An airport transportation path optimization and dispatch management system based on big data

Abstract

The application discloses an airport transportation path optimization and dispatching management system based on big data, and relates to the technical field of transportation path optimization.The airport transportation path optimization and dispatching management system based on big data comprises an airport luggage transportation data acquisition and preprocessing module, which is used for acquiring airport luggage transportation data in real time and preprocessing the airport luggage transportation data; a path delay evaluation and normal path screening module, which is used for constructing a passing path sequence, evaluating path operation states and outputting a normal path set; a transportation task dispatching and path selection module, which is used for analyzing the dispatching priority of candidate paths and completing the optimal allocation of the candidate paths; and a transportation execution feedback and path state updating module, which is used for quantifying the deviation degree of a path in actual execution, correcting path delay evaluation values and node parameters, and updating dispatching input.The problem that the prior art does not consider the queuing and waiting mechanism among nodes, thereby leading to transportation accumulation and deadlock, is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of transportation path optimization, in particular to an airport transportation path optimization and scheduling management system based on big data. BACKGROUND

[0002] With the continuous growth of air travel demand, large hub airports face multiple pressures such as intensive luggage transportation tasks, path resource shortage, and high scheduling timeliness requirements during peak periods. During the process of luggage from passenger check-in to loading onto the flight, it needs to go through multiple steps such as sorting, transfer, handover, etc., forming a highly complex transportation path network. In the face of higher requirements of modern aviation logistics in operation efficiency and system coordination, an intelligent management mechanism is constructed to realize efficient organization and dynamic scheduling of the luggage transportation process.

[0003] For example, the invention with publication number CN117521924A discloses a multi-condition path selection method for airport transportation. In this invention, a continuous time search algorithm based on minimum vertex covering is proposed, the base conflict obtained by the mutual exclusion lock principle is used to construct a base conflict graph, and the minimum vertex covering algorithm is used to decompose the AMR that occurs independent base conflict, and the conflict pair and heuristic value that have the greatest impact on the conflict graph are solved, breaking the symmetry of high-level search, reducing the number of high-level node splitting, improving the algorithm speed, and also minimizing the conflict.

[0004] However, the existing methods mainly consider static factors such as path length and transportation speed, ignoring the dynamic changes of queuing and waiting mechanisms between nodes and processing resources, resulting in path selection that is theoretically the shortest but may cause accumulation, delay, and even task deadlock in actual transportation. In terms of task scheduling, there is no adaptive model between the transportation task itself and the real-time state of the path, and it is impossible to implement a joint scheduling strategy based on task urgency, path load capacity, and historical scheduling conditions.

[0005] Therefore, in view of the above problems, there is an urgent need for an airport transportation path optimization and scheduling management system based on big data. SUMMARY

[0006] Technical problems solved

[0007] In view of the deficiencies of the prior art, the present application provides an airport transportation path optimization and scheduling management system based on big data, which solves the problem of transportation accumulation and deadlock caused by the queuing and waiting mechanism between nodes not considered in the prior art.

[0008] Technical scheme

[0009] In order to achieve the above object, the present application is realized by the following technical scheme: An airport transportation path optimization and scheduling management system based on big data, comprising: an airport baggage transportation data acquisition and preprocessing module, configured to collect multi-source data in an airport transportation path map, a sensor network, a baggage delivery system and a flight scheduling system in real time, extract airport baggage transportation data from the multi-source data, and preprocess the airport baggage transportation data; a path delay evaluation and normal path screening module, configured to construct a passable path sequence based on an airport baggage transportation path, evaluate the running state of each passable path in the passable path sequence based on the preprocessed airport baggage transportation data, screen out normal paths that can be passed from the passable path sequence based on the evaluation result, and output a normal path set; a transportation task scheduling and path selection module, configured to call the normal path set, screen paths that coincide with the passable paths, construct a candidate path set, analyze the scheduling priority of the candidate paths, complete the preferred allocation of the candidate paths, generate a scheduling instruction, and record a transportation task execution log; and a transportation execution feedback and path state updating module, configured to extract data in the transportation task execution log, establish a path execution feedback data set, quantify the deviation degree of the path in actual execution, adjust the runtime length evaluation value of the passable path and the processing capacity configuration of the processing point based on the quantification result, use the adjustment result as the basis for updating the path optimization and task scheduling, and construct a closed-loop scheduling mechanism.

