A smart logistics cost accounting and management method and system

Abstract

This invention relates to the field of logistics cost technology, and specifically discloses an intelligent logistics cost accounting and management method and system. The method includes: acquiring multi-source logistics data and performing data preprocessing to obtain a multi-source logistics dataset; constructing a mixed integer programming model with multiple logistics management objectives; acquiring the current logistics cost accounting scenario, selecting a fusion strategy to fuse preset optimization algorithms, generating a fusion optimization algorithm, dynamically solving the mixed integer programming model with multiple logistics management objectives, and determining the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route; intelligently calculating the logistics cost of each logistics order, and generating intelligent logistics cost accounting data. This invention, by constructing a mixed integer programming model with multiple logistics management objectives and designing a fusion optimization algorithm, effectively realizes the synergy of logistics scheduling, logistics route planning, and logistics cost, ensuring the quality of logistics cost accounting and management.

Description

Technical Field

[0001] This invention relates to the field of logistics cost technology, and in particular to an intelligent logistics cost accounting and management method and system. Background Technology

[0002] The logistics industry is expanding rapidly and logistics networks are becoming increasingly complex, leading to rising logistics costs. Current logistics cost accounting often adopts a model of planning logistics routes first and then calculating logistics costs, which means that even if the logistics route is short, the logistics cost may not be the lowest. In addition, the parameters of the ant colony algorithm or particle swarm algorithm used in current logistics route planning are usually set manually, making it difficult to adapt to complex and ever-changing logistics scenarios.

[0003] Therefore, the present invention provides an intelligent logistics cost accounting and management method and system. Summary of the Invention

[0004] This invention provides an intelligent logistics cost accounting and management method and system. It acquires multi-source logistics data and performs data preprocessing to obtain a multi-source logistics dataset; constructs a mixed-integer programming model with multiple logistics management objectives; obtains the current logistics cost accounting scenario, selects a fusion strategy to fuse preset optimization algorithms, generates a fusion optimization algorithm, dynamically solves the mixed-integer programming model with multiple logistics management objectives, and determines the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route; intelligently calculates the logistics cost of each logistics order, generating intelligent logistics cost accounting data. This invention, by constructing a mixed-integer programming model with multiple logistics management objectives and designing a fusion optimization algorithm, effectively realizes the synergy of logistics scheduling, logistics route planning, and logistics cost, ensuring the quality of logistics cost accounting and management.

[0005] This invention provides an intelligent logistics cost accounting and management method, comprising: Obtain multi-source logistics data through data interfaces and perform data preprocessing to obtain a multi-source logistics dataset. Obtain logistics management objectives and construct a mixed integer programming model with multiple logistics management objectives by combining multi-source logistics datasets; The current logistics cost accounting scenario is obtained, and the preset optimization algorithm is fused by the selected fusion strategy to generate a fusion optimization algorithm. The mixed integer programming model with multiple logistics management objectives is dynamically solved to determine the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route. Based on the optimal logistics vehicle scheduling plan and the optimal logistics transportation route, the system intelligently calculates the logistics cost of each logistics order and generates intelligent logistics cost accounting data.

[0006] According to the present invention, an intelligent logistics cost accounting and management method is provided, which acquires multi-source logistics data through a data interface and performs data preprocessing to obtain a multi-source logistics dataset, including: By accessing the logistics database in real time through a data interface, multi-source logistics data can be obtained, including: historical logistics order data, real-time logistics vehicle location data, real-time logistics transportation route data, real-time logistics warehousing data, real-time logistics transportation constraint data, and customer constraint data. Data preprocessing is performed on multi-source logistics data to obtain a multi-source logistics dataset. The data preprocessing includes: data cleaning, missing data handling, anomaly handling, data alignment, and data standardization.

[0007] According to the intelligent logistics cost accounting and management method provided by the present invention, logistics management objectives are obtained, and a mixed integer programming model with multiple logistics management objectives is constructed by combining multi-source logistics datasets, including: Obtain logistics management requirements and determine logistics management objectives, including logistics cost management objectives and customer satisfaction management objectives. Based on the weights of logistics management needs and the objectives of logistics management, the first objective function and the second objective function of logistics management are set. Obtain the constraints of logistics management, use multi-source logistics datasets as data input, and construct a mixed integer programming model with multiple logistics management objectives by combining the first objective function and the second objective function.

[0008] According to the present invention, an intelligent logistics cost accounting management method is provided, which obtains the current logistics cost accounting scenario, selects a fusion strategy to fuse preset optimization algorithms, and generates a fusion optimization algorithm, including: Based on the multi-source logistics dataset, the logistics cost accounting scenario for the current time period is perceived in real time, the logistics features are extracted and quantified, and the current logistics cost accounting scenario is determined by combining the preset scenario division threshold. The logistics cost accounting scenarios include: small-scale logistics cost accounting scenario, large-scale logistics cost accounting scenario, and real-time logistics cost accounting scenario. Obtain the fusion strategy and select the fusion strategy based on the current logistics cost accounting scenario. The fusion strategies include: serial fusion strategy, hierarchical fusion strategy, and parallel fusion strategy. The preset optimization algorithms are fused according to the selected fusion strategy to generate a fused optimization algorithm. The preset optimization algorithms include ant colony algorithm and particle swarm algorithm. The optimal logistics vehicle scheduling scheme and the optimal logistics transportation route are determined by dynamically solving the mixed integer programming model with multiple logistics management objectives based on the fusion optimization algorithm. If the current logistics cost accounting scenario is a small-scale logistics cost accounting scenario, then the preset optimization algorithm will be serially fused to solve the mixed integer programming model with multiple logistics management objectives. The parameters of the particle swarm optimization algorithm are initialized based on the quantified logistics characteristics, and the population size of the particle swarm optimization algorithm is set according to the number of logistics vehicles. The position and speed data of the logistics vehicles are obtained to determine the initial parameters of the logistics particles. The key parameters of the ant colony algorithm are obtained, the initial logistics particle parameters are converted into logistics ant colony parameters, and then transmitted to the ant colony algorithm for calculation. The optimal logistics transportation route cost is initially obtained, and the adaptability of each logistics vehicle to the current logistics cost accounting scenario is determined. The key parameters of the ant colony algorithm include: ant colony size parameter, pheromone heuristic factor parameter, expected heuristic factor parameter, pheromone evaporation factor parameter, and pheromone intensity constant. The fitness is evaluated, and the parameters of the initial logistics particles are updated based on the evaluation results and the particle swarm algorithm. Boundary processing is performed to ensure that the parameters are within the preset range. The initialized logistics particle parameters are re-transformed and updated, and then transmitted to the ant colony algorithm for iterative calculation. When the calculation of the particle swarm algorithm converges or reaches the maximum number of particle iterations, the iteration ends and the global optimal position of the logistics particle is obtained, which is denoted as the optimized logistics particle parameters. The key parameters of the ant colony algorithm are initialized based on the optimized logistics particle parameters, and the ant colony algorithm is then run. When the ant colony algorithm reaches the maximum number of ant colony iterations or the operation converges, the iteration ends and the optimal logistics transportation route is output. If the current logistics cost accounting scenario is a large-scale logistics cost accounting scenario, then the preset optimization algorithm will be processed in a hierarchical fusion manner to solve the mixed integer programming model with multiple logistics management objectives; The allocation of logistics vehicles is processed using the particle swarm optimization algorithm to obtain the customers of the logistics vehicles and determine the optimal vehicle scheduling scheme. The ant colony algorithm is used to process customers of logistics vehicles, and the logistics transportation routes of each logistics vehicle are independently optimized to determine the optimal logistics transportation route. If the current logistics cost accounting scenario is a real-time logistics cost accounting scenario, then the preset optimization algorithm will be processed in parallel and fused to solve the mixed integer programming model with multiple logistics management objectives; Based on the quantified logistics characteristics, the key parameters of the ant colony algorithm are initialized, and the parameters of the particle swarm algorithm are initialized. The preset number of independent iterations for each algorithm is used; ant colony algorithm and particle swarm algorithm perform independent iterations. The ant colony algorithm performs a preset number of independent iterations to obtain the optimal logistics transportation path for the current iteration; The particle swarm optimization algorithm performs a preset number of independent iterations to obtain the optimal vehicle scheduling scheme for the current iteration; Whenever the number of particle iterations reaches the preset number of independent iterations of the algorithm, the optimal logistics transportation path of the current iteration is transformed into the logistics particle parameters of the particle swarm algorithm, and the particle swarm algorithm performs a new iteration; Whenever the number of ant colony iterations reaches the preset number of independent algorithm iterations, the current iteration's optimal vehicle scheduling scheme is transformed into the current iteration's logistics transportation path for the ant colony algorithm, and the ant colony algorithm proceeds to a new iteration; When the ant colony algorithm and particle swarm algorithm reach the total number of iterations, the iteration converges, or the maximum number of iterations, the optimal solution of each algorithm is output.

