Method and system for optimizing cargo loading and unloading efficiency in public-water combined transportation process

Abstract

The invention discloses a cargo loading and unloading efficiency optimization method and system in a public-water combined transportation process, relates to the technical field of logistics management, and discloses the cargo loading and unloading efficiency optimization method and system in the public-water combined transportation process, by integrating real-time operation information of a truck and state data of wharf loading and unloading equipment, an optimal distribution plan is generated; road transportation dynamic information and wharf loading and unloading capacity data can be deeply integrated, the problem of resource matching imbalance is solved, and the overall operation efficiency of a public-water combined transportation hub is improved.

Description

Technical Field

[0001] This application relates to the field of logistics management technology, and in particular to methods and systems for optimizing cargo loading and unloading efficiency in multimodal transport processes involving both road and water. Background Technology

[0002] As a key link in the modern logistics system, road-water intermodal transport effectively optimizes the transportation structure and reduces social logistics costs by integrating the flexibility of road transport with the economy of waterway transport. However, in actual operation, when goods are transferred between road and waterway at ports or inland river terminals, a bottleneck in coordination efficiency is encountered. Specifically, arriving trucks often queue for extended periods outside the terminal gates or operating areas due to the inability to obtain real-time information on the availability of loading and unloading equipment, resulting in idle vehicles, excessive fuel consumption, and increased carbon emissions. Simultaneously, high-value loading and unloading equipment such as quay cranes and gantry cranes at the terminal frequently experience alternating periods of idleness and overcrowding due to uneven truck arrival times or poor information transmission, leading to low equipment utilization and the terminal's overall throughput capacity failing to reach design levels. Existing technical solutions have significant limitations, primarily focusing on the independent scheduling and optimization of loading and unloading equipment within the terminal or the separate planning of road transport routes, failing to consider the real-time operational status of trucks in transit and the availability of terminal loading and unloading equipment as a unified whole for coordinated management. The aforementioned fragmented processing approach results in the system lacking the ability to integrate multi-source data such as truck location, traffic congestion, and equipment status in real time. This makes it impossible to achieve accurate arrival time prediction and delay risk assessment, and consequently, it is difficult to generate a collaborative scheduling scheme that balances minimizing resource waiting time with maximizing operational efficiency.

[0003] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of this application is to provide a method and system for optimizing cargo loading and unloading efficiency in the road-water intermodal transport process, aiming to improve the overall operational efficiency of road-water intermodal transport hubs.

[0005] To achieve the above objectives, this application proposes a method for optimizing cargo loading and unloading efficiency in road-water intermodal transport, the method comprising: Acquire real-time truck operation information data and real-time status data of terminal loading and unloading equipment, and process the real-time truck operation information data to generate predicted arrival time data and delay risk level data; The real-time status data of the dock loading and unloading equipment is processed to generate a list of future workable time intervals. Based on the predicted arrival time data and the list of future workable time intervals, a preliminary cargo loading and unloading task allocation plan is generated. The preliminary cargo loading and unloading task allocation plan data is adjusted based on the delay risk level data to generate the final optimized cargo loading and unloading task allocation plan data. Based on the final optimized cargo loading and unloading task allocation plan data, truck dispatching instruction data and loading and unloading equipment operation instruction data are generated and issued.

[0006] In one embodiment, the real-time truck operation information data includes current location data reported by the vehicle terminal and traffic congestion data of the planned route obtained from the traffic information platform; the delay risk level data includes high delay risk indicator data and low delay risk indicator data. The steps for processing the real-time truck operation information data to generate predicted arrival time data and delay risk level data include: Based on the current location data and the traffic congestion data, combined with the electronic map route information, the basic estimated arrival time data is calculated. The estimated arrival time data is compared with the dynamic threshold of predicted deviation to obtain the predicted deviation data; if the estimated deviation data exceeds the dynamic threshold of predicted deviation, the high delay risk indicator data is generated by combining the vehicle's historical delay record data; otherwise, the low delay risk indicator data is generated. When the high delay risk indicator data is generated, a correction calculation process is initiated. Time correction data is generated based on the real-time truck operation information data, and the time correction data is added to the basic estimated arrival time data to generate the predicted arrival time data. When the low delay risk indicator data is generated, the basic estimated arrival time data is directly used as the predicted arrival time data.

[0007] In one embodiment, the method further includes: Retrieve a sample dataset of actual truck travel times on the same road segment within the same historical period from the historical database; Calculate the mean and standard deviation of the actual truck travel time sample dataset, and calculate the basic fluctuation range data based on the mean and standard deviation; Acquire real-time weather warning data and data on the number of vehicles queuing at the port gates; Based on the warning level of the real-time weather warning data and the difference between the number of vehicles queuing at the dock gate and the preset benchmark value, the basic fluctuation range data is expanded accordingly to generate the dynamic threshold of the prediction deviation.

[0008] In one embodiment, when the high delay risk indicator data is generated, the correction calculation process is initiated, and the step of generating time correction data based on the real-time truck operation information data includes: When the high delay risk indicator data is generated, the correction calculation process is initiated to collect the terminal operation load data for the current time period; The real-time truck operation information data is integrated with the terminal operation load data to construct the feature vector data to be corrected. The feature vector data to be corrected is input into a pre-trained time prediction correction model to output the time correction amount data.

[0009] In one embodiment, the step of generating preliminary cargo loading and unloading task allocation plan data by matching the predicted arrival time data with the list of future workable time intervals includes: Based on the cargo type matching rules, a sub-list of candidate loading and unloading equipment time intervals that can perform the current cargo loading and unloading task is selected from the future workable time interval data list. According to the order of the predicted arrival time data, each target truck is matched with the corresponding candidate loading and unloading equipment time interval sublist in turn, and each truck is assigned a target workable time interval data that meets its operation time requirements and has the earliest start time. Record the data of all trucks and their corresponding target workable time intervals and the corresponding loading and unloading equipment to form the preliminary cargo loading and unloading task allocation plan data.

[0010] In one embodiment, when no matching data for the target workable time interval that meets the conditions can be found for the current truck, the method further includes: From the tasks that have been assigned the target workable time interval data, determine the task pair data with the closest work duration from the task pairs that are interchangeable with the equipment; Exchange the equipment allocation schemes of the two tasks in the task pair to be exchanged, so as to release the target workable time interval data available for the current truck; All task allocation schemes after equipment exchange are checked for conflicts to ensure that there are no new time conflicts or equipment usage conflicts.

[0011] In one embodiment, the step of adjusting the preliminary cargo loading and unloading task allocation plan data based on the delay risk level data to generate the final optimized cargo loading and unloading task allocation plan data includes: Based on the delay risk level data, identify all core task items to be protected that are associated with high delay risk indicator data from the preliminary cargo loading and unloading task allocation plan data; For each core task item data to be protected, insert protection buffer time data before its assigned scheduled job start time; Check whether the time data inserted into the protection buffer conflicts with the preceding task on the same loading / unloading equipment; if there is a conflict, compress the time data in the protection buffer or adjust the time interval of the preceding task. All conflict-free task data are aggregated to generate the final optimized cargo loading and unloading task allocation plan data.

