A port intelligent shipping management method based on an internet of things

Abstract

The application discloses a port intelligent shipping management method based on an internet of things, and comprises the following steps: S1, collecting and preprocessing port internet of things terminal data; S2, generating a queuing sequence and an in-out port suggestion time by using an improved dynamic beat rearrangement algorithm; S3, constructing a crane loading capacity model, and outputting an efficiency score table by using an improved pre-loading capacity perspective algorithm; S4, matching the queuing sequence and the score table, generating a multi-constraint scheduling matrix, binding vehicles and cranes by using dynamic weights, and generating a scheduling table; S5, generating an electronic shipping order according to the scheduling table, embedding identity and crane information, and completing verification and binding; S6, after vehicles enter and exit an electronic fence, the system identifies and compares shipping order information, automatically releases and pushes a loading instruction after successful matching; and S7, continuously collecting data during task execution, and feeding back in real time. The application realizes intelligent closed-loop scheduling of port shipping, improves efficiency, reduces congestion, and optimizes resource allocation.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation and logistics scheduling technology, and in particular to an intelligent shipping management method for port areas based on the Internet of Things. Background Technology

[0002] In modern port logistics management, particularly in the transportation of bulk liquid cargoes such as crude oil and chemicals, the port's dispatching system plays a crucial role. With the continuous increase in transportation demand and operational density, traditional port dispatching management systems have gradually revealed numerous limitations, especially in vehicle dispatching, operational coordination, safety control, and customer service response, exhibiting significant information lag, resource waste, and management blind spots. Currently, most ports still rely on manual recording, on-site communication, or semi-automated single-point systems for vehicle entry and exit management, loading arrangements, and dispatching. This model is not only inefficient but also highly susceptible to human error, leading to frequent problems such as uneven utilization of loading resources, vehicle congestion, long waiting times, and high safety risks.

[0003] Especially in short-haul transportation scenarios involving bulk raw materials, such as crude oil delivery operations primarily using road transport, port dispatch faces particularly complex challenges. Firstly, port terminal layouts typically suffer from physical bottlenecks such as limited access channels, a fixed number of loading hooks, and narrow weighbridge paths, easily leading to logistics congestion during peak hours. Secondly, pre-entry queuing and dispatching of vehicles relies on manual notification and the experience of dispatchers, lacking scientific time allocation and resource matching criteria. This often results in vehicles congregating around the port area, increasing regional traffic pressure and even posing safety hazards. Furthermore, most current systems cannot effectively link with driver terminals, lacking precise means of predicting arrival times. Drivers cannot know in advance when to enter the port and the loading order, relying solely on verbal notifications or on-site observation, significantly reducing transportation efficiency and customer satisfaction.

[0004] From a system integration perspective, existing port operation systems generally suffer from fragmented modules, data silos, and inconsistent interfaces. Scheduling, metering, loading, and identity verification systems typically rely on manual data transfer or USB drive import / export, lacking a unified data center and information synchronization mechanism. This decentralized management model results in a lack of real-time tracking and global optimization capabilities throughout the shipping process, failing to form an end-to-end shipping information loop. Managers struggle to grasp the overall operational status and respond quickly to emergencies. Furthermore, traditional systems employ rudimentary scheduling algorithms, relying solely on static priority or first-come, first-served (FCFS) strategies, neglecting dynamic factors such as vehicle status, loading bay capacity differences, real-time port traffic, and equipment load, severely impacting the scientific rigor and rationality of overall scheduling.

[0005] In recent years, with the development of emerging technologies such as the Internet of Things, artificial intelligence, and big data, some port areas have attempted to introduce sensing devices and data analysis platforms into specific processes. For example, they have used license plate recognition systems to achieve automatic release or video surveillance systems to assist in loading confirmation. However, these improvements are mostly localized optimizations and have not yet formed a cross-process, end-to-end information fusion and intelligent scheduling system. Furthermore, most existing technologies rely on fixed rules and manual intervention, lacking data-driven adaptive scheduling capabilities. More importantly, there is a general lack of ability to uniformly model and dynamically optimize the allocation of resources between vehicle pickup plans, actual operating status, and loading resources, failing to fully utilize advanced algorithms for precise allocation of port resources.