[0009] According to the present invention, an intelligent logistics cost accounting and management method is provided, which dynamically solves a mixed integer programming model with multiple logistics management objectives using a fusion optimization algorithm to determine the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route, including: A dynamic solution cycle is set. When the dynamic solution cycle begins, the fusion optimization algorithm is run based on the latest multi-source logistics dataset to dynamically solve the mixed integer programming model with multiple logistics management objectives and update the logistics vehicle scheduling scheme and logistics transportation route. A dynamic solution-driven event is set. When the dynamic solution-driven event is detected, the affected logistics vehicles are located. The fusion optimization algorithm is used to dynamically solve only the affected logistics vehicles to determine the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route.

[0010] According to the intelligent logistics cost accounting management method provided by the present invention, the logistics cost of each logistics order is intelligently calculated based on the optimal logistics vehicle scheduling plan and the optimal logistics transportation route, and intelligent logistics cost accounting data is generated, including: Logistics operations that acquire logistics orders are categorized according to their types, including: logistics transportation operations, logistics warehousing operations, logistics service operations, and logistics management operations. Intelligent accounting of logistics costs for each logistics order, and determination of logistics transportation costs based on the optimal logistics transportation route; Obtain order data for logistics orders to determine the logistics and warehousing costs of logistics and warehousing operations; Based on the optimal logistics vehicle scheduling plan, obtain the customer service time window for each logistics order, determine customer satisfaction, and obtain the logistics service cost of logistics service operations. Obtain the resource usage required to generate the optimal logistics vehicle scheduling plan and the optimal logistics transportation route, and determine the logistics management cost of logistics management operations based on the total resource quantity. Based on the logistics operations, summarize the logistics costs and generate intelligent logistics cost accounting data.

[0011] The intelligent logistics cost accounting and management method provided by the present invention further includes: Obtain the logistics cost threshold, and when the intelligent logistics cost accounting data exceeds the logistics cost threshold, re-plan the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route; Set a logistics cost accounting cycle, and perform reinforcement learning processing on the parameters of the ant colony algorithm or particle swarm algorithm for the next logistics cost accounting cycle based on the logistics execution data within the current logistics cost accounting cycle.

[0012] The intelligent logistics cost accounting and management method provided by the present invention further includes: The optimal logistics vehicle scheduling plan, optimal logistics transportation route, and intelligent logistics cost accounting data are visualized according to the display dimensions, and interactive control is supported. The display dimensions include: time dimension, space dimension, logistics vehicle dimension, customer dimension, and cost dimension.

[0013] This invention provides an intelligent logistics cost accounting and management system, comprising: The multi-source logistics dataset module is used to acquire multi-source logistics data through a data interface and perform data preprocessing to obtain a multi-source logistics dataset. The planning model module is used to obtain logistics management objectives and, in conjunction with multi-source logistics datasets, construct a mixed integer programming model with multiple logistics management objectives. The dynamic solution module is used to obtain the current logistics cost accounting scenario, select a fusion strategy to fuse the preset optimization algorithm, generate a fusion optimization algorithm, and dynamically solve the mixed integer programming model with multiple logistics management objectives to determine the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route. The cost accounting module is used to intelligently calculate the logistics cost of each logistics order based on the optimal logistics vehicle scheduling plan and the optimal logistics transportation route, and generate intelligent logistics cost accounting data.

[0014] The beneficial effects of this invention compared to the prior art are as follows: By acquiring and preprocessing multi-source logistics data, a multi-source logistics dataset is obtained; a mixed-integer programming model with multiple logistics management objectives is constructed; the current logistics cost accounting scenario is obtained, and a fusion strategy is selected to fuse preset optimization algorithms, generating a fusion optimization algorithm to dynamically solve the multi-source logistics management objective mixed-integer programming model, determining the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route; the logistics cost of each logistics order is intelligently calculated, generating intelligent logistics cost accounting data; this invention effectively realizes the synergy of logistics scheduling, logistics route planning, and logistics cost by constructing a multi-source logistics management objective mixed-integer programming model and designing a fusion optimization algorithm, ensuring the quality of logistics cost accounting management.

[0015] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in this application.

