Data processing method for logistics platform

Abstract

The invention relates to the technical field of logistics management, in particular to a data processing method for a logistics platform. The method comprises the following steps: obtaining goods information data of a logistics platform; carrying out cargo transportation address extraction on the cargo information data of the logistics platform to obtain cargo transportation address data; performing logistics transportation tracking network construction on the standard logistics platform cargo information data according to the cargo transportation address data to generate a logistics transportation tracking network; carrying out transport vehicle space surplus analysis on the logistics transport tracking network to obtain transport vehicle space surplus data; carrying out cargo transportation distance vulnerability analysis on the cargo transportation address data to generate cargo transportation vulnerability data; and carrying out cargo transfer space placement adjustment by using the cargo transportation vulnerable data to generate cargo space position adjustment data. According to the invention, through data integration, space optimization, path adjustment, time sequence prediction and customer feedback, the overall efficiency and service quality of logistics are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics management, and in particular to a data processing method for a logistics platform. Background Art

[0002] Early logistics data processing mainly relied on manual records and basic database management systems. This approach is not only inefficient, but also prone to errors and difficult to meet real-time and accurate logistics needs. With the rapid development of technologies such as the Internet of Things (IoT), cloud computing, and artificial intelligence, data processing on logistics platforms has gradually become intelligent. IoT technology enables every logistics link to transmit data in real time, greatly improving the accuracy and timeliness of data collection. Cloud computing provides powerful computing and storage capabilities, enabling logistics platforms to process massive amounts of real-time data. In addition, the application of artificial intelligence and machine learning has made data analysis and prediction more intelligent, providing support for optimizing logistics routes, inventory management, and demand forecasting. In recent years, with the popularization of big data technology, the data processing methods of logistics platforms have paid more attention to deep mining and multidimensional analysis of data. However, in traditional logistics, the space use of transport vehicles is often not optimized, resulting in space waste or cargo damage. At the same time, improper selection of logistics routes or failure to adjust in time can easily lead to low transportation efficiency or delays, which in turn leads to low overall logistics efficiency and service quality. Summary of the invention

[0003] Based on this, it is necessary to provide a data processing method for a logistics platform to solve at least one of the above technical problems.

[0004] To achieve the above object, a data processing method for a logistics platform is provided, the method comprising the following steps:

[0005] Step S1: Obtain cargo information data from the logistics platform; extract cargo transportation addresses from the cargo information data from the logistics platform to obtain cargo transportation address data; construct a logistics transportation tracking network for the cargo information data of the standard logistics platform based on the cargo transportation address data to generate a logistics transportation tracking network;

[0006] Step S2: Analyze the remaining space of transport vehicles on the logistics transportation tracking network to obtain the remaining space data of transport vehicles; analyze the vulnerability of cargo transportation route on the cargo transportation address data to generate cargo transportation vulnerability data; use the cargo transportation vulnerability data to adjust the cargo transit space placement to generate cargo space position adjustment data;

[0007] Step S3: collecting road environment data from the logistics transportation tracking network to obtain cargo transportation road environment data; screening the remaining transportation paths of the cargo transportation path data to generate cargo transportation remaining path data; adjusting the transportation paths of the cargo transportation remaining path data using the cargo transportation road environment data to generate transportation path adjustment data; adjusting the transportation timing based on the transportation path adjustment data to generate cargo transportation timing prediction adjustment data;

[0008] Step S4: Collect logistics satisfaction feedback data on the cargo transportation timing prediction adjustment data and the cargo space position adjustment data to obtain cargo logistics satisfaction feedback data; optimize the logistics transportation tracking network process according to the cargo logistics satisfaction feedback data, thereby generating a logistics transportation tracking optimization strategy to perform efficient logistics operations.

[0009] By extracting cargo information data and constructing a logistics transportation tracking network, the platform can obtain the transportation information of each cargo in real time and comprehensively, ensuring data consistency and traceability during cargo transportation. The constructed tracking network effectively reduces information islands, making the entire logistics process more transparent and efficient. By analyzing the remaining space of the transport vehicle, the loading of the cargo can be optimized and the utilization rate of the transportation space can be improved. The vulnerable analysis of the cargo transportation route can identify vulnerable cargo in advance and adjust its placement, reduce the risk of damage during transportation, and improve cargo safety and transportation efficiency. By collecting real-time road environment data, the changes in the transportation route, such as traffic conditions, weather effects, etc., can be dynamically monitored, and the transportation route can be adjusted in time to avoid unnecessary delays. Path adjustment can ensure transportation timeliness and route safety, and improve overall transportation efficiency. At the same time, based on these adjustments, the transportation sequence can also be optimized to reduce time waste and ensure the punctuality of logistics. By collecting satisfaction feedback on cargo transportation sequence adjustment data and cargo space position adjustment data, customers' evaluation and demand changes for logistics services can be understood in real time. These feedbacks help optimize the transportation process and further improve service quality and customer satisfaction. The optimized logistics and transportation tracking strategy makes logistics operations more efficient, can better adapt to changes in customer demand, and enhance the competitiveness of the platform. Therefore, the present invention improves the overall efficiency and service quality of logistics through data integration, space optimization, path adjustment, time series prediction and customer feedback.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: Obtaining cargo information data from the logistics platform;

[0012] Step S12: preprocessing the logistics platform cargo information data to generate standard logistics platform cargo information data, wherein the data preprocessing includes data cleaning, data denoising, missing value filling and data standardization;

[0013] Step S13: extracting the cargo transportation address from the cargo information data of the standard logistics platform to obtain cargo transportation address data; screening the cargo information data of the standard logistics platform for the logistics transportation start-end storage site according to the cargo transportation address data to obtain cargo transportation logistics start storage site data and cargo transportation logistics end storage site data;

[0014] Step S14: constructing a logistics transportation tracking network based on the cargo transportation logistics starting storage site data and the cargo transportation logistics terminal storage site data for the logistics platform cargo information data to generate a logistics transportation tracking network.

[0015] The present invention can eliminate noise and abnormal data, improve data quality and consistency through data cleaning, denoising, missing value filling and standardization, thereby ensuring the accuracy of subsequent analysis and processing. Extracting and structuring cargo transportation address data can help accurately locate the transportation route of the goods, provide clear information support for logistics planning, and thus improve the efficiency and visualization of the logistics network. By screening the data of the starting and ending storage sites, the transportation process path of the goods can be accurately determined, which not only improves the traceability of the cargo circulation process, but also provides reliable data support for subsequent transportation scheduling and optimization. Constructing a logistics transportation tracking network integrates all key logistics information (such as starting sites, end sites, transportation routes, etc.) into a complete network structure, and realizes full tracking and real-time monitoring of the cargo transportation process, which helps to improve the transparency of the transportation process, identify potential problems in a timely manner and make adjustments, thereby reducing transportation delays, losses and other risks.

[0016] Preferably, step S14 comprises the following steps:

[0017] Step S141: Based on the cargo transportation logistics starting storage site data and the cargo transportation logistics terminal storage site data, the logistics platform cargo information data is set up with a logistics process to generate cargo logistics process setting data, wherein the cargo logistics process setting data includes a cargo loading process, a cargo transportation process, and a cargo unloading process;

[0018] Step S142: collecting process data of cargo loading process, cargo transportation process and cargo unloading process through multi-source sensors to generate cargo loading process data, cargo transportation process data and cargo unloading process data;

[0019] Step S143: data identification is performed on the cargo loading process data, the cargo transportation process data and the cargo unloading process data, and a logistics tracking node is constructed based on the identified cargo loading process data, the cargo transportation process data and the cargo unloading process data to generate a logistics tracking node;

[0020] Step S144: Perform network topology design on the logistics tracking nodes to generate logistics network topology design data; assign network attributes to the logistics tracking nodes according to the logistics network topology design data, thereby generating a logistics transportation tracking network.

[0021] The present invention can accurately define the operating specifications of each link by clearly setting the cargo loading, transportation and unloading processes, which helps to clarify the relationship between each process node and reduce the risk of misoperation and poor process. At the same time, these settings can provide a clear framework and data support for subsequent logistics scheduling, optimization and analysis. Using multi-source sensors for data collection can ensure that each link in the logistics process (such as loading, transportation, and unloading) has real-time and accurate data records, which not only improves the accuracy and integrity of the data, but also provides necessary information support for real-time monitoring and fault detection, making the logistics process more intelligent and automated. By identifying the logistics data and building logistics tracking nodes based on these identifiers, it is helpful to track the flow status of goods in each link in real time. The tracking node can provide accurate location and timestamp information, so that the transportation status of each cargo can be visualized, and when problems occur, it can quickly locate the specific link for rapid processing and optimization. Designing the network topology of the logistics tracking node and assigning network attributes can help create a more structured and efficient logistics transportation network. Through network topology, the connection relationship and data flow between nodes can be optimized, the efficiency of information transmission can be improved, and potential bottlenecks or optimization space can be analyzed, thereby further improving the efficiency and accuracy of logistics operations.

[0022] Preferably, step S2 comprises the following steps:

[0023] Step S21: extracting basic cargo information from the logistics and transportation tracking network based on the cargo loading process to obtain cargo logistics basic information data, wherein the cargo basic information includes cargo geometry information, cargo structure information, and cargo weight information; allocating logistics transportation vehicles to the cargo information data of the logistics platform according to the cargo logistics basic information data to obtain logistics transportation vehicle allocation data;

[0024] Step S22: analyzing the remaining space of the transport vehicle on the logistics transport vehicle allocation data to obtain the remaining space data of the transport vehicle; constructing the logistics transport path for the cargo transport logistics starting storage site data and the cargo transport logistics terminal storage site data through the cargo transport process to generate cargo transport path data, wherein the cargo transport path data includes a starting site, a terminal site and a plurality of transfer site data;

[0025] Step S23: performing path geographic analysis on the cargo transportation path data to generate cargo transportation path geographic elevation fluctuation data; quantifying the path bumpiness index of the cargo transportation path data based on the cargo transportation path geographic elevation fluctuation data to generate a transportation path bumpiness index;

[0026] Step S24: Perform cargo vulnerability analysis on the remaining space data of the transport vehicle according to the transport path bumpiness index to generate cargo transport vulnerability data; use the cargo transport vulnerability data to adjust the cargo transfer space placement of the transfer site data to generate cargo space position adjustment data.

