Marine transportation assembly box shipping management method based on Internet of Things platform

Abstract

The invention discloses a marine assembled box shipping management method based on an Internet of Things platform, and belongs to the technical field of logistics management. The method comprises the steps of obtaining a cargo list, extracting cargo attributes, analyzing chemical attributes and physical characteristics, and generating a conflict risk assessment report; constructing a time limit prediction model based on the multi-link time data, and optimizing the loading priority; a loading scheme is optimized through a space distribution and dynamic adjustment algorithm, so that the compatibility and the transportation timeliness of goods are ensured; and the shipping state is monitored in real time, emergency adjustment is triggered according to the delay risk, and execution of a transportation plan is ensured. The loading efficiency can be effectively improved, the transportation safety is guaranteed, the transportation risk and delay probability are reduced, and the logistics management level is comprehensively improved. The method is suitable for the fields of intelligent logistics, shipping assembly box transportation and the like, and efficient and accurate decision support is provided for shipping management.

Description

Technical Field

[0001] The present invention relates to the field of logistics management technology, and more particularly to a method for managing LCL shipping based on an Internet of Things (IoT) platform. This method utilizes IoT technology, data analysis, optimization algorithms, and real-time monitoring to improve loading efficiency, safety, and timeliness during LCL transportation. The method is applicable to related fields such as shipping, logistics management, and intelligent transportation systems. Background Art

[0002] As global trade and logistics demands grow, LCL shipping plays a vital role as one of the most important modes of cargo transportation. However, existing LCL shipping management methods face numerous challenges. Traditional shipping management systems often rely on manual experience or a single data processing approach, making them unable to cope with the complex changes and dynamic demands of shipping. This leads to problems such as low loading efficiency, high safety risks, and inaccurate timeliness predictions.

[0003] Currently, the technological development of LCL shipping management systems has primarily evolved from manual operations to information-based management. Subsequently, with the rise of new technologies such as the Internet of Things, artificial intelligence, and big data, intelligent management has gradually begun to be applied to the shipping sector. For example, data collection and real-time monitoring based on IoT technology can effectively improve data accuracy during shipping. However, existing methods still lack comprehensive solutions for data processing, risk assessment, and loading optimization. In particular, significant technical gaps remain in how to process multi-source time data, accurately assess cargo risks, and optimize loading plans.

[0004] Therefore, the purpose of the present invention is to solve the problems existing in the existing LCL shipping management methods, such as non-optimized loading, inaccurate risk assessment, and inaccurate time prediction, and to provide an intelligent LCL shipping management method based on the Internet of Things platform to improve transportation efficiency, reduce delays and ensure transportation safety. Summary of the Invention

[0005] The present invention provides a shipping management method for LCL containers based on the Internet of Things platform, which aims to optimize the loading and transportation process of LCL containers by integrating multi-source data, intelligent algorithms and real-time monitoring, thereby improving transportation efficiency, safety and timeliness.

[0006] The present invention provides a shipping management method for LCL shipping based on an Internet of Things platform, comprising: Step 1: Obtain a cargo list, extract the chemical and physical properties of each batch of cargo to form an initial attribute data set, and use the classification database to classify the cargo to obtain the cargo attribute feature set; Step 2: Analyze the interaction between chemical properties and physical characteristics based on the attribute feature set. If a chemical reaction or physical damage is detected, generate a conflict risk assessment report. Step 3: Extract a list of high-risk cargo combinations from the conflict risk assessment report, use a dynamic constraint verification mechanism to screen cargo matching solutions, and obtain a preliminary loading plan; Step 4: Obtain the time data of ship navigation, port loading and unloading, and customs clearance, build a real-time time dataset, and generate a comprehensive time limit prediction model based on it; Step 5: Based on the comprehensive time limit prediction model, sort the delivery time limit requirements of each batch of goods, and use the automatic weight adjustment algorithm to optimize the loading priority to obtain a loading priority list; Step 6: Extract the highest priority cargo from the loading priority list and dynamically adjust it based on the preliminary loading plan. If a priority conflict is detected, reallocate the container position to obtain the final loading plan. Step 7: Real-time monitoring of vessel navigation and port operation status. If a delay risk is detected, an emergency process is triggered to adjust loading priorities or reallocate containers, and obtain an adjusted loading plan. Step 8: Extract the adjustment records from the adjusted loading plan and verify them with the real-time data set to determine whether the time limit requirements for all goods are met and obtain the verification results; Step 9: Generate container loading plan and scheduling report based on the verification results.

[0007] The technical solution provided by the embodiment of the present invention may have the following beneficial effects: 1. Through precise cargo attribute analysis and risk assessment, the cargo loading plan is optimized, ensuring that high-risk cargo is properly handled, avoiding safety accidents caused by improper loading, and thus improving loading efficiency and safety.

[0008] 2. By integrating time data from multiple links and making time limit predictions based on big data and machine learning algorithms, we can more accurately grasp the transportation time limit of each batch of goods, thereby rationally arranging operations such as ship navigation, port loading and unloading, and customs clearance, thereby improving overall transportation timeliness.

[0009] 3. Real-time monitoring of risk factors in the transportation process, such as ship delays or abnormal port operations, and dynamic optimization through emergency adjustment processes to ensure that timeliness and safety are not affected by emergencies during transportation, thereby enhancing the flexibility and adaptability of logistics management.

[0010] 4. Based on the comprehensive time limit prediction model and automatic weight adjustment algorithm, the present invention can optimize the container loading sequence and priority, effectively avoid the waste of resources, reduce delays caused by unreasonable loading, and improve the utilization rate of logistics resources.

[0011] 5. It can obtain data in real time, predict time limits, optimize loading plans and make emergency adjustments, realizing comprehensive intelligent management of the LCL shipping process, greatly improving the efficiency and accuracy of the entire transportation process. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 The present invention is a flow chart of a shipping management method for LCL shipping based on the Internet of Things platform. DETAILED DESCRIPTION

[0013] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. All other embodiments derived by those skilled in the art based on the embodiments in this specification without creative effort shall fall within the scope of protection of this specification.