[0006] At the scheduling level, traditional systems lack modeling and capacity assessment mechanisms for crane positions, making it impossible to dynamically score and prioritize crane positions based on real-time loading efficiency. Regarding queuing and sorting, they also lack a scheduling index model that integrates multiple factors such as time, space, equipment capacity, and cargo demand, resulting in a severe disconnect between vehicle sorting and operational efficiency. Furthermore, the system fails to effectively identify special business scenarios such as "secondary loading" and does not provide customized management capabilities such as VIP queue jumping, anomaly handling, and scheduling alerts. These problems make traditional port dispatch management systems ill-suited to the current growing business volume and the demand for refined management.

[0007] In summary, the existing technology has the following main shortcomings: First, it lacks an identity binding and task coordination mechanism between vehicles, drivers, and loading positions, which cannot guarantee the accuracy and safety of scheduling; second, it has not established a dynamic scheduling algorithm model, and cannot intelligently optimize the queuing order and loading position allocation based on the real-time operating status of the port area and loading efficiency; third, the data cannot form a closed loop, and the scheduling results lack real-time feedback and system self-learning mechanisms, making continuous optimization impossible; fourth, it lacks the ability to adapt to special business scenarios and cannot meet the diversified and high-frequency loading scheduling needs of modern ports.

[0008] Therefore, how to provide a port area intelligent shipping management method based on the Internet of Things to achieve intelligent sorting of vehicle scheduling, optimal allocation of loading crane positions, accurate binding of task identities, and closed-loop feedback of data throughout the process is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0009] One objective of this invention is to propose an intelligent port dispatch management method based on the Internet of Things (IoT). This invention fully utilizes IoT sensing technology, big data analysis methods, and intelligent scheduling optimization algorithms, combined with an improved dynamic rhythm reordering algorithm and a pre-loading capacity perspective algorithm. It describes in detail the entire process of realizing intelligent vehicle sorting, dynamic scoring of crane positions, multi-constraint matching scheduling, and task identity binding. It has the advantages of high dispatch efficiency, high resource utilization, strong scheduling accuracy, full-process traceability, and strong system self-learning ability.

[0010] A port area intelligent shipping management method based on the Internet of Things according to an embodiment of the present invention includes the following steps:

[0011] S1. Collect IoT terminal data in the port area and preprocess it to construct a standardized shipping dataset.

[0012] S2. Based on the standardized shipping dataset, an improved dynamic beat reordering algorithm is used to dynamically sort all vehicles and generate vehicle queue sequences and suggested entry and exit times.

[0013] S3. Based on the standardized shipping dataset, construct a loading capacity model for each crane position in the port area within a unit of time, and score it using an improved pre-loading capacity perspective algorithm to output an efficiency score table for each crane position.

[0014] S4. Cross-match the vehicle queuing sequence with the efficiency score table to form a multi-constraint matching matrix, and bind high-loading capacity cranes with high-priority vehicles through a dynamic weight allocation mechanism to generate a queuing scheduling table with priority labels.

[0015] S5. Based on the queuing schedule and the suggested arrival and departure times, generate corresponding electronic waybills for all vehicles and embed the license plate number, driver's ID number and assigned crane position number. Verify the identity of the electronic waybill and bind it to the dispatch task.

[0016] S6. When a vehicle enters or leaves the port area's electronic fence, the vehicle's location is identified and compared with the electronic waybill information. If the match is successful, a release signal is triggered, and a loading instruction is pushed to the corresponding crane terminal.

[0017] S7. During the vehicle's dispatch mission, continuously collect IoT terminal data within the port area, update and record feedback in real time, form a closed-loop self-learning scheduling mechanism, and complete the archiving of dispatch data throughout the entire process.

[0018] Optionally, the IoT terminal data includes real-time vehicle location, license plate number information, driver identity, crane allocation status, vehicle cargo delivery plan, current port area traffic load and historical loading records, and the preprocessing includes data cleaning and format unification.

[0019] Optionally, S2 specifically includes:

[0020] S21. Based on the standardized shipping dataset, extract the estimated arrival time for each vehicle to be dispatched. Delivery plan quantity Last loading time Distance from current location to port area And the current average loading time in the port area and real-time port area traffic load factor The data is used as sorting input features;

[0021] S22. Construct a dynamic beat reordering optimization objective function, and use an improved dynamic beat reordering algorithm to calculate the vehicle priority index:

[0022] ;

[0023] in, For vehicles The scheduling priority index; a higher value indicates a higher scheduling priority. For vehicles The planned delivery quantity, in tons. For vehicles The remaining distance to the port area, in kilometers. For vehicles The estimated arrival time at the port area, in minutes. For vehicles The last loading completion time, in minutes. This represents the average loading time per vehicle in the current port area, expressed in minutes per vehicle. The current port area traffic load coefficient is a dimensionless number reflecting traffic and operational pressure. , , The weighted averages of the pickup volume factor, distance factor, and waiting time factor are respectively, satisfying the following conditions: , , To avoid introducing small positive quantities when the denominator is zero;