[0010] Further, the specific steps of collecting multi-source data in an airport transportation path map, a sensor network, a baggage delivery system and a flight scheduling system in real time, and extracting airport baggage transportation data from the multi-source data are as follows: the connection relationship and number information of each transportation processing point are extracted by structurally analyzing the airport transportation path map; the real-time values of the conveyor belt speed and the current path baggage number are periodically read by synchronously accessing the sensor network; the baggage delivery time and the corresponding processing point identifier are obtained from the baggage delivery system; the flight departure time and the baggage target flight segment mapping relationship are extracted from the flight scheduling system; and the above-mentioned data from various sources are aligned in a unified timestamp format, and the airport baggage transportation data including path length, conveyor belt speed, current path baggage number, node arrival baggage number, node maximum processing baggage amount, flight departure time and baggage delivery time are extracted.

[0011] Further, the specific steps of preprocessing the airport baggage transportation data are as follows: abnormal values in the path length and the conveyor belt speed are identified by an outlier detection and correction algorithm, and data drift caused by incorrect entry is eliminated; the airport baggage transportation data is denoised by a sliding window median filtering algorithm, and data jumps caused by system jitter and sensor instantaneous repeated recording are smoothed out; the airport baggage transportation data is statistically standardized by a Z-score standardization method; and the airport baggage transportation data is uniformly adjusted in range by decimal scaling normalization, so as to realize the normalization of the airport baggage transportation data.

[0012] Furthermore, the specific steps for constructing a passageway sequence based on the airport baggage transport route and evaluating the operational status of each passageway in the passageway sequence based on preprocessed airport baggage transport data are as follows: Several physical transport processing points are set up in the airport baggage transport route. Each transport processing point is used to perform baggage sorting, transfer, and handover operations, and a node number is assigned to each transport processing point; multiple consecutive transport processing points are connected sequentially to construct a passageway sequence from the check-in entrance to the flight loading area; based on the preprocessed airport baggage transport data, the operation status of each passageway in the sequence is evaluated. The operational status of each passable path is evaluated as follows: the path length is divided by the conveyor belt speed to obtain the basic transportation time; the current number of bags and the number of bags arriving at the node are added together, and then divided by the maximum baggage capacity of the node plus a minimum term to obtain the processing load time; the basic transportation time and the processing load time are added together to obtain the total transportation and processing time; the flight departure time is subtracted from the baggage check-in time and then the natural constant is added, and the logarithm is taken. The reciprocal of this logarithm is then added to one to obtain the urgency adjustment factor; the total time is multiplied by the urgency adjustment factor to obtain the path delay evaluation value.

[0013] Furthermore, the specific steps for selecting passable normal paths from the travel path sequence based on the evaluation results and outputting a set of normal paths are as follows: The path delay evaluation value and the path delay threshold are compared in real time. If the path delay evaluation value is less than the path delay threshold, it is marked as a normal path, and all normal paths are extracted to construct a set of normal paths. If the path delay evaluation value is greater than or equal to the path delay threshold, it is marked as a congested path, and the scheduling of that path is suspended. A fixed scheduling cycle is set, and the path delay evaluation value is updated periodically based on the latest collected airport baggage transportation data. The path labels are also dynamically updated according to the updated path delay evaluation value.

[0014] Furthermore, the specific steps for constructing a candidate path set by calling the normal path set, filtering out paths that overlap between the current task's feasible paths and those in the normal path set, are as follows: For each baggage transportation task to be scheduled, count the number of times the current task has been delayed in the past cycle, and record it as the scheduling wait count; determine the starting processing point number of the current task and the loading processing point number corresponding to the target flight, and extract all feasible paths between them; call the normal path set, filter out paths that overlap between the current task's feasible paths and those in the normal path set, and construct a candidate path set.