[0014] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 In an embodiment of the present application, an embodiment of a shipping management method for LCL based on an Internet of Things platform includes: Step 1: Obtain the cargo list, extract the chemical and physical properties data of each batch of cargo to form an initial attribute data set, and use the classification database to classify the cargo to obtain the attribute feature set of the cargo.

[0015] In a specific embodiment, the process of executing step 1 may specifically include the following steps: Based on the classification database, the initial attribute data set is matched, and the K-nearest neighbor algorithm is used to determine the preliminary classification of each batch of goods to obtain the classification result set; For the classification result set, the principal component analysis algorithm is used to extract the main features of chemical properties and physical characteristics to form a streamlined feature set; Determine whether the matching degree between the simplified feature set and the preset rules in the classification database is higher than a first preset value; if so, determine the attribute feature set through attribute analysis; if not, re-extract data from the initial attribute data set to obtain an updated attribute data set; Based on the updated attribute data set, the support vector machine algorithm is used to perform secondary classification on the cargo batches to obtain the optimized classification result set; Based on the correlation analysis between the optimized classification result set and the streamlined feature set, the attribute feature set of each batch of goods is determined to obtain the final feature description set; Based on the final feature description set, the classification label and attribute feature mapping of each batch of goods are generated to obtain the attribute feature set.

[0016] Specifically, after obtaining the cargo list, the chemical properties and physical characteristics data of each batch of cargo are extracted by parsing the list structure, including chemical composition, density, volume, weight, etc.

[0017] During the data matching phase, based on a pre-set classification database, the K-nearest neighbor algorithm was used to calculate the distance between each batch of goods and existing categories in the database, determining the similarity between the goods and each category, and then assigning them to the corresponding category for preliminary classification. To optimize the classification results and extract key features, the principal component analysis (PCA) algorithm was used to reduce the dimensionality of the chemical and physical properties in the dataset, extracting the most representative principal components, thereby obtaining a reduced feature set that contains the main features that can maximize the explanation of data variance.

[0018] Based on the reduced feature set, the degree of match with the preset rules in the classification database is calculated. If the match is higher than a first preset value, the attribute feature set of the goods is determined through attribute analysis. If the match is lower than the preset value, it indicates that the preliminary classification results may contain errors or insufficient features, and an updated attribute dataset needs to be re-extracted. For example, the preset rules in the classification database are as follows: Rule 1: If the chemical activity is greater than 0.8 and the temperature stability is higher than 70°C, it is a "high-risk chemical"; Rule 2: If the chemical activity is between 0.5 and 0.8 and the temperature stability is higher than 60°C, it is a "medium-risk chemical"; Rule 3: If the chemical activity is lower than 0.5 and the temperature stability is greater than or equal to 60°C, it is a "low-risk chemical"; Rule 4: If the temperature stability is higher than 100°C, it is an "ultra-high-temperature substance." Taking cargo A01 as an example, its streamlined feature set is chemical activity 0.85 and temperature stability 75°C. The matching degree of the streamlined feature set of A01 with Rule 1 is 100%, which meets the requirements of Rule 1 and is classified as a "high-risk chemical". For other cargoes, such as B02, its streamlined feature set is chemical activity 0.60 and temperature stability 90°C, which meets the requirements of Rule 2, but the matching degree with Rule 2 does not reach the first preset threshold, so it is necessary to re-extract the attribute data and perform secondary classification.

[0019] The updated attribute dataset is then classified based on the new data, and the goods are reclassified using the Support Vector Machine (SVM) algorithm. The SVM algorithm constructs a hyperplane to categorize data points into different categories and effectively handles complex nonlinear relationships, thereby optimizing the classification results. Through correlation analysis with the streamlined feature set, the attribute feature set for each batch of goods is ultimately determined, and a complete feature description set is generated. This feature description set includes the specific classification labels and attribute feature mappings for each batch of goods, ensuring that the goods' attribute information is accurately recorded and managed.

[0020] By combining the K-nearest neighbor algorithm with principal component analysis, and using support vector machine secondary classification, we can effectively extract the core features of cargo, improve classification accuracy, and ensure the accuracy of subsequent steps such as risk assessment and loading optimization. Furthermore, by streamlining the feature set and implementing multi-level classification optimization, we reduce redundant information and improve computational efficiency. In practical applications, this can significantly enhance the intelligence level of the entire LCL shipping management process, ensuring the safety and timeliness of transportation.

[0021] Step 2: Analyze the interaction between chemical properties and physical characteristics based on the attribute feature set. If a chemical reaction or physical damage is detected, generate a conflict risk assessment report.

[0022] In a specific embodiment, the process of performing step 2 may specifically include the following steps: Obtain the chemical composition and physical state data of the goods from the attribute feature set; If the reactivity of the chemical component exceeds a second preset value, the chemical reaction path is calculated using a thermodynamic model and the reaction risk level is determined; Determine the corresponding temperature threshold and pressure conditions based on the reaction risk level, and use finite element analysis to simulate changes in physical properties and obtain stress distribution results; If the stress distribution results show that the mechanical strength is lower than the third preset value, the corrosion tendency and thermal stability are analyzed through molecular dynamics simulation to determine the risk of physical damage; Based on the analysis results of corrosion tendency and thermal stability, key features are extracted, and support vector machines are used to classify risk levels to obtain classified risk assessment results; Based on the risk assessment results, density distribution and surface tension data are obtained, and the comprehensive impact intensity of each risk factor is calculated using the numerical integration method, and the conflict risk level is determined accordingly; Based on the conflict risk level, conflict risk assessment data including chemical reaction and physical damage risks are generated.

[0023] Specifically, the chemical composition and physical state data of the goods are extracted from the attribute feature set, including chemical components such as sodium chloride, sodium nitrate, etc., as well as physical properties such as density, volume, weight, etc.

[0024] Thermodynamic models calculate the likelihood and rate of reactions under different environmental conditions, helping to determine potential risks. If the chemical components of the cargo are highly reactive, exceeding a second preset value, the thermodynamic model will calculate the chemical reaction pathway and assess the risk level. If the reaction risk level exceeds the preset safety range, further analysis will be conducted on the potential threat posed by the substance during transportation.

