Logistics transportation cost optimization method and system based on multiple channels

Abstract

The invention relates to a multi-channel-based logistics transportation cost optimization method and system, and the method comprises the steps: obtaining real-time transportation data and storage capacity data of a multi-channel logistics transportation system, carrying out the channel classification of the real-time transportation data based on the storage capacity data, and obtaining channel transportation information; acquiring real-time cost data of the multi-channel logistics transportation system, and performing cost matching analysis on the real-time cost data and the channel transportation information to obtain a channel cost group; performing benefit optimization on the channel cost group and the transportation load prediction result to obtain an initial resource allocation scheme; and carrying out emergency transportation demand identification and path planning on the real-time transportation data based on the transportation load prediction result, and carrying out scheme integration with the initial resource allocation scheme to obtain a channel transportation optimization scheme. The method can give full play to the advantages of each channel, and achieves the optimal configuration of resources.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics and transportation, and in particular to a multi-channel-based logistics and transportation cost optimization method and system. Background Art

[0002] As an essential component of modern supply chain management, logistics and transportation systems play a key role in the globalized economy. With the booming development of e-commerce and the diversification of consumer demand, multi-channel logistics and transportation systems have emerged as a crucial solution for improving logistics efficiency and reducing transportation costs. However, in a complex multi-channel logistics environment, how to scientifically optimize transportation costs and achieve efficient resource allocation has become a key issue that urgently needs to be addressed in the field of logistics management. Existing logistics and transportation cost optimization methods often have the following limitations: most methods focus solely on cost control within a single transportation channel, ignoring the synergy and resource complementarity between multiple channels; secondly, traditional cost optimization models are typically based on static data analysis and are unable to cope with real-time changes in transportation demand and dynamically fluctuating market environments; furthermore, existing methods lack flexible response mechanisms to urgent transportation needs and lack accurate predictions of transportation loads, resulting in deviations between resource allocation plans and actual transportation demand. These issues not only affect the overall efficiency of logistics and transportation systems but also increase unnecessary operating costs. Summary of the Invention

[0003] The main purpose of the present invention is to provide a multi-channel logistics transportation cost optimization method and system, which can give full play to the advantages of each channel and achieve the optimal allocation of resources, thereby significantly reducing the overall transportation cost and improving the operational efficiency of the logistics system.

[0004] To achieve the above objectives, the present invention provides a multi-channel logistics transportation cost optimization method, comprising: Acquire real-time transportation data and storage capacity data of a multi-channel logistics transportation system, classify the real-time transportation data by channel based on the storage capacity data, and obtain channel transportation information; Acquire real-time cost data of the multi-channel logistics transportation system, perform cost matching analysis with the channel transportation information, and obtain a channel cost group; Obtaining historical transportation records of the multi-channel logistics transportation system, performing trend forecasting on the channel transportation information, and obtaining a transportation load forecast result; Performing benefit optimization on the channel cost group and the transportation load forecast result to obtain an initial resource allocation plan; Based on the transport load forecast result, the real-time transport data is used to identify urgent transport needs and plan routes, and the plan is integrated with the initial resource allocation plan to obtain a channel transport optimization plan.

[0005] Furthermore, the real-time transportation data and storage capacity data of the multi-channel logistics transportation system are obtained, and the real-time transportation data is classified by channel based on the storage capacity data to obtain channel transportation information, including: Collecting transportation data from the multi-channel logistics transportation system to obtain an initial transportation data set; Performing logistics node distribution analysis based on the initial transportation data set to obtain a node distribution matrix; Identifying storage point capacities of the multi-channel logistics and transportation system based on the node distribution matrix to obtain a storage capacity indicator set; Perform channel clustering on the node distribution matrix according to the storage capacity indicator set to obtain a preliminary channel grouping result; hierarchically sorting the preliminary channel grouping results to obtain a channel classification sequence; Performing transportation network association on the channel classification sequence to obtain a channel transportation relationship diagram; Channel mapping is performed on the real-time transportation data according to the channel transportation relationship diagram to obtain the channel transportation information.

[0006] Furthermore, the real-time cost data of the multi-channel logistics transportation system is obtained, and cost matching analysis is performed with the channel transportation information to obtain a channel cost group, including: Classify the real-time cost data by cost type labels to obtain dynamic transportation costs, static warehousing costs, and management indirect costs; Performing correlation matching of the transport channel time periods on the transport dynamic cost to obtain a channel time period cost correlation set; Based on the warehousing static cost, the warehousing radiation area allocation calculation is performed on the channel period cost association set to obtain a channel basic cost distribution table; Perform indirect cost superposition processing on the channel basic cost distribution table according to the management indirect cost to obtain a full cost channel distribution table; Performing structural decomposition on the full-cost channel distribution table to obtain a cost structure analysis data set; The channel cost group is obtained by iteratively weighting the channel-period cost association set based on the cost structure analysis data set.

[0007] Furthermore, the acquiring of historical transport records of the multi-channel logistics transport system, performing trend forecasting on the channel transport information, and obtaining transport load forecast results include: Extracting target records from the historical transportation records based on the channel transportation information to obtain a target historical transportation data set; performing channel classification on the target historical transportation data set according to the channel transportation information to obtain a channel historical transportation data subset; Extracting transport characteristics from the subset of channel historical transport data to obtain channel transport characteristic information; Performing cost cluster analysis on a subset of the channel's historical transportation data based on the channel's transportation characteristic information to obtain a transportation cost pattern category; Performing periodic analysis on the transportation cost pattern category to obtain the transportation cost variation pattern; The load of the channel transportation information is predicted according to the transportation cost variation rule to obtain the transportation load prediction result.

[0008] Furthermore, the benefit optimization of the channel cost group and the transportation load forecast result to obtain an initial resource allocation plan includes: Decomposing the channel cost group into transport cost elements to obtain channel cost structure data; Performing a channel transportation assessment based on the transportation load prediction result and the channel cost structure data to obtain a channel transportation capacity assessment result; Performing transportation optimization calculation on the channel cost structure data to obtain a transportation optimization objective function; Constructing transportation constraints on the channel transportation capacity evaluation result according to the transportation optimization objective function to obtain transportation constraints; Allocating transport resources based on the transport capacity assessment results of the channel according to the transport constraint conditions to obtain a preliminary allocation plan; Conducting transportation feasibility verification on the preliminary allocation plan to obtain a transportation verification result; The transportation resources are adjusted on the preliminary allocation plan according to the transportation verification result to obtain the initial resource allocation plan.

[0009] Furthermore, based on the transport load forecast result, the real-time transport data is subjected to emergency transport demand identification and route planning, and the solution is integrated with the initial resource allocation solution to obtain a channel transport optimization solution, including: Performing load warning analysis on the transport load prediction result and the real-time transport data to obtain a transport warning indicator; Evaluate the urgency of the real-time transportation data according to the transportation warning indicators to obtain an emergency transportation demand set; Extracting transportation nodes and constructing a path network for the emergency transportation demand set to obtain a transportation path network; Performing path planning on the transportation path network to obtain a transportation path set; Performing resource conflict detection and priority sorting on the initial resource allocation plan according to the transportation path set to obtain a conflict priority sequence; reallocating resources on the initial resource allocation scheme according to the conflict priority sequence to obtain an adjusted resource allocation scheme; The resource allocation adjustment plan and the transportation path set are integrated to obtain a channel transportation optimization plan.