[0016] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0017] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 A flowchart illustrating an intelligent logistics cost accounting and management method provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of an intelligent logistics cost accounting and management system provided in an embodiment of the present invention. Detailed Implementation

[0018] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention. Example 1:

[0019] This invention provides an intelligent logistics cost accounting and management method, with reference to Figure 1 ,include: Obtain multi-source logistics data through data interfaces and perform data preprocessing to obtain a multi-source logistics dataset. Obtain logistics management objectives and construct a mixed integer programming model with multiple logistics management objectives by combining multi-source logistics datasets; The current logistics cost accounting scenario is obtained, and the preset optimization algorithm is fused by the selected fusion strategy to generate a fusion optimization algorithm. The mixed integer programming model with multiple logistics management objectives is dynamically solved to determine the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route. Based on the optimal logistics vehicle scheduling plan and the optimal logistics transportation route, the system intelligently calculates the logistics cost of each logistics order and generates intelligent logistics cost accounting data.

[0020] In this embodiment, multi-source logistics data refers to data obtained from a logistics database.

[0021] In this embodiment, the multi-source logistics dataset refers to the data set obtained by preprocessing multi-source logistics data.

[0022] In this embodiment, the logistics management objective refers to the objective of logistics management determined based on logistics management needs.

[0023] In this embodiment, the mixed integer programming model with multiple logistics management objectives refers to a mixed integer programming model constructed based on the first objective function and the second objective function to reflect multiple logistics management objectives.

[0024] In this embodiment, the current logistics cost accounting scenario refers to the logistics cost accounting scenario in the current time period.

[0025] In this embodiment, the fusion strategy refers to the strategy of fusing preset optimization algorithms.

[0026] In this embodiment, the preset optimization algorithm refers to a preset algorithm used to optimize logistics transportation routes and logistics vehicle scheduling schemes.

[0027] In this embodiment, the fusion optimization algorithm refers to the algorithm obtained by fusing a preset optimization algorithm according to a fusion strategy.

[0028] In this embodiment, dynamic solving refers to the operation of updating the multi-source logistics dataset and thus updating the logistics vehicle scheduling scheme and logistics transportation route as time or events change.

[0029] In this embodiment, the optimal logistics vehicle scheduling scheme refers to the scheme that schedules logistics vehicles in the current logistics cost accounting scenario to achieve the highest customer satisfaction.

[0030] In this embodiment, the optimal logistics transportation route refers to the route with the shortest distance and the lowest corresponding logistics cost under the current logistics cost accounting scenario.

[0031] In this embodiment, the intelligent logistics cost accounting data refers to the data determined by intelligent accounting based on the optimal logistics vehicle scheduling plan and the optimal logistics transportation route.

[0032] The beneficial effects of the above technical solution are as follows: By acquiring multi-source logistics data and performing data preprocessing, a multi-source logistics dataset is obtained; a mixed-integer programming model with multiple logistics management objectives is constructed; the current logistics cost accounting scenario is obtained, and a fusion strategy is selected to fuse the preset optimization algorithm to generate a fusion optimization algorithm, which dynamically solves the mixed-integer programming model with multiple logistics management objectives to determine the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route; the logistics cost of each logistics order is intelligently calculated, and intelligent logistics cost accounting data is generated; this invention effectively realizes the coordination of logistics scheduling, logistics route planning and logistics cost by constructing a mixed-integer programming model with multiple logistics management objectives and designing a fusion optimization algorithm, thus ensuring the quality of logistics cost accounting management. Example 2:

[0033] This invention provides an intelligent logistics cost accounting and management method, which acquires multi-source logistics data through a data interface and performs data preprocessing to obtain a multi-source logistics dataset, including: By accessing the logistics database in real time through a data interface, multi-source logistics data can be obtained, including: historical logistics order data, real-time logistics vehicle location data, real-time logistics transportation route data, real-time logistics warehousing data, real-time logistics transportation constraint data, and customer constraint data. Data preprocessing is performed on multi-source logistics data to obtain a multi-source logistics dataset. The data preprocessing includes: data cleaning, missing data handling, anomaly handling, data alignment, and data standardization.

[0034] In this embodiment, the data interface refers to the interface used to connect to the logistics database.

[0035] In this embodiment, the logistics database refers to a database used to store logistics data sources, where the logistics data source refers to the source of logistics data, such as order data, warehousing data, logistics vehicle data, and computing resource data.

[0036] In this embodiment, logistics vehicle data includes, for example, logistics vehicle load data, logistics vehicle range data, and logistics vehicle transportation cost data.

[0037] In this embodiment, computing power resource data refers to the computing power data used for logistics planning during the logistics cost accounting and management process.

[0038] In this embodiment, multi-source logistics data refers to data obtained from a logistics database.

[0039] In this embodiment, customer constraint data includes, for example, customer service time constraint data and customer priority constraint conditions.

[0040] In this embodiment, customer service time refers to the time period during which the customer is satisfied with the logistics order. For example, if the logistics order is completed within the customer service time, the customer satisfaction is 1. If the customer service time is exceeded, the customer satisfaction will continue to decrease.

[0041] In this embodiment, the multi-source logistics dataset refers to the data set obtained by preprocessing multi-source logistics data.

[0042] In this embodiment, data preprocessing is performed on multi-source logistics data to ensure data quality and standardize the data.

[0043] The beneficial effects of the above technical solutions are as follows: by acquiring multi-source logistics data through data interfaces and performing data preprocessing, a multi-source logistics dataset is obtained, laying a data foundation for subsequent intelligent logistics cost accounting and management. Example 3:

[0044] This invention provides an intelligent logistics cost accounting and management method, which obtains logistics management objectives, combines multi-source logistics datasets, and constructs a mixed integer programming model with multiple logistics management objectives, including: Obtain logistics management requirements and determine logistics management objectives, including logistics cost management objectives and customer satisfaction management objectives. Based on the weights of logistics management needs and the objectives of logistics management, the first objective function and the second objective function of logistics management are set. Obtain the constraints of logistics management, use multi-source logistics datasets as data input, and construct a mixed integer programming model with multiple logistics management objectives by combining the first objective function and the second objective function.

[0045] In this embodiment, logistics management needs, such as cost requirements for logistics management, are discussed.

[0046] In this embodiment, the logistics management objectives are the goals for logistics management determined based on logistics management needs, including: logistics cost management objectives and customer satisfaction management objectives.

[0047] In this embodiment, the logistics cost management objective refers to the management objective of minimizing total logistics costs; the customer satisfaction management objective refers to the management objective of maximizing customer satisfaction.

[0048] In this embodiment, the logistics management demand weight refers to the importance of logistics management demand. The higher the logistics management demand weight, the higher the proportion of the corresponding logistics management objective in the logistics management process.

[0049] In this embodiment, the weight of logistics management demand can be set based on customer priority or historical data.