[0025] Finite element analysis (FEA) simulates the changes in a material's physical properties under different temperatures and pressures, particularly stress distribution. Finite element analysis establishes a mathematical model of the material under specific conditions and calculates its stress state under external pressure. If the stress distribution results indicate mechanical strength below a third preset value, indicating insufficient mechanical strength and potential physical damage during transportation, molecular dynamics simulation is used to analyze the material's corrosion propensity and thermal stability. Molecular dynamics simulation simulates molecular-level interactions to predict the material's stability under different environmental conditions. Corrosion propensity and thermal stability are combined to determine the risk of physical damage. Based on the corrosion propensity and thermal stability analysis results, key features are extracted, and a support vector machine (SVM) is used to classify risk levels. The SVM algorithm classifies the data into different risk levels by finding the optimal separating hyperplane, providing accurate classification results.

[0026] Risk-related physical property data, such as density and surface tension, is extracted from the cargo attribute feature set. This data can be obtained through experiments, material databases, or other means. Specifically, it includes the density (unit: kg / m³) and surface tension (unit: N / m) for each cargo batch. After obtaining this physical property data, all risk factors are weighted using a numerical integration method, combined with the chemical reaction risk and physical damage risk level for each cargo batch, to determine the comprehensive impact intensity for each cargo batch. Specifically, the comprehensive impact intensity is calculated using the following formula: Comprehensive impact intensity = w1 × chemical reaction risk + w2 × physical damage risk + w3 × density + w4 × surface tension. Where w1, w2, w3, and w4 are the weights of each risk factor, indicating their contribution to the overall conflict risk. Weights are determined based on their actual impact on the conflict risk. This formula combines the four factors of chemical reaction risk, physical damage risk, density, and surface tension to determine the comprehensive impact intensity for each cargo batch.

[0027] For example, assume the risk assessment results for cargo A01 are: high chemical reactivity risk, low physical damage risk, density of 2200 kg / m³, and surface tension of 72.5 N / m. Assuming a chemical reactivity risk weight of 0.4, a physical damage risk weight of 0.3, a density weight of 0.2, and a surface tension weight of 0.1, the combined impact intensity of A01 can be calculated using the above formula to be 447.63.

[0028] Conflict risk levels can be categorized according to the overall impact intensity. For example, a comprehensive impact intensity greater than 500 indicates high conflict risk; a comprehensive impact intensity less than 300 indicates medium conflict risk; and a comprehensive impact intensity less than 300 indicates low conflict risk. Based on this standard, the comprehensive impact intensity of cargo A01 is 447.63, placing it at a medium conflict risk level. The conflict risk levels of other cargoes can be determined similarly.

[0029] This conflict risk assessment data provides a comprehensive understanding of the potential chemical reactions and physical damage risks to cargo during transportation. This technology effectively identifies potential safety hazards during transportation and, through multi-level risk analysis and assessment, ensures transportation safety and prevents accidents or delays caused by improper cargo mixing or environmental fluctuations.

[0030] Step 3: Extract a list of high-risk cargo combinations from the conflict risk assessment report, use a dynamic constraint verification mechanism to screen cargo matching solutions, and obtain a preliminary loading plan.

[0031] In a specific embodiment, the process of executing step 3 may specifically include the following steps: For the high-risk cargo combination list, screen cargo matching solutions based on the constraint rule library to determine a compatible and safe cargo combination set; Based on the cargo collocation set, a linear programming algorithm is used to optimize the cargo loading sequence and generate the first loading plan; If the cargo combination in the first loading plan does not meet the compatibility and safety constraints, the cargo position is adjusted through the space allocation algorithm to obtain the optimized loading plan; The cargo location and collocation information is extracted from the optimized loading plan, and the conflict detection algorithm is used to verify whether there is a conflict risk. If not, the optimized loading plan is used as the preliminary loading plan.

[0032] For example, assume that a shipping company is carrying out ocean freight LCL transportation of multiple cargoes, including 5 batches of cargo, where the attributes of each batch of cargo are shown in Table 1: Table 1 Based on the cargo type and characteristics, a constraint rule library is used to select compatible and safe cargo combinations. This constraint rule library contains safety requirements and compatibility rules regarding cargo physical properties, chemical reactivity, temperature stability, weight, volume, and other aspects. These rules ensure that cargo interactions during loading do not lead to incompatibilities such as chemical reactions or physical damage. Assume the following pre-set rules: 1) Chemicals A01 and B02 can be loaded together if their chemical reactivity is less than 0.8; 2) Heavy items C03 cannot be loaded together with other cargo and must be loaded separately; 3) Non-hazardous items D04 can be loaded together with any cargo type, but the loading order must be maintained to prevent damage to other cargo. Based on these rules, the system selects the following cargo combinations: 1) Combination 1: A01 and B02; 2) Combination 2: D04 and A01; 3) Combination 3: E05 and D04.

[0033] Based on the selected cargo pairings, the system uses a linear programming algorithm to optimize the loading sequence, ensuring that the loading plan meets cargo compatibility requirements while maximizing space utilization. The linear programming algorithm optimizes the objective function within constraints to ensure that the loading sequence meets optimal space utilization and safety requirements. This objective function can include maximizing loading space utilization, minimizing risks to cargo safety, and maximizing transportation efficiency. For example, the objective function might be: Objective Function = Maximize Space Utilization + Minimize Loading Time + Minimize Risk.

[0034] Using a linear programming algorithm, the system optimizes the loading sequence, placing high-density cargo like C03 and E05 in the lower portion of the container, while lighter chemicals like A01 and B02 are placed in the upper layers. This ensures efficient use of loading space while minimizing potential risks. For example, the generated first loading plan is: A01, B02, D04, E05, C03; with space allocated: C03 at the bottom of the container, A01, B02, and E05 in the upper layers, and D04 in between.