[0015] Further, the specific steps for analyzing the scheduling priority of candidate paths are as follows: Based on real-time airport baggage transportation data and path delay assessment values, analyze the scheduling priority of candidate paths: Add one to the number of scheduling waits and divide by the path delay assessment value to obtain the path scheduling compensation term; Subtract baggage check-in time from flight departure time and add a minimum term, then take the reciprocal of this value to obtain the task urgency factor; Divide the conveyor belt speed by the path length to obtain the unit transportation efficiency factor; Multiply the path scheduling compensation term, the task urgency factor, and the unit transportation efficiency factor to obtain the scheduling adaptation assessment value.

[0016] Further, the specific steps for completing the optimal allocation of candidate paths, generating scheduling instructions, and recording the transportation task execution log are as follows: The scheduling suitability evaluation values ​​of the paths in the candidate path set are sorted from high to low, and the path with the highest scheduling suitability evaluation value is selected as the execution path for the current transportation task, thus achieving optimal path allocation; if there are multiple paths with the same scheduling suitability evaluation value in the candidate path set, based on the joint path sorting strategy that integrates Markov decision processes and queuing network models, the historical sequence of node waiting time and scheduling waiting count corresponding to the path is called to construct the sorting input state, and the current state transition probability and expected delay structure of each path are output for secondary sorting selection; if the candidate path set for the current task is empty, the task is marked as an unscheduled task, its scheduling waiting count is incremented by one, and it is retained until the next scheduling cycle to retry path selection; scheduling instructions are generated for transportation tasks with completed path allocation to drive subsequent transportation execution; and the task number, selected path number, starting and target processing point numbers, path delay evaluation value, scheduling time, and scheduling suitability evaluation value are written into the transportation task execution log.

[0017] Further, the following steps are taken to extract data from the transportation task execution log and establish a path execution feedback dataset to quantify the deviation of the path during actual execution: After the baggage transportation task is completed, the actual transportation time and the node waiting time of each transportation processing point in the path are collected to obtain the actual transportation time and the average node waiting time; data from the transportation task execution log is extracted and a path execution feedback dataset is established with the actual transportation time and the average node waiting time; based on the path execution feedback dataset, the deviation of the path from the scheduling prediction and the execution result is quantified: the actual transportation time is subtracted from the path delay assessment value, and then divided by the path delay assessment value plus a minimum term. The absolute value of this ratio is taken to obtain the scheduling deviation factor; the node waiting time, the current number of baggage on the path, and the number of baggage arriving at the node are added together to obtain the path comprehensive load term; the path comprehensive load term is divided by the maximum baggage capacity of the node plus a minimum term to obtain the load normalization factor; the scheduling deviation factor and the load normalization factor are added together to obtain the path execution deviation assessment value.

[0018] Furthermore, based on the quantification results, the runtime evaluation value of the travel path and the processing capacity configuration of the processing points are adjusted. The adjustment results are used as the basis for updating path selection and task scheduling. The specific steps of constructing a closed-loop scheduling mechanism are as follows: Real-time comparison of the path execution deviation evaluation value and the execution deviation threshold. When the path execution deviation evaluation value is greater than or equal to the execution deviation threshold, the path delay evaluation value of the path is corrected and improved in the next evaluation cycle to suppress the path from being frequently selected. When the path execution deviation evaluation value is less than the execution deviation threshold, the original path delay evaluation value of the path is maintained. When the node waiting time of a certain processing point in the path exceeds the node waiting time threshold in three consecutive scheduling cycles, the processing point is marked as an overloaded node, and the maximum baggage capacity of the node is reduced in subsequent scheduling cycles. After each scheduling cycle, the path delay evaluation value is updated based on the updated maximum baggage capacity of the node and real-time airport baggage transportation data. The updated path delay evaluation value is used as the input basis for calculating the scheduling adaptation evaluation value and path ranking in the next cycle, forming a closed-loop mechanism of scheduling-execution-feedback-update.

[0019] Beneficial effects

[0020] The present invention has the following beneficial effects:

[0021] (1) The airport transportation route optimization and scheduling management system based on big data, by constructing a route operation status evaluation mechanism, dynamically integrates route traffic efficiency and task timeliness requirements. It can not only comprehensively reflect the current route accessibility and processing capacity, but also identify the effective route range with scheduling conditions in real time under the conditions of concentrated flights and unbalanced node resources, providing a multi-factor driven route selection basis for subsequent task allocation.