[0024] S23, Priority index of all vehicles Sort the vehicles in descending order to obtain the vehicle queue sequence. ,in At the same time , , and Using the parameters, calculate the suggested arrival and departure times for each vehicle:

[0025] ;

[0026] in, For vehicles Suggested arrival and departure times. For vehicles Current actual speed, in kilometers per minute. This is an empirical adjustment factor used to balance cycle time and port congestion levels;

[0027] S24, Output vehicle queuing sequence Collection of recommended arrival and departure times .

[0028] Optionally, S3 specifically includes:

[0029] S31. Based on the standardized shipping dataset, extract crane position-related data, which includes each crane position... Historical assignment rounds Total load per round Corresponding task duration Number of vehicles currently waiting Number of abnormal events per unit time and equipment availability coefficient within the current work cycle. ;

[0030] S32. Construct a port area loading capacity model and define each crane position. Theoretical loading capacity per unit time:

[0031] ;

[0032] in, For the position of crane Loading capacity per unit time, expressed in tons per minute. For the first Loading capacity for this operation For the first The actual completion time for this assignment. For historical operation rounds;

[0033] S33. Based on the loading capacity model, an improved pre-loading capacity perspective algorithm is used to correct the real-time efficiency of each crane position, forming a multi-dimensional comprehensive scoring function and outputting an efficiency score value:

[0034] ;

[0035] in, For the position of crane The loading efficiency score, The equipment availability factor has a range of values. This represents the current operating status of the crane positioning equipment. This represents the number of abnormal events within the current period. This represents the current number of waiting vehicles. , , These are the availability enhancement factor, the anomaly penalty factor, and the queuing penalty factor, respectively, all of which are positive constants.

[0036] S34. Output the set of loading efficiency scores for all crane positions. .

[0037] Optionally, S4 specifically includes:

[0038] S41, Based on vehicle queuing sequence Vehicle priority index Delivery plan quantity Loading efficiency rating set for cranes Construct standardized vehicle vectors and crane position vector :

[0039] ;

[0040] in, Indicates vehicle The remaining distance to the port area To prevent division by zero for small positive numbers, For the position of crane The loading efficiency score, For the position of crane Historical average load per trip This represents the number of vehicles currently waiting to operate at this crane position. The maximum number of vehicles picked up in the current batch is used as the normalization benchmark. It is a function for maximizing the value;

[0041] S42. Combining the nonlinear suppression function, weighted cosine similarity is used to calculate vehicle similarity. With Crane Position Overall compatibility:

[0042] ;

[0043] in, For vehicles With Crane Position Overall compatibility score , The vehicles and cranes are respectively the first Feature values ​​in each dimension As feature weighting factors, satisfying , To avoid tiny values ​​of division by zero, As a loading quantity deviation suppression factor, it controls the sensitivity of the difference between the vehicle and the historical capacity of the crane position;

[0044] S43. To improve overall resource utilization efficiency and fairness, a dynamic weight allocation mechanism is introduced and a scheduling priority function is constructed:

[0045] ;

[0046] in, This represents the current port area traffic load factor, a dimensionless number reflecting traffic and operational pressure. For vehicles Assigned to crane position The scheduling utility value, For the position of crane The equipment availability factor, The current port area traffic load coefficient is a dimensionless number reflecting traffic and operational pressure. This represents the maximum delay time in the current batch, used for normalization. The delay time for vehicles exceeding the suggested arrival time. This refers to the actual entry and exit time. For vehicles Suggested arrival and departure times. , , Set optimization preferences for adjustable coefficients;

[0047] S44, All The rating values ​​constitute a two-dimensional scheduling utility matrix. The vehicle-crane position binding relationship is calculated based on the maximum weight matching strategy, and a queuing scheduling table with priority labels is generated:

[0048] ;

[0049] in, This is a scheduling table, containing the scheduling relationship between each vehicle and its assigned crane position. For the first The dispatched vehicle number, The crane position number it is associated with. For vehicles Suggested arrival and departure times. The corresponding scheduling utility value, ,Depend on The quantile value is determined in the overall distribution. The number of successfully matched vehicle-crane pairs.

