Large carrying vehicle comprehensive management method and device based on intelligent logistics and storage medium

Abstract

The invention discloses a large carrying vehicle comprehensive management method based on intelligent logistics, and the method comprises the steps: obtaining a target carrying task, and generating a target carrying demand according to the target carrying task; decomposing the target carrying demand, and determining a carrying capacity index and a driver fit index; matching the carrying capacity index with preset vehicle carrying capacity data to generate a loading characterization degree; matching the driver fit index with preset driver behavior data to generate a driving characterization degree; the compatibility characterization degree is determined by integrating the loading characterization degree and the driving characterization degree, and the vehicle and the driver corresponding to the maximum compatibility characterization degree are selected to undertake the target carrying task. Meanwhile, needed vehicles and drivers are subjected to matching planning, double-line selection of the vehicles and the drivers can be completed at a time, and the matching efficiency of the whole carrying task is improved; the vehicle and the driver are used as two to-be-matched items for fitting configuration, so that the scheduling efficiency of the to-be-carried vehicle and the matching precision of the driver are improved.

Description

Technical Field

[0001] The present invention relates to the field of smart logistics technology, and in particular to a comprehensive management method, device and storage medium for large transport vehicles based on smart logistics. Background Art

[0002] With the booming e-commerce and the rapid development of the logistics industry, massive amounts of logistics data have been generated. Logistics companies need to efficiently process and analyze large amounts of data to optimize operational processes and improve delivery efficiency. Traditional management methods are unable to cope with the rapid growth of data volume and are prone to problems such as insufficient data storage and slow processing speeds.

[0003] The existing technology lacks the means to carry out intelligent integrated management of transport vehicle information, which cannot meet the growing information needs of the logistics industry. It is easy to lead to problems such as low vehicle scheduling efficiency and low driver matching accuracy, which is not conducive to the efficient management and optimized utilization of the logistics industry. Summary of the Invention

[0004] In order to solve the technical problems existing in the background technology, the present invention proposes a comprehensive management method, device and storage medium for large-scale transport vehicles based on smart logistics.

[0005] The present invention proposes a comprehensive management method for large-scale transport vehicles based on smart logistics, including:

[0006] Obtaining a target transport mission, and generating a target transport demand according to the target transport mission;

[0007] Decompose the target transportation demand and determine the transportation capacity index and driver fit index;

[0008] Matching the carrying capacity index with the preset vehicle capacity data to generate a load characterization degree, and sorting each vehicle from high to low according to the load characterization degree;

[0009] Matching the driver compatibility index with preset driver behavior data to generate a driving characterization score, and ranking each driver from high to low according to the driving characterization score;

[0010] The compatible representation degree is determined by comprehensively considering the cargo representation degree and the driving representation degree, and the vehicle and driver corresponding to the maximum compatible representation degree are selected to undertake the target transport task.

[0011] Optionally, the target transport task includes a starting point location, an end point location, a driving route, a driving distance, a driving time, a cargo type, a total cargo weight, and a total cargo volume;

[0012] The target transportation demand includes vehicle performance parameters, transportation performance parameters, and driver credit parameters;

[0013] The vehicle performance parameters are formed by fitting the starting position, the end position, the driving route, the driving distance, and the driving time;

[0014] The transport performance parameters are formed by fitting the cargo type, total cargo weight, and total cargo volume;

[0015] The driver's driving experience and route preference are introduced and fitted to form the driver's credit parameter.

[0016] Optionally, the carrying capacity index is formed by fitting the vehicle performance parameters and the transport performance parameters;

[0017] The driver's historical cooperation times and historical credit evaluation data are introduced, and combined with the driver's credit parameters to form the driver fit index.

