time requirements of each order. The vehicle set includes the vehicle's rated load capacity, rated volume, current location, and dynamically updated cumulative weight and volume of allocated orders; The optimization module is used to calculate the spatial distance between the order destination and the current location of each vehicle based on the order destination and the current location of the vehicle. By setting a distance threshold, it pre-screens a set of geographically feasible candidate vehicles for each order and converts the order and vehicle data into a set of data points to construct a feature plane. A baseline region is determined on the feature plane, and the baseline region is partitioned according to the distribution characteristics of the data point set to obtain the optimization coefficients; The candidate vehicle set is adjusted by optimizing the coefficients to obtain the adjusted candidate vehicle set; The calculation module is used to calculate the remaining load capacity and remaining volume capacity of a vehicle based on the adjusted candidate vehicle set, after deducting the cumulative weight and volume of the allocated orders from the vehicle's approved load capacity and approved volume. The module also calculates the matching degree between the order's cargo weight and cargo volume and the vehicle's remaining load capacity and remaining volume capacity to obtain a comprehensive matching degree score. The processing module is used to allocate final matching vehicles to orders from the candidate vehicle set based on the comprehensive matching score, and update the vehicle capacity information of the allocated orders, including the cumulative weight and volume of the final matching vehicles; based on the updated vehicle capacity information, iterative matching is performed on the remaining orders until all orders have been allocated vehicles or there are no matching vehicles.

8. A computing device, characterized in that, include: One or more processors; A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that, when executed by a processor, implements the method as described in any one of claims 1 to 6.

Images