[0050] The beneficial effects of this invention are:

[0051] First, by constructing a standardized shipping dataset and introducing real-time sensing information from IoT terminals, this invention achieves comprehensive perception and data fusion of key elements such as vehicles, drivers, loading hooks, delivery plans, and port traffic. This breaks through the limitations of information silos and data fragmentation in traditional shipping management, providing an accurate, complete, and dynamic data foundation for the scheduling system and effectively improving the port's ability to visualize and control vehicle status and operational processes.

[0052] Secondly, the improved dynamic cycle time rearrangement algorithm and the pre-loading capacity perspective algorithm proposed in this invention work together to construct a multi-constraint scheduling optimization model with "vehicle priority - crane capacity matching - time coordination" as the core. This model can not only calculate the vehicle entry order in real time based on vehicle pickup demand, port load status and loading efficiency, but also dynamically identify and allocate the optimal crane resources to ensure that high-priority vehicles can complete loading operations quickly, which significantly improves the utilization rate of loading cycle time and the accuracy of scheduling response.

[0053] Finally, this invention constructs a closed-loop scheduling feedback and waybill binding mechanism throughout the entire process. Through vehicle electronic fence identification, loading execution status feedback, and task data archiving, it achieves closed-loop control of the entire process from schedule generation, task binding, execution monitoring to feedback optimization. The system possesses self-learning capabilities, continuously optimizing algorithm parameters based on historical operational data. This effectively reduces shipping bottlenecks caused by human intervention, resource misallocation, and operational delays, thereby comprehensively improving the intelligence level and operational safety of port area shipping management. Attached Figure Description

[0054] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0055] Figure 1 This is a flowchart of a port area intelligent shipping management method based on the Internet of Things proposed in this invention. Detailed Implementation

[0056] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, illustrating only the basic structure of the invention, and therefore only show the components relevant to the invention.

[0057] refer to Figure 1 A port area intelligent shipping management method based on the Internet of Things includes the following steps:

[0058] S1. Collect IoT terminal data in the port area and preprocess it to construct a standardized shipping dataset.

[0059] S2. Based on the standardized shipping dataset, an improved dynamic beat reordering algorithm is used to dynamically sort all vehicles and generate vehicle queue sequences and suggested entry and exit times.

[0060] S3. Based on the standardized shipping dataset, construct a loading capacity model for each crane position in the port area within a unit of time, and score it using an improved pre-loading capacity perspective algorithm to output an efficiency score table for each crane position.

[0061] S4. Cross-match the vehicle queuing sequence with the efficiency score table to form a multi-constraint matching matrix, and bind high-loading capacity cranes with high-priority vehicles through a dynamic weight allocation mechanism to generate a queuing scheduling table with priority labels.

[0062] S5. Based on the queuing schedule and the suggested arrival and departure times, generate corresponding electronic waybills for all vehicles and embed the license plate number, driver's ID number and assigned crane position number. Verify the identity of the electronic waybill and bind it to the dispatch task.

[0063] S6. When a vehicle enters or leaves the port area's electronic fence, the vehicle's location is identified and compared with the electronic waybill information. If the match is successful, a release signal is triggered, and a loading instruction is pushed to the corresponding crane terminal.

[0064] S7. During the vehicle's dispatch mission, continuously collect IoT terminal data within the port area, update and record feedback in real time, form a closed-loop self-learning scheduling mechanism, and complete the archiving of dispatch data throughout the entire process.

[0065] This invention introduces IoT terminal data collection and standardized processing to build a dynamically perceived shipping data foundation. Combined with an improved dynamic rhythm reordering algorithm and a pre-loading capacity perspective algorithm, it achieves efficient matching of vehicle priority ranking and crane space resources, generating a queuing and scheduling scheme with time-series and execution capabilities. This significantly improves vehicle traffic efficiency and loading resource utilization. Through an electronic waybill and identity information binding mechanism, it ensures precise matching of personnel and vehicle tasks during the shipping process, effectively reducing the risk of human intervention and operational errors. The system possesses real-time feedback and self-learning capabilities during scheduling execution, continuously optimizing scheduling strategies. Ultimately, it achieves intelligent, automated, and closed-loop control of port shipping management, resulting in more precise scheduling, more efficient operations, and safer operation.

[0066] In this embodiment, the IoT terminal data includes real-time vehicle location, license plate number information, driver identity, crane allocation status, vehicle cargo delivery plan, current port area traffic load and historical loading records. The preprocessing includes data cleaning and format unification.

[0067] This invention clarifies that the types of data collected cover key dimensions such as real-time vehicle location, license plate number, driver identity, crane status, port traffic flow, and historical loading information. The preprocessing process includes data cleaning and format unification operations, ensuring the accuracy and real-time nature of the data.