[0012] In one embodiment, before adjusting the preliminary cargo loading and unloading task allocation plan data based on the delay risk level data to generate the final optimized cargo loading and unloading task allocation plan data, the method further includes: Obtain downstream urgency assessment data related to the cargo currently awaiting loading and unloading at the terminal; Based on the downstream urgency assessment data, the relevant task items in the preliminary cargo loading and unloading task allocation plan data are distinguished to obtain data on high downstream urgency task items and ordinary task items. The data of the urgent tasks in the upstream and downstream sectors are marked as core task data to be protected.

[0013] In one embodiment, the step of generating truck dispatch instruction data based on the final optimized cargo loading and unloading task allocation plan data includes: Based on the final optimized cargo loading and unloading task allocation plan data, extract the planned arrival time data of the target trucks and the location data of the target loading and unloading equipment; By combining real-time electronic map data of the terminal area with traffic flow data within the terminal, the optimal on-site route data from the terminal entrance to the location of the target loading and unloading equipment is planned for the target truck. Based on the planned arrival time data and the current time, the suggested driving speed sequence data of the truck on each segment of the optimal on-site route data is calculated by reverse calculation. The optimal on-site route data and the suggested driving speed sequence data are encapsulated to generate the truck dispatch instruction data.

[0014] Furthermore, to achieve the above objectives, this application also proposes a cargo loading and unloading efficiency optimization system in the road-water intermodal transport process. The cargo loading and unloading efficiency optimization system in the road-water intermodal transport process includes: a memory, a processor, and a cargo loading and unloading efficiency optimization program in the road-water intermodal transport process stored in the memory and executable on the processor. The cargo loading and unloading efficiency optimization program in the road-water intermodal transport process is configured to implement the steps of the cargo loading and unloading efficiency optimization method in the road-water intermodal transport process.

[0015] The method and system for optimizing the loading and unloading efficiency of road-water intermodal transport proposed in this application generate an optimized allocation plan by integrating real-time truck operation information and terminal loading and unloading equipment status data. This deeply integrates dynamic information on road transport with terminal loading and unloading capacity data, solves the problem of resource matching imbalance, and improves the overall operational efficiency of road-water intermodal transport hubs. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating an embodiment of the method for optimizing cargo loading and unloading efficiency in the multimodal transport process of this application. Figure 2 This is a schematic diagram of a system for optimizing cargo loading and unloading efficiency in the combined road and water transport process according to this application.

[0019] Explanation of icon numbers: 10. Memory; 20. Processor.

[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] The technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of this application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0022] It should be understood that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0023] In existing technologies, multimodal transport between road and water generally suffers from low overall coordination efficiency during cargo loading and unloading operations. Specifically, arriving trucks often queue for extended periods due to the inability to match available loading and unloading equipment windows in real time, resulting in idle transport resources and increased fuel consumption. Simultaneously, loading and unloading equipment frequently experiences uneven workloads due to uneven truck arrivals or poor information coordination, leading to underutilization of the terminal's overall throughput capacity. Current technological solutions lack a systematic approach that treats dynamically en route road transport and terminal loading and unloading capacity as an organic whole for real-time, precise, and coordinated scheduling.

[0024] Based on this, this application provides a method for optimizing cargo loading and unloading efficiency in a road-water intermodal transport process, referring to... Figure 1 The method for optimizing cargo loading and unloading efficiency in the combined road and water transport process includes steps S100 to S500, wherein: Step S100: Obtain real-time truck operation information data and real-time status data of dock loading and unloading equipment, and process the real-time truck operation information data to generate predicted arrival time data and delay risk level data. Step S200: Process the real-time status data of the dock loading and unloading equipment to generate a list of future workable time intervals; Step S300: Based on the predicted arrival time data and the list of future workable time intervals, a preliminary cargo loading and unloading task allocation plan data is generated by matching the data. Step S400: Adjust the preliminary cargo loading and unloading task allocation plan data according to the delay risk level data to generate the final optimized cargo loading and unloading task allocation plan data. Step S500: Based on the final optimized cargo loading and unloading task allocation plan data, generate and issue truck dispatching instruction data and loading and unloading equipment operation instruction data.

[0025] In this embodiment, real-time truck operation information data refers to a collection of dynamic information reflecting the current location, speed, and direction of travel of trucks en route. This data is typically collected in real time via onboard terminals or GPS devices and uploaded to a central processing system to assess the current operating status of the trucks. Real-time status data of terminal loading and unloading equipment refers to a collection of information regarding the current working status, availability, workload, and maintenance plans of equipment used for cargo loading and unloading within the terminal (such as quay cranes, gantry cranes, and forklifts). This data is typically updated in real time by the terminal operation management system, reflecting the actual operational capacity of the equipment. Predicted arrival time data refers to the result of predicting the estimated arrival time of trucks at the terminal based on real-time truck operation information data, combined with factors such as road conditions and traffic flow. This data provides a time benchmark for subsequent task allocation. Delay risk level data refers to indicators assessing the likelihood and severity of delays during truck arrival at the terminal. This data can be used to identify potential delay risks and provide a basis for scheduling adjustments.

[0026] In this embodiment, the future available work time interval data list refers to the set of idle time periods during which terminal loading and unloading equipment can be used to perform cargo loading and unloading tasks within a certain period of time in the future. This list reflects the available operational capacity of the terminal loading and unloading equipment. The preliminary cargo loading and unloading task allocation plan data is an initial operation allocation scheme between trucks and loading and unloading equipment formed after preliminary matching of the predicted arrival time data of trucks with the future available work time interval data list of terminal loading and unloading equipment. This plan aims to achieve basic resource matching. The final optimized cargo loading and unloading task allocation plan data refers to the final cargo loading and unloading operation allocation scheme formed after adjustments and optimizations based on the preliminary cargo loading and unloading task allocation plan data, combined with factors such as delay risk level data. This plan aims to improve overall operational efficiency and the ability to respond to emergencies. The truck dispatch instruction data is an instruction issued to the truck driver or onboard system based on the final optimized cargo loading and unloading task allocation plan data, guiding the truck's driving route, arrival time, stopping location, and other information within the terminal. Loading and unloading equipment operation instruction data refers to the instructions issued to terminal loading and unloading equipment operators or automated control systems based on the final optimized cargo loading and unloading task allocation plan data, which guide the loading and unloading equipment to perform specific cargo loading and unloading tasks, including information such as operation time, operation content, and target truck.

[0027] In this embodiment, the method for optimizing cargo loading and unloading efficiency during road-water intermodal transport first acquires real-time truck operation information data and real-time status data of terminal loading and unloading equipment. Real-time truck operation information data can be obtained by periodically sending location coordinates, speed, and other information via GPS devices installed on the trucks, or by manually reporting the truck's current location and estimated arrival time via telephone or SMS. Real-time status data of terminal loading and unloading equipment can be obtained by terminal management personnel manually entering the equipment's current operating status (e.g., idle, in operation, malfunction), or by monitoring whether the equipment is running using simple sensors.

[0028] In this embodiment, after acquiring the aforementioned data, the real-time truck operation information data is processed to generate predicted arrival time data and delay risk level data. For example, the estimated arrival time at the terminal can be easily calculated based on the truck's current location and average speed, serving as the predicted arrival time data. The delay risk level data can be based on human experience; for instance, when a truck reports that its location is far from the terminal but its estimated arrival time is approaching, it is manually marked as having a high delay risk.