[0027] The present invention helps to accurately match goods with suitable transport vehicles by extracting basic logistics data based on geometric information, structural information and weight information of goods. Through the optimization of vehicle allocation, the utilization rate of vehicle resources can be improved, overloading or insufficient situations can be avoided, thereby achieving more efficient logistics scheduling and cost control. The analysis of the remaining space of the transport vehicle can help to effectively utilize the remaining space of each vehicle, reduce the empty rate or space waste, and improve logistics efficiency, which not only helps to reduce transportation costs, but also can be reasonably arranged when multiple goods are transported, and the allocation of transportation tasks can be optimized. The construction of the cargo transportation path and the analysis of geographic elevation fluctuations can identify the complex terrain and elevation changes on the transportation path, which is crucial for transportation planning, because the ups and downs of the path will affect the stability and safety of the transport vehicle, especially the impact on fragile goods. Therefore, quantifying these changes in advance can provide data support for subsequent transportation risk assessment and optimization decisions. Based on geographic elevation fluctuation data, quantifying the bump index of the transportation path helps to assess the bump risk faced by goods under different paths, which is crucial to ensuring the transportation safety of fragile goods, especially in areas with large bumps such as highways and mountain roads, and can provide real-time decision support to avoid damage to goods during transportation. Conducting a vulnerability analysis of the cargo based on the bumpiness index of the transport route and the analysis results of the remaining space in the vehicle can help identify which cargo is most vulnerable to damage during transportation. This analysis can not only optimize the spatial layout of the cargo, but also make reasonable adjustments to the cargo location at the transit station to ensure that vulnerable cargo is better protected, reduce the risk of cargo damage, and improve transit efficiency.

[0028] Preferably, analyzing the remaining space of transport vehicles on the logistics transport vehicle allocation data includes:

[0029] Perform initial space analysis on the logistics transport vehicle allocation data to generate initial space data on the logistics transport vehicles; perform cargo space area calculation on the cargo logistics basic information data to obtain cargo space area data;

[0030] Using the cargo space area data to perform cargo storage allocation on the initial space data of the logistics transport vehicle, generating cargo storage space allocation data; performing coordinate system conversion on the cargo storage space allocation data and the initial space data of the logistics transport vehicle, generating cargo storage space allocation coordinate data and the initial space coordinate data of the logistics transport vehicle;

[0031] The coordinate axis difference between the initial space coordinate data of the logistics transport vehicle and the cargo storage space allocation coordinate data is calculated to obtain the space remaining data of the transport vehicle.

[0032] The present invention can clearly understand the available space of each transport vehicle by performing initial spatial analysis on logistics transport vehicles, which is the basis for ensuring efficient arrangement of subsequent transport tasks and helping the transport management system to understand the cargo capacity of each vehicle, thereby providing an important basis for cargo allocation and space optimization. According to the geometric information and structure of the cargo, the cargo space area is calculated. This process ensures that the space demand of the cargo is accurately quantified, so that sufficient space can be provided for each cargo in the subsequent space allocation process, and the risk of extrusion, deformation or damage during transportation is reduced. By using the cargo space area data for cargo storage allocation, the position of the cargo in the transport vehicle can be reasonably arranged to avoid vehicle instability or low transportation efficiency caused by insufficient space or unbalanced loading. This process helps to optimize the loading process, improve vehicle space utilization, and reduce empty space. Through coordinate system conversion, the cargo storage space allocation data and the initial space data of the transport vehicle can be standardized into a unified coordinate system to ensure compatibility and comparability between different data sources. This operation provides a convenient data framework for subsequent spatial analysis and optimization and ensures the accuracy of coordinate conversion. The remaining space of the transport vehicle can be obtained by calculating the difference in coordinate axes. This calculation accurately reflects the available space left after the vehicle is loaded with goods, thereby helping to optimize the loading arrangement of the vehicle and ensure that every inch of space is used as much as possible without exceeding the maximum load. At the same time, it can also provide data support for subsequent optimization tasks, such as further improving space utilization efficiency by adding more goods or adjusting the position of goods.

[0033] Preferably, step S23 includes the following steps:

[0034] Step S231: using GIS technology to match the geographic coordinates of the starting station, the terminal station and the transfer station data in the cargo transportation route data to generate the geographic coordinate matching data of the cargo transportation station; performing geographic elevation conversion on the geographic coordinate matching data of the cargo transportation station to generate the geographic elevation information data of the cargo transportation station;

[0035] Step S232: Calculate the segmented slope of the cargo transportation station geographic elevation information data to obtain cargo transportation segmented slope data; perform height difference elevation statistics on the cargo transportation segmented slope data to generate cargo transportation route elevation height data;

[0036] Step S233: Draw an elevation curve graph for the cargo transportation segment slope data according to the cargo transportation route elevation data to generate an elevation curve graph for the cargo transportation route; perform elevation change fluctuation analysis on the cargo transportation elevation curve graph to generate geographic elevation fluctuation data for the cargo transportation route;

[0037] Step S234: quantifying the path bumpiness index of the cargo transportation path data according to the geographic elevation fluctuation data of the cargo transportation path based on the transportation path bumpiness quantification formula to generate the transportation path bumpiness index.

[0038] The present invention uses GIS technology to match the geographic coordinates of the starting site, the terminal site and the transfer site, ensuring the accurate docking of the data of the transportation path with the actual geographical environment. Through elevation conversion, the geographic elevation information of each site can be obtained, which provides the necessary basic data for subsequent path analysis. This process lays a data foundation for efficient transportation path planning and transportation safety analysis. The segmented slope calculation of the transportation path can quantify the ups and downs of the path, obtain the slope data, and perform height difference lifting statistics. This analysis helps to identify the steep areas or gentle areas in the transportation path, and then evaluate the operating load and stability of the transportation vehicle under different terrain conditions. The statistics of lifting height can provide guidance for the load adjustment of the transportation vehicle, driving behavior optimization, etc. Drawing an elevation curve and performing fluctuation analysis can intuitively display the elevation changes in the transportation path, which provides a clear data diagram for the visualization of the process of cargo transportation, helps to determine which sections have excessive bumps or violent ups and downs, and then helps to plan a smoother transportation route, which not only helps to reduce the bumps of the vehicle, but also effectively reduces the risk of cargo damage. Based on the geographic elevation fluctuation data of the transport route, the bumpiness index of the transport route can be accurately quantified through the route bumpiness quantification formula. This quantification result provides a scientific basis for the safety assessment of transport vehicles and goods. By quantifying the bumpiness index, it can help optimize the transport route and select the transport route suitable for different cargo characteristics, thereby improving transportation efficiency and reducing losses.

[0039] Preferably, the transport path bump quantification formula in step S234 is as follows:

[0040]

[0041] In the formula, B represents the bumpiness index of the transport path, L represents the total length of the path, and h(x) represents the elevation at position x on the path. Expressed as the rate of change of elevation with respect to distance, It is represented as the curvature of the path at position x, v(x) is represented as the speed at position x, σ(x) is represented as the road condition influencing factor, α is represented as the path curvature influencing coefficient, β is represented as the slope influencing coefficient, γ is represented as the influencing coefficient of controlling traffic flow, and δ is represented as the influencing coefficient of the road condition influencing factor on bumps.

[0042] The present invention analyzes and integrates a quantitative formula for transport path bumps, in which the elevation fluctuation and slope change of the path are one of the main causes of bumps. In particular, when the path involves a large slope or complex curves, the ups and downs of the vehicle or sudden braking and acceleration will cause greater vibrations. The second-order derivative of the elevation (i.e., curvature) describes the degree of ups and downs of the path. In areas where the elevation fluctuates violently, the vehicle needs to adapt to the changing terrain, and such a path usually produces more bumps. The slope (i.e., the first-order derivative of the elevation) is an indicator of the degree of inclination at each position on the path. Steeper slopes (uphill or downhill) will cause the vehicle to need to accelerate or brake continuously, thereby exacerbating the bumpy feeling. For example, when driving downhill for a long time, the frequent use of brakes will also cause vehicle vibrations, increasing the unsteadiness during transportation. Traffic flow or the speed v(x) of the vehicle is significantly related to bumps. When the traffic flow is high and the road is congested, the vehicle needs to slow down, stop or accelerate frequently, and such actions will cause more vibrations. At a lower speed, the vehicle is relatively stable and the vibration is small. However, if the vehicle is driving under unstable traffic conditions (such as constantly accelerating or braking while driving slowly), the bump index will increase. Weather factors (such as rain, snow, slippery roads, wind speed, etc.) have a significant impact on bumps. Extreme weather conditions (such as heavy rain, heavy snow or storms) will reduce the adhesion of the road, making the vehicle unstable and increasing vibration. Slippery roads (such as after rain) will increase the slippage between the vehicle tires and the road surface, causing the wheels to move unsteadily, thereby exacerbating the vibration. The formula The second derivative of elevation (curvature) directly affects the undulation of the path, especially on roads that involve sharp turns or large ups and downs. Larger and more dramatic elevation fluctuations will cause the vehicle to experience more vibrations. The weight coefficient α is used to adjust the contribution of curvature to the overall bumpiness. Generally, a larger α will increase the impact of path undulations. The slope reflects the steepness of the path at different locations. Steep uphill and downhill slopes will cause the vehicle's engine and brakes to work frequently, increasing the vibration. The weight coefficient β determines the contribution of the slope to the bumps. A larger slope weighting will significantly increase the impact of this term. γ·(v(x)) 2, the traffic flow or the speed of the vehicle directly affects the acceleration and deceleration mode of the vehicle. A higher traffic flow means frequent braking and acceleration, which increases the bumpy feeling. When the speed or traffic flow is low, the vehicle drives more smoothly. The weight coefficient γ controls the contribution of speed to the bumps, and a larger γ will strengthen the influence of speed on the bump index. δ·(σ(x)), the weather factor σ(x) can dynamically adjust the impact of road conditions on bumps. For example, rainy and snowy weather, wind speed, slippery roads, etc. will aggravate bumps. The weight coefficient δ controls the degree of influence of weather and road conditions to ensure that the bump index of the path increases under adverse conditions. When using the conventional transport path bump quantification formula in the field, the transport path bump index can be obtained. By applying the transport path bump quantification formula provided by the present invention, the transport path bump index can be calculated more accurately. The formula comprehensively quantifies the bump degree of the transport path by combining multiple factors such as elevation changes, slope, traffic flow, weather and road conditions. The contribution of each factor to the bump is adjusted by the weight coefficient, so that the model can be dynamically adjusted according to the actual transportation environment. Elevation curvature and slope mainly consider the impact of the geographical environment on vehicle vibration. Large ups and downs and steep slopes will significantly increase bumps. Traffic flow and speed reflect the instability of the vehicle during driving. Higher traffic flow usually means more frequent acceleration and deceleration, which will increase bumps. Weather and road conditions simulate the impact of the external environment. Bad weather or slippery roads will cause unstable vehicle driving, thereby increasing the bumpy feeling.