[0010] Furthermore, the extracting of transport nodes and constructing of a path network for the emergency transport demand set to obtain a transport path network includes: Performing node identification on the emergency transportation demand set to obtain a network node set; Performing node attribute analysis on the network node set to obtain a node attribute set; Classifying the network node set according to the node attribute set to obtain a transportation network node classification set; Calculating the transport distances between the transport network node classification set to obtain a transport distance matrix; Connecting the nodes of the transportation network node classification set according to the transportation distance matrix to obtain an initial path network; Calculating the path capacity of the initial path network according to the emergency transportation demand set to obtain a path capacity matrix; The initial path network is optimized according to the path capacity matrix to obtain the transportation path network.

[0011] Furthermore, the performing path planning on the transport path network to obtain a transport path set includes: Performing Pareto optimization calculation on the transportation path network to obtain a Pareto solution set; Performing cumulative calculation of path costs on the Pareto solution set to obtain a cost distribution table; Performing conflict detection on the Pareto solution set according to the initial resource allocation plan to obtain a conflict-free transportation path candidate set; Performing path scoring on the conflict-free transport path candidate set to obtain a transport path scoring table; Performing path screening on the path scoring table to obtain a high-priority path subset; Resource allocation verification is performed on the high-priority path subset to obtain the transportation path set.

[0012] The present invention further provides a multi-channel logistics and transportation cost optimization system, which is applied to any of the multi-channel logistics and transportation cost optimization methods described above, comprising: A collection module, the collection module is used to obtain real-time transportation data and storage capacity data of a multi-channel logistics transportation system, and classify the real-time transportation data by channel based on the storage capacity data to obtain channel transportation information; An analysis module, configured to obtain real-time cost data of the multi-channel logistics transportation system, perform cost matching analysis with the channel transportation information, and obtain a channel cost group; A correlation module, the correlation module is used to obtain historical transportation records of the multi-channel logistics transportation system, perform trend forecasting on the channel transportation information, and obtain a transportation load forecast result; a processing module, configured to optimize the benefits of the channel cost group and the transport load forecast result to obtain an initial resource allocation plan; A control module is used to identify urgent transportation needs and plan routes for the real-time transportation data based on the transportation load prediction result, and integrate the plan with the initial resource allocation plan to obtain a channel transportation optimization plan.

[0013] The present invention provides a multi-channel logistics transportation cost optimization method and system, which has the following beneficial effects: By acquiring real-time transportation data and storage capacity data from multi-channel logistics and transportation systems, and classifying channels based on storage capacity data, it is possible to accurately identify and categorize different transportation channels, thereby improving the refinement of channel management. By performing cost matching analysis between real-time cost data and channel transportation information, it is possible to accurately identify the cost structure of each channel, providing a reliable basis for subsequent resource optimization. By analyzing historical transportation records and predicting channel transportation information trends, it is possible to accurately predict transportation loads, effectively avoiding discrepancies between resource allocation and actual demand.

[0014] By optimizing the benefits of channel cost groups and transport load forecasts, a more scientific and reasonable initial resource allocation plan can be developed, improving resource utilization efficiency. By identifying urgent transport needs and planning routes based on real-time transport data based on transport load forecasts and integrating this with the initial resource allocation plan, rapid response to sudden transport demands can be achieved, improving the flexibility and adaptability of the logistics system. Through multi-channel collaborative optimization, the advantages of each channel can be fully utilized to achieve optimal resource allocation, significantly reducing overall transportation costs and improving the operational efficiency of the logistics system. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of a multi-channel logistics transportation cost optimization method provided by the present invention; Figure 2This is a structural diagram of a multi-channel logistics and transportation cost optimization system provided by the present invention.

[0016] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0019] Reference Figure 1 As shown, the present invention provides a multi-channel logistics transportation cost optimization method, comprising: Step S1: Acquire real-time transportation data and storage capacity data of a multi-channel logistics transportation system, classify the real-time transportation data by channel based on the storage capacity data, and obtain channel transportation information; Step S2: Acquire real-time cost data of the multi-channel logistics transportation system, perform cost matching analysis with channel transportation information, and obtain a channel cost group; Step S3: Obtain historical transportation records of the multi-channel logistics transportation system, perform trend forecasting on the channel transportation information, and obtain transportation load forecast results; Step S4: Optimize the benefits of the channel cost group and the transportation load forecast results to obtain an initial resource allocation plan; Step S5: Based on the transport load forecast results, the real-time transport data is used to identify urgent transport needs and plan routes, and the scheme is integrated with the initial resource allocation scheme to obtain a channel transport optimization scheme.

[0020] Based on the above steps, the detailed process is as follows: Step S1: Real-time data collection for the multi-channel logistics and transportation system is achieved through IoT devices, GPS positioning systems, and warehouse management systems. Real-time transportation data includes key information such as cargo type, transportation volume, destination, and transportation time. Warehouse capacity data reflects the storage capacity, available space, and cargo turnover rate of each channel's warehouses. After data collection, machine learning algorithms are used to extract features and perform pattern recognition on the transportation data. The transportation data is then divided into different channel categories based on storage capacity characteristics. The channel classification process considers factors such as warehouse location, storage capacity, and cargo handling efficiency to establish a channel feature matrix. The classification results form channel transportation information, which includes each channel's transportation demand, storage capacity, and operational status. Channel transportation information provides the data foundation for subsequent cost analysis and load forecasting.

[0021] Step S2: Real-time cost data collection covers multiple dimensions, including transportation costs, warehousing costs, labor costs, and equipment maintenance costs. Cost data is obtained through enterprise resource planning systems, financial management systems, and operations management systems. Cost matching analysis utilizes a multi-dimensional cost accounting approach, linking cost data with channel transportation information. The analysis establishes a cost-channel mapping model to calculate unit transportation costs, warehousing costs, and comprehensive operating costs for each channel. The cost matching results form a channel cost group, which includes each channel's cost structure, cost-benefit ratio, and cost optimization potential. The channel cost group provides a cost basis for subsequent resource allocation and solution optimization.

[0022] Step S3: Historical transport records contain data on transport volumes, transport times, cargo types, and channel usage over the past period. Trend forecasting utilizes a combination of time series analysis, machine learning, and deep learning. The forecasting model considers seasonal factors, market trends, and the impact of emergencies, establishing a multi-dimensional forecasting indicator system. The forecasting process extracts features and identifies patterns in channel transport information to generate a forecast for transport loads over the next period. The forecast results include the expected transport volume, transport time distribution, and resource requirements for each channel. The transport load forecast provides a basis for subsequent resource allocation and identification of urgent transport needs.

[0023] Step S4: Using the channel cost group and transport load forecast results as input, a multi-objective optimization algorithm is used to design a resource allocation plan. The optimization process considers three core indicators: cost-effectiveness, resource utilization, and transport efficiency. A multi-objective optimization model is established to match the cost data in the channel cost group with the transport load forecast results, and the resource demand and cost constraints of each channel are calculated. The optimization algorithm uses intelligent optimization methods such as genetic algorithms and particle swarm optimization to maximize resource utilization and transport efficiency while meeting cost constraints. The optimization results generate an initial resource allocation plan, which includes the resource allocation ratio of each channel, transport route planning, and cost control objectives. This initial resource allocation plan provides a basic framework for the integration of subsequent plans.