[0022] (2) This airport transportation route optimization and scheduling management system based on big data introduces a scheduling adaptation evaluation model that combines scheduling waiting times, route delay evaluation values, flight departure time and baggage check-in time. It maps task urgency, route capacity and scheduling history behavior into a unified scheduling adaptation evaluation value, and sorts and selects candidate routes accordingly. This achieves bidirectional adaptation between task status and route status, thereby enhancing the ability to perceive task time limits and route load during scheduling.

[0023] (3) This airport transportation route optimization and scheduling management system based on big data establishes a feedback data link between scheduling instructions and transportation task execution logs, constructs a route execution feedback dataset, calculates the route execution deviation evaluation value to characterize the deviation between the predicted delay and the actual time, and corrects key parameters such as the route delay evaluation value and the maximum baggage capacity of the node accordingly, so as to realize the continuous updating of the route evaluation model.

[0024] (4) This airport transportation route optimization and scheduling management system based on big data forms a scheduling closed-loop mechanism with route delay evaluation as the evaluation basis, scheduling adaptation evaluation as the selection basis, and route execution deviation evaluation as the update driver. It realizes a complete data closed loop from real-time data collection, route status evaluation, task route allocation to execution result feedback. The system updates the route evaluation parameters in each scheduling cycle, thereby enhancing the dynamic adaptability and stable scheduling capability of the system for baggage transportation tasks under high load and high fluctuation scenarios. Attached Figure Description

[0025] Fig. 1 This is a structural diagram of an airport transportation route optimization and scheduling management system based on big data.

[0026] Fig. 2 A bar chart showing the path delay assessment values;

[0027] Fig. 3 Ranking graph of candidate path scheduling adaptation evaluation values. Detailed Implementation

[0028] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] Please see Figs. 1-3This invention provides a technical solution: an airport transportation route optimization and scheduling management system based on big data, comprising: an airport baggage transportation data acquisition and preprocessing module, used to collect multi-source data from airport transportation route maps, sensor networks, baggage check-in systems, and flight scheduling systems in real time, extract airport baggage transportation data from the multi-source data, and preprocess the airport baggage transportation data; and a route delay assessment and normal route screening module, used to construct a sequence of passage routes based on airport baggage transportation routes, assess the operating status of each passage route in the sequence based on the preprocessed airport baggage transportation data, and screen out passable routes from the sequence based on the assessment results. The system outputs a set of normal paths. The transportation task scheduling and path selection module calls the normal path set, filters paths overlapping with passable paths, constructs a candidate path set, analyzes the scheduling priority of candidate paths, completes the optimal allocation of candidate paths, generates scheduling instructions, and records the transportation task execution log. The transportation execution feedback and path status update module extracts data from the transportation task execution log, establishes a path execution feedback dataset, quantifies the deviation of paths during actual execution, adjusts the runtime evaluation value of the passable path and the processing capacity configuration of processing points based on the quantification results, and uses the adjustment results as the basis for updating path optimization and task scheduling, thus constructing a closed-loop scheduling mechanism.

[0030] Specifically, the process involves real-time acquisition of multi-source data from airport transportation route maps, sensor networks, baggage handling systems, and flight scheduling systems. The specific steps for extracting airport baggage transportation data from these multi-source data are as follows: The airport transportation route map is structured and analyzed to extract the connection relationships and numbering information of each transportation processing point, establishing a mapping structure between route nodes. The sensor network is simultaneously accessed to periodically read the real-time values ​​of conveyor belt speed and the current number of baggage items on the route, and these are recorded in conjunction with the route number. Baggage check-in time and corresponding processing point identifiers are obtained from the baggage handling system, and historical route segments are extracted and recorded to help determine the cumulative change in the number of baggage items arriving at nodes. Simultaneously, the mapping relationship between flight departure time and baggage target segment is extracted from the flight scheduling system, establishing a corresponding index between flight number and route endpoint node. The data from all sources are aligned according to a unified timestamp format, and airport baggage transportation data, including route length, conveyor belt speed, current number of baggage items on the route, number of baggage items arriving at nodes, maximum baggage handling capacity at nodes, flight departure time, and baggage check-in time, is extracted to form a basic dataset for subsequent route evaluation and scheduling calculations.