[0043] Preferably, step S3 comprises the following steps:

[0044] Step S31: collecting road environment data on the logistics transportation tracking network based on the cargo transportation process to obtain cargo transportation road environment data; screening the cargo transportation path data for remaining transportation paths to generate cargo transportation remaining path data;

[0045] Step S32: using the cargo transportation road environment data to perform transportation path congestion analysis on the cargo transportation remaining path data to generate transportation path congestion data; using the transportation path congestion data to perform transportation path adjustment on the cargo transportation remaining path data to generate transportation path adjustment data;

[0046] Step S33: performing transportation timing prediction on the cargo transportation path data based on the transportation path adjustment data to generate cargo transportation timing prediction data;

[0047] Step S34: performing additional transportation timing adjustments on the cargo transportation timing forecast data according to the cargo space position adjustment data to generate cargo transportation timing forecast adjustment data.

[0048] By collecting environmental data of the cargo transportation road, the present invention can fully understand the road conditions, traffic conditions and potential risk factors in the transportation process. These data are helpful to screen out the most suitable transportation path, thereby avoiding transportation delays or safety problems caused by poor road conditions. The remaining path data after screening provides basic data for subsequent optimization of the transportation path, which is helpful to formulate a more reasonable transportation plan. Based on the road environment data, the transportation path is blocked and analyzed, and the sections with traffic congestion or poor traffic can be identified in advance, and the transportation path can be adjusted in time to avoid unnecessary delays in the transportation process. This analysis can greatly improve the transportation efficiency and reduce the time waste caused by the blockage of the goods. At the same time, through the adjusted path data, the dynamic optimization of the transportation path can be achieved to ensure a smoother transportation process. The time series prediction of the transportation path can accurately predict the transportation demand and traffic conditions in different time periods during the cargo transportation process, thereby providing data support for logistics scheduling. This time series prediction data can help transportation management personnel to carry out more accurate transportation scheduling and resource allocation, improve transportation efficiency, and optimize each link in the transportation process, reducing unnecessary waiting and empty loads. Further adjustment of the timing forecast results based on the cargo space position adjustment data can optimize the timing arrangement during transportation and ensure that the cargo arrives at each destination on schedule. This adjustment helps avoid timing confusion caused by insufficient space or differences in cargo characteristics and improves overall transportation efficiency. In addition, accurate timing adjustment can reduce transportation delays, improve customer satisfaction, and ensure the efficiency and reliability of transportation services.

[0049] Preferably, step S33 includes the following steps:

[0050] Step S331: extracting adjustment-related features from the transport path adjustment data to obtain transport path adjustment feature data; generating time series labels from the transport path adjustment feature data to obtain transport path adjustment time series labels;

[0051] Step S332: divide the cargo transportation path data into data sets by adjusting the time series labels of the transportation paths, and generate a model training set and a model test set; perform model training on the model training set using a long short-term memory neural network algorithm, and generate a cargo transportation time series prediction pre-model;

[0052] Step S333: perform model optimization iteration on the cargo transportation time series prediction pre-model according to the model test set, so as to generate a cargo transportation time series prediction model; import the cargo transportation route data into the cargo transportation time series prediction model to perform transportation time series prediction, and generate cargo transportation time series prediction data.

[0053] The present invention can identify the key factors involved in the path adjustment, such as traffic flow, road condition changes, etc., by extracting features from the transport path adjustment data. These features provide necessary information for the generation of time series labels, so that the changes in the transport path can be accurately mapped to the time series. This process can provide accurate input data for the subsequent prediction model to ensure the accuracy and reliability of the time series prediction. By dividing the data set into a training set and a test set, and using a long short-term memory (LSTM) neural network for training, the characteristics of the time series data can be fully utilized to capture the time dependency and trend changes in the transport path. The LSTM network is good at processing and predicting time series data, so it can effectively predict future transport path changes and help optimize transport timing and scheduling. The preliminary model is optimized and iterated according to the test set data to improve the accuracy and generalization ability of the model. The optimized transport timing prediction model can make more accurate predictions in a variety of scenarios, thereby providing accurate decision support for transportation management personnel. This process can reduce scheduling errors caused by prediction errors and improve logistics efficiency. The cargo transportation route data is input into the optimized time series forecasting model to conduct actual transportation time series forecasting. The generated forecasting data can accurately predict the transportation demand, traffic conditions and cargo arrival time in different time periods, thereby providing clear action guidance for dispatchers. Through time series forecasting, transportation plans can be optimized, delays can be reduced, cargo can be ensured to arrive on time, customer satisfaction can be improved, and unnecessary waste of resources can be reduced.

[0054] Preferably, step S4 comprises the following steps:

[0055] Step S41: collecting cargo logistics satisfaction feedback data based on cargo unloading process data for cargo transportation time sequence prediction adjustment data and cargo space position adjustment data to obtain cargo logistics satisfaction feedback data;

[0056] Step S42: Tracing the cargo flow of the logistics and transportation tracking network according to the cargo logistics satisfaction feedback data to generate cargo flow tracing data; optimizing the logistics and transportation tracking network based on the cargo flow tracing data to generate a logistics and transportation tracking optimization strategy to perform efficient logistics operations.

[0057] The present invention can directly reflect the customer experience in the transportation process by collecting satisfaction feedback on the transportation timing prediction data and the cargo space position adjustment data based on the cargo unloading process data. By collecting satisfaction feedback data in the cargo transportation process in real time, it is possible to identify problems or bottlenecks in the transportation process, such as time delays, cargo damage, and distribution accuracy, which provides real and effective data support for subsequent optimization of logistics operations and can help managers understand and improve service quality. According to the collected logistics satisfaction feedback data, the cargo process is traced, which helps to comprehensively track all links of the cargo in the transportation process, and every step from the starting point to the end point can be accurately recorded and monitored. The traceability data can reveal various potential problems in the transportation process, such as improper operation, timeliness problems, or the lack of logistics links. By tracking these links, the transparency of the logistics process can be improved, and data support can be provided for further optimization of the process. Based on the cargo process traceability data, the logistics transportation tracking network can optimize the process, which can not only improve logistics efficiency, but also help identify bottlenecks and inefficient links in the transportation process, such as long lag time, improper transportation route selection, etc. Through optimization strategies, corresponding adjustments can be made in different transportation links to improve operating efficiency, reduce transportation costs, and ultimately achieve efficient logistics operations. After generating a logistics transportation tracking optimization strategy, the optimization strategy can be implemented in actual transportation operations to ensure the realization of efficient logistics operations. Through real-time feedback and data-driven decision-making, the precise scheduling and implementation of each transportation task can be ensured, thereby reducing resource waste, improving delivery accuracy, and optimizing customer experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 A schematic diagram of the steps of a data processing method for a logistics platform;

[0059] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0060] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0061] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0062] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0063] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0064] It should be understood that although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, and the term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0065] To achieve this, please refer to Figures 1 to 3 , a data processing method for a logistics platform, the method comprising the following steps:

[0066] Step S1: Obtain cargo information data from the logistics platform; extract cargo transportation addresses from the cargo information data from the logistics platform to obtain cargo transportation address data; construct a logistics transportation tracking network for the cargo information data of the standard logistics platform based on the cargo transportation address data to generate a logistics transportation tracking network;

[0067] Step S2: Analyze the remaining space of transport vehicles on the logistics transportation tracking network to obtain the remaining space data of transport vehicles; analyze the vulnerability of cargo transportation route on the cargo transportation address data to generate cargo transportation vulnerability data; use the cargo transportation vulnerability data to adjust the cargo transit space placement to generate cargo space position adjustment data;

[0068] Step S3: collecting road environment data from the logistics transportation tracking network to obtain cargo transportation road environment data; screening the remaining transportation paths of the cargo transportation path data to generate cargo transportation remaining path data; adjusting the transportation paths of the cargo transportation remaining path data using the cargo transportation road environment data to generate transportation path adjustment data; adjusting the transportation timing based on the transportation path adjustment data to generate cargo transportation timing prediction adjustment data;

[0069] Step S4: Collect logistics satisfaction feedback data on the cargo transportation timing prediction adjustment data and the cargo space position adjustment data to obtain cargo logistics satisfaction feedback data; optimize the logistics transportation tracking network process according to the cargo logistics satisfaction feedback data, thereby generating a logistics transportation tracking optimization strategy to perform efficient logistics operations.

[0070] By extracting cargo information data and constructing a logistics transportation tracking network, the platform can obtain the transportation information of each cargo in real time and comprehensively, ensuring data consistency and traceability during cargo transportation. The constructed tracking network effectively reduces information islands, making the entire logistics process more transparent and efficient. By analyzing the remaining space of the transport vehicle, the loading of the cargo can be optimized and the utilization rate of the transportation space can be improved. The vulnerable analysis of the cargo transportation route can identify vulnerable cargo in advance and adjust its placement, reduce the risk of damage during transportation, and improve cargo safety and transportation efficiency. By collecting real-time road environment data, the changes in the transportation route, such as traffic conditions, weather effects, etc., can be dynamically monitored, and the transportation route can be adjusted in time to avoid unnecessary delays. Path adjustment can ensure transportation timeliness and route safety, and improve overall transportation efficiency. At the same time, based on these adjustments, the transportation sequence can also be optimized to reduce time waste and ensure the punctuality of logistics. By collecting satisfaction feedback on cargo transportation sequence adjustment data and cargo space position adjustment data, customers' evaluation and demand changes for logistics services can be understood in real time. These feedbacks help optimize the transportation process and further improve service quality and customer satisfaction. The optimized logistics and transportation tracking strategy makes logistics operations more efficient, can better adapt to changes in customer demand, and enhance the competitiveness of the platform. Therefore, the present invention improves the overall efficiency and service quality of logistics through data integration, space optimization, path adjustment, time series prediction and customer feedback.

[0071] In the embodiment of the present invention, reference Figure 1 FIG. 1 is a flow chart of steps of a data processing method for a logistics platform of the present invention. In this example, the data processing method for a logistics platform includes the following steps:

[0072] Step S1: Obtain cargo information data from the logistics platform; extract cargo transportation addresses from the cargo information data from the logistics platform to obtain cargo transportation address data; construct a logistics transportation tracking network for the cargo information data of the standard logistics platform based on the cargo transportation address data to generate a logistics transportation tracking network;

[0073] In the embodiment of the present invention, cargo information data is obtained from various logistics platforms (such as transportation management systems, warehouse management systems, distribution systems, etc.). The data content includes cargo name, weight, volume, transportation status, shipping address, receiving address, delivery time, transportation tool information, etc. The obtained logistics platform cargo information data is preprocessed to remove redundant information, correct data format errors, etc. Transport-related address information is extracted from the cargo information data, including shipping address, destination address, transit point address, etc. Natural language processing (NLP) technology, such as regular expressions, place name entity recognition (NER) models, etc., are used to ensure the accuracy and completeness of address data. According to the extracted cargo transportation address, a transportation path is constructed using geographic information system (GIS) technology or other map data. The transportation path connects various nodes from the shipping location to the destination (such as transit warehouses, distribution centers, etc.) to form a spatial network of logistics transportation. Each address or transit point is regarded as a node. According to the transportation route of the goods, the transportation path between adjacent nodes is connected. According to factors such as transportation time, distance, and cost, the logistics transportation path is optimized to generate the shortest path or optimal path plan. Construct a graph data structure of the logistics transportation tracking network, where the nodes in the graph represent locations and the edges represent transportation paths. The network can be represented in the form of adjacency matrix, adjacency list, etc. Each node contains relevant information about the location, such as address, coordinates, historical transportation records, etc. Each edge contains relevant information about transportation, such as transportation tools, transportation time, transportation status, etc. Generate a transportation network graph using a graphics processing library (such as NetworkX, Gephi, etc.). Each node in the graph represents a location for transportation, and the edge represents the transportation path of the goods. Update the transportation path and status during the logistics transportation process in real time. For example, the latest progress of cargo transportation can be dynamically monitored through GPS positioning and real-time updates of the transportation management system to ensure that the tracking network reflects the current logistics status.