[0050] In this embodiment, a first objective function and a second objective function for logistics management are set according to the weight of logistics management needs and the logistics management objectives. For example, the first objective function for logistics management is set according to the logistics cost management objective, and the second objective function for logistics management is set according to the customer satisfaction management objective.

[0051] In this embodiment, determining the logistics management objective based on the weight of logistics management needs means determining whether the logistics management objective is the primary objective or the secondary objective. For example, if the weight of the logistics cost management objective is greater than the weight of the customer satisfaction management objective, then the logistics cost management objective is the primary objective and the customer satisfaction objective is the secondary objective.

[0052] In this embodiment, the first objective refers to the objective that is given priority in the logistics management process, and the second objective refers to the objective that is considered on the premise that the first objective is met in the logistics management process.

[0053] In this embodiment, the first objective function refers to a function quantized according to the first objective; the second objective function refers to a function quantized according to the second objective.

[0054] In this embodiment, logistics management constraints refer to constraints in the logistics management process, such as vehicle load constraints and customer service time constraints.

[0055] In this embodiment, the multi-logistics management objective mixed integer programming model refers to a mixed integer programming model constructed based on the first objective function and the second objective function to reflect multiple logistics management objectives. It is used to transform logistics management objectives into data objective functions and to optimize and solve them using multi-source logistics datasets, thereby obtaining the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route.

[0056] In this embodiment, the logistics cost management objective and the customer satisfaction management objective are weighted and summed by the logistics management demand weights, thereby transforming multiple objectives into a single objective, providing a foundation for subsequent optimization and solution of the mixed integer programming model with multiple logistics management objectives.

[0057] The beneficial effects of the above technical solutions are: obtaining logistics management objectives, combining multi-source logistics datasets, and constructing a mixed integer programming model with multiple logistics management objectives, which is beneficial for fully considering logistics management objectives when carrying out subsequent logistics scheduling and logistics route planning. Example 4:

[0058] This invention provides an intelligent logistics cost accounting and management method, which obtains the current logistics cost accounting scenario, selects a fusion strategy to fuse preset optimization algorithms, and generates a fusion optimization algorithm, including: Based on the multi-source logistics dataset, the logistics cost accounting scenario for the current time period is perceived in real time, the logistics features are extracted and quantified, and the current logistics cost accounting scenario is determined by combining the preset scenario division threshold. The logistics cost accounting scenarios include: small-scale logistics cost accounting scenario, large-scale logistics cost accounting scenario, and real-time logistics cost accounting scenario. Obtain the fusion strategy and select the fusion strategy based on the current logistics cost accounting scenario. The fusion strategies include: serial fusion strategy, hierarchical fusion strategy, and parallel fusion strategy. The preset optimization algorithms are fused according to the selected fusion strategy to generate a fused optimization algorithm. The preset optimization algorithms include ant colony algorithm and particle swarm algorithm. The optimal logistics vehicle scheduling scheme and the optimal logistics transportation route are determined by dynamically solving the mixed integer programming model with multiple logistics management objectives based on the fusion optimization algorithm. If the current logistics cost accounting scenario is a small-scale logistics cost accounting scenario, then the preset optimization algorithm will be serially fused to solve the mixed integer programming model with multiple logistics management objectives. The parameters of the particle swarm optimization algorithm are initialized based on the quantified logistics characteristics, and the population size of the particle swarm optimization algorithm is set according to the number of logistics vehicles. The position and speed data of the logistics vehicles are obtained to determine the initial parameters of the logistics particles. The key parameters of the ant colony algorithm are obtained, the initial logistics particle parameters are converted into logistics ant colony parameters, and then transmitted to the ant colony algorithm for calculation. The optimal logistics transportation route cost is initially obtained, and the adaptability of each logistics vehicle to the current logistics cost accounting scenario is determined. The key parameters of the ant colony algorithm include: ant colony size parameter, pheromone heuristic factor parameter, expected heuristic factor parameter, pheromone evaporation factor parameter, and pheromone intensity constant. The fitness is evaluated, and the parameters of the initial logistics particles are updated based on the evaluation results and the particle swarm algorithm. Boundary processing is performed to ensure that the parameters are within the preset range. The initialized logistics particle parameters are re-transformed and updated, and then transmitted to the ant colony algorithm for iterative calculation. When the calculation of the particle swarm algorithm converges or reaches the maximum number of particle iterations, the iteration ends and the global optimal position of the logistics particle is obtained, which is denoted as the optimized logistics particle parameters. The key parameters of the ant colony algorithm are initialized based on the optimized logistics particle parameters, and the ant colony algorithm is then run. When the ant colony algorithm reaches the maximum number of ant colony iterations or the operation converges, the iteration ends and the optimal logistics transportation route is output. If the current logistics cost accounting scenario is a large-scale logistics cost accounting scenario, then the preset optimization algorithm will be processed in a hierarchical fusion manner to solve the mixed integer programming model with multiple logistics management objectives; The allocation of logistics vehicles is processed using the particle swarm optimization algorithm to obtain the customers of the logistics vehicles and determine the optimal vehicle scheduling scheme. The ant colony algorithm is used to process customers of logistics vehicles, and the logistics transportation routes of each logistics vehicle are independently optimized to determine the optimal logistics transportation route. If the current logistics cost accounting scenario is a real-time logistics cost accounting scenario, then the preset optimization algorithm will be processed in parallel and fused to solve the mixed integer programming model with multiple logistics management objectives; Based on the quantified logistics characteristics, the key parameters of the ant colony algorithm are initialized, and the parameters of the particle swarm algorithm are initialized. The preset number of independent iterations for each algorithm is used; ant colony algorithm and particle swarm algorithm perform independent iterations. The ant colony algorithm performs a preset number of independent iterations to obtain the optimal logistics transportation path for the current iteration; The particle swarm optimization algorithm performs a preset number of independent iterations to obtain the optimal vehicle scheduling scheme for the current iteration; Whenever the number of particle iterations reaches the preset number of independent iterations of the algorithm, the optimal logistics transportation path of the current iteration is transformed into the logistics particle parameters of the particle swarm algorithm, and the particle swarm algorithm performs a new iteration; Whenever the number of ant colony iterations reaches the preset number of independent algorithm iterations, the current iteration's optimal vehicle scheduling scheme is transformed into the current iteration's logistics transportation path for the ant colony algorithm, and the ant colony algorithm proceeds to a new iteration; When the ant colony algorithm and particle swarm algorithm reach the total number of iterations, the iteration converges, or the maximum number of iterations, the optimal solution of each algorithm is output.

[0059] In this embodiment, the logistics cost accounting scenario refers to a scenario in which logistics cost accounting is performed based on real-time perception and determination of multi-source logistics datasets, such as a small-scale logistics cost accounting scenario.