[0018] Optionally, matching the carrying capacity index with preset vehicle capacity data to generate a load representation degree specifically includes:

[0019] Mapping the vehicle performance parameter into a target vector A;

[0020] Mapping the transport performance parameter into a target vector B;

[0021] Mapping the preset vehicle capacity data into a reference vector C;

[0022] According to the Jaccard similarity algorithm, the similarity between the target vector A and the reference vector C, and the similarity between the target vector B and the reference vector C are calculated respectively, and the similarity indexes J(A, C) and J(B, C) are output;

[0023]

[0024] Calculate the payload representation R based on the similarity indices J(A, C) and J(B, C), R = aJ(A, C) + bJ(B, C);

[0025] Among them, a and b are preset weight values.

[0026] Optionally, matching the driver fit index with preset driver behavior data to generate a driving representation degree specifically includes:

[0027] Mapping the driver's historical cooperation times into a target vector D;

[0028] Mapping the historical credit evaluation data into a target vector E;

[0029] Mapping the driver credit parameter to a target vector F;

[0030] Mapping the preset driver behavior data into a reference vector G;

[0031] According to the Jaccard similarity algorithm, the similarity between the target vector D and the reference vector G, the target vector E and the reference vector G, and the target vector F and the reference vector G are calculated respectively, and the similarity indexes J(D, G), J(E, G), and J(F, G) are output;

[0032]

[0033] Calculate the driving representation M based on the similarity indices J(D,G), J(E,G), and J(F,G);

[0034] M=cJ(D,G)+dJ(E,G)+eJ(F,G);

[0035] Among them, c, d, and e are all preset weight values.

[0036] Optionally, when the target transport task requires m vehicles and n drivers, the first m vehicles ranked from high to low in terms of cargo representation are selected, and the first n drivers ranked from high to low in terms of driving representation are selected.

[0037] The present invention also proposes a comprehensive management device for large transport vehicles based on smart logistics, including: a memory and a processor, the memory is used to store information including program instructions, the processor is used to control the execution of program instructions, and when the program instructions are loaded and executed by the processor, the comprehensive management method for large transport vehicles based on smart logistics is implemented.

[0038] The present invention also proposes a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements the aforementioned method for comprehensive management of large transport vehicles based on smart logistics.

[0039] From the above solutions, it can be seen that the comprehensive management method for large-scale transport vehicles based on smart logistics provided by this application has at least the following beneficial effects compared with the existing technology:

[0040] At the same time, matching planning is carried out for the vehicles and drivers required for the transport mission, completing the dual-line selection of vehicles and drivers in one go, improving the efficiency of the entire transport mission matching. When performing the above matching planning, the vehicle and driver are treated as two matching items and are fitted and configured separately. A variety of reference information such as vehicle performance parameters, transportation performance parameters, driver credit parameters, vehicle capacity data, driver behavior data, route preferences, etc. are introduced to comprehensively plan and select the vehicles and drivers to be transported, improving the efficiency of dispatching vehicles to be transported and the accuracy of driver matching, while ensuring the timeliness and safety of the transport mission. When selecting the vehicle to be transported, both the vehicle performance parameters and the transportation performance parameters are used as target vectors and compared with the preset vehicle capacity data for similarity. The data overlap is calculated by comparing the similarity of the two sets. The vehicle corresponding to the highest overlap can best meet the current transport mission requirements, thereby ensuring the efficiency and accuracy of vehicle configuration. When selecting a driver, the driver's historical cooperation times, historical credit evaluation data, and driver credit parameters are all used as target vectors. The Jaccard similarity algorithm is used to perform similarity comparison with the preset driver behavior data to screen out the most suitable driver, improve the accuracy of driver matching, and ensure the safety of the transportation mission. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a flowchart of a comprehensive management method for large transport vehicles based on smart logistics. DETAILED DESCRIPTION

[0042] like Figure 1 As shown, Figure 1 This is a flowchart of a comprehensive management method for large transport vehicles based on smart logistics proposed by the present invention.