[0074] Step S2: Analyze the remaining space of transport vehicles on the logistics transportation tracking network to obtain the remaining space data of transport vehicles; analyze the vulnerability of cargo transportation route on the cargo transportation address data to generate cargo transportation vulnerability data; use the cargo transportation vulnerability data to adjust the cargo transit space placement to generate cargo space position adjustment data;

[0075] In the embodiment of the present invention, the basic information of each transport vehicle is obtained from the logistics platform and the transportation management system, including the type of transport vehicle, load, remaining space, transportation route, estimated arrival time, etc. The data should include detailed information of each transport task. The remaining space is calculated based on the maximum load of each transport vehicle and the weight of the currently loaded goods. This information can come from the vehicle's sensor or logistics management system. Combined with the volume information of the goods (such as the size and shape of each cargo), the remaining space of each vehicle is calculated through an optimization algorithm (such as a greedy algorithm, a knapsack problem optimization algorithm, etc.). As the cargo loading and unloading process changes during transportation, the remaining space of each vehicle is updated in real time, and the remaining space data of each transport vehicle is generated, including: the remaining space amount (volume or weight) of each vehicle; the current loading status of each vehicle; the loading efficiency (load fullness) of each vehicle, etc. According to factors such as the type, size, material, road conditions of the transportation route, weather conditions, etc. of the goods, the risks and vulnerability encountered by the goods during transportation are evaluated. According to the material, packaging method, etc. of the goods, the vulnerability is evaluated by classification. For example, fragile, perishable, and deformable items should be specially marked. Based on the route data in the logistics transportation tracking network, the road conditions of the transportation route are analyzed (such as whether there are sharp turns, slopes, whether it passes through extreme climate areas, etc.). Through GIS data, traffic flow, climate forecast and other information, the vulnerability of each section of the journey during transportation is evaluated. For example, temperature and humidity, vibration, external impact, etc., have adverse effects on certain goods, especially perishable, fragile or chemical goods. Based on the above analysis, the vulnerability data of goods transportation is generated, including: vulnerability scores of each transportation route (high, medium, and low vulnerability); vulnerability classification of goods (such as fragile items, rotten items, valuables, etc.); risk points of each section during transportation (such as dangerous sections, bad weather areas, etc.). According to the vulnerability data of goods and the remaining space analysis of vehicles, the transportation route and transit mode of goods are optimized. The main purpose is to reduce the time that vulnerable goods are exposed to dangerous sections or harsh environments and ensure the safety of the transportation process. Through space planning and matching of goods types, ensure that vulnerable goods are placed in the safest position in the transportation vehicle or transit warehouse first. Factors to consider include temperature and humidity control, vibration protection, shock-absorbing design, and avoiding exposure to high or low temperatures. During transportation, the placement of goods is dynamically adjusted based on real-time data (such as road conditions, weather, vehicle space changes, etc.). For example, if a certain section of the journey is marked as "highly vulnerable", the location of vulnerable goods can be adjusted in advance to avoid exposure to high-risk sections. Use backpack algorithms or multi-objective optimization algorithms to ensure maximum efficiency in cargo distribution within limited transportation space, while giving priority to the protection of vulnerable goods. Real-time monitoring during transportation ensures that vulnerable goods are always placed in the best location. Generate spatial position adjustment data for goods based on the above placement adjustment plan and algorithm results.This data contains the precise location and placement of each item, ensuring that fragile goods are effectively protected.

[0076] Step S3: collecting road environment data from the logistics transportation tracking network to obtain cargo transportation road environment data; screening the remaining transportation paths of the cargo transportation path data to generate cargo transportation remaining path data; adjusting the transportation paths of the cargo transportation remaining path data using the cargo transportation road environment data to generate transportation path adjustment data; adjusting the transportation timing based on the transportation path adjustment data to generate cargo transportation timing prediction adjustment data;

[0077] In the embodiment of the present invention, road environment data is obtained from sensors, road monitoring systems (such as traffic cameras, road surface monitoring sensors), GPS devices, meteorological data sources, etc. Intelligent sensors are deployed at key locations on the road to collect data such as road conditions, temperature and humidity, and road damage in real time. The integrated traffic management platform or weather forecast system obtains real-time information such as traffic flow, weather, and accidents through the API interface. The GPS and mobile devices of logistics transportation vehicles are used to collect environmental data along the way, and the data is fed back to the logistics management platform in real time. The various road environment data collected are integrated, formatted uniformly, and stored in the database to facilitate subsequent analysis and decision-making. Based on the logistics transportation tracking network, detailed information of each transportation route is extracted, including the starting point, end point, path node, transportation time, path distance, etc. Paths passing through unobstructed roads are preferentially screened to avoid traffic congestion or areas with frequent accidents. Road sections that are easily affected by bad weather, such as mountain roads, bridges, highways, etc., are avoided, and areas that are greatly affected by storms, heavy snow, and freezing are screened out. Areas with poor road conditions and prone to traffic accidents (such as damaged sections and construction sections) are screened out. Combined with the road environment data, the original paths are screened, and the paths that are not suitable for driving due to poor environment or road conditions are removed to obtain feasible "remaining transportation paths". The specific steps include: weighted evaluation of factors such as road conditions, traffic flow, and weather impact on each path. According to the evaluation results, the remaining safe and efficient transportation paths are screened. The remaining path data screened is saved as path network data, including path number, starting and ending points, path length, path estimated time, road condition score and other information. The transportation path is dynamically adjusted according to real-time road environment changes (such as congestion, accidents, and weather). For example, if a certain section of the path is delayed due to bad weather or traffic accidents, other remaining paths can be selected. By analyzing the traffic flow and bottleneck areas on the path, the transportation route is dynamically adjusted to avoid traffic peaks or areas with frequent accidents. The transportation path is adjusted according to the time-based traffic flow and weather changes. For example, during the morning rush hour, avoid busy sections of the city; at night, you can choose a path with low traffic flow. Use intelligent optimization algorithms (such as genetic algorithms or simulated annealing algorithms) to optimize the transportation path through multiple iterations to achieve the goal of shortest time, least obstacles or lowest transportation cost. According to the route adjustment plan, record the detailed information of each route adjustment, including the route selection before and after the adjustment, the estimated transportation time, the reason for the adjustment, etc. Combined with the road environment data and the transportation route adjustment data, analyze the factors affecting the timing of the cargo transportation process, including: changes in traffic flow in different time periods during the transportation process, especially during peak hours in the morning and evening, holidays, etc. Weather factors (such as heavy rain, heavy snow, etc.) affect the transportation time, and the estimated time needs to be adjusted. If there are road closures or traffic accidents during the transportation process, the transportation sequence needs to be readjusted.Combined with traffic flow, weather, historical transportation data, etc., regression analysis, time series prediction or machine learning models (such as LSTM networks) are used to predict the transportation timing. Based on the adjusted path data, the estimated transportation time of each path is calculated and compared with other paths to select the optimal timing. Based on the results of the path adjustment, combined with real-time traffic and weather changes, the transportation timing of the goods is adjusted to generate transportation timing forecast adjustment data.

[0078] Step S4: Collect logistics satisfaction feedback data on the cargo transportation timing prediction adjustment data and the cargo space position adjustment data to obtain cargo logistics satisfaction feedback data; optimize the logistics transportation tracking network process according to the cargo logistics satisfaction feedback data, thereby generating a logistics transportation tracking optimization strategy to perform efficient logistics operations.

[0079] In the embodiment of the present invention, customer satisfaction information on logistics services is collected through channels such as questionnaires, customer support platforms, and social media comments. Feedback from front-line employees such as transport drivers and warehouse personnel is used to obtain their opinions on problems, obstacles, vehicle problems, road conditions, etc. during transportation. Combined with the transportation timing adjustment data, spatial position adjustment data, and real-time monitoring data of the transportation management system, operation data related to logistics is collected, such as: whether the transportation is carried out on time; whether any delays or damage occurs to the goods during transportation; whether the goods arrive at the predetermined location as required after the spatial adjustment, etc. Feedback data from different sources are uniformly formatted and standardized to form a structured data set for subsequent analysis. These feedback data can be stored in a database or data warehouse and updated in real time. By analyzing the collected logistics satisfaction feedback data, the main problems in the transportation process are identified. If customers often report delays in transportation time, analyze the deviation between the timing adjustment data and the actual arrival time, and find the reasons (such as insufficient path optimization, deteriorating road conditions, weather factors, etc.). If the feedback indicates that the proportion of damaged or lost goods is high, it is necessary to check whether the spatial position adjustment is reasonable and whether the safety of the transportation path is fully guaranteed. Problems such as slow customer service response and opaque information reflect defects in the system or process. Through data mining techniques such as cluster analysis and association rule analysis, potential rules and patterns are extracted from a large amount of feedback data. These patterns reveal the weaknesses of certain stages or links in logistics operations. For example, if most of the negative feedback is concentrated on certain transportation routes or weather conditions, it indicates that there is room for further optimization of these routes or environments. If most of the problems in customer feedback occur in a specific time period or a specific type of goods, it means that these time periods or types of goods require special treatment. Based on the transportation timeliness data and real-time road conditions information fed back by customers, the path selection algorithm is further optimized. More dynamic data (such as real-time traffic flow, weather changes, etc.) needs to be introduced to ensure the flexibility and timeliness of path selection. According to the feedback data of damaged or lost goods, the spatial placement strategy of goods is adjusted. It is necessary to further optimize the placement order and priority of goods and ensure that vulnerable goods are additionally protected. According to the results of feedback data analysis, a specific logistics transportation tracking optimization strategy is designed, which mainly includes: based on feedback data, optimize the transportation path selection algorithm, focusing on solving the timeliness problem. Introduce more dynamic data (such as real-time road conditions, weather, etc.) and formulate a dynamic adjustment strategy. Based on cargo damage data, the cargo space placement is carefully managed to ensure that fragile and valuable cargo is given priority protection and to reduce unnecessary space waste. Customer satisfaction is improved through process improvement, including improving customer service response time, enhancing the transparency of transportation information, and handling customer complaints in a timely manner. After generating a logistics transportation tracking optimization strategy, it is implemented in conjunction with the logistics management system, and the effect of the optimization strategy is monitored in real time.KPIs (key performance indicators) can be set to track optimization results, such as transportation punctuality, customer satisfaction, cargo damage rate, etc.