[0029] In this embodiment, the real-time status data of the terminal loading and unloading equipment is then processed to generate a list of future available work time intervals. For example, the terminal management system can easily calculate the available idle time intervals for each loading and unloading equipment in the future based on the current working status of the equipment and the scheduled work plans, and summarize them into a list. Subsequently, the predicted arrival time data and the list of future available work time intervals are matched to generate preliminary cargo loading and unloading task allocation plan data. Specifically, each truck can be simply matched with the time interval of the first available loading and unloading equipment according to the order of the predicted arrival times of the trucks, as long as the time interval can meet the truck's working time requirements. Thus, a preliminary allocation scheme is formed.

[0030] Furthermore, the initial cargo loading and unloading task allocation plan data is adjusted based on the delay risk level data to generate the final optimized cargo loading and unloading task allocation plan data. For example, for trucks marked as having a high delay risk, a fixed buffer time can be reserved before their original operating time to cope with potential delays. If reserving the buffer time causes a conflict with subsequent tasks, the subsequent tasks can simply be postponed as a whole.

[0031] In this embodiment, truck dispatch instructions and loading / unloading equipment operation instructions are generated and issued based on the final optimized cargo loading / unloading task allocation plan data. Truck dispatch instructions can be a simple text message informing the truck driver of their planned arrival time and the target loading / unloading equipment number. Loading / unloading equipment operation instructions can be a printed work order containing the operation start time, operation details, and corresponding truck information, which is manually executed by the equipment operator.

[0032] In this embodiment, by acquiring truck operation information and the status of terminal loading and unloading equipment in real time, and performing prediction and matching, the problems of long truck queuing times and low utilization rates of loading and unloading equipment in traditional road-water intermodal transport can be effectively solved. This method realizes the coordinated scheduling of road transport and terminal operations, reduces resource idleness and fuel consumption, improves the overall throughput capacity of the terminal, and thus optimizes cargo loading and unloading efficiency.

[0033] In one feasible implementation, the real-time truck operation information data includes current location data reported by the onboard terminal and traffic congestion data of the planned route obtained from the traffic information platform; the delay risk level data includes high delay risk indicator data and low delay risk indicator data; the step of processing the real-time truck operation information data to generate predicted arrival time data and delay risk level data includes: calculating basic estimated arrival time data based on the current location data and the traffic congestion data, combined with electronic map route information; and comparing the basic estimated arrival time data with a dynamic threshold for prediction deviation. The estimated deviation data is obtained by comparison. If the estimated deviation data exceeds the dynamic threshold of the predicted deviation, the high delay risk indicator data is generated by combining the vehicle's historical delay record data; otherwise, the low delay risk indicator data is generated. When the high delay risk indicator data is generated, the correction calculation process is started, and the time correction amount data is generated based on the truck's real-time operation information data. The time correction amount data is then added to the basic estimated arrival time data to generate the predicted arrival time data. When the low delay risk indicator data is generated, the basic estimated arrival time data is directly used as the predicted arrival time data.

[0034] In this embodiment, the current location data reported by the onboard terminal in the real-time truck operation information data is typically obtained in real time through the Global Positioning System (GPS), BeiDou Navigation Satellite System, or other satellite positioning technologies to acquire the truck's geographic coordinate information, including longitude, latitude, altitude, speed, and direction. This data is reported to the central processing system at a preset frequency, ensuring the real-time nature and accuracy of the location information. The traffic congestion data for the planned route obtained from the traffic information platform can be acquired from the data interface of a third-party traffic data service provider or a government traffic management department. This data typically includes real-time vehicle speeds, congestion indices, and event information (such as accidents and construction) for specific road sections, reflecting the impact of current road conditions on vehicle travel time. The high delay risk indicator data in the delay risk level data indicates a high probability of truck delays, requiring more refined prediction and scheduling adjustments from the system; while the low delay risk indicator data indicates that the truck is expected to arrive on time or nearly on time, with highly reliable predicted arrival times.

[0035] In this embodiment, the steps of processing the real-time truck operation information data to generate predicted arrival time data and delay risk level data include: First, calculating basic estimated arrival time data based on the current location data and traffic congestion data, combined with electronic map route information. During this process, the system uses electronic map route information to determine the optimal or preset route to the dock based on the truck's current location data. Subsequently, the system dynamically evaluates the travel time of each road segment along the route, combining real-time acquired traffic congestion data. For example, for congested road segments, the travel time is extended based on real-time vehicle speed or congestion index. Finally, the estimated travel times of all road segments are summed, and the remaining travel time from the truck's current location to the dock entrance is added to obtain a preliminary, unadjusted basic estimated arrival time data.

[0036] In this embodiment, the basic estimated arrival time data is then compared with a dynamic threshold for predicted deviation to obtain predicted deviation data. This dynamic threshold is not fixed but dynamically adjusted based on various factors (such as weather conditions, historical traffic patterns, and port operation load). For example, the threshold may be appropriately relaxed during severe weather or peak hours to accommodate greater uncertainty. The predicted deviation data refers to the difference between the currently calculated basic estimated arrival time and the truck's original planned arrival time (or a certain baseline time). If the predicted deviation data exceeds the dynamic threshold, high-delay-risk flag data is generated by combining historical vehicle delay records; otherwise, low-delay-risk flag data is generated. The historical vehicle delay records include information such as the comparison of the actual arrival time and planned arrival time of a specific truck or similar truck over a past period, delay duration, and reasons for delay. When the predicted deviation exceeds the dynamic threshold, the system queries the truck's historical delay records. If the truck has a history of frequent delays or long delays, it is further confirmed as having high-delay-risk.

[0037] In this embodiment, when the high-delay-risk flag data is generated, a correction calculation process is initiated. Time correction data is generated based on the truck's real-time operation information data, and this time correction data is added to the basic estimated arrival time data to generate the predicted arrival time data. When a truck is marked as having high delay risk, the system initiates a more complex prediction model or algorithm. This model comprehensively considers more real-time operation information data (e.g., the truck's average speed change trend, stopping time, driver behavior patterns, etc.) and may combine machine learning models for prediction. The time correction data is the output of the correction calculation process; it is a positive value (indicating further delay is expected) or a negative value (indicating earlier arrival is expected), used to adjust the basic estimated arrival time data to make it closer to the actual situation. When the low-delay-risk flag data is generated, the basic estimated arrival time data is directly used as the predicted arrival time data. For trucks marked as having low delay risk, their basic estimated arrival time data is considered sufficiently accurate, requiring no additional complex corrections, thus simplifying the calculation process and improving system response efficiency.

[0038] In this embodiment, by introducing current location data reported by the vehicle terminal and traffic congestion data obtained from the traffic information platform, combined with electronic map route information, the basic estimated arrival time data of trucks can be calculated in real time and accurately. Furthermore, by comparing this basic estimated arrival time data with a dynamically adjusted prediction deviation threshold and combining it with historical vehicle delay records, this application can intelligently identify trucks with high delay risk and initiate a targeted correction calculation process to generate more accurate time correction data, thereby obtaining highly reliable predicted arrival time data. For trucks with low delay risk, the basic estimated arrival time data is directly used, avoiding unnecessary computational overhead. This hierarchical and dynamic prediction and risk assessment mechanism improves the accuracy and reliability of predicted arrival time data and delay risk level data, providing a solid data foundation for the subsequent formulation of preliminary cargo loading and unloading task allocation plans. It effectively avoids planning conflicts and resource waste caused by inaccurate predictions, thereby improving the overall efficiency and scheduling flexibility of cargo loading and unloading in the entire road-water intermodal transport process.