[0043] Reference Figure 1 The present invention proposes a comprehensive management method for large-scale transport vehicles based on smart logistics, including:

[0044] Obtaining a target transport mission, and generating a target transport demand according to the target transport mission;

[0045] Decompose the target transportation demand and determine the transportation capacity index and driver fit index;

[0046] Matching the carrying capacity index with the preset vehicle capacity data to generate a load characterization degree, and sorting each vehicle from high to low according to the load characterization degree;

[0047] Matching the driver compatibility index with preset driver behavior data to generate a driving characterization score, and ranking each driver from high to low according to the driving characterization score;

[0048] The compatible representation degree is determined by comprehensively considering the cargo representation degree and the driving representation degree, and the vehicle and driver corresponding to the maximum compatible representation degree are selected to undertake the target transport task.

[0049] When the system receives a new transport mission, it immediately generates a transport demand based on the transport mission; it then decomposes the transport demand to determine the performance of the vehicle and the comprehensive quality of the driver that can fully undertake this transport mission; then, based on the above decomposition results, it performs a matching search in the system database to screen out the most suitable transport vehicles and drivers for the trip; this method selects transport vehicles and drivers in a targeted manner based on actual transport needs, which is conducive to improving the efficiency of vehicle and driver scheduling, the accuracy of matching, and ensuring the timeliness and safety of transportation.

[0050] This method simultaneously matches and plans the vehicles and drivers required for a delivery mission, completing both vehicle and driver selection in a single pass, improving the efficiency of the overall delivery mission matching process. During this matching process, the method treats the vehicle and driver as two separate matching items, performing separate matching configurations. This avoids the low matching accuracy of a single matching item caused by binding a vehicle and driver together, outputting the optimal vehicle + driver combination, comprehensively improving the rationality and scientific nature of dispatching and allocation.

[0051] In a further embodiment, the target transport task includes a starting location, an end location, a driving route, a driving distance, a driving time, a cargo type, a total cargo weight, and a total cargo volume;

[0052] The target transportation demand includes vehicle performance parameters, transportation performance parameters, and driver credit parameters;

[0053] The vehicle performance parameters are formed by fitting the starting position, the end position, the driving route, the driving distance, and the driving time;

[0054] The transport performance parameters are formed by fitting the cargo type, total cargo weight, and total cargo volume;

[0055] The driver's driving experience and route preference are introduced and fitted to form the driver's credit parameter.

[0056] When matching vehicles intelligently, the geographical locations of the starting and ending points (e.g., east, south, west, and north have different requirements for vehicle performance), the terrain of the areas passed through (e.g., plains, hills, mountains, plateaus, and basins have different requirements for vehicle performance), and whether it is ultra-long-distance transportation (different requirements for vehicle power, carrying capacity, etc.) can be determined based on multiple data information such as the starting point location, end point location, driving route, driving distance, and driving time. Then, vehicles with the actual required performance are targeted and screened to ensure the accuracy of the screening results. At the same time, transportation performance parameters are formed by fitting the cargo type, total cargo weight, and total cargo volume, and the above-screened vehicles (vehicle length, load capacity, solid, liquid, and gas special vehicles, etc.) are screened for the second time to optimize the transportation efficiency of vehicles and cargo, reduce the empty load rate and transportation costs, and improve the configuration accuracy of vehicles and cargo. When intelligently screening drivers, the driver's compatibility with the difficulty of the transportation task is assessed based on their driving experience and route preferences (long-distance and short-distance driving, different terrains, and driving to the east, west, south, and north, etc.); this method refines multiple reference indicators and comprehensively analyzes the performance of the required vehicle and the quality of the required driver from multiple dimensions, in order to achieve dual-line adaptation of the vehicle, driver, and transportation task.

[0057] In a further embodiment, the carrying capacity index is formed by fitting the vehicle performance parameter and the transport performance parameter;

[0058] The driver's historical cooperation times and historical credit evaluation data are introduced, and combined with the driver's credit parameters to form the driver fit index.

[0059] The driver's historical cooperation times and historical credit rating data are further used as secondary screening items. The results of the first screening are combined with the driver's historical driving behavior for comprehensive analysis to eliminate interference items and output the combination of the optimal vehicle + the optimal driver to achieve dual-line optimization of transportation timeliness + transportation safety.