[0080] Preferably, step S1 comprises the following steps:

[0081] Step S11: Obtaining cargo information data from the logistics platform;

[0082] Step S12: preprocessing the logistics platform cargo information data to generate standard logistics platform cargo information data, wherein the data preprocessing includes data cleaning, data denoising, missing value filling and data standardization;

[0083] Step S13: extracting the cargo transportation address from the cargo information data of the standard logistics platform to obtain cargo transportation address data; screening the cargo information data of the standard logistics platform for the logistics transportation start-end storage site according to the cargo transportation address data to obtain cargo transportation logistics start storage site data and cargo transportation logistics end storage site data;

[0084] Step S14: constructing a logistics transportation tracking network based on the cargo transportation logistics starting storage site data and the cargo transportation logistics terminal storage site data for the logistics platform cargo information data to generate a logistics transportation tracking network.

[0085] In an embodiment of the present invention, information including the name of the goods, the weight of the goods, the transportation route, the mode of transportation, the origin and the destination is obtained from the logistics platform system. This information usually comes from the database or sensor data acquisition system of the logistics platform, and can be obtained through API, file import and other methods. The obtained logistics platform cargo information data is cleaned, useless data and noise are removed, missing values ​​are filled, and the data format is standardized. Remove erroneous or inconsistent records, such as invalid transportation addresses or repeated cargo information. Remove measurement errors or random noise in the data through filtering algorithms or outlier detection methods. Use appropriate filling methods (such as mean filling, interpolation methods, prediction methods based on machine learning, etc.) to fill in missing information. Normalize or standardize the data to ensure that different types of data have a unified metric standard for subsequent analysis. Extract the specific address data of the transportation origin and destination from the standard logistics platform cargo information data. According to the extracted transportation address, further filter out the starting storage site and the terminal storage site of the cargo transportation. The screening process can be based on specific rules, such as distance, regional scope, accessibility and other standards. The data of the starting storage site and the terminal storage site are integrated, combined with the transportation path, transportation mode, transportation time and other information to generate a logistics transportation network. The graph structure in graph theory can be used, where the nodes represent each storage site and the edges represent the transportation path of the goods. According to each site in the transportation process, the transportation path of the goods is constructed, and the transportation status (such as shipped, in transit, arrived, etc.) is recorded. The real-time transportation status of the goods is tracked through sensors, GPS, RFID and other equipment, and the tracking network is dynamically updated.

[0086] Preferably, step S14 comprises the following steps:

[0087] Step S141: Based on the cargo transportation logistics starting storage site data and the cargo transportation logistics terminal storage site data, the logistics platform cargo information data is set up with a logistics process to generate cargo logistics process setting data, wherein the cargo logistics process setting data includes a cargo loading process, a cargo transportation process, and a cargo unloading process;

[0088] Step S142: collecting process data of cargo loading process, cargo transportation process and cargo unloading process through multi-source sensors to generate cargo loading process data, cargo transportation process data and cargo unloading process data;

[0089] Step S143: data identification is performed on the cargo loading process data, the cargo transportation process data and the cargo unloading process data, and a logistics tracking node is constructed based on the identified cargo loading process data, the cargo transportation process data and the cargo unloading process data to generate a logistics tracking node;

[0090] Step S144: Perform network topology design on the logistics tracking nodes to generate logistics network topology design data; assign network attributes to the logistics tracking nodes according to the logistics network topology design data, thereby generating a logistics transportation tracking network.

[0091] In the embodiment of the present invention, the entire logistics transportation process of the goods is set according to the extracted data of the starting storage site and the terminal storage site, including the loading process, the transportation process and the unloading process. The loading process of the goods from the warehouse or the distribution center is defined, and the loading order, equipment, personnel and other information are recorded. It usually includes the loading, inspection and acceptance of the goods. The process that the goods go through during transportation is defined, including the transportation route, transportation mode (such as trucks, ships, railways, etc.), transportation transfer stations, transportation time and other information. The unloading process after the goods arrive at the terminal storage site is defined, covering the unloading sequence, unloading equipment, unloading inspection and other links. The generated cargo logistics process setting data will provide a detailed description of each logistics link, laying the foundation for subsequent process collection and network construction. In each process link, multi-source sensors (such as RFID, GPS, temperature and humidity sensors, cameras, etc.) are deployed to collect data from each link in the logistics process in real time. Collect data from the loading link, such as loading time, cargo type, loading location, loading personnel, etc. Collect data from the transportation link, including the transportation route, GPS location of the transportation vehicle or transportation tool, transportation time, vehicle status and other information. Collect data from the unloading process, such as unloading time, unloading location, unloading personnel, unloading method, etc. The data collected by these sensors can update the progress of each logistics process in real time to ensure dynamic monitoring of the entire cargo transportation process. Identify the collected cargo loading process data, cargo transportation process data, and cargo unloading process data. The identification can be based on process links, timestamps, geographic locations, equipment IDs, and other information. Construct logistics tracking nodes based on the identified data: Each process (loading, transportation, unloading) can be regarded as a node, and the connection between nodes represents the transfer of goods from one process link to another. Loading node: indicates the loading status of goods at the starting storage site. Transportation node: indicates the intermediate stop or key location of goods during transportation. Unloading node: indicates the status of the completion of unloading of goods at the terminal storage site. The data identification of each node includes node type (loading, transportation, unloading), timestamp, geographic location, relevant personnel and equipment information, etc. According to the constructed logistics tracking nodes and their associated data, the topology design of the logistics tracking network is carried out. Using graph theory, each logistics tracking node can be regarded as a node in the graph, and the transportation routes between nodes can be regarded as edges. Network topology design includes determining the relative position of each node, the connectivity of the transportation path, the priority of the transportation route, etc., to ensure that the logistics transportation network is efficient and scalable. According to the logistics network topology design data, network attributes are assigned, such as the status of each node (loading, transportation, unloading), the transportation timeliness of each edge, the transportation cost, the reliability of the node, etc. The purpose of network attribute assignment is to quantify the various characteristics of nodes and edges to provide support for subsequent logistics tracking and optimization.The assigned data will form a logistics transportation tracking network, which not only includes the transportation status of the goods, but also reflects the specific attributes of each logistics link, such as transportation time, cost, transportation tools and other information.

[0092] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0093] Step S21: extracting basic cargo information from the logistics and transportation tracking network based on the cargo loading process to obtain cargo logistics basic information data, wherein the cargo basic information includes cargo geometry information, cargo structure information, and cargo weight information; allocating logistics transportation vehicles to the cargo information data of the logistics platform according to the cargo logistics basic information data to obtain logistics transportation vehicle allocation data;

[0094] Step S22: analyzing the remaining space of the transport vehicle on the logistics transport vehicle allocation data to obtain the remaining space data of the transport vehicle; constructing the logistics transport path for the cargo transport logistics starting storage site data and the cargo transport logistics terminal storage site data through the cargo transport process to generate cargo transport path data, wherein the cargo transport path data includes a starting site, a terminal site and a plurality of transfer site data;

[0095] Step S23: performing path geographic analysis on the cargo transportation path data to generate cargo transportation path geographic elevation fluctuation data; quantifying the path bumpiness index of the cargo transportation path data based on the cargo transportation path geographic elevation fluctuation data to generate a transportation path bumpiness index;

[0096] Step S24: Perform cargo vulnerability analysis on the remaining space data of the transport vehicle according to the transport path bumpiness index to generate cargo transport vulnerability data; use the cargo transport vulnerability data to adjust the cargo transfer space placement of the transfer site data to generate cargo space position adjustment data.

[0097] In an embodiment of the present invention, during the cargo loading process, the system extracts the geometric information, structural information and weight information of the cargo from the logistics platform. The dimensions (length, width and height) of the cargo are extracted by sensors or three-dimensional scanning technology to determine the volume occupied by the cargo. The structural feature data of the cargo are extracted according to the type, packaging form and sensitivity (such as fragile, easy to press, etc.) of the cargo. The total weight information of the cargo is obtained according to the sensor data or the weighing system, and the load capacity of the cargo is provided. The system allocates the transport vehicle according to the geometric information, structural information and weight information of the cargo. For example, for heavy or large-volume cargo, large-capacity trucks can be allocated preferentially; for fragile or special-required cargo, a transport vehicle with appropriate protection can be selected to generate logistics transport vehicle allocation data, which includes information such as the type of allocated vehicle, load capacity, and vehicle number. The space remaining amount of the allocated transport vehicles is analyzed to evaluate the size of the remaining available space of each vehicle. Based on the geometric dimensions of the vehicle and the information of the loaded cargo, the remaining space of the vehicle is calculated, and the space remaining amount data of the transport vehicle is generated, which includes the remaining space volume, load capacity, loading priority, etc. of the vehicle. According to the cargo transportation process, the cargo transportation path is constructed by combining the data of the starting storage site and the terminal storage site. The path construction includes selecting the starting site and the terminal site, as well as the data of the transfer site. The path selection should take into account factors such as the geographical location, the accessibility of the transportation tool, and the traffic conditions, and generate the cargo transportation path data, including: a starting site, a terminal site, and several transfer sites. The data of each site contains information such as the geographical location, site capacity, and facility type. The cargo transportation path is analyzed for geographic elevation and the geographic elevation fluctuation on the path is analyzed. The elevation data of each point on the path is obtained through the digital elevation model (DEM), and the elevation change of the transportation path is calculated to generate the geographic elevation fluctuation data of the cargo transportation path. The data records the elevation changes of different points on the path and evaluates the impact of elevation fluctuations on the transportation process. According to the geographic elevation fluctuation data, the bumpiness index of the path is calculated to quantify the bumpiness of the path. The bumpiness index calculation takes into account factors such as the undulation of the terrain, the quality of the road, and the adaptability of the transportation tool to generate the bumpiness index of the transportation path. This indicator can help evaluate the bumpiness encountered during transportation. According to the transport path bump index, the risk of damage to goods during transportation is analyzed to generate data on the vulnerability of goods during transportation. The safety of goods is assessed by comparing the characteristics of vulnerable goods (such as fragility and deformation) with the transport path bump index. Vulnerable goods are graded and labeled to ensure that special protective measures are taken during transportation. Based on the cargo transport vulnerability data and the path bump index, the storage location of goods at the transit station is adjusted to optimize the storage method of goods.For example, for fragile items, you can choose to place them in the center of the vehicle to reduce the impact force on them; for heavy goods, you can place them at the bottom to ensure that the weight is evenly distributed and generate cargo space position adjustment data, which provides the specific position arrangement of the goods during transportation to ensure the safety and transportation efficiency of the goods.