[0039] In one feasible implementation, the method further includes: retrieving a sample dataset of actual truck travel times for the same road segment within the same historical period from a historical database; calculating the mean and standard deviation of the sample dataset of actual truck travel times, and calculating basic fluctuation range data based on the mean and standard deviation; acquiring real-time weather warning data and data on the number of vehicles queuing at the dock gate; and performing corresponding expansion processing on the basic fluctuation range data according to the warning level of the real-time weather warning data and the difference between the number of vehicles queuing at the dock gate and a preset benchmark value, to generate the dynamic threshold for prediction deviation.

[0040] In this embodiment, to accurately assess the risk of truck delays, a reliable benchmark must first be established. To this end, the system retrieves a sample dataset of actual truck travel times on the same road segment within the same historical period from a historical database. This historical database can store records of actual truck travel times on specific road segments on specific dates and time periods over the past few months or even years. By limiting the scope to "within the same historical period" and "the same road segment," it ensures that the retrieved data reflects typical traffic conditions on that road segment under similar external conditions (such as seasons, weekdays / weekends, peak / off-peak hours), thereby eliminating interference from periodic changes and making the sample data more representative.

[0041] In this embodiment, after obtaining the sample dataset of actual truck travel times, the system performs statistical analysis on it, calculating the mean and standard deviation of the sample dataset. The mean reflects the typical travel time of the road segment within the same historical period, while the standard deviation quantifies the degree of fluctuation in travel time. Based on the mean and standard deviation, basic fluctuation range data can be calculated. For example, this basic fluctuation range data can be defined as the mean plus or minus a certain multiple of the standard deviation (such as one or two standard deviations), thereby representing the reasonable range of possible fluctuations in truck travel time under normal circumstances. This basic fluctuation range data provides an initial, historically experience-based reference for subsequent dynamic adjustment of the prediction deviation threshold.

[0042] In this embodiment, to adapt the prediction deviation threshold to real-time changes in the external environment, this application further acquires real-time weather warning data and data on the number of vehicles queuing at the terminal gate. Real-time weather warning data can originate from warning information issued by meteorological departments, such as warnings for heavy fog, heavy rain, and snow. These severe weather conditions typically reduce road capacity, thus affecting the actual arrival time of trucks. Data on the number of vehicles queuing at the terminal gate reflects the real-time congestion at the terminal entrance; the larger the queue, the longer it takes for trucks to enter the terminal. These real-time data are important external factors affecting truck arrival time, but they may not always be explicit features in historical data, or their influence may vary depending on the real-time situation.

[0043] In this embodiment, the basic fluctuation range data is expanded based on the difference between the warning level of the real-time weather warning data and the number of vehicles queuing at the dock gate exceeding a preset benchmark value, thereby generating the dynamic threshold for prediction deviation. For example, when the weather warning level is high (such as issuing an orange rainstorm warning), or when the number of vehicles queuing at the dock gate exceeds a preset normal benchmark value, the system will consider that the current environment has a greater impact on truck transit time, and therefore the basic fluctuation range data needs to be appropriately expanded. This expansion can be achieved by multiplying by a dynamic adjustment coefficient or adding a dynamic adjustment amount. In this way, the dynamic threshold for prediction deviation can adaptively adjust according to changes in the real-time external environment, making it closer to the actual situation.

[0044] In this embodiment, through the above technical solution, this application can comprehensively consider historical traffic patterns and real-time external environmental factors to dynamically generate a dynamic threshold for predicted deviation. This makes the assessment of delay risk level data more accurate and robust. When adverse external conditions (such as severe weather or port congestion) lead to widespread delays, the dynamic threshold will be relaxed accordingly to avoid misjudging widespread delays as high-risk, thereby reducing unnecessary task adjustments and resource waste. Conversely, when the external environment is favorable, the threshold remains tight to ensure sensitivity to abnormal delays and timely identification and handling of genuine delay risks. This dynamic adjustment mechanism improves the accuracy and reliability of delay risk assessment, provides a more solid foundation for subsequent adjustments to the initial cargo loading and unloading task allocation plan data, and ultimately optimizes the cargo loading and unloading efficiency in the road-water intermodal transport process.

[0045] In one feasible implementation, when the high delay risk indicator data is generated, the correction calculation process is initiated. The step of generating time correction data based on the real-time truck operation information data includes: when the high delay risk indicator data is generated, the correction calculation process is initiated, and the terminal operation load data for the current time period is collected; the real-time truck operation information data and the terminal operation load data are integrated to construct feature vector data to be corrected; the feature vector data to be corrected is input into a pre-trained time prediction correction model to output the time correction data.

[0046] In this embodiment, collecting terminal operation load data for the current time period refers to obtaining information on the busyness and utilization rate of various loading and unloading equipment, storage yards, gates, and other resources within the terminal during a specific time period. This data reflects the current operational pressure and potential bottlenecks at the terminal. For example, if the terminal's operational load is high, even if trucks arrive on time, waiting times may increase due to resource constraints within the terminal, resulting in actual delays. This data can be collected in various ways, such as obtaining real-time equipment status, berth occupancy, storage yard utilization, and the number of vehicles queuing at gates from the Terminal Operations Management System (TOS), or through real-time monitoring and statistics using sensors, video surveillance, and other means. This data provides important environmental context information for subsequent time adjustments.

[0047] In this embodiment, the real-time truck operation information data and the terminal operation load data are integrated to construct the feature vector data to be corrected. Integrating the real-time truck operation information data and the terminal operation load data aims to converge the internal and external factors affecting truck arrival time correction into a unified, structured input form, namely, the feature vector data to be corrected. The real-time truck operation information data may include the truck's current location, speed, historical driving trajectory, estimated remaining mileage, traffic congestion status, etc. The terminal operation load data includes the resource utilization status within the terminal. Constructing the feature vector involves standardizing, normalizing, or encoding these heterogeneous data to form a multi-dimensional numerical sequence. For example, the feature vector may include the truck's current latitude and longitude, current speed, traffic congestion index, number of vehicles queuing at the terminal gate, average waiting time for loading and unloading equipment, etc. This integration provides comprehensive and rich information for the subsequent time prediction correction model, enabling it to capture the complex relationships between different factors.

[0048] Further, the feature vector data to be corrected is input into a pre-trained time prediction correction model to output the time correction amount. The pre-trained time prediction correction model is an artificial intelligence model that has been learned and optimized using a large amount of historical data. Its goal is to accurately predict the deviation of the actual arrival time of trucks from the basic estimated arrival time data, i.e., the time correction amount, based on the input feature vector data to be corrected. Before being put into use, the model is trained using historical truck operation data, port operation data, and actual delay data. During training, the model learns how to identify key patterns and rules leading to delays from various features. For example, when a truck encounters congestion on a specific road segment and there are many vehicles queuing at the port gate, the model can learn that a large positive time correction amount needs to be applied. This model can be based on machine learning algorithms, such as Support Vector Machine (SVM), Random Forest, Gradient Boosting Tree (GBDT), or deep learning algorithms, such as Recurrent Neural Network (RNN), Long Short-Term Memory Network (LSTM), etc. Through pre-training, the model has the ability to intelligently judge and correct complex delay situations, thereby outputting accurate time correction amount data.