[0024] Step S5: Based on the transport load forecast results, a real-time monitoring system and intelligent algorithms are used to identify urgent transport needs. Urgent demand identification takes into account factors such as cargo priority, transport timeliness, and customer requirements. Path planning uses a dynamic programming algorithm, combining real-time traffic conditions, weather conditions, and road restrictions to generate the optimal transport route. Urgent transport needs and path planning results are integrated with the initial resource allocation plan, and a multi-criteria decision-making method is used to evaluate and optimize the plan. The integration process considers the balance between resource constraints, cost control, and transport efficiency to generate the final channel transport optimization plan. The optimization plan includes resource allocation strategies for each channel, transport route planning, and emergency response mechanisms to achieve overall optimization of the logistics and transportation system.

[0025] The present invention provides a multi-channel logistics and transportation cost optimization method. By acquiring real-time transportation data and storage capacity data from a multi-channel logistics and transportation system and classifying channels based on the storage capacity data, the method enables accurate identification and classification of different transportation channels, thereby improving the refinement of channel management. By performing cost matching analysis between real-time cost data and channel transportation information, the cost structure of each channel can be accurately identified, providing a reliable basis for subsequent resource optimization. By analyzing historical transportation records and performing trend forecasting on channel transportation information, accurate prediction of transportation load can be achieved, effectively avoiding discrepancies between resource allocation and actual demand. By optimizing the efficiency of channel cost groups and transportation load forecast results, a more scientific and reasonable initial resource allocation plan can be formulated, improving resource utilization efficiency. By identifying and planning urgent transportation needs and routes based on the transportation load forecast results, and integrating the real-time transportation data with the initial resource allocation plan, the method enables rapid response to sudden transportation demands and improves the flexibility and adaptability of the logistics system. Through multi-channel collaborative optimization, the advantages of each channel can be fully utilized to achieve optimal resource allocation, significantly reducing overall transportation costs and improving the operational efficiency of the logistics system.

[0026] In one embodiment, real-time transportation data and storage capacity data of a multi-channel logistics transportation system are obtained, and the real-time transportation data is classified by channel based on the storage capacity data to obtain channel transportation information, including: The multi-channel logistics and transportation system optimizes transportation costs by integrating resources from different transportation channels. The system includes a transportation data collection module, a node analysis module, a capacity identification module, a channel clustering module, a hierarchical sorting module, a network association module, and a channel mapping module.

[0027] The transportation data collection module collects data from multi-channel logistics and transportation systems to generate an initial transportation dataset. This dataset includes fields such as the origin and destination of shipments, cargo type, transportation time, transportation distance, and transportation cost. The system collects transportation data in real time through IoT devices, GPS positioning systems, and transportation management systems to ensure data integrity and timeliness. This initial transportation dataset is stored in a structured manner to facilitate subsequent analysis and processing.

[0028] The node analysis module analyzes the distribution of logistics nodes based on the initial transportation dataset and generates a node distribution matrix. This matrix is represented as a two-dimensional array, with its elements reflecting the frequency and volume of transportation between nodes. The system uses a spatial clustering algorithm to identify key logistics nodes and calculate the transportation correlation between them. The node distribution matrix includes attributes such as node location, node type, and node size, providing foundational data for subsequent storage capacity analysis.

[0029] The capacity identification module identifies storage point capacities within a multi-channel logistics and transportation system based on a node distribution matrix and generates a set of storage capacity indicators. These indicators include maximum storage capacity, current inventory levels, inbound and outbound frequency, and storage costs. The system monitors the capacity status of each storage point in real time through the warehouse management system and analyzes capacity trends based on historical data. The storage capacity indicator set utilizes a dynamic update mechanism to ensure data accuracy.

[0030] The channel clustering module clusters the node distribution matrix according to the storage capacity indicator set, generating preliminary channel grouping results. These preliminary channel groupings divide logistics nodes into different channel groups based on transportation and capacity characteristics. The system uses the K-means clustering algorithm, using transportation distance, transportation cost, and storage capacity as clustering features, to determine the optimal channel grouping scheme. These preliminary channel groupings include information such as the channel group number, a list of nodes within the group, and a channel feature vector.

[0031] The hierarchical ranking module hierarchically sorts the preliminary channel grouping results to generate a channel classification sequence. This channel classification sequence prioritizes channel groups based on metrics such as transportation efficiency, cost-effectiveness, and capacity utilization. The system uses the Analytic Hierarchy Process (AHP) to construct an evaluation index system and calculate a comprehensive score for each channel group. The channel classification sequence is stored as an ordered list to facilitate subsequent network correlation analysis.

[0032] The network association module associates the channel classification sequence with the transportation network to generate a channel transportation relationship diagram. This diagram represents the transportation connections between channels as a directed graph, with nodes representing channel groups and edges representing transportation paths. The system uses graph theory algorithms to analyze the accessibility and connectivity between channels and identify critical transportation paths. The diagram includes attributes such as the channel connection matrix, path weights, and transportation constraints.

[0033] The channel mapping module maps real-time transportation data based on a channel transportation relationship diagram, generating channel transportation information. This information includes transportation task allocation plans, channel selection strategies, and cost optimization recommendations. The system uses a dynamic programming algorithm to determine the optimal transportation plan, combining real-time transportation demand and channel status. This information is displayed through a visual interface to support transportation decision-making and scheduling management.

[0034] This embodiment establishes a complete channel classification system through real-time transportation data collection and storage capacity data analysis, so that the distribution characteristics and storage capacity of logistics nodes are fully utilized. Channel clustering based on node distribution matrix and storage capacity indicators realizes the scientific grouping of logistics channels, avoiding the subjectivity and arbitrariness of traditional manual classification methods. Through hierarchical sorting and network association analysis, a systematic channel transportation relationship diagram is constructed, providing a reliable basis for transportation route optimization. This method organically combines real-time transportation data with channel classification to form dynamic channel transportation information, making transportation scheduling more reasonable and significantly improving the operating efficiency of the logistics system. At the same time, the modular design of this method ensures the scalability of the system, facilitates functional expansion and optimization and upgrading according to actual needs, and provides logistics companies with a scientific transportation cost management tool.

[0035] In one embodiment, real-time cost data of a multi-channel logistics transportation system is obtained and cost matching analysis is performed with channel transportation information to obtain a channel cost group, including: The acquisition and processing of real-time cost data for multi-channel logistics and transportation systems involves multiple key links. Real-time cost data originates from various business aspects of the logistics and transportation system, including modules such as transportation, warehousing, and management. This data is collected in real time through system interfaces to form a raw cost data set. The cost type label classification process divides the raw cost data into three categories based on business attributes: dynamic transportation costs, static warehousing costs, and indirect management costs. Dynamic transportation costs primarily refer to variable costs directly related to transportation activities, such as fuel costs, tolls, and driver wages; static warehousing costs include warehouse rent, equipment depreciation, and fixed staff salaries; and indirect management costs cover management staff salaries, office expenses, and system maintenance costs.