[0060] In this embodiment, the current logistics cost accounting scenario refers to the logistics cost accounting scenario in the current time period.

[0061] In this embodiment, the scenario division threshold refers to a preset threshold used to divide scenarios. For example, the preset scenario division threshold is a1. If the quantization result is not lower than the scenario division threshold, the current logistics cost accounting scenario is determined to be a large-scale logistics cost accounting scenario; if the quantization result is lower than the scenario division threshold, the current logistics cost accounting scenario is determined to be a small-scale logistics cost accounting scenario.

[0062] In this embodiment, the real-time logistics cost accounting scenario is determined based on the quantification result of the time feature in the logistics characteristics. If the quantification result of the time feature is not higher than the time period b1, the current logistics cost accounting scenario is determined to be a real-time logistics cost accounting scenario, that is, a scenario in which logistics cost accounting needs to be performed immediately.

[0063] In this embodiment, the fusion strategy refers to the strategy of fusing preset optimization algorithms, such as serial fusion strategy, hierarchical fusion strategy, and parallel fusion strategy.

[0064] In this embodiment, the preset optimization algorithm refers to a preset algorithm used to optimize logistics transportation routes and logistics vehicle scheduling schemes, such as ant colony optimization or particle swarm optimization.

[0065] In this embodiment, the fusion optimization algorithm refers to the algorithm obtained by fusing a preset optimization algorithm according to a fusion strategy.

[0066] In this embodiment, the serial fusion strategy refers to passing the parameters of the ant colony algorithm and the particle swarm algorithm, and adjusting the parameters of the ant colony algorithm through the global optimization of the particle swarm algorithm to achieve a higher quality algorithm optimization.

[0067] In this embodiment, the parallel fusion strategy refers to the strategy of synchronously iterating and optimizing the ant colony algorithm and the particle swarm algorithm and periodically exchanging parameters.

[0068] In this embodiment, the hierarchical fusion strategy refers to the strategy of using ant colony optimization and particle swarm optimization to handle different content. For example, particle swarm optimization is used to handle the allocation of logistics vehicles, while ant colony optimization is used to handle the customers of logistics vehicles.

[0069] In this embodiment, solving the mixed integer programming model with multiple logistics management objectives refers to solving the mixed integer programming model with multiple logistics management objectives without considering dynamic changes.

[0070] In this embodiment, the initial speed data of the logistics vehicle is randomly generated within a speed range.

[0071] In this embodiment, initializing the logistics particle parameters refers to the parameters obtained by initializing the particle swarm algorithm based on the quantized logistics characteristics.

[0072] In this embodiment, the logistics particle parameters refer to the parameters used when the particle swarm algorithm performs calculations.

[0073] In this embodiment, key parameters refer to parameters that play an important role in the operation of the ant colony algorithm, such as ant colony size parameter, pheromone heuristic factor parameter, expected heuristic factor parameter, pheromone evaporation factor parameter, and pheromone intensity constant.

[0074] In this embodiment, the logistics ant colony parameters refer to the key parameters of the ant colony algorithm.

[0075] In this embodiment, the optimal logistics transportation route cost refers to the logistics transportation route with the lowest cost.

[0076] In this embodiment, fitness refers to the degree of matching between the logistics vehicle and the current logistics cost accounting scenario. The higher the fitness, the more suitable the logistics vehicle is for logistics transportation in the current logistics cost accounting scenario, and the lower the corresponding logistics cost.

[0077] In this embodiment, fitness is evaluated. For example, a fitness threshold is set. When the fitness is lower than the fitness threshold, it is determined that the corresponding logistics vehicle is not suitable for the current logistics cost accounting scenario, that is, using the corresponding logistics vehicle will result in high logistics costs.

[0078] In this embodiment, boundary processing refers to ensuring that the logistics particle parameters, the initialized logistics particle parameters, and the logistics ant colony parameters are within the corresponding preset ranges to avoid parameter anomalies.

[0079] In this embodiment, the preset range refers to a preset range used to ensure that the parameters are normal.

[0080] In this embodiment, the maximum number of particle iterations refers to the maximum number of iterations performed by the particle swarm algorithm.

[0081] In this embodiment, optimizing the logistics particle parameters refers to obtaining the global optimal position of the logistics particles through iteration based on the particle swarm optimization algorithm.

[0082] In this embodiment, the global optimal position refers to the position of the logistics particle obtained by iteratively according to the particle swarm algorithm when it is globally optimal. The global optimal means that the logistics transportation path is optimal in the current logistics cost accounting scenario.

[0083] In this embodiment, the maximum number of ant colony iterations refers to the maximum number of iterations performed during the operation of the ant colony algorithm.

[0084] In this embodiment, the optimal logistics transportation route refers to the route with the shortest distance and the lowest corresponding logistics cost under the current logistics cost accounting scenario.

[0085] In this embodiment, the optimal logistics vehicle scheduling scheme refers to the scheme that schedules logistics vehicles in the current logistics cost accounting scenario to achieve the highest customer satisfaction.

[0086] In this embodiment, the customers who acquire logistics vehicles refer to the customers served by the logistics vehicles when they are used for logistics transportation, and the order in which the customers are served. A logistics vehicle may have multiple customers, and the order in which the customers are served is determined according to the customer priority.

[0087] In this embodiment, the allocation of logistics vehicles refers to the allocation of logistics transportation routes to logistics vehicles under the current logistics cost accounting scenario.

[0088] In this embodiment, independently optimizing the logistics transportation path of each logistics vehicle means optimizing the logistics transportation path of each logistics vehicle separately according to the ant colony algorithm, in order to ensure that the logistics transportation path of each logistics vehicle is optimal.

[0089] In this embodiment, the number of independent iterations of the algorithm refers to the preset number of iterations performed by each algorithm when performing fusion processing under the parallel fusion strategy.

[0090] In this embodiment, independent iteration means that the iteration of one algorithm does not affect the iteration of another algorithm.

[0091] In this embodiment, the optimal logistics transportation path for the current iteration refers to the optimal logistics transportation path obtained in the current iteration.

[0092] In this embodiment, the optimal vehicle scheduling scheme for the current iteration refers to the optimal vehicle scheduling scheme obtained under the current iteration number.

[0093] In this embodiment, the total number of iterations refers to the maximum number of iterations that the algorithm is designed to perform.