[0068] In this embodiment, S2 specifically includes:

[0069] S21. Based on the standardized shipping dataset, extract the estimated arrival time for each vehicle to be dispatched. Delivery plan quantity Last loading time Distance from current location to port area And the current average loading time in the port area and real-time port area traffic load factor The data is used as sorting input features;

[0070] S22. Construct a dynamic beat reordering optimization objective function, and use an improved dynamic beat reordering algorithm to calculate the vehicle priority index:

[0071] ;

[0072] in, For vehicles The scheduling priority index; a higher value indicates a higher scheduling priority. For vehicles The planned delivery quantity, in tons. For vehicles The remaining distance to the port area, in kilometers. For vehicles The estimated arrival time at the port area, in minutes. For vehicles The last loading completion time, in minutes. This represents the average loading time per vehicle in the current port area, expressed in minutes per vehicle. The current port area traffic load coefficient is a dimensionless number reflecting traffic and operational pressure. , , The weighted averages of the pickup volume factor, distance factor, and waiting time factor are respectively, satisfying the following conditions: , , To avoid introducing small positive quantities when the denominator is zero;

[0073] S23, Priority index of all vehicles Sort the vehicles in descending order to obtain the vehicle queue sequence. ,in At the same time , , and Using the parameters, calculate the suggested arrival and departure times for each vehicle:

[0074] ;

[0075] in, For vehicles Suggested arrival and departure times. For vehicles Current actual speed, in kilometers per minute. This is an empirical adjustment factor used to balance cycle time and port congestion levels;

[0076] S24, Output vehicle queuing sequence Collection of recommended arrival and departure times .

[0077] This invention introduces an improved dynamic rhythm reordering algorithm to achieve dynamic sorting of vehicles to be dispatched and intelligent calculation of suggested entry and exit times. Compared with the traditional first-come, first-served (FCFS) based sorting logic, this invention comprehensively considers multiple factors such as vehicle priority, cargo volume, location distance, and port flow, and can accurately predict the most reasonable entry time and loading sequence, significantly reducing queuing congestion and improving vehicle turnover efficiency and the continuity of operation rhythm.

[0078] In this embodiment, S3 specifically includes:

[0079] S31. Based on the standardized shipping dataset, extract crane position-related data, which includes each crane position... Historical assignment rounds Total load per round Corresponding task duration Number of vehicles currently waiting Number of abnormal events per unit time and equipment availability coefficient within the current work cycle. ;

[0080] S32. Construct a port area loading capacity model and define each crane position. Theoretical loading capacity per unit time:

[0081] ;

[0082] in, For the position of crane Loading capacity per unit time, expressed in tons per minute. For the first Loading capacity for this operation For the first The actual completion time for this assignment. For historical operation rounds;

[0083] S33. Based on the loading capacity model, an improved pre-loading capacity perspective algorithm is used to correct the real-time efficiency of each crane position, forming a multi-dimensional comprehensive scoring function and outputting an efficiency score value:

[0084] ;

[0085] in, For the position of crane The loading efficiency score, The equipment availability factor has a range of values. This represents the current operating status of the crane positioning equipment. This represents the number of abnormal events within the current period. This represents the current number of waiting vehicles. , , These are the availability enhancement factor, the anomaly penalty factor, and the queuing penalty factor, respectively, all of which are positive constants.

[0086] S34. Output the set of loading efficiency scores for all crane positions. .

[0087] Based on real-time and historical data from the port area, this invention constructs a loading capacity model for each crane berth and employs an improved pre-loading capacity perspective algorithm for dynamic scoring. This algorithm integrates indicators such as loading rate, equipment availability, abnormal operation records, and current waiting pressure, outputting a score table reflecting the true operational efficiency of the crane berth. This effectively solves the problems of incomplete understanding and uneven allocation of loading resources in traditional scheduling, promoting the transformation of crane berth resource utilization from "average allocation" to precise matching driven by "capacity."