[0036] The transport channel-period correlation matching process establishes a mapping between dynamic transport costs and specific transport channels and time periods. The system pre-defines channel-period matching rules, including channel type (e.g., road, rail, air), time period divisions (e.g., peak, off-peak, and off-peak periods), and cost calculation cycles (e.g., daily, weekly, and monthly). The rules engine processes dynamic transport cost data to generate a channel-period cost correlation set. This correlation set records the cost structure and amount for each transport channel across different time periods.

[0037] Warehouse radius allocation is calculated based on static warehouse costs. The system defines the warehouse radius and zone division rules, dividing the influence area of each warehouse point into core, expansion, and edge zones. A distance decay model is used to calculate the cost allocation coefficient based on the distance between each zone and the warehouse point. The channel-based cost distribution table records the cost distribution of each transportation channel in different warehouse radius zones, including the allocated amount and percentage of fixed costs.

[0038] The indirect cost overlay process utilizes cost driver analysis to add management indirect costs to the channel-based cost distribution table according to pre-set allocation rules. These allocation rules include allocation by transportation volume, storage area, and headcount. Based on each channel's actual business volume, the system calculates the indirect cost allocation ratio and generates a full-cost channel distribution table. This table fully reflects the total cost structure of each channel, including both direct and indirect costs.

[0039] The cost structure analysis dataset is generated using a structural decomposition method. The system performs a multi-dimensional analysis of cost items in the full-cost channel distribution table, including cost type, time, region, and channel dimensions. The analysis results in a structured dataset containing information such as cost composition ratios, change trends, and regional differences. This dataset provides a basis for subsequent decision-making regarding weight allocation.

[0040] The channel cost group generation process utilizes an iterative weighting algorithm. Based on the cost structure analysis dataset, combined with historical data and business rules, the system weights the associated set of channel and time period costs. This weighting takes into account factors such as cost-benefit ratio, service quality, and market competitiveness. Through multiple iterations of optimization, a channel cost group is ultimately generated, reflecting the optimal cost allocation for each channel.

[0041] This embodiment labels and classifies cost data according to dynamic transportation costs, static warehousing costs, and indirect management costs, making the cost structure clearer and facilitating subsequent analysis and optimization. Through the correlation matching of transportation channel time periods, the corresponding relationship between costs and transportation channels and time periods is established, and accurate tracking and allocation of costs are achieved. The cost allocation calculation based on the warehousing radiation area reasonably allocates the static warehousing costs, and improves the accuracy and fairness of cost allocation. The superposition processing of indirect costs adopts multi-dimensional allocation rules to ensure the reasonable allocation of management costs. The generation of cost structure analysis data sets provides comprehensive data support for cost optimization. Through the iterative weight allocation algorithm, the final generated channel cost group can reflect the optimal cost configuration plan for each channel, thereby improving the overall operational efficiency of the logistics and transportation system.

[0042] In one embodiment, historical transport records of a multi-channel logistics transport system are obtained, and trend forecasting of channel transport information is performed to obtain transport load forecast results, including: The logistics and transportation cost optimization method uses historical transportation records from a multi-channel logistics and transportation system to predict channel transportation trends and generate transportation load forecasts. Channel transportation information refers to a data set containing key elements such as transportation mode, route, time, and cost. Historical transportation records are a complete collection of data on past transportation mission execution stored in the system.

[0043] Targeted historical transport records are extracted based on channel transport information to obtain a target historical transport dataset. This target record extraction process is based on pre-set filtering criteria, including transport time range, transport mode type, and route characteristics. A data filtering algorithm selects eligible data entries from the massive historical records to form a structured target historical transport dataset. This dataset includes key fields such as transport task number, start and end locations, transport time, and transport cost.

[0044] The target historical transportation dataset is classified by channel based on channel transportation information to form channel historical transportation data subsets. This channel classification utilizes multi-dimensional criteria, including transportation mode, geographic region, and transportation timeliness. A classification algorithm divides the target historical transportation dataset into multiple non-overlapping data subsets, each representing a specific channel transportation data set. Channel historical transportation data subsets have clear channel identification and a complete data structure.

[0045] Transport feature extraction is performed on a subset of the channel's historical transport data to obtain channel transport characteristic information. This process uses feature engineering techniques to extract representative characteristic indicators from the raw data. Extracted features include transport distance, transport time, transport cost, cargo weight, and transport frequency. Channel transport characteristic information is represented as feature vectors, each of which corresponds to a feature set for a transport task.

[0046] Cost cluster analysis is performed on a subset of historical channel transportation data based on channel transportation characteristics to identify transportation cost pattern categories. This cost cluster analysis uses an unsupervised learning algorithm to group transportation tasks with similar cost characteristics into the same category. The clustering algorithm divides transportation tasks into multiple cost pattern categories, each representing a typical cost structure. These cost pattern categories contain key information such as category centers, category boundaries, and category characteristics.

[0047] Cyclic analysis of transportation cost patterns reveals patterns in transportation cost fluctuations. Cyclic analysis uses time series analysis to identify cyclical characteristics of cost changes. Cost trends are analyzed over different time scales, including daily, weekly, monthly, and quarterly variations. The patterns of transportation cost variation are represented by mathematical models, including trend, cyclic, and random terms.

[0048] Based on the changing patterns of transportation costs, we perform load forecasting on channel transportation information to generate a transport load forecast. This load forecast utilizes a time series forecasting method to predict future transport loads based on historical data and cost trends. The forecasting model calculates transport load values at various future time points, creating a complete load forecast curve. The transport load forecast results include key metrics such as the predicted value, confidence interval, and prediction error.

[0049] This embodiment ensures the accuracy and completeness of the data based on preset screening conditions through the target record extraction process, providing a reliable data foundation for subsequent analysis. Channel classification adopts multi-dimensional classification standards to achieve refined classification of transportation data, improving the pertinence and effectiveness of data analysis. The transportation feature extraction process adopts feature engineering methods to extract representative feature indicators from the original data, providing comprehensive data support for cost analysis. Cost clustering analysis adopts unsupervised learning algorithms to effectively identify the cost patterns of different transportation tasks, providing a scientific basis for cost optimization. Cycle analysis adopts time series analysis methods to reveal the cyclical characteristics of cost changes, providing an important theoretical basis for the prediction model. Load forecasting adopts time series forecasting methods, based on historical data and cost change laws, to achieve accurate prediction of future transportation loads, providing a reliable basis for transportation decision-making.

[0050] In one embodiment, the channel cost group and the transportation load forecast results are optimized to obtain an initial resource allocation plan, including: The channel cost group is decomposed into transportation cost elements to obtain channel cost structure data. The channel cost group includes all cost items in the transportation process, including direct transportation costs, indirect transportation costs, fixed costs and variable costs. The decomposition process uses cost driver analysis to identify the driving factors of each cost item. Direct transportation costs include vehicle fuel costs, tolls, driver wages, etc., and indirect transportation costs include vehicle depreciation, insurance costs, administrative expenses, etc. Fixed costs are not related to transportation volume and include vehicle purchase costs, equipment maintenance costs, etc. Variable costs vary with transportation volume and include fuel costs, tolls, etc. The decomposed channel cost structure data contains information such as the amount, proportion, and change pattern of each cost item, providing a data basis for subsequent optimization.