[0049] In this embodiment, by employing the aforementioned technical solution, when identifying high-delay-risk indicator data and initiating the correction calculation process, this application no longer relies solely on the truck's own operational information data but further collects terminal operation load data for the current time period. The real-time truck operational information data is integrated with the terminal operation load data to construct a feature vector data to be corrected, which is then input into a pre-trained time prediction correction model. This model can comprehensively consider various complex factors such as external traffic conditions and internal terminal operation pressure, thereby more accurately predicting the deviation between the actual arrival time of the truck and the basic estimated arrival time data, i.e., the time correction amount data. This correction mechanism improves the accuracy of the predicted arrival time data, avoiding the problem of additional delays caused by changes in the terminal's internal operation load not being identified and corrected in a timely manner. Ultimately, by outputting more accurate time correction amount data, the final generated predicted arrival time data becomes more reliable, providing a solid foundation for subsequent preliminary cargo loading and unloading task allocation plan data, thereby effectively reducing truck waiting time at the terminal, improving the utilization rate of loading and unloading equipment, and optimizing the overall cargo loading and unloading efficiency in the road-water intermodal transport process.

[0050] In one feasible implementation, the step of generating preliminary cargo loading and unloading task allocation plan data by matching the predicted arrival time data and the list of future workable time intervals includes: selecting a candidate loading and unloading equipment time interval sub-list that can perform the current cargo loading and unloading task from the list of future workable time intervals according to cargo type matching rules; matching each target truck with the corresponding candidate loading and unloading equipment time interval sub-list in the order of the predicted arrival time data, and assigning each truck a target workable time interval data that meets its operation time requirements and has the earliest start time; recording the correspondence between all trucks and their corresponding target workable time interval data and their respective loading and unloading equipment to form the preliminary cargo loading and unloading task allocation plan data.

[0051] In this embodiment, the cargo type matching rule defines the compatibility relationship between different types of cargo and terminal loading and unloading equipment. For example, some loading and unloading equipment may be dedicated to handling containers, while others are suitable for bulk cargo or general cargo. This rule can be pre-configured in the system, for example, in the form of a database table, rule engine, or configuration file, to quickly determine whether a specific cargo can be loaded and unloaded by a specific loading and unloading equipment during task allocation. The purpose is to ensure that the allocated loading and unloading equipment can meet the specific operational requirements of the cargo to be loaded and unloaded, avoiding operational delays or errors due to equipment incompatibility.

[0052] In this embodiment, when filtering the candidate loading and unloading equipment time interval sub-list that can perform the current cargo loading and unloading task, the system first identifies all loading and unloading equipment capable of handling the cargo type carried by the truck about to perform the loading and unloading operation, based on a preset cargo type matching rule. Then, from the future operational time interval data list of all loading and unloading equipment at the terminal, it filters out available time intervals only related to these compatible loading and unloading equipment, forming a dedicated candidate list for the current truck and cargo type. This filtering process ensures the effectiveness and feasibility of subsequent matching, avoiding the assignment of tasks to equipment lacking the corresponding processing capabilities.

[0053] In this embodiment, during the matching process, the system sorts all trucks awaiting task assignment based on their predicted arrival time data, typically processing them in chronological order from earliest to latest. This sorting strategy aims to prioritize trucks that are about to arrive or are expected to arrive early, minimizing truck waiting time at the terminal and improving terminal turnover efficiency. Following this order, the system sequentially matches each target truck with its corresponding candidate loading / unloading equipment time interval sub-list, searching for suitable loading / unloading equipment and time intervals for each target truck. For each truck, the system iterates through its corresponding candidate loading / unloading equipment time interval sub-list, attempting to assign it an idle time slot that meets its operational needs.

[0054] In this embodiment, when assigning target workable time interval data to each truck, the system selects an available time interval from its candidate loading / unloading equipment time interval sub-list that can fully cover the required operation time for loading and unloading cargo for that truck. Provided the operation time requirements are met, the system prioritizes the time interval with the earliest start time. This selection strategy aims to allow trucks to start operations as early as possible, thereby shortening their dwell time at the terminal and optimizing the utilization rate of loading / unloading equipment. Once a target workable time interval data and its associated loading / unloading equipment are successfully assigned to a truck, the system records this assignment result. These records include the truck identifier, the assigned loading / unloading equipment identifier, and the specific start and end times of the operation. The aggregation of all trucks and their corresponding target workable time interval data and associated loading / unloading equipment forms the preliminary cargo loading / unloading task allocation plan data, providing a foundation for subsequent plan adjustments and instruction issuance.

[0055] In this embodiment, through the above-described technical solution, this application provides a refined and systematic matching mechanism, effectively solving the problem of how to efficiently and accurately match loading and unloading tasks of different cargo types with limited loading and unloading equipment resources when generating preliminary cargo loading and unloading task allocation plan data. Specifically, by introducing cargo type matching rules, the compatibility between loading and unloading tasks and equipment is ensured, avoiding operational interruptions or inefficiencies caused by equipment mismatch. Simultaneously, truck tasks are allocated according to the order of predicted arrival time data, prioritizing the earliest available workable time interval, shortening truck waiting times, and improving the turnaround efficiency of terminal loading and unloading equipment and overall operational smoothness. This matching strategy not only optimizes resource allocation but also provides a more reasonable and reliable preliminary planning basis for subsequent delay risk adjustments, thereby improving the overall cargo loading and unloading efficiency in the road-water intermodal transport process.

[0056] In one feasible implementation, when the current truck cannot find target workable time interval data that meets the conditions, the method further includes: determining the task pair data with the longest operation time from the tasks that have been allocated the target workable time interval data, among the task pairs with interchangeable equipment; exchanging the equipment allocation schemes of the two tasks in the task pair to be exchanged, so as to release the target workable time interval data available for the current truck; and performing conflict verification on all task allocation schemes after the equipment exchange to ensure that there are no new time conflicts or equipment usage conflicts.

[0057] In this embodiment, when a truck cannot find matching target workable time interval data that meets the conditions, the system identifies the task pair with the closest work duration from among the tasks already assigned the target workable time interval data, specifically those with interchangeable equipment. This step aims to identify tasks in the initial cargo loading and unloading task allocation plan data that have been assigned target workable time interval data but whose loading and unloading equipment can be interchanged with that of another task. Specifically, the system iterates through the assigned tasks, identifying tasks with the same or compatible cargo types that can be performed by multiple loading and unloading equipment. Among these interchangeable tasks, the system further filters out task pairs whose work duration is closest to the required work duration of the currently unmatched truck. For example, if the current truck requires 30 minutes of work time, the system will prioritize task pairs with work durations of 25-35 minutes from the assigned tasks to minimize resource waste or time fragmentation caused by the exchange.

[0058] In this embodiment, the equipment allocation schemes of the two tasks in the task pair to be exchanged are then swapped to release the target workable time interval data available to the current truck. This step involves adjusting the actual equipment allocation scheme of the identified task pair data to be exchanged. Specifically, the first task in the task pair to be exchanged may be transferred from its original allocation device A to device B (which was originally allocated to the second task in the task pair to be exchanged), while the second task is transferred from device B to device A. Through this swapping of equipment allocation schemes, one device (e.g., device A) is released for a certain period of time, thereby forming a new target workable time interval data available to the current truck. This exchange strategy aims to solve the truck matching problem by optimizing the existing resource configuration without increasing the additional equipment load.