[0088] In this embodiment, S4 specifically includes:

[0089] S41, Based on vehicle queuing sequence Vehicle priority index Delivery plan quantity Loading efficiency rating set for cranes Construct standardized vehicle vectors and crane position vector :

[0090] ;

[0091] in, Indicates vehicle The remaining distance to the port area To prevent division by zero for small positive numbers, For the position of crane The loading efficiency score, For the position of crane Historical average load per trip This represents the number of vehicles currently waiting to operate at this crane position. The maximum number of vehicles picked up in the current batch is used as the normalization benchmark. It is a function for maximizing the value;

[0092] S42. Combining the nonlinear suppression function, weighted cosine similarity is used to calculate vehicle similarity. With Crane Position Overall compatibility:

[0093] ;

[0094] in, For vehicles With Crane Position Overall compatibility score , The vehicles and cranes are respectively the first Feature values ​​in each dimension As feature weighting factors, satisfying , To avoid tiny values ​​of division by zero, As a loading quantity deviation suppression factor, it controls the sensitivity of the difference between the vehicle and the historical capacity of the crane position;

[0095] S43. To improve overall resource utilization efficiency and fairness, a dynamic weight allocation mechanism is introduced and a scheduling priority function is constructed:

[0096] ;

[0097] in, This represents the current port area traffic load factor, a dimensionless number reflecting traffic and operational pressure. For vehicles Assigned to crane position The scheduling utility value, For the position of crane The equipment availability factor, The current port area traffic load coefficient is a dimensionless number reflecting traffic and operational pressure. This represents the maximum delay time in the current batch, used for normalization. The delay time for vehicles exceeding the suggested arrival time. This refers to the actual entry and exit time. For vehicles Suggested arrival and departure times. , , Set optimization preferences for adjustable coefficients;

[0098] S44, All The rating values ​​constitute a two-dimensional scheduling utility matrix. The vehicle-crane position binding relationship is calculated based on the maximum weight matching strategy, and a queuing scheduling table with priority labels is generated:

[0099] ;

[0100] in, This is a scheduling table, containing the scheduling relationship between each vehicle and its assigned crane position. For the first The dispatched vehicle number, The crane position number it is associated with. For vehicles Suggested arrival and departure times. The corresponding scheduling utility value, ,Depend on The quantile value is determined in the overall distribution. The number of successfully matched vehicle-crane pairs.

[0101] This invention constructs a multi-constraint scheduling matrix by cross-matching vehicle queuing sequences with crane position efficiency scores and introduces a dynamic weight allocation mechanism. This enables the system to achieve optimal binding logic between "high-capacity crane positions" and "high-priority vehicles." This mechanism supports real-time adjustment of allocation strategies based on actual operational conditions, effectively improving overall scheduling flexibility and task responsiveness, significantly reducing vehicle waiting time and resource idle rate, and enhancing the overall operational efficiency of loading operations in the port area.

[0102] Example 1:

[0103] To verify the feasibility of this invention in practice, it was applied to a crude oil shipping operation scenario at a large coastal port. This port primarily handles crude oil transshipment, with over 200 crude oil loading vehicles daily. The port has one import / export channel system, two weighbridge systems, and four loading arms. Due to concentrated customers, high-frequency shipments, and dense vehicle arrivals, this port has long faced challenges in traditional shipping management, including difficulties in scheduling loading resources, vehicle queues and congestion, information asymmetry, and heavy workloads for manual dispatching. Especially during peak hours when traffic surges, long vehicle waiting times, high loading arm vacancy rates, and delayed information exchange frequently occur, severely impacting operational efficiency and safety.

[0104] In implementing this invention, a unified IoT access platform was first deployed, integrating existing port data acquisition devices such as license plate recognition systems, driver identification terminals, vehicle GPS positioning systems, weighbridge sensors, and loading control units, standardizing data acquisition frequency and format. The system automatically collects and preprocesses information such as real-time vehicle location, license plate number, driver identification information, planned tonnage for pickup, crane operation status, current port flow load, and historical loading efficiency, constructing a standardized shipping dataset. The data processing cycle is within 15 seconds, ensuring high timeliness and accuracy of the basic data for scheduling calculations.

[0105] In the dispatching process, the system first invokes an improved dynamic takt time rescheduling algorithm to calculate vehicle dispatching priorities based on multiple parameters, including vehicle pickup plans, arrival time predictions, previous operation times, and the current port load factor, generating executable queuing and suggested entry / exit times. Subsequently, an improved pre-loading capacity perspective algorithm is invoked to construct a unit-time loading capacity scoring model based on the loading speed, number of operation interruptions, equipment utilization rate, and the number of vehicles currently waiting to be loaded for each crane position over the past 24 hours. The system cross-matches vehicle priority indices with the crane position scoring table to construct a multi-constraint dispatching scoring matrix. A dynamic weight adjustment mechanism is then used to comprehensively derive the dispatching utility score, achieving optimal vehicle-crane binding and outputting a queuing dispatching table with priority labels.