[0051] Channel transport assessments are conducted based on transport load forecasts and channel cost structure data to generate channel transport capacity estimates. Transport load forecasts are derived from a forecasting model based on historical transport data, market trends, and seasonal factors. The assessment process analyzes various transport channel indicators, including transport capacity, efficiency, and cost. Capacity indicators include maximum transport volume, transport speed, and transport distance; efficiency indicators include load factor, turnover rate, and on-time performance; and cost indicators include unit transport cost and marginal cost. The assessment results generate transport capacity curves, cost curves, and efficiency curves for each channel, determining the optimal transport volume range and cost-sensitive range.

[0052] Transport optimization calculations are performed on channel cost structure data to generate the transport optimization objective function. The optimization process converts factors such as transport cost, transport efficiency, and service quality into mathematical expressions. The objective function focuses on minimizing total transport cost while also considering constraints such as transport time and transport quality. Total transport cost includes direct transport cost, indirect transport cost, and opportunity cost. Transport time constraints include transport time limits and time windows, while transport quality constraints include cargo integrity rate and on-time delivery rate. Decision variables in the objective function include transport volume, transport routes, and transport time for each channel.

[0053] Based on the transport optimization objective function, transport constraints are constructed based on the channel transport capacity assessment results to obtain transport constraints. Constraints include capacity constraints, time constraints, and cost constraints. Capacity constraints ensure that the transport volume of each channel does not exceed its maximum carrying capacity, time constraints ensure that the transport process meets the time window requirements, and cost constraints keep the total transport cost within the budget. Constraints also consider practical limitations such as transport network connectivity, transport tool availability, and staffing. The constructed constraints form a linear or nonlinear system of equations, which together with the objective function form the optimization model.

[0054] Transport resources are allocated based on the channel capacity assessment results according to transport constraints, resulting in a preliminary allocation plan. This resource allocation process utilizes mathematical programming to solve an optimization model and determine the optimal transport volume for each channel. The allocation plan includes specific aspects such as transport route planning, transport tool allocation, and personnel scheduling. Transport route planning determines the optimal transport path, taking into account factors such as distance, road conditions, and traffic conditions. Transport tool allocation determines the type and number of vehicles required for each route, while personnel scheduling determines the allocation of drivers and loading and unloading personnel.

[0055] The preliminary allocation plan is verified for transport feasibility and results are obtained. This verification process utilizes simulation methods to simulate actual transport scenarios. Verification covers the transport plan's feasibility, stability, and risk profile. Feasibility verification checks whether resources such as transportation vehicles, personnel, and routes meet the plan's requirements. Stability verification assesses the plan's adaptability to emergencies. Risk verification identifies potential risks and countermeasures. The verification results are compiled into a plan evaluation report, including feasibility analysis, risk analysis, and improvement recommendations.

[0056] Based on the transport verification results, transport resources are adjusted from the preliminary allocation plan to produce an initial resource allocation plan. This adjustment process optimizes any issues identified during verification. Adjustments include volume reallocation, route optimization, and time adjustments. Volume reallocation adjusts transport tasks based on the actual transport capacity of each channel. Route optimization improves transport routes to increase efficiency. Time adjustments optimize transport time windows to improve on-time delivery. The adjusted initial resource allocation plan meets transport needs, optimizes costs, and is practically operational. The plan includes detailed transport plans, resource allocation plans, and contingency plans to provide guidance for actual transport operations.

[0057] This embodiment uses the cost driver analysis method to decompose the channel cost group into elements, which can accurately identify the driving factors of various types of transportation costs and provide accurate data support for subsequent optimization. Based on the transportation load forecast of historical data and market trends, combined with the channel cost structure data, it is possible to scientifically evaluate the transportation capacity of each transportation channel and provide a reliable basis for resource allocation. By constructing an optimization objective function that includes multiple dimensions such as transportation cost, efficiency, and quality, and establishing corresponding constraints, it is possible to achieve a reasonable allocation of transportation resources and effectively reduce overall transportation costs. The use of mathematical programming methods for resource allocation, combined with simulation verification, can ensure the feasibility and stability of transportation plans, and improve transportation efficiency and service quality. Through the dynamic adjustment mechanism, it is possible to respond to emergencies in the transportation process in a timely manner, ensure the smooth implementation of the transportation plan, and improve the overall operational efficiency of the logistics and transportation system.

[0058] In one embodiment, urgent transportation demand identification and route planning are performed on real-time transportation data based on transportation load forecast results, and the solution is integrated with the initial resource allocation plan to obtain a channel transportation optimization solution, including: Transport load forecast results and real-time transport data are fed into the load warning analysis module. The transport load forecast includes the projected cargo throughput, transport tool utilization, and human resource requirements for each transport node over the next period of time. Real-time transport data includes the actual cargo throughput, transport tool operating status, human resource allocation, and weather conditions at the current transport node. The load warning analysis module presets warning thresholds, triggering a warning when actual cargo throughput exceeds 120% of the forecast value or transport tool utilization exceeds 90%. Warning indicators include overload level, resource gap, and risk level. The overload level reflects the deviation between the actual load and the forecast value, the resource gap represents the gap between currently available resources and demand, and the risk level is comprehensively assessed based on the overload level and resource gap.

[0059] Transport warning indicators are fed into the urgency assessment module. This module categorizes transport demand based on the severity of the warning indicators. Urgency is divided into three levels: urgent, emergency, and general. Urgent corresponds to situations with a high risk level and a resource shortfall exceeding 50%, emergency corresponds to situations with a medium risk level and a resource shortfall between 30% and 50%, and general corresponds to situations with a low risk level and a resource shortfall below 30%. The assessment results form an emergency transport demand set, comprising the demand level, time window, and resource requirements.

[0060] The urgent transport demand set enters the transport node extraction and path network construction module. This module extracts the origin, transit, and destination nodes from the demand set. Node extraction follows the principle of proximity, prioritizing available nodes closest to the demand point. Path network construction is based on actual distances between nodes, road conditions, and transport restrictions. Edge weights within the network take into account transport time, cost, and risk. The resulting transport path network consists of a node set, an edge set, and a weight matrix.

[0061] The transport route network enters the route planning module. This module uses a modified Dijkstra algorithm for route search. The algorithm considers time window constraints, capacity limits, and priority rules. Time window constraints ensure that transport is completed within the specified time, capacity limits ensure that the transport vehicle's carrying capacity is not exceeded, and priority rules determine the order of route selection based on urgency. The planning results in a transport route set, which includes route sequence, time schedule, and resource allocation.

[0062] The transportation route set and initial resource allocation plan enter the resource conflict detection and prioritization module. This module detects temporal and spatial conflicts in resource usage. Temporal conflicts occur when the same resource is occupied by multiple tasks at the same time. Spatial conflicts occur when multiple tasks compete for limited resources at the same location. The conflict detection results form a conflict list, which includes conflict type, conflict severity, and impact scope. Prioritization is based on three dimensions: urgency, resource dependency, and impact scope. The results form a conflict priority sequence.