[0098] Preferably, analyzing the remaining space of transport vehicles on the logistics transport vehicle allocation data includes:

[0099] Perform initial space analysis on the logistics transport vehicle allocation data to generate initial space data on the logistics transport vehicles; perform cargo space area calculation on the cargo logistics basic information data to obtain cargo space area data;

[0100] Using the cargo space area data to perform cargo storage allocation on the initial space data of the logistics transport vehicle, generating cargo storage space allocation data; performing coordinate system conversion on the cargo storage space allocation data and the initial space data of the logistics transport vehicle, generating cargo storage space allocation coordinate data and the initial space coordinate data of the logistics transport vehicle;

[0101] The coordinate axis difference between the initial space coordinate data of the logistics transport vehicle and the cargo storage space allocation coordinate data is calculated to obtain the space remaining data of the transport vehicle.

[0102] In the embodiment of the present invention, the basic space parameters of each transport vehicle are extracted according to the distribution data of the logistics transport vehicle, including the compartment size (length, width, height), maximum load, volume and other information. The vehicle space data includes the volume of the vehicle compartment and the available space of each compartment (excluding unavailable areas such as compartment doors, obstacles, fixed equipment, etc.), and the initial space data of the logistics transport vehicle is generated. The data can represent the boundary information of the compartment in three-dimensional coordinates and be distinguished in detail according to different vehicle types (such as container trucks, flatbed trucks, refrigerated trucks, etc.). Based on the basic information data of the goods, especially the geometric information (length, width, height) of the goods, the space occupied by each piece of goods is calculated. Spatial area calculation method: For regular-shaped goods, the length × width × height formula can be directly used to calculate the volume; for irregular goods, the volume of its bounding box is calculated using three-dimensional scanning or other algorithms. The cargo space area data includes information such as the volume, surface area, and center of gravity position of each piece of cargo to ensure the calculation of the space requirements of the cargo. The cargo space area data is combined with the initial space data of the logistics transport vehicle to perform reasonable storage and allocation of the goods. The specific process includes: evaluating the volume of each piece of cargo and the available space of the transport vehicle, and making reasonable loading and space allocation. Prioritize arranging heavier or fragile cargo in the appropriate position of the transport vehicle (such as the center of the vehicle to avoid excessive bumps). After the cargo storage space allocation data is generated, it will include the position of each piece of cargo in the transport vehicle, the space allocation strategy, and the loading order of each cargo. Perform coordinate system conversion on the cargo storage space allocation data and the initial space data of the logistics transport vehicle. This step ensures that the space coordination between the cargo and the vehicle is accurate. The initial space coordinate data of the logistics transport vehicle is usually based on the position and direction of the vehicle's compartment, and the coordinates of each space position in the compartment are defined in the vehicle coordinate system. Define the position of the cargo relative to the transport vehicle coordinate system, such as the docking position of the cargo and the compartment, the center point of the cargo, etc. The purpose of the coordinate system conversion is to ensure that all spatial calculations are performed in the same unified coordinate system to reduce errors caused by inconsistent coordinates. The conversion method includes: the storage location of each cargo is calculated relative to the coordinate system of a specific point in the carriage (such as the lower left corner of the carriage), and the carriage coordinate system is converted to the global coordinate system for further data analysis or cross-regional scheduling. The coordinate axis difference calculation is performed on the initial spatial coordinate data of the logistics transport vehicle and the cargo storage space allocation coordinate data. The difference between each cargo after loading and the free space in the carriage is calculated to obtain the remaining space. The result of the coordinate axis difference calculation will show the remaining space in each space area in each transport vehicle, as well as the specific storage location of each cargo. The remaining space data obtained by the coordinate axis difference calculation can be further used to generate the space remaining data for each transport vehicle. The space remaining data will include: the remaining volume of each vehicle, the distribution of available space, the location of unused space, etc.In addition, the "space utilization" of each vehicle can be further calculated based on the different types, load and volume restrictions of transport vehicles.

[0103] Preferably, step S23 includes the following steps:

[0104] Step S231: using GIS technology to match the geographic coordinates of the starting station, the terminal station and the transfer station data in the cargo transportation route data to generate the geographic coordinate matching data of the cargo transportation station; performing geographic elevation conversion on the geographic coordinate matching data of the cargo transportation station to generate the geographic elevation information data of the cargo transportation station;

[0105] Step S232: Calculate the segmented slope of the cargo transportation station geographic elevation information data to obtain cargo transportation segmented slope data; perform height difference elevation statistics on the cargo transportation segmented slope data to generate cargo transportation route elevation height data;

[0106] Step S233: Draw an elevation curve graph for the cargo transportation segment slope data according to the cargo transportation route elevation data to generate an elevation curve graph for the cargo transportation route; perform elevation change fluctuation analysis on the cargo transportation elevation curve graph to generate geographic elevation fluctuation data for the cargo transportation route;

[0107] Step S234: quantifying the path bumpiness index of the cargo transportation path data according to the geographic elevation fluctuation data of the cargo transportation path based on the transportation path bumpiness quantification formula to generate the transportation path bumpiness index.

[0108] In an embodiment of the present invention, by using GIS technology (geographic information system), the geographic coordinates of each site data (starting site, terminal site, transfer site, etc.) in the cargo transportation path data are matched. The matching process mainly includes: matching the longitude and latitude information of each site with the actual geographic coordinate system to ensure that the location data of all sites are accurate. Use geographic information data sources (such as Amap, Google Maps or other geographic databases) to accurately locate the longitude and latitude of the site, and generate cargo transportation site geographic coordinate matching data, which contains the accurate longitude and latitude, relative position and other information of each site. Based on the cargo transportation site geographic coordinate matching data, the geographic elevation of each site is further converted using GIS technology: the elevation information can usually be obtained through a digital elevation model (DEM) or other elevation data sources. The coordinates of each site are converted to an elevation, the actual altitude data of the site location is obtained, and the geographic elevation information data of the cargo transportation site is generated, including the elevation data of each transportation site. Based on the geographic elevation information data of the cargo transportation site, the slope of the cargo transportation path is calculated. Slope can be defined as the ratio of the height difference between two adjacent sites to the distance. The calculation formula is usually as follows: Sslope = Δh ÷ d; where Δh is the elevation difference between two adjacent sites, and d is the horizontal distance between them. The transportation route is divided into sections (for example, from the starting site to the transfer site, from the transfer site to the terminal site), and the slope is calculated section by section to generate the cargo transportation segment slope data, which includes the slope value of each section of the route (increase, decrease, gentle, etc.). By analyzing the cargo transportation segment slope data, the rise and fall of each path segment are counted. Specifically, it includes: calculating the elevation difference of each section of the transportation route, and analyzing the overall trend of rise and fall during cargo transportation. Based on the slope of each section of the route, the cumulative rise and fall of the elevation during the transportation process is calculated, and the elevation height data of the entire route is summarized to generate the cargo transportation route elevation height data, and the total elevation height of each section of the route and the related trends are recorded. Based on the elevation height data of the cargo transportation route, an elevation curve of the cargo transportation route is drawn. The curve chart will show the trend of geographical elevation changes of the entire transportation route. The X-axis represents the geographical location of the path (such as the stations on the path), and the Y-axis represents the corresponding geographical elevation (altitude). The volatility of the curve shows the smoothness and fluctuations of the elevation changes in the transportation path, and generates a cargo transportation route elevation curve. By graphically presenting the elevation fluctuations of the path, it helps to analyze the elevation changes during transportation. A detailed analysis of the cargo transportation elevation curve is mainly to judge the bumpiness of the path through the fluctuations of the curve: analyze the fluctuations of the path, that is, the amplitude of the elevation changes between each station. According to the amplitude, frequency and other characteristics of the elevation fluctuations, the volatility of the path is quantitatively evaluated, and the geographical elevation fluctuation data of the cargo transportation path is generated. This data describes the elevation fluctuations on the path, covering peaks, troughs and flat sections.According to the geographic elevation fluctuation data of the transportation path, a specific transportation path bumpiness quantification formula is used to quantify the bumpiness of the path. The calculation of the bumpiness index usually includes factors such as the elevation fluctuation amplitude and fluctuation frequency to generate the transportation path bumpiness index, which can be used to evaluate the impact of vibration, bumps and instability during transportation.

[0109] Preferably, the transport path bump quantification formula in step S234 is as follows:

[0110]

[0111] In the formula, B represents the bumpiness index of the transport path, L represents the total length of the path, and h(x) represents the elevation at position x on the path. Expressed as the rate of change of elevation with respect to distance, It is represented as the curvature of the path at position x, v(x) is represented as the speed at position x, σ(x) is represented as the road condition influencing factor, α is represented as the path curvature influencing coefficient, β is represented as the slope influencing coefficient, γ is represented as the influencing coefficient of controlling traffic flow, and δ is represented as the influencing coefficient of the road condition influencing factor on bumps.