[0106] After receiving the dispatch notification via a mobile app, the driver enters the port area within the suggested time frame. The identification system at the port's entrance and exit channels automatically recognizes the license plate and waybill information, verifies the driver's identity, and matches the electronic waybill. If the information matches correctly, the system automatically triggers the gate to release the vehicle and sends loading instructions to the corresponding crane terminal. Throughout the entire process, the system collects real-time data on each vehicle's entry time, waiting time, operation duration, and actual loading, and feeds the results back to the dispatch module in real time for automatic correction and continuous learning of dispatch parameters and algorithm models.

[0107] Taking the implementation data of a port area from March 10th to March 17th, 2025, as an example, the system dispatched a total of 1580 oil trucks, averaging 225 trucks per day. The following is a "Comparison Table of the Implementation Effectiveness of the Intelligent Shipping Management System," showing the actual improvement in key dispatching indicators of the port area before and after the system's implementation:

[0108] Table 1 Comparison of the Implementation Results of the Intelligent Shipping Management System

[0109] ;

[0110] Before the system went live, the average waiting time per vehicle was approximately 48 minutes, and the loading arm utilization rate was 71.3%. After the system went live, the average waiting time per vehicle was reduced to 18 minutes, and the loading arm utilization rate increased to 89.6%. Simultaneously, the average error between the system's calculated suggested arrival time and the actual arrival time of vehicles was less than 3 minutes, with an overall scheduling accuracy rate of 99.2%. During this period, the system automatically handled over 130 complex scenarios, including secondary loading and priority vehicles cutting in line, successfully completing task binding, dynamic loading arm adjustment, and execution without any scheduling conflicts or failures. During system operation, the number of scheduling personnel was reduced from 3 per shift to 1, significantly reducing the intensity of manual scheduling and personnel costs.

[0111] The results of implementation show that the application of this invention in port area dispatch management effectively solves problems such as long vehicle waiting times, uneven resource allocation, low dispatch efficiency, and lack of information loop in the traditional dispatch model. It realizes intelligent dispatch, precise loading, system linkage, and transparent management, and significantly improves the automation and operational efficiency of port area shipping management while ensuring safe production.

[0112] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A port area intelligent shipping management method based on the Internet of Things, characterized in that, Includes the following steps: S1. Collect IoT terminal data in the port area and preprocess it to construct a standardized shipping dataset. S2. Based on the standardized shipping dataset, an improved dynamic beat reordering algorithm is used to dynamically sort all vehicles and generate vehicle queue sequences and suggested entry and exit times. S3. Based on the standardized shipping dataset, construct a loading capacity model for each crane position in the port area within a unit of time, and score it using an improved pre-loading capacity perspective algorithm to output an efficiency score table for each crane position. S4. Cross-match the vehicle queuing sequence with the efficiency score table to form a multi-constraint matching matrix, and bind high-loading capacity cranes with high-priority vehicles through a dynamic weight allocation mechanism to generate a queuing scheduling table with priority labels. S5. Based on the queuing schedule and the suggested arrival and departure times, generate corresponding electronic waybills for all vehicles and embed the license plate number, driver's ID number and assigned crane position number. Verify the identity of the electronic waybill and bind it to the dispatch task. S6. When a vehicle enters or leaves the port area's electronic fence, the vehicle's location is identified and compared with the electronic waybill information. If the match is successful, a release signal is triggered, and a loading instruction is pushed to the corresponding crane terminal. S7. During the vehicle's dispatch mission, continuously collect IoT terminal data within the port area, update and record feedback in real time, and complete the archiving of dispatch data throughout the entire process.

2. The port area intelligent shipping management method based on the Internet of Things according to claim 1, characterized in that, The IoT terminal data includes real-time vehicle location, license plate number information, driver identity, crane allocation status, vehicle cargo delivery plan, current port area traffic load and historical loading records. The preprocessing includes data cleaning and format unification.