[0060] In a further embodiment, matching the carrying capacity index with preset vehicle capacity data to generate a load representation degree specifically includes:

[0061] Mapping the vehicle performance parameter into a target vector A;

[0062] Mapping the transport performance parameter into a target vector B;

[0063] Mapping the preset vehicle capacity data into a reference vector C;

[0064] According to the Jaccard similarity algorithm, the similarity between the target vector A and the reference vector C, and the similarity between the target vector B and the reference vector C are calculated respectively, and the similarity indexes J(A, C) and J(B, C) are output;

[0065]

[0066] Calculate the payload representation R based on the similarity indices J(A, C) and J(B, C), R = aJ(A, C) + bJ(B, C);

[0067] Among them, a and b are preset weight values.

[0068] The Jaccard Similarity algorithm is introduced to compare the similarity between vehicle performance parameters and preset vehicle capacity data, and between transport performance parameters and preset vehicle capacity data. The recommendation system then selects vehicles highly suitable for the target transport mission from the system's preset database, ensuring the scientific and reasonableness of the algorithm's results. When calculating the load representation R, a preset weight is again introduced to balance the selection errors of the two similarity indicators, reducing interference and improving the accuracy of the results.

[0069] In a further embodiment, matching the driver fit index with preset driver behavior data to generate a driving representation metric specifically includes:

[0070] Mapping the driver's historical cooperation times into a target vector D;

[0071] Mapping the historical credit evaluation data into a target vector E;

[0072] Mapping the driver credit parameter to a target vector F;

[0073] Mapping the preset driver behavior data into a reference vector G;

[0074] According to the Jaccard similarity algorithm, the similarity between the target vector D and the reference vector G, the target vector E and the reference vector G, and the target vector F and the reference vector G are calculated respectively, and the similarity indexes J(D, G), J(E, G), and J(F, G) are output;

[0075]

[0076] Calculate the driving representation M based on the similarity indices J(D,G), J(E,G), and J(F,G);

[0077] M=cJ(D,G)+dJ(E,G)+eJ(F,G);

[0078] Among them, c, d, and e are all preset weight values.

[0079] Using the Jaccard Similarity algorithm, the system compares the similarity between a driver's historical cooperation history and pre-set driver behavior data, their historical credit rating data and pre-set driver behavior data, and their credit parameters and pre-set driver behavior data. By comparing user interest tags, the system selects drivers suitable for the target delivery task from the pre-set database. When calculating the driving representation degree M, the system assigns pre-set weights to the three similarity indicators to reduce the influence of individual indicators on the overall results and improve the rationality and scientific nature of driver selection.

[0080] In a further embodiment, when the target transport task requires m vehicles and n drivers, the first m vehicles ranked from high to low in terms of cargo representation are selected, and the first n drivers ranked from high to low in terms of driving representation are selected.

[0081] After decomposing the target transportation task into target transportation requirements, information such as cargo type, total cargo weight, and total cargo volume is obtained. If there are different cargo types in a single transportation task, the cargo is first classified, and then the carrying capacity index and driver compatibility index of each cargo type are determined separately. Then, the Jaccard similarity algorithm is used to screen the vehicles and drivers required for the transportation of each cargo type. Finally, different types of vehicle and driver combinations corresponding to multiple cargo types are output. If the transportation volume of the same cargo type is huge, the corresponding number of vehicles and drivers are selected in order according to the load representation and driving representation under the current calculation mode, without repeated calculation, thus improving calculation efficiency.

[0082] The present invention also proposes a comprehensive management device for large transport vehicles based on smart logistics, including: a memory and a processor, the memory is used to store information including program instructions, the processor is used to control the execution of program instructions, and when the program instructions are loaded and executed by the processor, the comprehensive management method for large transport vehicles based on smart logistics is implemented.