[0063] The conflicting priority sequence and initial resource allocation plan enter the resource reallocation module. This module adjusts resource allocation based on priority. High-priority tasks receive priority resource allocation, while lower-priority tasks undergo time adjustments or resource substitution. Resource reallocation adheres to the principle of minimal adjustment, minimizing disruption to the original plan while meeting high-priority needs. The resulting adjustments form an adjusted resource allocation plan, including a new resource allocation table and timeline.

[0064] Adjust the resource allocation plan and transportation route set and enter the plan integration module. This module integrates the two plans. The integration process considers time continuity, resource utilization, and cost-effectiveness. Time continuity ensures that all links are closely connected, resource utilization ensures that resources are fully utilized, and cost-effectiveness evaluates the economic feasibility of the integrated plan. The integration results in a channel transportation optimization plan, which includes a complete transportation plan, resource allocation plan, and contingency plan.

[0065] This embodiment, through the preset threshold mechanism of the load warning analysis module, can promptly identify transportation anomalies, avoid excessive concentration or idleness of transportation resources, and improve resource utilization efficiency. Through the three-level classification mechanism of the urgency assessment module, accurate classification of transportation needs is achieved, ensuring that emergency transportation needs are given priority and improving emergency response capabilities. Through the weight matrix design of the transportation node extraction and path network construction module, transportation time, cost and risk factors are comprehensively considered to achieve optimal selection of transportation routes. Through the multi-dimensional evaluation mechanism of the resource conflict detection and priority sorting module, reasonable allocation of resources is achieved and resource conflicts are reduced. Through the minimum adjustment principle of the resource reallocation module, the stability of the original transportation plan is maintained to the maximum extent while meeting emergency needs. Through the comprehensive evaluation mechanism of the solution integration module, the continuity and economy of the transportation plan are ensured, and the overall transportation efficiency is improved.

[0066] In one embodiment, transport nodes are extracted from the urgent transport demand set and a path network is constructed to obtain a transport path network, including: The urgent transport demand set refers to a data set containing multiple urgent transport tasks, each of which includes information such as the starting point, destination, cargo type, quantity, and time requirements. The network node set is a set obtained by performing node identification on the urgent transport demand set, and contains the starting points and destinations involved in all transport tasks. The node attribute set is the result of attribute analysis on the network node set, and contains attribute information such as the geographic location, traffic conditions, loading and unloading capabilities, and storage capacity of each node. The transportation network node classification set is the result of classifying the network node set based on the node attribute set, dividing the nodes into different types of sets according to criteria such as function, scale, and importance.

[0067] The transport distance matrix is the result of calculating inter-transport distances for a set of transport network node classifications. It represents the transport distance between any two nodes in the network. The initial path network is the network structure obtained by connecting the nodes of the transport network node classification set according to the transport distance matrix. It represents the initial connection relationships between nodes. The path capacity matrix is the result of calculating the path capacity of the initial path network based on the set of urgent transport demands. It represents the transport capacity of each path in the network. The transport path network is the final network structure obtained by optimizing the initial path network according to the path capacity matrix. It represents the optimized node connection relationships and path capacity allocation.

[0068] In the node identification phase, each transport task in the urgent transport demand set is parsed, all starting and ending points are extracted, and duplicate nodes are removed to form a network node set. In the node attribute analysis phase, each node in the network node set is analyzed, collecting information such as its geographic location, traffic conditions, loading and unloading capabilities, and storage capacity to form a node attribute set. In the node classification phase, based on the attribute information in the node attribute set, the network node set is divided into different types of nodes, such as starting nodes, ending nodes, and transit nodes, to form a transportation network node classification set.

[0069] During the inter-transport distance calculation phase, the transport distance between any two nodes in the transport network node classification set is calculated based on the geographic location information in the node attribute set, forming a transport distance matrix. Transport distances can be straight-line distances, actual road distances, or distances adjusted for traffic conditions. During the node connection phase, nodes in the transport network node classification set are connected based on the shortest distance principle according to the transport distance matrix to form an initial path network. Connections in the initial path network can be direct or through transit nodes.

[0070] During the route capacity calculation phase, the transport capacity of each route in the initial route network is calculated based on the transport task information in the emergency transport demand set, forming a route capacity matrix. Route capacity includes factors such as the number of vehicles, load capacity, and transport speed. During the network optimization phase, the initial route network is optimized based on the route capacity matrix, adjusting node connectivity and route capacity allocation to form a transport route network. Optimization objectives include minimizing total transport distance, maximizing route utilization, and balancing network load.

[0071] The resulting transport path network includes optimized node connectivity and path capacity allocation, which can be used for subsequent transport planning and cost optimization. This network structure effectively supports multi-channel logistics, improves transport efficiency, and reduces transport costs.

[0072] By constructing a transportation path network, this embodiment can effectively integrate multi-channel logistics resources, realize intelligent classification of transportation nodes and path optimization, and significantly improve logistics transportation efficiency. Based on the results of node attribute analysis, the functional characteristics and transportation capacity of various nodes can be accurately identified, providing a reliable basis for subsequent path planning. Through the calculation of the transportation distance matrix and path capacity analysis, the system can automatically generate the optimal transportation path, reduce transportation distance and number of transfers, and reduce logistics costs. The network optimization process fully considers path capacity constraints to ensure that transportation resources are reasonably allocated and avoid network congestion and resource waste. This method can adapt to logistics needs of different scales and complexities, has strong practicality and scalability, and provides scientific decision-making support for logistics companies.

[0073] In one embodiment, path planning is performed on the transportation path network to obtain a transportation path set, including: A transportation path network is a graph structure composed of multiple nodes and edges. Nodes represent the origins, destinations, and transit points of logistics transportation, while edges represent the transportation paths between nodes. Each node has attributes such as location coordinates, capacity constraints, and resource requirements, while each edge has attributes such as distance, transit time, transportation cost, and capacity constraints. Together, the nodes and edges in a transportation path network form a complete logistics transportation system.

[0074] During the genetic algorithm initialization phase, the system randomly generates a set of initial transportation route plans. Each plan consists of multiple transportation routes connecting the starting point, a transfer station, and the final destination. The system assigns a unique identifier to each plan and records all the route information it contains. The size of the initial set of plans is determined by the complexity of the problem and typically contains 50-100 plans.

[0075] During the crossover phase, the system selects two parent solutions from the current solution set. This selection process uses a roulette wheel approach, with solutions with higher scores being more likely to be selected. The system randomly selects a crossover point and swaps the two parent solutions at that point, generating two new child solutions. The crossover operation preserves the advantages of the parent solutions while introducing new combination possibilities.

[0076] During the mutation phase, the system randomly modifies the offspring solutions. Mutation methods include route replacement, node adjustment, and parameter changes. Route replacement involves replacing an existing route with a new one; node adjustment involves changing the transit points along the route; and parameter changes involve adjusting parameters like transport speed and load capacity. Mutation increases solution diversity and prevents the algorithm from falling into local optimality.

[0077] During the selection phase, the system screens options based on their quality. This quality assessment considers three objectives: transportation cost, transportation time, and transportation reliability. The system calculates the specific values for each option on these three objectives and compares them with other options. If an option outperforms the others on at least one objective and is not inferior to them on any other objective, it is retained. Options that are not retained are eliminated and replaced by newer options.