[0035] If certain cargo combinations in the first loading plan do not meet compatibility and safety constraints (for example, A01 and E05 may react due to temperature mismatch), adjustments must be made using the space allocation algorithm. This algorithm rearranges the cargo based on its size, weight, and the volume constraints of the loading space, ensuring that each batch of cargo is positioned within the container in a manner that meets safety requirements and optimizes loading space. The system automatically adjusts cargo positions to prevent incompatible cargo from being placed together and causing conflicts. Suppose the adjusted loading plan is: A01, D04, B02, E05, C03; and space allocation is adjusted: E05 and D04 are assigned to different locations to ensure adequate spacing between them.

[0036] From the optimized loading scheme, the position and matching information of the goods are extracted, and the conflict detection algorithm is used for verification. The conflict detection algorithm can detect whether each pair of goods combination can cause conflict or safety problem according to the chemical reactivity, physical stability and temperature of the goods. Assuming that the detection result is: no conflict risk is found. Since the conflict detection result is no, the system takes the optimized loading scheme as the preliminary loading scheme, and finally generates the container loading plan.

[0037] Through the combination of dynamic constraint verification mechanism and optimization algorithm, the loading scheme of each batch of goods can be determined efficiently and accurately, ensuring the safety and efficiency of the transportation process. By considering the multi-dimensional characteristics and safety requirements of the goods, the application avoids accidents caused by physical property mismatch or potential risks such as chemical reaction, and effectively improves the utilization rate of loading space and reduces the risk in the transportation process.

[0038] Step 4, obtain ship navigation, port loading and unloading, and customs clearance time data, build real-time time data set, and generate comprehensive time limit prediction model accordingly.

[0039] In a specific embodiment, the process of performing step 4 can specifically include the following steps: Obtain ship navigation data, port loading and unloading data, and customs clearance data to obtain a multi-source time data set, and obtain a standardized data set after cleaning, alignment, and linear interpolation of missing values; Extract features from the standardized data set to obtain a time feature data set, extract internal time sequence features using a random forest algorithm, and form a time sequence feature vector; Train a long short-term memory network model using the time sequence feature vector to obtain a comprehensive time limit prediction model.

[0040] Specifically, due to the existence of missing values, inconsistent formats, etc. in data from different sources, data cleaning and alignment are required. The cleaning process includes removing incorrect or incomplete records, filling missing values, and ensuring data consistency and integrity. In this process, missing values can be filled by linear interpolation method to ensure data continuity and accuracy. After completing data cleaning, a standardized data set is obtained to ensure that the measurement units of each time variable are consistent.

[0041] By extracting time-related important features such as time difference between transportation links, time sequence pattern of each link, delay trend, etc., a feature data set reflecting the dynamic changes of the transportation process is formed. These features contain information about possible delays and progress changes that the goods may encounter during transportation, providing effective input for subsequent prediction models. In order to further improve the prediction accuracy, random forest algorithm is used to analyze these time feature data sets and extract their internal time sequence features. Random forest algorithm can identify the most predictive time sequence features by constructing multiple decision trees, evaluating and optimizing each feature, and generating a time sequence feature vector.

[0042] As an effective time series data processing model, LSTM can capture long-term dependencies through its memory mechanism and perform well in processing complex time series data. LSTM adjusts its internal weights and state to optimize the prediction of future time limits. The trained LSTM model can predict the time limit of goods in the transportation process based on real-time data, helping the management system to optimize the loading plan and adjust the transportation arrangement to cope with possible delays and unexpected situations.

[0043] By comprehensively analyzing multi-source time data and combining advanced algorithms for prediction, the invention not only provides more accurate time limit prediction, but also dynamically adjusts the transportation plan to reduce delays and uncertainties in the transportation process, significantly improving the efficiency and accuracy of container shipping management, and solving the problem of transportation delays caused by the lack of real-time time limit prediction.

[0044] Step 5, according to the comprehensive time limit prediction model, sort the delivery time limit requirements of each batch of goods, use automatic weight adjustment algorithm to optimize the loading priority, and get the loading priority list.

[0045] In a specific embodiment, the process of performing step 5 can specifically include the following steps: Based on the time limit constraints and batch information of each batch of goods obtained from the goods identification, generate an initial goods list; According to the initial goods list, arrange the delivery time limit requirements of each batch of goods, and get the time limit sorting result; If there is a time limit constraint conflict in the time limit sorting result, call the automatic weight adjustment algorithm, calculate the loading priority of each batch of goods according to the dynamic weight parameter, and generate a priority adjustment list; According to the priority adjustment list, use optimization algorithm to iteratively optimize the loading priority, and get the loading priority list.

[0046] Specifically, the time limit constraints of each batch of goods include its predetermined delivery time requirement and time limit requirements at each link in the transportation process. According to these time limit requirements, the delivery time limit of each batch of goods is sorted to obtain a time limit sorting result. The sorting process arranges the goods according to their delivery time limit and transportation priority, ensuring that goods with more urgent delivery time limits are processed first during transportation.

[0047] If there is a time limit constraint conflict in the time limit sorting result, meaning that the delivery time limit of some goods cannot be met at the same time, an automatic weight adjustment algorithm is started. This algorithm adjusts the loading priority of the goods according to the dynamic weight parameter, ensuring that the time limit conflict is effectively solved. The dynamic weight parameter is adjusted in real time according to the time limit constraints, transportation priority, and loading requirements of each batch of goods, giving higher priority to more urgent goods. Through this adjustment process, the demand of goods with urgent delivery time limits can be prioritized while maintaining the stability of the overall transportation plan.

[0048] According to the adjusted priority list, the system uses an optimization algorithm to iteratively optimize the loading priority to obtain a final loading priority list. The optimization algorithm considers the loading space, transportation efficiency, and time limit requirements of the goods in each iteration to adjust the loading order to maximize space utilization and minimize transportation delays. In each iteration process, the loading order is optimized according to the priority adjustment, and a priority list that balances timeliness and loading efficiency is finally generated. This list provides clear guidance for subsequent loading and transportation scheduling, ensuring that each batch of goods is processed in a timely manner according to its time limit requirements, while optimizing the use of transportation resources.