[0083] The present invention also proposes a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements the comprehensive management method of large-scale transport vehicles based on smart logistics.

[0084] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A comprehensive management method for large transport vehicles based on smart logistics, characterized in that: include: Obtaining a target transport mission, and generating a target transport demand according to the target transport mission; Decompose the target transportation demand and determine the transportation capacity index and driver fit index; Matching the carrying capacity index with the preset vehicle capacity data to generate a load characterization degree, and sorting each vehicle from high to low according to the load characterization degree; Matching the driver compatibility index with preset driver behavior data to generate a driving characterization score, and ranking each driver from high to low according to the driving characterization score; The compatible representation degree is determined by comprehensively considering the cargo representation degree and the driving representation degree, and the vehicle and driver corresponding to the maximum compatible representation degree are selected to undertake the target transport task.

2. The large-scale transport vehicle integrated management method based on intelligent logistics according to claim 1 is characterized in that: The target transport task includes the starting location, the end location, the driving route, the driving distance, the driving time, the cargo type, the total cargo weight, and the total cargo volume; The target transportation demand includes vehicle performance parameters, transportation performance parameters, and driver credit parameters; The vehicle performance parameters are formed by fitting the starting position, the end position, the driving route, the driving distance, and the driving time; The transport performance parameters are formed by fitting the cargo type, total cargo weight, and total cargo volume; The driver's driving experience and route preference are introduced and fitted to form the driver's credit parameter.

3. The large-scale transport vehicle integrated management method based on intelligent logistics according to claim 2 is characterized in that: The carrying capacity index is formed by fitting the vehicle performance parameters and the transport performance parameters; The driver's historical cooperation times and historical credit evaluation data are introduced, and combined with the driver's credit parameters to form the driver fit index.

4. The large-scale transport vehicle integrated management method based on intelligent logistics according to claim 3 is characterized in that: The matching of the carrying capacity index with the preset vehicle capacity data to generate a load representation degree specifically includes: Mapping the vehicle performance parameter into a target vector A; Mapping the transport performance parameter into a target vector B; Mapping the preset vehicle capacity data into a reference vector C; According to the Jaccard similarity algorithm, the similarity between the target vector A and the reference vector C, and the similarity between the target vector B and the reference vector C are calculated respectively, and the similarity indexes J(A, C) and J(B, C) are output; Calculate the payload representation R based on the similarity indices J(A, C) and J(B, C), R = aJ(A, C) + bJ(B, C); Among them, a and b are preset weight values.

5. The large-scale transport vehicle integrated management method based on intelligent logistics according to claim 3 is characterized in that: The matching of the driver fit index with the preset driver behavior data to generate a driving representation degree specifically includes: Mapping the driver's historical cooperation times into a target vector D; Mapping the historical credit evaluation data into a target vector E; Mapping the driver credit parameter to a target vector F; Mapping the preset driver behavior data into a reference vector G; According to the Jaccard similarity algorithm, the similarity between the target vector D and the reference vector G, the target vector E and the reference vector G, and the target vector F and the reference vector G are calculated respectively, and the similarity indexes J(D, G), J(E, G), and J(F, G) are output; Calculate the driving representation M based on the similarity indices J(D,G), J(E,G), and J(F,G); M=cJ(D,G)+dJ(E,G)+eJ(F,G); Among them, c, d, and e are all preset weight values.

6. The large-scale transport vehicle integrated management method based on intelligent logistics according to claim 1 is characterized in that: When the target transport task requires m vehicles and n drivers, the first m vehicles ranked from high to low in terms of cargo representation are selected, and the first n drivers ranked from high to low in terms of driving representation are selected.

7. A comprehensive management device for large transport vehicles based on smart logistics, comprising: A memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions, characterized in that when the program instructions are loaded and executed by the processor, the integrated management method for large transport vehicles based on smart logistics as described in any one of claims 1 to 6 is implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for comprehensive management of large transport vehicles based on smart logistics as described in any one of claims 1 to 6 is implemented.

Images