[0078] The iterative process repeats crossover, mutation, and selection until a termination condition is met. Termination conditions include reaching the maximum number of iterations, no significant improvement in solution quality, or reaching a computational time limit. After each iteration, the system records the current optimal Pareto solution set and updates the solution set.

[0079] The Pareto solution set is generated using a non-dominated sorting method. The system sorts all solutions according to dominance, eliminating dominated solutions and retaining non-dominated solutions. A dominance relationship means that one solution is non-inferior to another on all objectives and strictly superior to another on at least one objective. The resulting Pareto solution set contains multiple non-dominated solutions that exhibit different combinations of advantages across the three objectives.

[0080] The Pareto solution set is maintained using an elite retention strategy. The system retains a certain number of optimal solutions in each iteration to ensure they are not lost in subsequent operations. This elite retention strategy improves the algorithm's convergence speed and ensures the quality of the final solution set. Furthermore, the system uses congestion calculations to maintain the diversity of the solution set and prevent it from being overly concentrated in a specific area.

[0081] The final output of the Pareto solution set includes multiple transportation route options, each with specific values for the three objectives. These options form a complete Pareto front, from which decision makers can select the appropriate option based on their actual needs. The shape of the Pareto front reflects the trade-offs between the three objectives, providing a reference for subsequent decision-making.

[0082] The cumulative path cost calculation evaluates the cost of each transport route option in the Pareto solution set. Costs include transportation cost, time cost, and risk cost. Transportation cost is composed of fuel consumption, labor costs, and equipment depreciation; time cost is composed of transportation time, waiting time, and loading and unloading time; and risk cost is composed of risk factors such as cargo damage, delay, and loss. The cost distribution table records the specific values of each transport route option in different cost dimensions, providing a basis for subsequent route screening.

[0083] Conflict detection analyzes resource contention among transportation routing options. The initial resource allocation plan specifies resource capacity constraints for each node and edge, including the number of vehicles, loading and unloading equipment, and human resources. Conflict detection analyzes the resource usage of different transportation routes and identifies route combinations that involve resource contention. The conflict-free candidate transport path set, obtained after conflict detection, is a set of feasible routes whose resource usage does not conflict.

[0084] The route scoring system comprehensively evaluates each option in the set of conflict-free transport route candidates. Scoring metrics include transport efficiency, resource utilization, and option feasibility. Transport efficiency reflects the time and cost performance of a route option; resource utilization reflects the extent to which a route option utilizes system resources; and option feasibility reflects the feasibility of a route option in actual implementation. The transport route scoring table records each option's score on each metric, providing a basis for route selection.

[0085] Path screening involves selecting the optimal transport route based on the scoring results. The screening criteria include scoring thresholds, resource constraints, and business requirements. The scoring threshold specifies the minimum score a solution must meet; resource constraints ensure that the solution meets system resource constraints; and business requirements ensure that the solution meets actual transport requirements. The high-priority path subset is a set of high-quality paths identified after screening, consisting of solutions that meet high standards in terms of scoring, resources, and business requirements.

[0086] Resource allocation verification is the final confirmation of resource allocation for a subset of high-priority routes. The verification process consists of three steps: resource requirement calculation, resource availability check, and allocation plan generation. Resource requirement calculation determines the required resources for each option; resource availability check confirms whether the system can provide the required resources; and allocation plan generation creates a specific resource allocation plan. The transportation route set is the finalized set of transportation options, each of which is equipped with a corresponding resource allocation plan and can be directly used for actual transportation execution.

[0087] This embodiment uses Pareto optimization calculations to simultaneously optimize the three objectives of transportation cost, transportation time, and transportation reliability, avoiding the one-sidedness that may result from single-objective optimization and improving the overall quality of the transportation plan. Through the crossover and mutation operations of the genetic algorithm, it is possible to effectively explore various possible combinations of transportation paths, avoid falling into local optimal solutions, and obtain better transportation plans. Through non-dominated sorting and elite retention strategies, it is possible to maintain the diversity and quality of the Pareto solution set, providing decision makers with multiple transportation plan options with different advantages. Through cost accumulation calculations and conflict detection, it is possible to accurately evaluate the resource requirements and feasibility of the transportation plan, avoid execution difficulties caused by resource conflicts, and improve the operability of the plan. Through path scoring and screening, it is possible to select the optimal transportation plan based on actual needs, ensure that the plan meets business requirements and resource constraints, and improve transportation efficiency.

[0088] Reference Figure 2 As shown, the present invention further provides a multi-channel logistics and transportation cost optimization system, which is applied to any of the above-mentioned multi-channel logistics and transportation cost optimization methods, including: The acquisition module is used to obtain real-time transportation data and storage capacity data of the multi-channel logistics transportation system, classify the real-time transportation data by channel based on the storage capacity data, and obtain channel transportation information; Analysis module: The analysis module is used to obtain real-time cost data of multi-channel logistics and transportation systems, perform cost matching analysis with channel transportation information, and obtain channel cost groups; The correlation module is used to obtain historical transportation records of the multi-channel logistics transportation system, perform trend forecasting on channel transportation information, and obtain transportation load forecast results; The processing module is used to optimize the benefits of the channel cost group and the transportation load forecast results to obtain an initial resource allocation plan; The control module is used to identify urgent transportation needs and plan routes for real-time transportation data based on transportation load forecast results, and integrate the plan with the initial resource allocation plan to obtain a channel transportation optimization plan.

[0089] The present invention provides a multi-channel logistics and transportation cost optimization system. By acquiring real-time transportation data and storage capacity data from a multi-channel logistics and transportation system and classifying channels based on storage capacity data, the system can accurately identify and classify different transportation channels, thereby improving the level of refined channel management. By performing cost matching analysis between real-time cost data and channel transportation information, the cost structure of each channel can be accurately identified, providing a reliable basis for subsequent resource optimization and allocation. By analyzing historical transportation records and performing trend forecasting on channel transportation information, the system can accurately predict transportation loads and effectively avoid discrepancies between resource allocation and actual demand.

[0090] By optimizing the benefits of channel cost groups and transport load forecasts, a more scientific and reasonable initial resource allocation plan can be developed, improving resource utilization efficiency. By identifying urgent transport needs and planning routes based on real-time transport data based on transport load forecasts and integrating this with the initial resource allocation plan, rapid response to sudden transport demands can be achieved, improving the flexibility and adaptability of the logistics system. Through multi-channel collaborative optimization, the advantages of each channel can be fully utilized to achieve optimal resource allocation, significantly reducing overall transportation costs and improving the operational efficiency of the logistics system.

[0091] It should be noted that, those skilled in the art will clearly understand that, for the sake of convenience and brevity of description, the specific working processes of the above-described system and each module can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0092] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A multi-channel logistics transportation cost optimization method, characterized in that: include: Acquire real-time transportation data and storage capacity data of a multi-channel logistics transportation system, classify the real-time transportation data by channel based on the storage capacity data, and obtain channel transportation information; Acquire real-time cost data of the multi-channel logistics transportation system, perform cost matching analysis with the channel transportation information, and obtain a channel cost group; Obtaining historical transportation records of the multi-channel logistics transportation system, performing trend forecasting on the channel transportation information, and obtaining a transportation load forecast result; Performing benefit optimization on the channel cost group and the transportation load forecast result to obtain an initial resource allocation plan; Based on the transport load forecast result, the real-time transport data is used to identify urgent transport needs and plan routes, and the plan is integrated with the initial resource allocation plan to obtain a channel transport optimization plan.