[0049] Through the combination of the time limit prediction model and the automatic weight adjustment algorithm, the system can automatically adjust the transportation plan according to real-time data, ensuring that goods can be delivered smoothly within the specified time limit, significantly improving transportation efficiency and reducing the risk of delays caused by unreasonable loading.

[0050] Step 6: Extract the highest priority goods from the loading priority list and dynamically adjust them in combination with the preliminary loading plan. If a priority conflict is detected, reassign the container positions to obtain the final loading plan.

[0051] In a specific embodiment, the process of performing step 6 can specifically include the following steps: Obtain the highest priority goods set, calculate the initial loading position based on the container position allocation rules in the preliminary loading plan using a linear programming algorithm, and obtain the preliminary loading configuration. Analyze the preliminary loading configuration. If there is a priority conflict, recalculate the allocation weight based on the conflict degree and container capacity constraints to obtain the adjusted loading configuration. The adjusted loading configuration is optimized twice using a greedy algorithm to reallocate container positions and obtain an optimized loading solution. The correspondence between container locations and cargo is extracted from the optimized loading plan. If there is unallocated cargo, it is reallocated according to the remaining container capacity to obtain a supplementary loading plan. If the supplementary loading plan meets the stability and priority requirements, it will be determined as the final loading plan.

[0052] Specifically, the highest-priority cargo is retrieved from the loading priority list. A pre-defined priority sorting algorithm is used to determine the cargo identification and priority value, resulting in a set of the highest-priority cargoes. Subsequently, these cargoes are dynamically adjusted by analyzing their time constraints and transportation requirements, taking into account the allocated container locations and other constraints in the preliminary loading plan.

[0053] For example, the container location allocation rule includes that heavy cargo is preferentially loaded in the bottom area of ​​the container, light cargo is preferentially loaded in the upper area of ​​the container, and the like.

[0054] The loading location of each cargo is influenced by multiple constraints, including container capacity and the size and weight of each cargo. During the dynamic adjustment process, a linear programming algorithm is used to calculate the initial loading location for each cargo batch based on the container's space limitations and the cargo type and characteristics. This algorithm calculates the optimal loading location for each cargo batch by setting an objective function (e.g., maximizing space utilization) and incorporating container space constraints (e.g., bottom and top area space, and cargo size and weight). This algorithm not only considers the loading sequence but also ensures compatibility and safety among cargoes during loading. Consider a container with a capacity of 10 m³, with a bottom area that can accommodate 6 m³ of cargo and a top area that can accommodate 4 m³ of cargo. If the highest-priority cargoes (e.g., heavy cargo A01 and light cargo B02) are extracted from a loading priority list, the linear programming algorithm will assign initial locations to each cargo. Heavy cargo A01 will be prioritized in the bottom area, occupying 3 m³ of space, while light cargo B02 will be assigned to the top area, occupying 2 m³ of space.

[0055] If there are priority conflicts in the initial loading configuration, for example, certain high-priority cargoes conflict with other cargoes in loading positions, or the cargo mix does not meet safety constraints, the system will recalculate the allocation weights and adjust the cargo loading positions based on the degree of conflict and container capacity constraints. At this time, the conflicting cargoes will be reconsidered and rearranged to ensure that high-priority cargoes are loaded first without affecting the safety and loading efficiency of other cargoes.

[0056] The greedy algorithm optimizes the layout of goods in the container step by step to maximize space utilization while considering safety and loading order. In each optimization, the algorithm selects the current optimal solution and gradually adjusts the positions of goods in the container until the entire loading plan meets all safety and space utilization requirements. If there are unallocated goods, the algorithm redistributes the positions of goods based on the remaining container capacity to generate a supplementary loading plan. The supplementary loading plan ensures that each piece of goods is reasonably allocated and does not violate capacity and safety constraints. Then, the algorithm checks again whether the supplementary loading plan meets the stability and priority requirements. If the plan meets the requirements, it is determined as the final loading plan.

[0057] By dynamically adjusting the loading plan and optimizing the loading priority, the timeliness and safety of transportation can be better balanced, ensuring that each batch of goods is reasonably processed according to the priority, while optimizing the use of container space, improving overall transportation efficiency and safety.

[0058] Step 7, real-time monitoring of ship navigation and port operation status, if delay risk is detected, trigger emergency process, adjust loading priority or redistribute containers, get adjusted loading plan.

[0059] In a specific embodiment, the process of executing step 7 can specifically include the following steps: Obtain ship navigation state and port operation state data, generate real-time state data set; If the real-time state data set indicates that the delay risk exceeds the fourth preset value, use the random forest algorithm to analyze the risk factors to determine the delay risk level; According to the delay risk level, extract the adaptive rules from the dynamic scheduling rule library to generate a priority adjustment strategy; According to the priority adjustment strategy, use the linear programming algorithm to optimize the container allocation scheme to get a preliminary adjustment scheme; Verify the preliminary adjustment scheme through simulation analysis, determine whether the verification result meets the preset efficiency threshold, if yes, take the preliminary adjustment scheme as the adjusted loading plan, if no, reacquire the real-time state data set, iteratively optimize the container allocation scheme, and get the adjusted loading plan.

[0060] Specifically, the navigation state data and operation state data of the ship are collected in real time through sensors, GPS devices, port operation management systems, etc. The real-time state data set contains the current position, navigation speed, and expected arrival time of the ship, as well as the port operation progress and unloading speed, etc.

[0061] If the real-time status dataset indicates a delay risk exceeding a fourth preset threshold (for example, if the scheduled arrival time is delayed by more than a certain time threshold), a random forest algorithm is used to analyze risk factors and assess the delay risk level. This algorithm trains multiple decision trees to analyze real-time status data and identify key factors that may cause delays, such as port loading and unloading progress, vessel speed, and weather conditions. Based on this, the delay risk can be accurately assessed and a corresponding delay risk level generated, reflecting potential issues in the current transportation process.