[0094] The beneficial effects of the above technical solution are as follows: by acquiring the current logistics cost accounting scenario, selecting the fusion strategy to fuse the preset optimization algorithm and generate the fusion optimization algorithm, the problem of insufficient algorithm adaptability caused by parameter fixation and local optima in the transmission path planning process is effectively solved, ensuring the accuracy of the optimal logistics vehicle scheduling scheme and the optimal logistics transportation path, and integrating logistics cost into the algorithm to ensure that the optimal logistics transportation path corresponds to the lowest logistics cost. Example 5:

[0095] This invention provides an intelligent logistics cost accounting and management method, which dynamically solves a mixed integer programming model with multiple logistics management objectives using a fusion optimization algorithm to determine the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route, including: A dynamic solution cycle is set. When the dynamic solution cycle begins, the fusion optimization algorithm is run based on the latest multi-source logistics dataset to dynamically solve the mixed integer programming model with multiple logistics management objectives and update the logistics vehicle scheduling scheme and logistics transportation route. A dynamic solution-driven event is set. When the dynamic solution-driven event is detected, the affected logistics vehicles are located. The fusion optimization algorithm is used to dynamically solve only the affected logistics vehicles to determine the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route.

[0096] In this embodiment, the dynamic solution cycle refers to the cycle of solving at fixed times. For example, every fixed time t1, the fusion optimization algorithm is run based on the latest multi-source logistics dataset to update the logistics vehicle scheduling scheme and logistics transportation route, so as to ensure that the logistics vehicle scheduling scheme and logistics transportation route are optimal in each time period.

[0097] In this embodiment, dynamic solving refers to the operation of updating the multi-source logistics dataset and thus updating the logistics vehicle scheduling scheme and logistics transportation route as time or events change.

[0098] In this embodiment, the dynamic solution driving event refers to the event that drives the dynamic solution, such as a sudden congestion event.

[0099] The beneficial effects of the above technical solution are as follows: by dynamically solving the mixed integer programming model with multiple logistics management objectives based on the fusion optimization algorithm, the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route are determined, ensuring the adaptability of the fusion optimization algorithm to complex and ever-changing logistics scenarios. Example 6:

[0100] This invention provides an intelligent logistics cost accounting and management method, which intelligently calculates the logistics cost of each logistics order based on the optimal logistics vehicle scheduling plan and the optimal logistics transportation route, and generates intelligent logistics cost accounting data, including: Logistics operations that acquire logistics orders are categorized according to their types, including: logistics transportation operations, logistics warehousing operations, logistics service operations, and logistics management operations. Intelligent accounting of logistics costs for each logistics order, and determination of logistics transportation costs based on the optimal logistics transportation route; Obtain order data for logistics orders to determine the logistics and warehousing costs of logistics and warehousing operations; Based on the optimal logistics vehicle scheduling plan, obtain the customer service time window for each logistics order, determine customer satisfaction, and obtain the logistics service cost of logistics service operations. Obtain the resource usage required to generate the optimal logistics vehicle scheduling plan and the optimal logistics transportation route, and determine the logistics management cost of logistics management operations based on the total resource quantity. Based on the logistics operations, summarize the logistics costs and generate intelligent logistics cost accounting data.

[0101] In this embodiment, logistics operations refer to operations that divide logistics, such as transportation operations, warehousing operations, and management operations.

[0102] In this embodiment, the logistics operation type refers to the type of logistics operation.

[0103] In this embodiment, intelligent logistics cost accounting refers to the operation of calculating the logistics cost of each logistics order item by item based on the logistics operations.

[0104] In this embodiment, logistics transportation cost refers to the cost of transportation operations; logistics warehousing cost refers to the cost of warehousing operations; logistics service cost refers to the cost of logistics services, that is, the cost of logistics to satisfy customers; and logistics management cost refers to the cost incurred in generating the optimal logistics vehicle scheduling plan and the optimal logistics transportation route for resource allocation, thereby achieving cost accounting.

[0105] In this embodiment, intelligent logistics cost accounting data is generated by summarizing logistics costs based on logistics operations; ; Wherein, C represents intelligent logistics cost accounting data; L(i1,j1) represents the logistics transportation route of the j1st vehicle in the i1st logistics order; c(i1,j1) represents the basic logistics transportation cost data of the j1st vehicle in the i1st logistics order; Vi1 represents the order volume data of the i1st logistics order; Ti1 represents the order storage time data of the i1st logistics order; c1 represents the basic storage cost data of the order; pi1 represents the resource usage for generating the optimal logistics vehicle scheduling plan and optimal logistics transportation route for the i1st logistics order; P1 represents the total resource quantity; c2 represents the logistics management cost data corresponding to the total resource quantity; ti1 represents the timeout data of the i1st logistics order exceeding the customer service time window. This represents the customer satisfaction level for the i1th logistics order; This indicates the decrease in customer satisfaction caused by the timeout data ti1; This function determines when the i-th logistics order exceeds the timeout period of the customer service time window, and outputs the result. Otherwise, output 0; c3 represents the customer satisfaction loss cost data; n1 represents the number of logistics orders; mi1 represents the number of logistics vehicles for the i1th logistics order.

[0106] In this embodiment, the customer service time window refers to a time window constructed based on the customer service time, which is used to accurately represent the customer service time.

[0107] In this embodiment, the basic logistics transportation cost data refers to the logistics transportation cost per unit distance. The basic logistics transportation cost data are different for different logistics vehicles and logistics orders.

[0108] In this embodiment, the basic cost data for order warehousing refers to the warehousing cost per unit volume and per unit time.

[0109] In this embodiment, timeout data refers to the time data of a logistics order exceeding the customer service time window. The longer the timeout, the lower the customer satisfaction and the higher the cost of customer satisfaction loss. For example, if a logistics order exceeds the customer service time window for time t2, then the timeout data is t2.

[0110] In this embodiment, the customer satisfaction loss cost data refers to the loss cost per unit of customer satisfaction. For example, if customer satisfaction decreases by 0.1, logistics costs increase by C10.

[0111] The beneficial effects of the above technical solutions are as follows: based on the optimal logistics vehicle scheduling plan and the optimal logistics transportation route, the logistics cost of each logistics order is intelligently calculated, and intelligent logistics cost accounting data is generated, effectively realizing intelligent accounting management of logistics costs. Example 7:

[0112] This invention provides an intelligent logistics cost accounting and management method, which further includes: Obtain the logistics cost threshold, and when the intelligent logistics cost accounting data exceeds the logistics cost threshold, re-plan the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route; Set a logistics cost accounting cycle, and perform reinforcement learning processing on the parameters of the ant colony algorithm or particle swarm algorithm for the next logistics cost accounting cycle based on the logistics execution data within the current logistics cost accounting cycle.

[0113] In this embodiment, the logistics cost threshold refers to the maximum acceptable logistics cost.

[0114] In this embodiment, when the intelligent logistics cost accounting data exceeds the logistics cost threshold, that is, when the logistics cost exceeds the budget.

[0115] In this embodiment, the logistics cost accounting cycle refers to the cycle in which logistics cost accounting is performed.