3. The port area intelligent shipping management method based on the Internet of Things according to claim 1, characterized in that, S2 specifically includes: S21. Based on the standardized shipping dataset, extract the estimated arrival time for each vehicle to be dispatched. Delivery plan quantity Last loading time Distance from current location to port area And the current average loading time in the port area and real-time port area traffic load factor The data is used as sorting input features; S22. Construct a dynamic beat reordering optimization objective function, and use an improved dynamic beat reordering algorithm to calculate the vehicle priority index: ； in, For vehicles The scheduling priority index; a higher value indicates a higher scheduling priority. For vehicles The planned delivery quantity, in tons. For vehicles The remaining distance to the port area, in kilometers. For vehicles The estimated arrival time at the port area, in minutes. For vehicles The last loading completion time, in minutes. This represents the average loading time per vehicle in the current port area, expressed in minutes per vehicle. The current port area traffic load coefficient is a dimensionless number reflecting traffic and operational pressure. , , The weighted averages of the pickup volume factor, distance factor, and waiting time factor are respectively, satisfying the following conditions: , , To avoid introducing small positive quantities when the denominator is zero; S23, Priority index of all vehicles Sort the vehicles in descending order to obtain the vehicle queue sequence. ,in At the same time , , and Using the parameters, calculate the suggested arrival and departure times for each vehicle: ； in, For vehicles Suggested arrival and departure times. For vehicles Current actual speed, in kilometers per minute. This is an empirical adjustment factor used to balance cycle time and port congestion levels; S24, Output vehicle queuing sequence Collection of recommended arrival and departure times .

4. The port area intelligent shipping management method based on the Internet of Things according to claim 1, characterized in that, S3 specifically includes: S31. Based on the standardized shipping dataset, extract crane position-related data, which includes each crane position... Historical assignment rounds Total load per round Corresponding task duration Number of vehicles currently waiting Number of abnormal events per unit time and equipment availability coefficient within the current work cycle. ; S32. Construct a port area loading capacity model and define each crane position. Theoretical loading capacity per unit time: ； in, For the position of crane Loading capacity per unit time, expressed in tons per minute. For the first Loading capacity for this operation For the first The actual completion time for this assignment. For historical operation rounds; S33. Based on the loading capacity model, an improved pre-loading capacity perspective algorithm is used to correct the real-time efficiency of each crane position, forming a multi-dimensional comprehensive scoring function and outputting an efficiency score value: ； in, For the position of crane The loading efficiency score, The equipment availability factor has a range of values. This represents the current operating status of the crane positioning equipment. This represents the number of abnormal events within the current period. This represents the current number of waiting vehicles. , , These are the availability enhancement factor, the anomaly penalty factor, and the queuing penalty factor, respectively, all of which are positive constants. S34. Output the set of loading efficiency scores for all crane positions. .

5. The port area intelligent shipping management method based on the Internet of Things according to claim 1, characterized in that, S4 specifically includes: S41, Based on vehicle queuing sequence Vehicle priority index Delivery plan quantity Loading efficiency rating set for cranes Construct standardized vehicle vectors and crane position vector : ； in, Indicates vehicle The remaining distance to the port area To prevent division by zero for small positive numbers, For the position of crane The loading efficiency score, For the position of crane Historical average load per trip This represents the number of vehicles currently waiting to operate at this crane position. The maximum number of vehicles picked up in the current batch is used as the normalization benchmark. It is a function for maximizing the value; S42. Combining the nonlinear suppression function, weighted cosine similarity is used to calculate vehicle similarity. With Crane Position Overall compatibility: ； in, For vehicles With Crane Position Overall compatibility score , The vehicles and cranes are respectively the first Feature values ​​in each dimension As feature weighting factors, satisfying , To avoid tiny values ​​of division by zero, As a loading quantity deviation suppression factor, it controls the sensitivity of the difference between the vehicle and the historical capacity of the crane position; S43. To improve overall resource utilization efficiency and fairness, a dynamic weight allocation mechanism is introduced and a scheduling priority function is constructed: ； in, This represents the current port area traffic load factor, a dimensionless number reflecting traffic and operational pressure. For vehicles Assigned to crane position The scheduling utility value, For the position of crane The equipment availability factor, The current port area traffic load coefficient is a dimensionless number reflecting traffic and operational pressure. This represents the maximum delay time in the current batch, used for normalization. The delay time for vehicles exceeding the suggested arrival time. This refers to the actual entry and exit time. For vehicles Suggested arrival and departure times. , , Set optimization preferences for adjustable coefficients; S44, All The rating values ​​constitute a two-dimensional scheduling utility matrix. The vehicle-crane position binding relationship is calculated based on the maximum weight matching strategy, and a queuing scheduling table with priority labels is generated: ； in, This is a scheduling table, containing the scheduling relationship between each vehicle and its assigned crane position. For the first The dispatched vehicle number, The crane position number it is associated with. For vehicles Suggested arrival and departure times. The corresponding scheduling utility value, ,Depend on The quantile value is determined in the overall distribution. The number of successfully matched vehicle-crane pairs.

Images