[0062] The dynamic scheduling rule base contains scheduling solutions tailored to different risk levels, such as prioritizing time-critical shipments in high-risk situations or adjusting the loading order of non-urgent shipments in less risky situations. These rules adjust the loading priorities of shipments to minimize delays and ensure the timely delivery of critical shipments. Once the priority adjustment strategy is generated, a linear programming algorithm is used to generate a preliminary adjustment plan. This algorithm optimizes the loading order of shipments within the container by considering multiple factors, including container capacity, cargo priority, and space constraints, ensuring that the adjusted loading plan meets the new priority and space utilization requirements.

[0063] The efficiency threshold refers to whether the cargo loading, transportation process, and arrival time meet the predetermined requirements within a given timeframe. If the initial adjustment plan meets this threshold, it will be used as the emergency loading plan. If not, the system will re-acquire the real-time status data set and iteratively optimize the container allocation plan to ensure that the emergency loading plan can meet transportation needs.

[0064] This dynamic adjustment process enables rapid response based on real-time data feedback during the actual transport process, allowing for flexible adjustments to transportation plans, reducing delays and improving transportation efficiency. This intelligent loading optimization solution, based on delay risk analysis and real-time adjustments, effectively addresses the lack of real-time monitoring and dynamic adjustments inherent in traditional methods, ensuring on-time delivery of goods while improving container space utilization and optimizing overall logistics scheduling.

[0065] Step 8: Extract the adjustment records from the adjusted loading plan and verify them with the real-time time data set to determine whether the time limit requirements for all goods are met and obtain the verification results.

[0066] In a specific embodiment, the process of executing step 8 may specifically include the following steps: Extracting records containing cargo information and dispatch instructions from adjustment records to obtain a structured adjustment dataset; Compare the structured adjustment dataset with the real-time dataset by timestamp. If there are goods that do not meet the time limit requirements, use the linear programming algorithm to optimize the emergency adjustment loading plan and rearrange the scheduling instructions to obtain the optimized adjustment dataset. Extract the updated dispatch instructions and cross-validate all cargo time limits with the real-time data set to obtain a validation data set; Based on the verification data set, a decision tree algorithm is used to determine whether there are goods that do not meet the time limit requirements. If so, the scheduling instructions are iteratively updated and re-verified in combination with the real-time time data set to obtain the verification results.

[0067] Specifically, the structured adjustment dataset includes information such as the loading order, loading location, and scheduling instructions for each batch of goods, which can accurately describe the distribution of goods in the container and its relationship with the time limit requirements.

[0068] The generated structured adjusted dataset is compared with the real-time time dataset, specifically comparing the loading plan and actual transit time for each shipment based on the timestamp. If the comparison indicates that time limits for certain shipments are not being met, an optimization process is triggered. A linear programming algorithm is invoked to optimize the emergency loading plan and re-adjust the location and loading order of the shipments. The linear programming algorithm calculates a new optimal loading plan based on factors such as container capacity, shipment priority, and time constraints, generating an updated adjusted dataset.

[0069] Updated scheduling instructions are extracted from the optimized, adjusted dataset and cross-validated against the real-time dataset to determine the timeliness of all shipments. Cross-validation compares the loading time, estimated arrival time, and actual transportation time of each shipment to determine whether delivery can be completed on time. The validation dataset aggregates the loading status, transportation progress, and timeliness of all shipments. Decision trees provide fast, transparent, and flexible decision support for timeliness verification and are particularly well-suited for multi-dimensional, multi-constrained loading and transportation scheduling problems. Based on the validation dataset, the decision tree algorithm automatically determines whether any loading plans are unacceptable, taking into account factors such as the shipment's timeliness, transportation status, and loading sequence. If the decision tree algorithm detects a timeliness conflict or that certain shipments are not delivered on time, it reverts to the initial loading plan and iteratively updates the scheduling instructions based on the new timeliness constraints. The algorithm then revalidates the instructions against the real-time dataset until a final loading plan that meets the timeliness requirements is achieved.

[0070] By combining linear programming, decision trees, and real-time data verification, it can flexibly respond to changes in the transportation process, ensuring that each batch of goods can be delivered smoothly within the specified time, and avoiding delays or waste of resources due to improper loading, thereby improving the flexibility and responsiveness of the entire logistics chain.

[0071] Step 9: Generate container loading plan and scheduling report based on the verification results.

[0072] In a specific embodiment, the process of executing step 9 may specifically include the following steps: Read container parameters and transportation time limits from the logistics management system to form a structured data set; Based on the structured data set, a linear programming algorithm is used to generate the initial loading plan; Determine whether the initial loading plan meets the container capacity and weight constraints. If so, use it as the container loading plan. If not, adjust the parameter weights until an initial loading plan that meets the container capacity and weight constraints is obtained. According to the container loading plan and transportation time limit, a time window algorithm is used to generate a time limit scheduling plan; Determine whether the time limit scheduling plan meets the time limit control threshold. If so, generate a scheduling report based on it. If not, optimize the time window algorithm parameter weights until a time limit scheduling plan that meets the requirements is generated.

[0073] Specifically, the structured dataset includes information such as container capacity, time constraints for each shipment, cargo type, and its weight and volume. Based on this data, a linear programming algorithm is used to generate a preliminary loading plan. This process calculates the initial loading plan by setting an objective function and constraints, taking into account the container's space and weight restrictions, as well as the cargo's priority and time constraints.

[0074] For example, the initial loading plan is: A01: Volume 3m³, Weight 2000kg; B02: Volume 2m³, Weight 1500kg; C03: Volume 4m³, Weight 3000kg; D04: Volume 1.5m³, Weight 1000kg; E05: Volume 2.5m³, Weight 1800kg. The total capacity and total weight of the containers are then calculated: Total capacity = 3m³ + 2m³ + 4m³ + 1.5m³ + 2.5m³ = 13m³; Total weight = 2000kg + 1500kg + 3000kg + 1000kg + 1800kg = 9300kg. Since the maximum container capacity limit is 10m³, and the total capacity is 13m³, this exceeds the volume limit. Furthermore, the maximum container load is 8000kg, and the total weight is 9300kg, also exceeding the weight limit. Therefore, the initial loading plan did not meet the capacity and weight constraints of the container.