[0059] In this embodiment, based on this, conflict verification is performed on all task allocation schemes after equipment exchange to ensure that there are no new time conflicts or equipment usage conflicts. This step ensures the effectiveness and feasibility of the equipment allocation scheme adjustment. After exchanging the equipment allocation schemes for the task pairs to be exchanged, the system needs to perform a comprehensive check on all updated task allocation schemes. Time conflict refers to the same loading / unloading equipment being assigned two or more tasks within the same time period. Equipment usage conflict refers to assigning a task to loading / unloading equipment that does not have the corresponding operational capabilities, such as assigning a task requiring a heavy crane to a light forklift. Conflict verification can be completed by traversing the timeline of all loading / unloading equipment, checking for overlapping task time periods, and verifying the compatibility of each task with its assigned equipment. If a conflict is found, it may be necessary to backtrack or try other task pairs to be exchanged until a conflict-free solution is found.

[0060] In this embodiment, through the above-described technical solution, when a truck cannot be matched with a suitable loading / unloading time interval, this application no longer simply rejects or delays the truck, but actively seeks optimization space from the existing task allocation. By intelligently identifying data on task pairs to be exchanged that are interchangeable with equipment and have similar operation durations, and exchanging equipment allocation schemes, it can effectively release available target workable time interval data for the current truck. This dynamic adjustment mechanism avoids the overall efficiency decline caused by local resource shortages, and improves the utilization rate and scheduling flexibility of terminal loading / unloading resources. At the same time, strict conflict verification ensures that the adjusted task allocation plan is still valid and executable, avoiding the generation of new time conflicts or equipment usage conflicts, thereby ensuring the smooth operation of cargo loading / unloading operations in the road-water intermodal transport process, improving the overall loading / unloading efficiency and the ability to cope with emergencies.

[0061] In one feasible implementation, the step of adjusting the preliminary cargo loading and unloading task allocation plan data based on the delay risk level data to generate the final optimized cargo loading and unloading task allocation plan data includes: identifying all core task items to be protected that are associated with high delay risk indicator data from the preliminary cargo loading and unloading task allocation plan data based on the delay risk level data; inserting a protection buffer time data before the allocated planned operation start time for each core task item to be protected; checking whether the inserted protection buffer time data conflicts with the preceding task on the same loading and unloading equipment; if there is a conflict, compressing the protection buffer time data or adjusting the time interval of the preceding task; and summarizing all task item data without conflicts to generate the final optimized cargo loading and unloading task allocation plan data.

[0062] In this embodiment, delay risk level data is used to indicate the degree of delay a truck may face before arriving at the terminal for loading and unloading operations. This data is typically generated after acquiring and processing real-time truck operation information and may include high delay risk indicator data and low delay risk indicator data to distinguish different levels of delay probability. The preliminary cargo loading and unloading task allocation plan data is an initial task allocation scheme formed by matching the predicted arrival time data of trucks with the future operational time interval data list of terminal loading and unloading equipment. It details when each truck should operate and by which loading and unloading equipment. High delay risk indicator data is a specific identifier within the delay risk level data, clearly indicating that a particular truck or its associated loading and unloading task has a high probability of delay. The generation of this indicator is typically based on a comprehensive assessment of multiple factors such as the truck's current location, traffic congestion, and historical delay records. The core task item data to be protected refers to those loading and unloading tasks associated with the high delay risk indicator data in the preliminary cargo loading and unloading task allocation plan data. These tasks are at high risk of delay due to the trucks they involve, and delays could have a significant impact on the overall workflow. Therefore, additional protective measures are needed to mitigate the risk.

[0063] In this embodiment, the protection buffer time data refers to an extra period of time reserved before the planned start time of the core task data to be protected. Its purpose is to absorb or buffer minor delays that may occur due to high-delay-risk trucks, preventing these delays from directly affecting the normal operation of subsequent tasks. The size of the protection buffer time data can be dynamically determined based on factors such as delay risk level, historical delay statistics, and task importance. The planned start time is the preset start time point for each loading and unloading task in the preliminary cargo loading and unloading task allocation plan data. Preceding tasks on the same loading and unloading equipment refer to the loading and unloading tasks assigned on a certain loading and unloading equipment before the core task data to be protected. When inserting protection buffer time data, it is necessary to check whether the buffer overlaps with the time intervals of these preceding tasks, thus causing a conflict. In this context, a conflict refers to a situation where the inserted protection buffer time data overlaps with the operation time interval of a preceding task on the same loading and unloading equipment, causing the equipment to be unable to operate continuously as planned. When the inserted protection buffer time data conflicts with a preceding task, compressing the protection buffer time data means shortening its duration to eliminate or reduce overlap with the preceding task, thereby resolving the conflict. Compression should be performed while ensuring sufficient buffer capacity. When the inserted buffer time data conflicts with a preceding task, adjusting the time interval of the preceding task involves fine-tuning its planned end or start time to prevent overlap with the buffer time data. This adjustment typically requires an assessment of its impact on the preceding task itself and its associated trucks. Conflict-free task data refers to a state where, after buffer insertion, conflict checking, compression, or adjustment, all task items (including original tasks and those with inserted buffers) have eliminated time or equipment usage conflicts. The final optimized cargo loading / unloading task allocation plan data is the final, more robust task allocation scheme formed based on the initial cargo loading / unloading task allocation plan data, after considering delay risks and making corresponding adjustments (such as inserting buffers and resolving conflicts).

[0064] In this embodiment, by inserting protective buffer time data before the planned start time of core task items to be protected, which are associated with high-delay-risk indicator data, in the initial cargo loading and unloading task allocation plan data, and by checking and handling potential conflicts, this application can effectively address potential truck delays. This mechanism allows terminal loading and unloading equipment to absorb even minor delays caused by high-risk trucks through the reserved buffer time, avoiding a chain reaction of delays and ensuring the smooth progress of subsequent tasks. Through intelligent conflict handling, such as compressing the protective buffer or adjusting the time of preceding tasks, the rationality and feasibility of the plan are ensured, avoiding resource waste and operational interruptions. The resulting optimized plan data improves the overall robustness and efficiency of cargo loading and unloading operations in the road-water intermodal transport process, reduces operational risks caused by uncertainties, and ensures the continuity and stability of terminal operations.

[0065] In one feasible implementation, before adjusting the preliminary cargo loading and unloading task allocation plan data based on the delay risk level data to generate the final optimized cargo loading and unloading task allocation plan data, the method further includes: acquiring downstream urgency assessment data associated with the cargo to be loaded and unloaded at the current terminal; distinguishing relevant task items in the preliminary cargo loading and unloading task allocation plan data based on the downstream urgency assessment data to obtain high downstream urgency task item data and ordinary task item data; and marking the high downstream urgency task item data as core task item data to be protected.

[0066] In this embodiment, the downstream urgency assessment data is used to quantify the urgency of subsequent transportation, transshipment, or processing of goods after the completion of terminal operations. This data can be obtained from the shipper's order system, shipping schedules from downstream shipping companies, train schedules from railway companies, or delivery times agreed upon with the final consignee, through system interfaces or manual input. For example, goods that need to catch specific shipping or train schedules will show a higher priority in the downstream urgency assessment data; for perishable goods or urgent orders, the downstream urgency assessment data will also be correspondingly increased.