[0116] In this embodiment, logistics execution data refers to the actual logistics data executed based on the optimal logistics vehicle scheduling plan and optimal logistics transportation route within the current logistics cost accounting cycle.

[0117] In this embodiment, reinforcement learning processing is performed on the parameters of the ant colony algorithm or particle swarm algorithm for the next logistics cost accounting cycle. The parameters of the ant colony algorithm or particle swarm algorithm include, for example, the key parameters of the ant colony algorithm and the initial logistics particle parameters of the particle swarm algorithm.

[0118] In this embodiment, a deep reinforcement learning algorithm can be used for reinforcement learning processing.

[0119] The beneficial effects of the above technical solutions are as follows: by replanning the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route, and by performing reinforcement learning processing on the algorithm parameters, the quality of the current and future optimal logistics vehicle scheduling scheme and the optimal logistics transportation route is effectively ensured, thereby ensuring the quality of logistics cost accounting. Example 8:

[0120] This invention provides an intelligent logistics cost accounting and management method, which further includes: The optimal logistics vehicle scheduling plan, optimal logistics transportation route, and intelligent logistics cost accounting data are visualized according to the display dimensions, and interactive control is supported. The display dimensions include: time dimension, space dimension, logistics vehicle dimension, customer dimension, and cost dimension.

[0121] In this embodiment, the display dimension refers to the dimension for visualization, such as time dimension, space dimension, logistics vehicle dimension, customer dimension, and cost dimension.

[0122] The beneficial effects of the above technical solutions are as follows: by visually displaying the optimal logistics vehicle scheduling plan, the optimal logistics transportation route, and intelligent logistics cost accounting data according to the display dimensions, and supporting interactive control, it is beneficial to manage and utilize the logistics cost accounting results. Example 9:

[0123] This invention provides an intelligent logistics cost accounting and management system, such as... Figure 2 As shown, it specifically includes: The multi-source logistics dataset module is used to acquire multi-source logistics data through a data interface and perform data preprocessing to obtain a multi-source logistics dataset. The planning model module is used to obtain logistics management objectives and, in conjunction with multi-source logistics datasets, construct a mixed integer programming model with multiple logistics management objectives. The dynamic solution module is used to obtain the current logistics cost accounting scenario, select a fusion strategy to fuse the preset optimization algorithm, generate a fusion optimization algorithm, and dynamically solve the mixed integer programming model with multiple logistics management objectives to determine the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route. The cost accounting module is used to intelligently calculate the logistics cost of each logistics order based on the optimal logistics vehicle scheduling plan and the optimal logistics transportation route, and generate intelligent logistics cost accounting data.

[0124] The beneficial effects of the above technical solution are as follows: By acquiring multi-source logistics data and performing data preprocessing, a multi-source logistics dataset is obtained; a mixed-integer programming model with multiple logistics management objectives is constructed; the current logistics cost accounting scenario is obtained, and a fusion strategy is selected to fuse the preset optimization algorithm to generate a fusion optimization algorithm, which dynamically solves the mixed-integer programming model with multiple logistics management objectives to determine the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route; the logistics cost of each logistics order is intelligently calculated, and intelligent logistics cost accounting data is generated; this invention effectively realizes the coordination of logistics scheduling, logistics route planning and logistics cost by constructing a mixed-integer programming model with multiple logistics management objectives and designing a fusion optimization algorithm, thus ensuring the quality of logistics cost accounting management.

[0125] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A smart logistics cost accounting management method, characterized in that, include: Obtain multi-source logistics data through data interfaces and perform data preprocessing to obtain a multi-source logistics dataset. Obtain logistics management objectives and construct a mixed integer programming model with multiple logistics management objectives by combining multi-source logistics datasets; The current logistics cost accounting scenario is obtained, and the preset optimization algorithm is fused by the selected fusion strategy to generate a fusion optimization algorithm. The mixed integer programming model with multiple logistics management objectives is dynamically solved to determine the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route. Based on the optimal logistics vehicle scheduling plan and the optimal logistics transportation route, the system intelligently calculates the logistics cost of each logistics order and generates intelligent logistics cost accounting data.

2. The intelligent logistics cost accounting management method according to claim 1, characterized in that, Multi-source logistics data is acquired through data interfaces and preprocessed to obtain a multi-source logistics dataset, including: By accessing the logistics database in real time through a data interface, multi-source logistics data can be obtained, including: historical logistics order data, real-time logistics vehicle location data, real-time logistics transportation route data, real-time logistics warehousing data, real-time logistics transportation constraint data, and customer constraint data. Data preprocessing is performed on multi-source logistics data to obtain a multi-source logistics dataset. The data preprocessing includes: data cleaning, missing data handling, anomaly handling, data alignment, and data standardization.

3. The intelligent logistics cost accounting management method according to claim 1, characterized in that, To obtain logistics management objectives, and based on multi-source logistics datasets, a mixed-integer programming model with multiple logistics management objectives is constructed, including: Obtain logistics management requirements and determine logistics management objectives, including logistics cost management objectives and customer satisfaction management objectives. Based on the weights of logistics management needs and the objectives of logistics management, the first objective function and the second objective function of logistics management are set. Obtain the constraints of logistics management, use multi-source logistics datasets as data input, and construct a mixed integer programming model with multiple logistics management objectives by combining the first objective function and the second objective function.