[0075] To meet the constraints, the system adjusts the parameter weights, re-optimizes, and iterates until an effective loading plan is obtained that meets the container capacity and weight requirements. For example, some low-priority cargo is removed or adjusted in position. Assuming the system selects to remove C03 (volume 4m3, weight 3000kg) after adjustment according to the linear programming, the new loading scheme is: A01: volume 3m3, weight 2000kg; B02: volume 2m3, weight 1500kg; D04: volume 1.5m3, weight 1000kg; E05: volume 2.5m3, weight 1800kg. At this time: total capacity = 3m3+ 2m3+ 1.5m3+ 2.5m3= 9m3; total weight = 2000kg + 1500kg + 1000kg + 1800kg = 6300kg. The new loading scheme meets the capacity and weight constraints of the container, so it will be used as the container loading plan.

[0076] According to the above container loading plan, the system also needs to ensure that the cargos are delivered on time. Assuming the transportation time limits are as follows: A01 transportation time limit 48 hours; B02 transportation time limit 36 hours; D04 transportation time limit 24 hours; E05 transportation time limit 60 hours. The time window algorithm generates a time limit scheduling plan according to the time limit requirements of each cargo and the time constraints of the transportation link. Assuming that the transportation time limits of B02 and D04 are relatively urgent according to the actual transportation arrangement, the system needs to prioritize these cargos. According to the priority, the system adjusts the loading order and determines the shortest transportation time and feasible transportation plan for each batch of cargo. Assuming that the calculated time limit scheduling plan is: B02: priority loading, transportation time limit 36 hours; D04: second priority, transportation time limit 24 hours; A01: third priority, transportation time limit 48 hours; E05: last loading, transportation time limit 60 hours. The system develops a time limit scheduling plan according to these priorities and time limits.

[0077] Assuming that the time limit control threshold is 48 hours, i.e. the delivery time of each batch of cargo cannot exceed 48 hours. In this case, B02 and D04 meet the time limit requirements, but E05 has a delivery time of 60 hours, which exceeds the time limit control threshold. The system detects the time limit conflict and triggers further optimization. In order to solve the time limit conflict, the system adjusts the parameter weights of the time window algorithm, for example, by adjusting the priority or redistributing the loading order, to ensure that the time limit requirements of E05 are not violated. Assuming that the system adjusts the loading order and transportation route of E05 through optimization, a new time limit scheduling plan is finally obtained to ensure that all cargos can be transported within the specified time limit.

[0078] Based on the new dispatch plan, the system generates a dispatch report, including information such as the loading sequence, transit time, estimated arrival time, and whether time limits are met for each shipment. Using a data transmission protocol, the loading plan and dispatch report are integrated into a structured output and transmitted to the logistics management system, resulting in the final plan recorded by the system. A logging mechanism is used to store the operation history of the final plan recorded by the system, generating a traceable record of business execution.

[0079] Time window algorithms (TWAs) are algorithms used for scheduling and optimization problems, particularly those with time constraints. In the logistics and transportation sectors, TWAs are often used to optimize processes such as cargo loading, transportation, and delivery, ensuring that tasks are completed within a predetermined timeframe while maximizing resource utilization. At its core, they employ the concept of "time windows." Each task (such as transporting cargo or performing loading and unloading operations) has a specific time window within which it must begin or complete. Specifically, each task has a range of start and end times, known as a time window. Failure to complete a task within the specified time window is considered a default, potentially resulting in delays, fines, or other penalties. Common TWAs include greedy algorithms, dynamic programming, genetic algorithms (GAs), simulated annealing (SAs), and particle swarm optimization (PSOs).

[0080] By combining linear programming and time window algorithms, the system can ensure on-time delivery of goods while ensuring container space utilization, improving transportation efficiency and reliability, and solving problems in traditional logistics management such as inaccurate loading and scheduling, waste of resources, and transportation delays.

[0081] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A shipping management method for LCL shipping based on the Internet of Things platform, characterized in that: The method comprises: Step 1: Obtain a cargo list, extract the chemical and physical properties of each batch of cargo to form an initial attribute data set, and use the classification database to classify the cargo to obtain the cargo attribute feature set; Step 2: Analyze the interaction between chemical properties and physical characteristics based on the attribute feature set, and generate a conflict risk assessment report if a chemical reaction or physical damage is detected; Step 3: extract a list of high-risk cargo combinations from the conflict risk assessment report, use a dynamic constraint verification mechanism to screen cargo matching solutions, and obtain a preliminary loading solution; Step 4: Obtain the time data of ship navigation, port loading and unloading, and customs clearance, build a real-time time dataset, and generate a comprehensive time limit prediction model based on it; Step 5: sort the delivery time requirements of each batch of goods according to the comprehensive time limit prediction model, optimize the loading priority using an automatic weight adjustment algorithm, and obtain a loading priority list; Step 6: Extract the highest priority cargo from the loading priority list, and dynamically adjust it based on the preliminary loading plan. If a priority conflict is detected, reallocate the container position to obtain the final loading plan. Step 7: Real-time monitoring of vessel navigation and port operation status. If a delay risk is detected, an emergency process is triggered to adjust loading priorities or reallocate containers, and obtain an adjusted loading plan. Step 8: Extracting adjustment records from the adjusted loading plan, verifying them in combination with the real-time data set, determining whether the time limit requirements for all goods are met, and obtaining a verification result; Step 9: Generate a container loading plan and scheduling report based on the verification results.

2. The method according to claim 1, characterized in that The step 1 comprises: Performing data matching on the initial attribute data set based on the classification database, using a K-nearest neighbor algorithm to determine a preliminary classification of each batch of goods, and obtaining a classification result set; For the classification result set, principal component analysis algorithm is used to extract the main features of chemical properties and physical characteristics to form a simplified feature set; Determining whether the matching degree between the simplified feature set and the preset rules in the classification database is higher than a first preset value; if so, determining the attribute feature set through attribute analysis; if not, re-extracting data from the initial attribute data set to obtain an updated attribute data set; Based on the updated attribute data set, a support vector machine algorithm is used to perform secondary classification on the cargo batches to obtain an optimized classification result set; Based on the correlation analysis between the optimized classification result set and the simplified feature set, the attribute feature set of each batch of goods is determined to obtain a final feature description set; According to the final feature description set, a classification label and attribute feature mapping for each batch of goods are generated to obtain the attribute feature set.