[0112] The present invention analyzes and integrates a quantitative formula for transport path bumps, in which the elevation fluctuation and slope change of the path are one of the main causes of bumps. In particular, when the path involves a large slope or complex curves, the ups and downs of the vehicle or sudden braking and acceleration will cause greater vibrations. The second-order derivative of the elevation (i.e., curvature) describes the degree of ups and downs of the path. In areas where the elevation fluctuates violently, the vehicle needs to adapt to the changing terrain, and such a path usually produces more bumps. The slope (i.e., the first-order derivative of the elevation) is an indicator of the degree of inclination at each position on the path. Steeper slopes (uphill or downhill) will cause the vehicle to need to accelerate or brake continuously, thereby exacerbating the bumpy feeling. For example, when driving downhill for a long time, the frequent use of brakes will also cause vehicle vibrations, increasing the unsteadiness during transportation. Traffic flow or the speed v(x) of the vehicle is significantly related to bumps. When the traffic flow is high and the road is congested, the vehicle needs to slow down, stop or accelerate frequently, and such actions will cause more vibrations. At a lower speed, the vehicle is relatively stable and the vibration is small. However, if the vehicle is driving under unstable traffic conditions (such as constantly accelerating or braking while driving slowly), the bump index will increase. Weather factors (such as rain, snow, slippery roads, wind speed, etc.) have a significant impact on bumps. Extreme weather conditions (such as heavy rain, heavy snow or storms) will reduce the adhesion of the road, making the vehicle unstable and increasing vibration. Slippery roads (such as after rain) will increase the slippage between the vehicle tires and the road surface, causing the wheels to move unsteadily, thereby exacerbating the vibration. The formula The second derivative of elevation (curvature) directly affects the undulation of the path, especially on roads that involve sharp turns or large ups and downs. Larger and more dramatic elevation fluctuations will cause the vehicle to experience more vibrations. The weight coefficient α is used to adjust the contribution of curvature to the overall bumpiness. Generally, a larger α will increase the impact of path undulations. The slope reflects the steepness of the path at different locations. Steep uphill and downhill slopes will cause the vehicle's engine and brakes to work frequently, increasing the vibration. The weight coefficient β determines the contribution of the slope to the bumps. A larger slope weighting will significantly increase the impact of this term. γ·(v(x)) 2 , the traffic flow or the speed of the vehicle directly affects the acceleration and deceleration mode of the vehicle. A higher traffic flow means frequent braking and acceleration, which increases the bumpy feeling. When the speed or traffic flow is low, the vehicle drives more smoothly. The weight coefficient γ controls the contribution of speed to the bumps, and a larger γ will strengthen the influence of speed on the bump index. δ·(σ(x)), the weather factor σ(x) can dynamically adjust the impact of road conditions on bumps. For example, rainy and snowy weather, wind speed, slippery roads, etc. will aggravate bumps. The weight coefficient δ controls the degree of influence of weather and road conditions to ensure that the bump index of the path increases under adverse conditions. When using the conventional transport path bump quantification formula in the field, the transport path bump index can be obtained. By applying the transport path bump quantification formula provided by the present invention, the transport path bump index can be calculated more accurately. The formula comprehensively quantifies the bump degree of the transport path by combining multiple factors such as elevation changes, slope, traffic flow, weather and road conditions. The contribution of each factor to the bump is adjusted by the weight coefficient, so that the model can be dynamically adjusted according to the actual transportation environment. Elevation curvature and slope mainly consider the impact of the geographical environment on vehicle vibration. Large ups and downs and steep slopes will significantly increase bumps. Traffic flow and speed reflect the instability of the vehicle during driving. Higher traffic flow usually means more frequent acceleration and deceleration, which will increase bumps. Weather and road conditions simulate the impact of the external environment. Bad weather or slippery roads will cause unstable vehicle driving, thereby increasing the bumpy feeling.

[0113] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0114] Step S31: collecting road environment data on the logistics transportation tracking network based on the cargo transportation process to obtain cargo transportation road environment data; screening the cargo transportation path data for remaining transportation paths to generate cargo transportation remaining path data;

[0115] Step S32: using the cargo transportation road environment data to perform transportation path congestion analysis on the cargo transportation remaining path data to generate transportation path congestion data; using the transportation path congestion data to perform transportation path adjustment on the cargo transportation remaining path data to generate transportation path adjustment data;

[0116] Step S33: performing transportation timing prediction on the cargo transportation path data based on the transportation path adjustment data to generate cargo transportation timing prediction data;

[0117] Step S34: performing additional transportation timing adjustments on the cargo transportation timing forecast data according to the cargo space position adjustment data to generate cargo transportation timing forecast adjustment data.

[0118] In the embodiment of the present invention, based on the cargo transportation path data, various sensors (such as vehicle GPS, road monitoring cameras, traffic flow sensors, etc.) are used to collect data on the road environment through which the cargo is transported, and the cargo transportation road environment data is generated. The data describes the real-time status of the roads involved in the entire transportation process, and helps to further analyze the feasibility of the transportation path. Based on the cargo transportation path data, the remaining available parts of the transportation path are analyzed. This process includes: according to the road environment data, the road sections that have been blocked, closed or impassable are excluded. The paths with good road environment and moderate traffic flow are retained, and those sections that are greatly affected by weather, accidents, etc. are removed to generate the remaining cargo transportation path data, which describes the effective paths available during the transportation process to ensure that the cargo will not encounter unforeseen road obstacles during the transportation process. The cargo transportation road environment data is used to perform congestion analysis on the remaining cargo transportation path data. This step is mainly based on real-time traffic information to evaluate the congestion of each transportation path: traffic monitoring data (such as traffic cameras, road sensors, etc.) is used to judge the congestion status of each path. Combined with historical data, the sections that are prone to congestion in a specific time period are identified. Monitor changes in factors such as weather, accidents, and temporary road closures in real time, issue early warnings on the smoothness of the path, and generate transportation path congestion data, including information such as the degree of congestion of each transportation path, the expected congestion time, and the affected area. Based on the transportation path congestion data, adjust the path data of the remaining path of cargo transportation. This process includes: adjusting the transportation path according to the real-time traffic conditions, selecting alternative paths to avoid congested areas. Analyze the peak traffic period and recommend transportation during the period with low traffic flow. Based on the real-time traffic monitoring information, adjust the path selection during the transportation process, and generate transportation path adjustment data, which includes the adjusted path selection plan to ensure that the goods can avoid congestion or obstacle areas and reduce transportation delays. Based on the transportation path adjustment data, predict the time series during the transportation of goods. This step uses time series analysis and prediction models (such as regression models, time series analysis, machine learning algorithms, etc.) to predict the transportation time. The specific steps include: comparing the adjusted transportation path with the historical time series data and analyzing the transportation time under different paths. Consider factors such as real-time traffic flow, weather conditions, and road facilities to perform time series prediction. Use machine learning or deep learning algorithms to train the prediction model, and predict the transportation timing based on the adjusted transportation path data to generate cargo transportation timing prediction data, which predicts the specific timing of cargo transportation, including the expected arrival time, path travel time, etc. Based on the cargo spatial position adjustment data (i.e., the position change of cargo during transportation, storage adjustment, etc.), further adjust the cargo transportation timing prediction data. Specific operations include: analyzing the changes in the spatial position of cargo during transportation, such as the impact of operations such as transit and warehousing on the timing. Based on the cargo space adjustment data, further optimize the transportation timing on the basis of the transportation timing prediction.For example, if the cargo transit is delayed or the spatial position changes, the estimated arrival time will be adjusted in real time. Combined with the transportation route adjustment data, road environment data, etc., calibration is performed to ensure the accuracy of the transportation timing forecast and generate cargo transportation timing forecast adjustment data. This data updates the final transportation timing forecast and ensures that the timing and cargo spatial position adjustment are optimized synchronously.

[0119] Preferably, step S33 includes the following steps:

[0120] Step S331: extracting adjustment-related features from the transport path adjustment data to obtain transport path adjustment feature data; generating time series labels from the transport path adjustment feature data to obtain transport path adjustment time series labels;

[0121] Step S332: divide the cargo transportation path data into data sets by adjusting the time series labels of the transportation paths, and generate a model training set and a model test set; perform model training on the model training set using a long short-term memory neural network algorithm, and generate a cargo transportation time series prediction pre-model;

[0122] Step S333: perform model optimization iteration on the cargo transportation time series prediction pre-model according to the model test set, so as to generate a cargo transportation time series prediction model; import the cargo transportation route data into the cargo transportation time series prediction model to perform transportation time series prediction, and generate cargo transportation time series prediction data.

[0123] In an embodiment of the present invention, features related to time series prediction are extracted based on the transport path adjustment data (for example, the influence of factors such as path changes, traffic jams, and weather). These features include: starting point, end point, transit station along the way, path length, traffic flow, etc. Such as weather conditions (sunny, rainy, etc.), road conditions (unblocked, blocked, under construction, etc.). Such as the timeliness of the transport path (peak period, non-peak period), etc., these data characterize the various factors that affect the transport timing during the transport path adjustment process. The extracted transport path adjustment feature data is used to generate time series labels. Each label represents the corresponding timeliness information, such as the estimated arrival time, path travel time, etc. These labels will be used as target variables for supervised learning in model training. For each transport path, based on historical transportation data, traffic flow, etc., corresponding time series labels (such as the passing time of each path, the estimated arrival time, etc.) are generated. These labels can include specific time intervals or more accurate duration predictions to ensure that the model can learn effective time series relationships. Based on the generated transport path adjustment time series labels, the entire data set is divided into two parts: the model training set is used for the model training process, and the data should include historical path adjustment features and corresponding time series labels. The model test set is used for model verification and optimization, and the data should include historical path adjustment features that are not involved in training and real time series labels. The reasonable distribution of the training set and the test set on the time series should be ensured to avoid data leakage, and the test set should be independent of the training set. The long short-term memory neural network (LSTM) is used for model training. LSTM is a neural network structure suitable for processing time series data and can capture long-term dependencies in time series. The transport path adjustment feature data and the corresponding time series label (target variable) are input. The freight transportation time series prediction pre-model is output, which can predict the timeliness or estimated arrival time of the transport path based on the given path adjustment features. The training process of the LSTM model includes: data preprocessing, model architecture selection, parameter optimization, loss function definition (such as mean square error MSE), etc. By comparing the prediction results of the test set with the true value, the performance indicators of the model (such as prediction accuracy, mean square error MSE, etc.) are calculated. The weights of the LSTM model are adjusted through the back-propagation algorithm, and the accuracy of the model is further optimized through hyperparameter optimization (such as learning rate, number of hidden layers, batch size, etc.). Multiple rounds of training and adjustment are performed to improve the prediction accuracy. Methods such as cross-validation can be used to verify the generalization ability of the model. After multiple rounds of optimization and iteration, a high-precision cargo transportation timing prediction model is finally generated, which can adjust the data according to the input transportation path and predict the transportation timing (for example, estimated arrival time, path travel time, etc.).The cargo transportation path data (i.e. the adjusted path data and environmental data, etc.) are imported into the cargo transportation timing prediction model for prediction, and the cargo transportation timing prediction data are obtained. These data contain information such as the expected transportation timing and estimated arrival time of each transportation path.

[0124] Preferably, step S4 comprises the following steps:

[0125] Step S41: collecting cargo logistics satisfaction feedback data based on cargo unloading process data for cargo transportation time sequence prediction adjustment data and cargo space position adjustment data to obtain cargo logistics satisfaction feedback data;

[0126] Step S42: Tracing the cargo flow of the logistics and transportation tracking network according to the cargo logistics satisfaction feedback data to generate cargo flow tracing data; optimizing the logistics and transportation tracking network based on the cargo flow tracing data to generate a logistics and transportation tracking optimization strategy to perform efficient logistics operations.