[0067] In this embodiment, the relevant task items in the preliminary cargo loading and unloading task allocation plan data are then distinguished based on the downstream urgency assessment data to obtain data on high downstream urgency task items and ordinary task items. Specifically, one or more thresholds can be set. For example, if the downstream shipping schedule or train journey of the cargo is about to depart within a preset time, or if the cargo is marked as "urgent," then the loading and unloading task item corresponding to that cargo will be identified as high downstream urgency task item data. This distinction process can be automatically completed based on preset business rules, priority matrices, or classification criteria derived from analyzing historical data through machine learning models.

[0068] In this embodiment, the data of highly downstream urgent tasks are marked as core task data to be protected. This marking operation aims to elevate these tasks, which have a critical impact on downstream processes, to the same protection level as tasks with high delay risk. By adding a specific identifier to the task data structure or including it in a dedicated core task list, it is ensured that these tasks can be prioritized in subsequent planning adjustment phases, such as by allocating protective buffer time data to them, thereby reducing the risk of delays during terminal loading and unloading.

[0069] In this embodiment, through the above-described technical solution, this application, while considering the delay risk of the trucks themselves, further incorporates consideration of the urgency of the downstream goods. This enables the system to identify and prioritize the protection of loading and unloading tasks that have a critical impact on the entire supply chain, even if the trucks corresponding to these tasks do not have a high delay risk. For example, for goods that are about to catch a ship, even if the trucks arrive on time, the system will mark them as core tasks to be protected and reserve a protection buffer for them in the plan, thereby effectively avoiding delays caused by internal terminal scheduling or temporary equipment failures, and ensuring that the goods can be transferred on time. This dual protection mechanism, which considers both the delay risk of upstream and the urgency of downstream, ensures that the final optimized cargo loading and unloading task allocation plan data can not only cope with the uncertainty of truck arrivals, but also effectively guarantee the smooth flow of critical goods, reducing the risk of overall supply chain disruption and economic losses caused by delays in the terminal process, thereby comprehensively improving the overall efficiency and reliability of the road-water intermodal transport process.

[0070] In one feasible implementation, the step of generating truck dispatch instruction data based on the final optimized cargo loading and unloading task allocation plan data includes: extracting the planned arrival time data of the target truck and the location data of the target loading and unloading equipment based on the final optimized cargo loading and unloading task allocation plan data; combining the real-time electronic map data of the terminal area and the traffic flow data within the terminal area to plan the optimal on-site path data for the target truck from the terminal entrance to the location data of the target loading and unloading equipment; calculating the suggested driving speed sequence data of the truck on each segment of the optimal on-site path data based on the planned arrival time data and the current time; and encapsulating the optimal on-site path data and the suggested driving speed sequence data to generate the truck dispatch instruction data.

[0071] In this embodiment, when generating truck dispatch instruction data, it is first necessary to accurately obtain the planned arrival time data of each target truck and its corresponding target loading / unloading equipment location data from the optimized cargo loading / unloading task allocation plan data. This data is the basis for subsequent on-site path planning and speed control, ensuring the synchronization of dispatch instructions with the overall optimization plan. Subsequently, in order to guide trucks to move efficiently within the terminal, the system combines real-time electronic map data of the terminal area with on-site traffic flow data to plan the optimal on-site path data for the target trucks from the terminal entrance to their target loading / unloading equipment location data. Among them, the real-time electronic map data of the terminal area provides geographical information such as roads, areas, and obstacles within the terminal, and can be updated in real time to reflect the dynamic changes in the layout of the area; the on-site traffic flow data contains information such as the real-time location, speed, and density of vehicles within the terminal, which is used to assess the congestion status of each road segment. By comprehensively utilizing this real-time information, the system can employ path planning algorithms (e.g., algorithms based on shortest time, shortest distance, or avoiding congested areas) to calculate the most efficient driving route for trucks under current conditions, thus avoiding delays caused by improper route selection within the depot.

[0072] Building upon this foundation, to ensure trucks arrive at the target loading / unloading equipment precisely according to the planned arrival time data, the system uses the extracted planned arrival time data and the current real-time time to reverse-calculate the suggested driving speed sequence data for each segment of the optimal on-site route data. This means the system not only plans "which route to take" but also precisely guides "how fast to take." For example, if the truck needs to arrive in a short time, the system may suggest a higher speed on certain sections (within safety and regulatory limits); if there is ample time, it may suggest a more consistent speed to save energy or improve safety. This reverse-calculation dynamically adjusts the truck's driving rhythm, ensuring a highly consistent arrival time with the plan even in complex on-site environments.

[0073] In this embodiment, the planned optimal on-site route data and the calculated suggested driving speed sequence data are finally encapsulated to form complete truck dispatch instruction data. This instruction data can be sent to the truck's onboard terminal or the driver's mobile device, providing the driver with clear and executable navigation and speed guidance, thereby achieving refined management of truck movement within the terminal.

[0074] In this embodiment, through the above-described technical solution, this application can refine the macro-level loading and unloading task allocation plan into micro-level truck yard dispatch instructions. By accurately extracting plan information, combining real-time yard data to plan the optimal route, and calculating the suggested driving speed, the efficiency and punctuality of truck movement within the terminal are ensured. This not only avoids delays caused by improper route selection or congestion, but also allows trucks to precisely control their driving rhythm, ensuring they arrive at the designated loading and unloading equipment on time, avoiding delays caused by arriving too early or too late. Therefore, this solution effectively guarantees the smooth execution of the final optimized cargo loading and unloading task allocation plan data, improves the overall coordination and efficiency of loading and unloading operations, and further optimizes the cargo loading and unloading efficiency in the road-water intermodal transport process.

[0075] In the embodiments of this application, the method for optimizing the loading and unloading efficiency of road-water intermodal cargo generates an optimized allocation plan by integrating real-time truck operation information and terminal loading and unloading equipment status data. This method can deeply integrate dynamic information on road transportation with terminal loading and unloading capacity data, solve the problem of resource matching imbalance, and improve the overall operational efficiency of road-water intermodal transport hubs.

[0076] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the method for optimizing the loading and unloading efficiency of multimodal transport cargo in this application. Any simple modifications based on this technical concept are within the scope of protection of this application.

[0077] This application also provides a cargo loading and unloading efficiency optimization system in the road-water intermodal transport process, for reference. Figure 2 The cargo loading and unloading efficiency optimization system in the road-water intermodal transport process includes: a memory 10, a processor 20, and a cargo loading and unloading efficiency optimization program in the road-water intermodal transport process stored on the memory 10 and executable on the processor 20. The cargo loading and unloading efficiency optimization program in the road-water intermodal transport process is configured to implement the steps of the cargo loading and unloading efficiency optimization method in the road-water intermodal transport process.

[0078] The cargo loading and unloading efficiency optimization system for road-water intermodal transport provided in this application adopts the cargo loading and unloading efficiency optimization method for road-water intermodal transport in the above embodiments, which can improve the overall operational efficiency of road-water intermodal transport hubs. Compared with the prior art, the beneficial effects of the cargo loading and unloading efficiency optimization system for road-water intermodal transport provided in this application are the same as the beneficial effects of the cargo loading and unloading efficiency optimization method for road-water intermodal transport provided in the above embodiments, and other technical features of the cargo loading and unloading efficiency optimization system for road-water intermodal transport are the same as the features disclosed in the methods of the above embodiments, and will not be repeated here.