3. The method according to claim 1, characterized in that The step 2 includes: Obtaining chemical composition and physical state data of the goods from the attribute feature set; If the reactivity of the chemical component exceeds a second preset value, the chemical reaction path is calculated using a thermodynamic model and a reaction risk level is determined; Determine the corresponding temperature threshold and pressure conditions according to the reaction risk level, and use finite element analysis to simulate the changes in physical properties to obtain stress distribution results; If the stress distribution result shows that the mechanical strength is lower than a third preset value, analyzing the corrosion tendency and thermal stability through molecular dynamics simulation to determine the risk of physical damage; Extracting key features based on the analysis results of the corrosion tendency and the thermal stability, classifying the risk levels using a support vector machine, and obtaining a classified risk assessment result; Based on the risk assessment results, density distribution and surface tension data are obtained, and the comprehensive impact intensity of each risk factor is calculated using a numerical integration method, and the conflict risk level is determined accordingly; Based on the conflict risk level, the conflict risk assessment data including the risk of chemical reaction and the risk of physical damage is generated.

4. The method according to claim 1, wherein The step 3 includes: For the high-risk cargo combination list, screen cargo matching solutions based on the constraint rule library to determine a compatible and safe cargo combination set; According to the cargo collocation set, a linear programming algorithm is used to optimize the cargo loading sequence to generate a first loading plan; If the cargo combination in the first loading plan does not meet the compatibility and safety constraints, the cargo position is adjusted through the space allocation algorithm to obtain an optimized loading plan; The cargo location and collocation information is extracted from the optimized loading plan, and a conflict detection algorithm is used to verify whether there is a conflict risk. If not, the optimized loading plan is used as the preliminary loading plan.

5. The method according to claim 1, wherein The step 4 comprises: Obtain ship navigation data, port loading and unloading data, and customs clearance data to obtain a multi-source time dataset. After cleaning, alignment, and linear interpolation of missing values, a standardized dataset is obtained. Performing feature extraction on the standardized data set to obtain a time feature data set, and extracting the internal time series features thereof using a random forest algorithm to form a time series feature vector; The time series feature vector is used to train a long short-term memory network model to obtain the comprehensive time limit prediction model.

6. The method according to claim 1, characterized in that The step 5 comprises: Generate an initial cargo list based on the time limit constraints and cargo batch information of each batch of cargo obtained from the cargo identification; Arranging the delivery time requirements for each batch of goods according to the initial goods list to obtain a time limit sorting result; If there is a time constraint conflict in the time limit sorting result, the automatic weight adjustment algorithm is called to calculate the loading priority of each batch of goods according to the dynamic weight parameters and generate a priority adjustment list; According to the priority adjustment list, the loading priority is iteratively optimized using an optimization algorithm to obtain the loading priority list.

7. The method according to claim 1, characterized in that The step 6 comprises: Obtaining a set of cargoes with the highest priority, calculating an initial loading position using a linear programming algorithm based on a container position allocation rule in the preliminary loading plan, and obtaining a preliminary loading configuration; Analyzing the preliminary loading configuration, and if there is a priority conflict, recalculating the allocation weights according to the conflict degree and the container capacity constraint to obtain an adjusted loading configuration; A greedy algorithm is used to perform secondary optimization on the adjusted loading configuration to reallocate container positions to obtain an optimized loading plan; Extracting the correspondence between container positions and cargo from the optimized loading plan, and if there is unallocated cargo, reallocating it according to the remaining container capacity to obtain a supplementary loading plan; If the supplementary loading plan meets the stability and priority requirements, it is determined as the final loading plan.

8. The method according to claim 1, characterized in that The step 7 comprises: Obtain ship navigation status and port operation status data to generate real-time status data sets; If the real-time status data set indicates that the delay risk exceeds a fourth preset value, a random forest algorithm is used to analyze risk factors to determine a delay risk level; Extracting adaptation rules from a dynamic scheduling rule base based on the delay risk level to generate a priority adjustment strategy; According to the priority adjustment strategy, a linear programming algorithm is used to optimize the container allocation plan to obtain a preliminary adjustment plan; The preliminary adjustment plan is verified through simulation analysis to determine whether the verification result meets the preset efficiency threshold. If so, the preliminary adjustment plan is used as the adjusted loading plan. If not, the real-time status data set is re-acquired, the container allocation plan is iteratively optimized, and the adjusted loading plan is obtained.

9. The method according to claim 1, characterized in that The step 8 comprises: Extracting records containing cargo information and dispatch instructions from the adjustment records to obtain a structured adjustment data set; Comparing the structured adjustment dataset with the real-time dataset based on timestamps, and if there are goods that do not meet the time limit requirements, invoking a linear programming algorithm to optimize the adjusted loading plan and rearrange scheduling instructions to obtain an optimized adjustment dataset; Extracting the updated dispatch instructions and cross-validating all cargo time limits with the real-time data set to obtain a validation data set; Based on the verification data set, a decision tree algorithm is used to determine whether there are goods that do not meet the time limit requirements. If so, the scheduling instructions are iteratively updated and re-verified in combination with the real-time time data set to obtain the verification result.

10. The method according to claim 1, characterized in that The step 9 comprises: Read container parameters and transportation time limits from the logistics management system to form a structured data set; Based on the structured data set, an initial loading plan is generated using a linear programming algorithm; Determining whether the initial loading plan satisfies the container capacity and weight constraints; if so, using the initial loading plan as the container loading plan; if not, adjusting parameter weights until obtaining the initial loading plan that satisfies the container capacity and weight constraints; Generating a time-limited scheduling plan using a time window algorithm according to the container loading plan and the transportation time limit; Determine whether the time limit scheduling plan meets the time limit control threshold. If so, generate the scheduling report accordingly. If not, optimize the time window algorithm parameter weights until the time limit scheduling plan that meets the requirements is generated.

Images