4. The intelligent logistics cost accounting management method according to claim 1, characterized in that, Obtain the current logistics cost accounting scenario, select a fusion strategy to fuse the preset optimization algorithms, and generate a fused optimization algorithm, including: Based on the multi-source logistics dataset, the logistics cost accounting scenario for the current time period is perceived in real time, the logistics features are extracted and quantified, and the current logistics cost accounting scenario is determined by combining the preset scenario division threshold. The logistics cost accounting scenarios include: small-scale logistics cost accounting scenario, large-scale logistics cost accounting scenario, and real-time logistics cost accounting scenario. Obtain the fusion strategy and select the fusion strategy based on the current logistics cost accounting scenario. The fusion strategies include: serial fusion strategy, hierarchical fusion strategy, and parallel fusion strategy. The preset optimization algorithms are fused according to the selected fusion strategy to generate a fused optimization algorithm. The preset optimization algorithms include ant colony algorithm and particle swarm algorithm. The optimal logistics vehicle scheduling scheme and the optimal logistics transportation route are determined by dynamically solving the mixed integer programming model with multiple logistics management objectives based on the fusion optimization algorithm. If the current logistics cost accounting scenario is a small-scale logistics cost accounting scenario, then the preset optimization algorithm will be serially fused to solve the mixed integer programming model with multiple logistics management objectives. The parameters of the particle swarm optimization algorithm are initialized based on the quantified logistics characteristics, and the population size of the particle swarm optimization algorithm is set according to the number of logistics vehicles. The position and speed data of the logistics vehicles are obtained to determine the initial parameters of the logistics particles. The key parameters of the ant colony algorithm are obtained, the initial logistics particle parameters are converted into logistics ant colony parameters, and then transmitted to the ant colony algorithm for calculation. The optimal logistics transportation route cost is initially obtained, and the adaptability of each logistics vehicle to the current logistics cost accounting scenario is determined. The key parameters of the ant colony algorithm include: ant colony size parameter, pheromone heuristic factor parameter, expected heuristic factor parameter, pheromone evaporation factor parameter, and pheromone intensity constant. The fitness is evaluated, and the parameters of the initial logistics particles are updated based on the evaluation results and the particle swarm algorithm. Boundary processing is performed to ensure that the parameters are within the preset range. The initialized logistics particle parameters are re-transformed and updated, and then transmitted to the ant colony algorithm for iterative calculation. When the calculation of the particle swarm algorithm converges or reaches the maximum number of particle iterations, the iteration ends and the global optimal position of the logistics particle is obtained, which is denoted as the optimized logistics particle parameters. The key parameters of the ant colony algorithm are initialized based on the optimized logistics particle parameters, and the ant colony algorithm is then run. When the ant colony algorithm reaches the maximum number of ant colony iterations or the operation converges, the iteration ends and the optimal logistics transportation route is output. If the current logistics cost accounting scenario is a large-scale logistics cost accounting scenario, then the preset optimization algorithm will be processed in a hierarchical fusion manner to solve the mixed integer programming model with multiple logistics management objectives; The allocation of logistics vehicles is processed using the particle swarm optimization algorithm to obtain the customers of the logistics vehicles and determine the optimal vehicle scheduling scheme. The ant colony algorithm is used to process customers of logistics vehicles, and the logistics transportation routes of each logistics vehicle are independently optimized to determine the optimal logistics transportation route. If the current logistics cost accounting scenario is a real-time logistics cost accounting scenario, then the preset optimization algorithm will be processed in parallel and fused to solve the mixed integer programming model with multiple logistics management objectives; Based on the quantified logistics characteristics, the key parameters of the ant colony algorithm are initialized, and the parameters of the particle swarm algorithm are initialized. The preset number of independent iterations for each algorithm is used; ant colony algorithm and particle swarm algorithm perform independent iterations. The ant colony algorithm performs a preset number of independent iterations to obtain the optimal logistics transportation path for the current iteration; The particle swarm optimization algorithm performs a preset number of independent iterations to obtain the optimal vehicle scheduling scheme for the current iteration; Whenever the number of particle iterations reaches the preset number of independent iterations of the algorithm, the optimal logistics transportation path of the current iteration is transformed into the logistics particle parameters of the particle swarm algorithm, and the particle swarm algorithm performs a new iteration; Whenever the number of ant colony iterations reaches the preset number of independent algorithm iterations, the current iteration's optimal vehicle scheduling scheme is transformed into the current iteration's logistics transportation path for the ant colony algorithm, and the ant colony algorithm proceeds to a new iteration; When the ant colony algorithm and particle swarm algorithm reach the total number of iterations, the iteration converges, or the maximum number of iterations, the optimal solution of each algorithm is output.

5. The intelligent logistics cost accounting management method according to claim 4, characterized in that, The mixed-integer programming model with multiple logistics management objectives is dynamically solved using a fusion optimization algorithm to determine the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route, including: A dynamic solution cycle is set. When the dynamic solution cycle begins, the fusion optimization algorithm is run based on the latest multi-source logistics dataset to dynamically solve the mixed integer programming model with multiple logistics management objectives and update the logistics vehicle scheduling scheme and logistics transportation route. A dynamic solution-driven event is set. When the dynamic solution-driven event is detected, the affected logistics vehicles are located. The fusion optimization algorithm is used to dynamically solve only the affected logistics vehicles to determine the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route.

6. The intelligent logistics cost accounting management method according to claim 1, characterized in that, Based on the optimal logistics vehicle scheduling plan and optimal logistics transportation route, the system intelligently calculates the logistics cost of each logistics order and generates intelligent logistics cost accounting data, including: Logistics operations that acquire logistics orders are categorized according to their types, including: logistics transportation operations, logistics warehousing operations, logistics service operations, and logistics management operations. Intelligent accounting of logistics costs for each logistics order, and determination of logistics transportation costs based on the optimal logistics transportation route; Obtain order data for logistics orders to determine the logistics and warehousing costs of logistics and warehousing operations; Based on the optimal logistics vehicle scheduling plan, obtain the customer service time window for each logistics order, determine customer satisfaction, and obtain the logistics service cost of logistics service operations. Obtain the resource usage required to generate the optimal logistics vehicle scheduling plan and the optimal logistics transportation route, and determine the logistics management cost of logistics management operations based on the total resource quantity. Based on the logistics operations, summarize the logistics costs and generate intelligent logistics cost accounting data.

7. The intelligent logistics cost accounting management method according to claim 6, characterized in that, Also includes: Obtain the logistics cost threshold, and when the intelligent logistics cost accounting data exceeds the logistics cost threshold, re-plan the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route; Set a logistics cost accounting cycle, and perform reinforcement learning processing on the parameters of the ant colony algorithm or particle swarm algorithm for the next logistics cost accounting cycle based on the logistics execution data within the current logistics cost accounting cycle.

8. The intelligent logistics cost accounting management method according to claim 1, characterized in that, Also includes: The optimal logistics vehicle scheduling plan, optimal logistics transportation route, and intelligent logistics cost accounting data are visualized according to the display dimensions, and interactive control is supported. The display dimensions include: time dimension, space dimension, logistics vehicle dimension, customer dimension, and cost dimension.

9. An intelligent logistics cost accounting management system, characterized by, include: The multi-source logistics dataset module is used to acquire multi-source logistics data through a data interface and perform data preprocessing to obtain a multi-source logistics dataset. The planning model module is used to obtain logistics management objectives and, in conjunction with multi-source logistics datasets, construct a mixed integer programming model with multiple logistics management objectives. The dynamic solution module is used to obtain the current logistics cost accounting scenario, select a fusion strategy to fuse the preset optimization algorithm, generate a fusion optimization algorithm, and dynamically solve the mixed integer programming model with multiple logistics management objectives to determine the optimal logistics vehicle scheduling scheme and the optimal logistics transportation route. The cost accounting module is used to intelligently calculate the logistics cost of each logistics order based on the optimal logistics vehicle scheduling plan and the optimal logistics transportation route, and generate intelligent logistics cost accounting data.

Images