[0079] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0080] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. All equivalent structural transformations made under the technical concept of this application using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included within the scope of patent protection of this application.

Claims

1. A method for optimizing cargo loading and unloading efficiency in a road-water intermodal transport process, characterized in that, The method includes: Acquire real-time truck operation information data and real-time status data of terminal loading and unloading equipment, and process the real-time truck operation information data to generate predicted arrival time data and delay risk level data; The real-time status data of the dock loading and unloading equipment is processed to generate a list of future workable time intervals. Based on the predicted arrival time data and the list of future workable time intervals, a preliminary cargo loading and unloading task allocation plan is generated. The preliminary cargo loading and unloading task allocation plan data is adjusted based on the delay risk level data to generate the final optimized cargo loading and unloading task allocation plan data. Based on the final optimized cargo loading and unloading task allocation plan data, truck dispatching instruction data and loading and unloading equipment operation instruction data are generated and issued.

2. The method for optimizing cargo loading and unloading efficiency in the multimodal transport process as described in claim 1, characterized in that, The real-time truck operation information data includes the current location data reported by the on-board terminal and the traffic congestion data of the planned route obtained from the traffic information platform; the delay risk level data includes high delay risk indicator data and low delay risk indicator data. The steps for processing the real-time truck operation information data to generate predicted arrival time data and delay risk level data include: Based on the current location data and the traffic congestion data, combined with the electronic map route information, the basic estimated arrival time data is calculated. The estimated arrival time data is compared with the dynamic threshold of predicted deviation to obtain the predicted deviation data; if the estimated deviation data exceeds the dynamic threshold of predicted deviation, the high delay risk indicator data is generated by combining the vehicle's historical delay record data; otherwise, the low delay risk indicator data is generated. When the high delay risk indicator data is generated, a correction calculation process is initiated. Time correction data is generated based on the real-time truck operation information data, and the time correction data is added to the basic estimated arrival time data to generate the predicted arrival time data. When the low delay risk indicator data is generated, the basic estimated arrival time data is directly used as the predicted arrival time data.

3. The method for optimizing cargo loading and unloading efficiency in the multimodal transport process as described in claim 2, characterized in that, The method further includes: Retrieve a sample dataset of actual truck travel times on the same road segment within the same historical period from the historical database; Calculate the mean and standard deviation of the actual truck travel time sample dataset, and calculate the basic fluctuation range data based on the mean and standard deviation; Acquire real-time weather warning data and data on the number of vehicles queuing at the port gates; Based on the warning level of the real-time weather warning data and the difference between the number of vehicles queuing at the dock gate and the preset benchmark value, the basic fluctuation range data is expanded accordingly to generate the dynamic threshold of the prediction deviation.

4. The method for optimizing cargo loading and unloading efficiency in the multimodal transport process as described in claim 2, characterized in that, When the high delay risk indicator data is generated, the correction calculation process is initiated. The steps for generating time correction data based on the real-time truck operation information data include: When the high delay risk indicator data is generated, the correction calculation process is initiated to collect the terminal operation load data for the current time period; The real-time truck operation information data is integrated with the terminal operation load data to construct the feature vector data to be corrected. The feature vector data to be corrected is input into a pre-trained time prediction correction model to output the time correction amount data.

5. The method for optimizing cargo loading and unloading efficiency in the multimodal transport process as described in claim 1, characterized in that, The steps for generating preliminary cargo loading and unloading task allocation plan data by matching the predicted arrival time data with the list of future workable time intervals include: Based on the cargo type matching rules, a sub-list of candidate loading and unloading equipment time intervals that can perform the current cargo loading and unloading task is selected from the future workable time interval data list. According to the order of the predicted arrival time data, each target truck is matched with the corresponding candidate loading and unloading equipment time interval sublist in turn, and each truck is assigned a target workable time interval data that meets its operation time requirements and has the earliest start time. Record the data of all trucks and their corresponding target workable time intervals and the corresponding loading and unloading equipment to form the preliminary cargo loading and unloading task allocation plan data.

6. The method for optimizing cargo loading and unloading efficiency in the road-water intermodal transport process as described in claim 5, characterized in that, When no matching data for the target workable time interval that meets the conditions can be found for the current truck, the method further includes: From the tasks that have been assigned the target workable time interval data, determine the task pair data with the closest work duration from the task pairs that are interchangeable with the equipment; Exchange the equipment allocation schemes of the two tasks in the task pair to be exchanged, so as to release the target workable time interval data available for the current truck; All task allocation schemes after equipment exchange are checked for conflicts to ensure that there are no new time conflicts or equipment usage conflicts.

7. The method for optimizing cargo loading and unloading efficiency in the multimodal transport process as described in claim 1, characterized in that, The steps for adjusting the preliminary cargo loading and unloading task allocation plan data based on the delay risk level data to generate the final optimized cargo loading and unloading task allocation plan data include: Based on the delay risk level data, identify all core task items to be protected that are associated with high delay risk indicator data from the preliminary cargo loading and unloading task allocation plan data; For each core task item data to be protected, insert protection buffer time data before its assigned scheduled job start time; Check whether the time data inserted into the protection buffer conflicts with the preceding task on the same loading / unloading equipment; if there is a conflict, compress the time data in the protection buffer or adjust the time interval of the preceding task. All conflict-free task data are aggregated to generate the final optimized cargo loading and unloading task allocation plan data.

8. The method for optimizing cargo loading and unloading efficiency in the multimodal transport process as described in claim 7, characterized in that, Before the step of adjusting the preliminary cargo loading and unloading task allocation plan data based on the delay risk level data to generate the final optimized cargo loading and unloading task allocation plan data, the method further includes: Obtain downstream urgency assessment data related to the cargo currently awaiting loading and unloading at the terminal; Based on the downstream urgency assessment data, the relevant task items in the preliminary cargo loading and unloading task allocation plan data are distinguished to obtain data on high downstream urgency task items and ordinary task items. The data of the urgent tasks in the upstream and downstream sectors are marked as core task data to be protected.

9. The method for optimizing cargo loading and unloading efficiency in the multimodal transport process as described in claim 1, characterized in that, The steps for generating truck dispatch instruction data based on the final optimized cargo loading and unloading task allocation plan data include: Based on the final optimized cargo loading and unloading task allocation plan data, extract the planned arrival time data of the target trucks and the location data of the target loading and unloading equipment; By combining real-time electronic map data of the terminal area with traffic flow data within the terminal, the optimal on-site route data from the terminal entrance to the location of the target loading and unloading equipment is planned for the target truck. Based on the planned arrival time data and the current time, the suggested driving speed sequence data of the truck on each segment of the optimal on-site route data is calculated by reverse calculation. The optimal on-site route data and the suggested driving speed sequence data are encapsulated to generate the truck dispatch instruction data.

10. A cargo loading and unloading efficiency optimization system in a road-water intermodal transport process, characterized in that, The cargo loading and unloading efficiency optimization system in the road-water intermodal transport process includes: a memory, a processor, and a cargo loading and unloading efficiency optimization program in the road-water intermodal transport process stored in the memory and executable on the processor. The cargo loading and unloading efficiency optimization program in the road-water intermodal transport process is configured to implement the steps of the cargo loading and unloading efficiency optimization method in the road-water intermodal transport process as described in any one of claims 1 to 9.

Images