[0127] In the embodiment of the present invention, by extracting key logistics activity information from the cargo unloading process data, such as the time of unloading, the place of unloading, the efficiency of the unloading personnel, whether there are delays in the transportation process, etc., the cargo transportation time series prediction data and cargo space position adjustment data generated in step S33 are used, combined with the data of the unloading process, to conduct comprehensive feedback collection on logistics satisfaction. This feedback collection is intended to understand the factors that affect the efficiency of customers or the transportation process in each link. For example, whether the transportation arrives at the unloading point at the scheduled time, whether there are delays or early arrival. According to the analysis of the space adjustment data, whether the unloading is carried out according to the planned spatial position, and whether there is a non-optimal allocation of the spatial layout. Including customer satisfaction in the unloading process, the work attitude and professionalism of the logistics personnel, etc. Finally, through the analysis of the above factors, the cargo logistics satisfaction feedback data is generated, which will serve as an important basis for subsequent process optimization. Based on the cargo logistics satisfaction feedback data, each link in the entire logistics transportation process is traced. The purpose of tracing is to analyze the problems in each link and the root causes of their occurrence, so as to improve the transportation operation. Through the logistics tracking network, the path of cargo transportation is traced back to determine whether there are any delays or abnormalities in the transportation process. Backtrack each time node, analyze the deviation between the transportation sequence and the predicted sequence, and understand the time distribution of each link. Check whether the spatial position adjustment of the cargo is in line with the plan, and find out the irrationality of space utilization and its impact on the transportation process. Compare customer satisfaction, unloading process feedback and other data with each link in the transportation process to understand which factors lead to the decline in satisfaction. Through the traceability of the logistics process, obtain the cargo process traceability data, which contains detailed transportation process information, potential problem points and customer feedback information. Based on the cargo process traceability data, optimize the logistics transportation tracking network to improve the efficiency and accuracy of transportation operations. By analyzing the transportation path and sequence, re-evaluate the transportation route of the cargo, reduce unnecessary detours or congestion, and choose a faster transportation path. According to the spatial position adjustment data and customer feedback of the cargo, optimize the spatial layout of the unloading process to reduce space waste and time waste. Combine the transportation sequence and logistics feedback data to optimize the unloading and distribution process, reduce waiting time and processing time, and improve efficiency. According to the needs of logistics transportation and the work efficiency of employees, reasonably dispatch personnel to improve the overall efficiency of logistics operations. Through these optimization measures, a logistics transportation tracking optimization strategy is generated to provide guidance for performing more efficient logistics operations.

[0128] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0129] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A data processing method for a logistics platform, characterized in that: The following steps are involved: Step S1: Obtain cargo information data from the logistics platform; extract cargo transportation addresses from the cargo information data from the logistics platform to obtain cargo transportation address data; construct a logistics transportation tracking network for the cargo information data of the standard logistics platform based on the cargo transportation address data to generate a logistics transportation tracking network; Step S2: Analyze the remaining space of transport vehicles on the logistics transportation tracking network to obtain the remaining space data of transport vehicles; analyze the vulnerability of cargo transportation route on the cargo transportation address data to generate cargo transportation vulnerability data; use the cargo transportation vulnerability data to adjust the cargo transit space placement to generate cargo space position adjustment data; Step S3: collecting road environment data from the logistics transportation tracking network to obtain cargo transportation road environment data; screening the remaining transportation paths of the cargo transportation path data to generate cargo transportation remaining path data; adjusting the transportation paths of the cargo transportation remaining path data using the cargo transportation road environment data to generate transportation path adjustment data; adjusting the transportation timing based on the transportation path adjustment data to generate cargo transportation timing prediction adjustment data; Step S4: collecting logistics satisfaction feedback data on the cargo transportation time sequence prediction adjustment data and the cargo space position adjustment data to obtain cargo logistics satisfaction feedback data; The logistics and transportation tracking network process is optimized based on the cargo logistics satisfaction feedback data, thereby generating a logistics and transportation tracking optimization strategy to perform efficient logistics operations.

2. The data processing method for a logistics platform according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Obtaining cargo information data from the logistics platform; Step S12: preprocessing the logistics platform cargo information data to generate standard logistics platform cargo information data, wherein the data preprocessing includes data cleaning, data denoising, missing value filling and data standardization; Step S13: extracting the cargo transportation address from the cargo information data of the standard logistics platform to obtain cargo transportation address data; screening the cargo information data of the standard logistics platform for the logistics transportation start-end storage site according to the cargo transportation address data to obtain cargo transportation logistics start storage site data and cargo transportation logistics end storage site data; Step S14: constructing a logistics transportation tracking network based on the cargo transportation logistics starting storage site data and the cargo transportation logistics terminal storage site data for the logistics platform cargo information data to generate a logistics transportation tracking network.

3. The data processing method for a logistics platform according to claim 2, characterized in that: Step S14 includes the following steps: Step S141: Based on the cargo transportation logistics starting storage site data and the cargo transportation logistics terminal storage site data, the logistics platform cargo information data is set up with a logistics process to generate cargo logistics process setting data, wherein the cargo logistics process setting data includes a cargo loading process, a cargo transportation process, and a cargo unloading process; Step S142: collecting process data of cargo loading process, cargo transportation process and cargo unloading process through multi-source sensors to generate cargo loading process data, cargo transportation process data and cargo unloading process data; Step S143: data identification is performed on the cargo loading process data, the cargo transportation process data and the cargo unloading process data, and a logistics tracking node is constructed based on the identified cargo loading process data, the cargo transportation process data and the cargo unloading process data to generate a logistics tracking node; Step S144: Perform network topology design on the logistics tracking nodes to generate logistics network topology design data; assign network attributes to the logistics tracking nodes according to the logistics network topology design data, thereby generating a logistics transportation tracking network.

4. The data processing method for a logistics platform according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: extracting basic cargo information from the logistics and transportation tracking network based on the cargo loading process to obtain cargo logistics basic information data, wherein the cargo basic information includes cargo geometry information, cargo structure information, and cargo weight information; allocating logistics transportation vehicles to the cargo information data of the logistics platform according to the cargo logistics basic information data to obtain logistics transportation vehicle allocation data; Step S22: analyzing the remaining space of the transport vehicle on the logistics transport vehicle allocation data to obtain the remaining space data of the transport vehicle; constructing the logistics transport path for the cargo transport logistics starting storage site data and the cargo transport logistics terminal storage site data through the cargo transport process to generate cargo transport path data, wherein the cargo transport path data includes a starting site, a terminal site and a plurality of transfer site data; Step S23: performing path geographic analysis on the cargo transportation path data to generate cargo transportation path geographic elevation fluctuation data; quantifying the path bumpiness index of the cargo transportation path data based on the cargo transportation path geographic elevation fluctuation data to generate a transportation path bumpiness index; Step S24: Perform cargo vulnerability analysis on the remaining space data of the transport vehicle according to the transport path bumpiness index to generate cargo transport vulnerability data; use the cargo transport vulnerability data to adjust the cargo transfer space placement of the transfer site data to generate cargo space position adjustment data.

5. The data processing method for a logistics platform according to claim 4, characterized in that: Analysis of the remaining space of transport vehicles for logistics transport vehicle allocation data includes: Perform initial space analysis on the logistics transport vehicle allocation data to generate initial space data on the logistics transport vehicles; perform cargo space area calculation on the cargo logistics basic information data to obtain cargo space area data; Using the cargo space area data to perform cargo storage allocation on the initial space data of the logistics transport vehicle, generating cargo storage space allocation data; performing coordinate system conversion on the cargo storage space allocation data and the initial space data of the logistics transport vehicle, generating cargo storage space allocation coordinate data and the initial space coordinate data of the logistics transport vehicle; The coordinate axis difference between the initial space coordinate data of the logistics transport vehicle and the cargo storage space allocation coordinate data is calculated to obtain the space remaining data of the transport vehicle.

6. The data processing method for a logistics platform according to claim 4, characterized in that: Step S23 includes the following steps: Step S231: using GIS technology to match the geographic coordinates of the starting station, the terminal station and the transfer station data in the cargo transportation route data to generate the geographic coordinate matching data of the cargo transportation station; performing geographic elevation conversion on the geographic coordinate matching data of the cargo transportation station to generate the geographic elevation information data of the cargo transportation station; Step S232: Calculate the segmented slope of the cargo transportation station geographic elevation information data to obtain cargo transportation segmented slope data; perform height difference elevation statistics on the cargo transportation segmented slope data to generate cargo transportation route elevation height data; Step S233: Draw an elevation curve graph for the cargo transportation segment slope data according to the cargo transportation route elevation data to generate an elevation curve graph for the cargo transportation route; perform elevation change fluctuation analysis on the cargo transportation elevation curve graph to generate geographic elevation fluctuation data for the cargo transportation route; Step S234: quantifying the path bumpiness index of the cargo transportation path data according to the geographic elevation fluctuation data of the cargo transportation path based on the transportation path bumpiness quantification formula to generate the transportation path bumpiness index.

7. The data processing method for a logistics platform according to claim 5, characterized in that: The transport path bump quantification formula in step S234 is as follows: In the formula, B represents the bumpiness index of the transport path, L represents the total length of the path, and h(x) represents the elevation at position x on the path. Expressed as the rate of change of elevation with respect to distance, It is represented as the curvature of the path at position x, v(x) is represented as the speed at position x, σ(x) is represented as the road condition influencing factor, α is represented as the path curvature influencing coefficient, β is represented as the slope influencing coefficient, γ is represented as the influencing coefficient of controlling traffic flow, and δ is represented as the influencing coefficient of the road condition influencing factor on bumps.

8. The data processing method for a logistics platform according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: collecting road environment data on the logistics transportation tracking network based on the cargo transportation process to obtain cargo transportation road environment data; screening the cargo transportation path data for remaining transportation paths to generate cargo transportation remaining path data; Step S32: using the cargo transportation road environment data to perform transportation path congestion analysis on the cargo transportation remaining path data to generate transportation path congestion data; using the transportation path congestion data to perform transportation path adjustment on the cargo transportation remaining path data to generate transportation path adjustment data; Step S33: performing transportation timing prediction on the cargo transportation path data based on the transportation path adjustment data to generate cargo transportation timing prediction data; Step S34: performing additional transportation timing adjustments on the cargo transportation timing forecast data according to the cargo space position adjustment data to generate cargo transportation timing forecast adjustment data.

9. The data processing method for a logistics platform according to claim 8, characterized in that: Step S33 includes the following steps: Step S331: extracting adjustment-related features from the transport path adjustment data to obtain transport path adjustment feature data; generating time series labels from the transport path adjustment feature data to obtain transport path adjustment time series labels; Step S332: divide the cargo transportation path data into data sets by adjusting the time series labels of the transportation paths, and generate a model training set and a model test set; perform model training on the model training set using a long short-term memory neural network algorithm, and generate a cargo transportation time series prediction pre-model; Step S333: perform model optimization iteration on the cargo transportation time series prediction pre-model according to the model test set, so as to generate a cargo transportation time series prediction model; import the cargo transportation route data into the cargo transportation time series prediction model to perform transportation time series prediction, and generate cargo transportation time series prediction data.

10. The data processing method for a logistics platform according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: collecting cargo logistics satisfaction feedback data based on cargo unloading process data for cargo transportation time sequence prediction adjustment data and cargo space position adjustment data to obtain cargo logistics satisfaction feedback data; Step S42: Tracing the cargo flow of the logistics and transportation tracking network according to the cargo logistics satisfaction feedback data to generate cargo flow tracing data; optimizing the logistics and transportation tracking network based on the cargo flow tracing data to generate a logistics and transportation tracking optimization strategy to perform efficient logistics operations.

Images