2. The multi-channel logistics transportation cost optimization method according to claim 1 is characterized in that: The acquiring of real-time transportation data and storage capacity data of a multi-channel logistics transportation system, and performing channel classification on the real-time transportation data based on the storage capacity data to obtain channel transportation information, includes: Collecting transportation data from the multi-channel logistics transportation system to obtain an initial transportation data set; Performing logistics node distribution analysis based on the initial transportation data set to obtain a node distribution matrix; Identifying storage point capacities of the multi-channel logistics and transportation system based on the node distribution matrix to obtain a storage capacity indicator set; Perform channel clustering on the node distribution matrix according to the storage capacity indicator set to obtain a preliminary channel grouping result; hierarchically sorting the preliminary channel grouping results to obtain a channel classification sequence; Performing transportation network association on the channel classification sequence to obtain a channel transportation relationship diagram; Channel mapping is performed on the real-time transportation data according to the channel transportation relationship diagram to obtain the channel transportation information.

3. The multi-channel logistics transportation cost optimization method according to claim 1 is characterized in that: The acquiring of the real-time cost data of the multi-channel logistics transportation system and performing cost matching analysis with the channel transportation information to obtain a channel cost group includes: Classify the real-time cost data by cost type labels to obtain dynamic transportation costs, static warehousing costs, and management indirect costs; Performing correlation matching of the transport channel time periods on the transport dynamic cost to obtain a channel time period cost correlation set; Based on the warehousing static cost, the warehousing radiation area allocation calculation is performed on the channel period cost association set to obtain a channel basic cost distribution table; Perform indirect cost superposition processing on the channel basic cost distribution table according to the management indirect cost to obtain a full cost channel distribution table; Performing structural decomposition on the full-cost channel distribution table to obtain a cost structure analysis data set; The channel cost group is obtained by iteratively weighting the channel-period cost association set based on the cost structure analysis data set.

4. The multi-channel logistics transportation cost optimization method according to claim 1, characterized in that: The acquiring of historical transport records of the multi-channel logistics transport system, performing trend forecasting on the channel transport information, and obtaining a transport load forecast result includes: Extracting target records from the historical transportation records based on the channel transportation information to obtain a target historical transportation data set; performing channel classification on the target historical transportation data set according to the channel transportation information to obtain a channel historical transportation data subset; Extracting transport characteristics from the subset of channel historical transport data to obtain channel transport characteristic information; Performing cost cluster analysis on a subset of the channel's historical transportation data based on the channel's transportation characteristic information to obtain a transportation cost pattern category; Performing periodic analysis on the transportation cost pattern category to obtain the transportation cost variation pattern; The load of the channel transportation information is predicted according to the transportation cost variation rule to obtain the transportation load prediction result.

5. The multi-channel logistics transportation cost optimization method according to claim 1, characterized in that: The benefit optimization of the channel cost group and the transportation load forecast result to obtain an initial resource allocation plan includes: Decomposing the channel cost group into transport cost elements to obtain channel cost structure data; Performing a channel transportation assessment based on the transportation load prediction result and the channel cost structure data to obtain a channel transportation capacity assessment result; Performing transportation optimization calculation on the channel cost structure data to obtain a transportation optimization objective function; Constructing transportation constraints on the channel transportation capacity evaluation result according to the transportation optimization objective function to obtain transportation constraints; Allocating transport resources based on the transport capacity assessment results of the channel according to the transport constraint conditions to obtain a preliminary allocation plan; Conducting transportation feasibility verification on the preliminary allocation plan to obtain a transportation verification result; The transportation resources are adjusted on the preliminary allocation plan according to the transportation verification result to obtain the initial resource allocation plan.

6. The multi-channel logistics transportation cost optimization method according to claim 1, characterized in that: The method of identifying urgent transportation needs and planning routes for the real-time transportation data based on the transportation load forecast result, and integrating the plan with the initial resource allocation plan to obtain a channel transportation optimization plan includes: Performing load warning analysis on the transport load prediction result and the real-time transport data to obtain a transport warning indicator; Evaluate the urgency of the real-time transportation data according to the transportation warning indicators to obtain an emergency transportation demand set; Extracting transportation nodes and constructing a path network for the emergency transportation demand set to obtain a transportation path network; Performing path planning on the transportation path network to obtain a transportation path set; Performing resource conflict detection and priority sorting on the initial resource allocation plan according to the transportation path set to obtain a conflict priority sequence; reallocating resources on the initial resource allocation scheme according to the conflict priority sequence to obtain an adjusted resource allocation scheme; The resource allocation adjustment plan and the transportation path set are integrated to obtain a channel transportation optimization plan.

7. The multi-channel logistics transportation cost optimization method according to claim 6, characterized in that: The extracting of transport nodes and constructing of a path network for the emergency transport demand set to obtain a transport path network includes: Performing node identification on the emergency transportation demand set to obtain a network node set; Performing node attribute analysis on the network node set to obtain a node attribute set; Classifying the network node set according to the node attribute set to obtain a transportation network node classification set; Calculating the transport distances between the transport network node classification set to obtain a transport distance matrix; Connecting the nodes of the transportation network node classification set according to the transportation distance matrix to obtain an initial path network; Calculating the path capacity of the initial path network according to the emergency transportation demand set to obtain a path capacity matrix; The initial path network is optimized according to the path capacity matrix to obtain the transportation path network.

8. The multi-channel logistics transportation cost optimization method according to claim 6, characterized in that: The performing path planning on the transport path network to obtain a transport path set includes: Performing Pareto optimization calculation on the transportation path network to obtain a Pareto solution set; Performing cumulative calculation of path costs on the Pareto solution set to obtain a cost distribution table; Performing conflict detection on the Pareto solution set according to the initial resource allocation plan to obtain a conflict-free transportation path candidate set; Performing path scoring on the conflict-free transport path candidate set to obtain a transport path scoring table; Performing path screening on the path scoring table to obtain a high-priority path subset; Resource allocation verification is performed on the high-priority path subset to obtain the transportation path set.

9. A multi-channel logistics transportation cost optimization system, characterized by: The multi-channel logistics and transportation cost optimization method applied to any one of claims 1 to 8 above comprises: A collection module, the collection module is used to obtain real-time transportation data and storage capacity data of a multi-channel logistics transportation system, and classify the real-time transportation data by channel based on the storage capacity data to obtain channel transportation information; An analysis module, configured to obtain real-time cost data of the multi-channel logistics transportation system, perform cost matching analysis with the channel transportation information, and obtain a channel cost group; A correlation module, the correlation module is used to obtain historical transportation records of the multi-channel logistics transportation system, perform trend forecasting on the channel transportation information, and obtain a transportation load forecast result; a processing module, configured to optimize the benefits of the channel cost group and the transport load forecast result to obtain an initial resource allocation plan; A control module is used to identify urgent transportation needs and plan routes for the real-time transportation data based on the transportation load prediction result, and integrate the plan with the initial resource allocation plan to obtain a channel transportation optimization plan.

Images