[0031] In this implementation plan, a multi-source data acquisition mechanism covering path structure, operational status, and task plan is constructed to achieve complete acquisition of path length, conveyor belt speed, current number of baggage on the path, number of baggage arriving at nodes, maximum baggage capacity handled by nodes, flight departure time, and baggage check-in time. This provides timely and accurate data support for the precise calculation of path delay assessment and scheduling adaptation assessment.

[0032] Specifically, the preprocessing steps for airport baggage transportation data are as follows: Outlier detection and correction algorithms are used to identify abnormal values ​​in path length and conveyor belt speed, and historical path structure information is combined to eliminate data drift caused by equipment malfunctions or manual input errors; a sliding window median filtering algorithm is used to denoise the airport baggage transportation data, smoothing jumps in path length, conveyor belt speed, current path baggage count, and node arrival baggage count within a continuous time window, reducing interference from system jitter and instantaneous repeated recordings by sensors; Z-score standardization is used to statistically standardize path length, current path baggage count, and maximum baggage capacity at nodes, eliminating the influence of different data dimensions; decimal scaling normalization is used to adjust the interval mapping of flight departure time, baggage check-in time, and node arrival baggage count, achieving normalization of airport baggage transportation data and providing a unified data input basis for subsequent calculations of path delay assessment and scheduling adaptation assessment.

[0033] In this implementation plan, by constructing a multi-dimensional data preprocessing workflow covering path length, conveyor belt speed, current path baggage count, node arrival baggage count, node maximum baggage handling capacity, flight departure time, and baggage check-in time, the stability, consistency, and computability of airport baggage transportation data at the input stage are effectively improved, laying a high-quality data foundation for accurate modeling of path delay assessment values ​​and scheduling adaptation assessment values.

[0034] Specifically, the steps for constructing a passageway sequence based on airport baggage transport routes and evaluating the operational status of each passageway in the sequence based on preprocessed airport baggage transport data are as follows: Several physical transport processing points are set up within the airport baggage transport routes. Each transport processing point is used to perform baggage sorting, transfer, and handover operations, and a node number is assigned to each transport processing point to identify the node location and the target binding of the scheduling instruction. Multiple consecutive transport processing points are connected sequentially, and a passageway sequence from the baggage check-in entrance to the flight loading area is constructed by combining the path graph topology, forming a candidate path structure set. Based on the preprocessed airport baggage transport data, the operational status of each passable path is evaluated: The basic transportation time is obtained by dividing the path length by the conveyor belt speed and combining it with real-time sensor data. The current number of bags and the number of bags arriving at the node are added together, and then divided by the node's maximum baggage handling capacity plus a minimum term to reflect the current node's resource load level, resulting in the processing load time. The basic transportation time and the processing load time are added together to form the total transportation and processing time, which is used to characterize the overall operational pressure of the current path. The logarithm of the flight departure time minus the baggage check-in time plus a natural constant is taken, and the reciprocal of this logarithm is added to construct an urgency adjustment factor based on the time urgency. The total time is multiplied by the urgency adjustment factor to obtain the path delay assessment value, which is used to measure the feasibility of the current path within the scheduling cycle and the level of queuing risk.

[0035] The specific formula for calculating the path delay assessment value is as follows:

[0036] ;

[0037] In the formula, D represents the path delay assessment value, L represents the path length, S represents the conveyor belt speed, N represents the number of bags on the current path, R represents the number of bags arriving at the node, C represents the maximum baggage capacity handled by the node, and T represents the flight departure time. Indicates baggage check-in time. denoted by minterm, and e denotes the base of the natural logarithm.

[0038] In this embodiment, Table 1 is a path delay assessment data table, which details the path structure parameters and path delay assessment calculation results of five feasible paths in the current scheduling cycle. Each feasible path is calculated based on its path length, conveyor belt speed, current number of bags on the path, number of bags arriving at nodes, maximum baggage capacity handled by nodes, flight departure time, and baggage check-in time, using a set assessment formula to obtain a corresponding path delay assessment value. This value is used to measure the delay risk and scheduling feasibility of the path under the current transportation task scheduling. Specifically, feasible path P1 has a path length of 45, a conveyor belt speed of 1.50, a current number of bags of 10, a number of bags arriving at nodes of 6, a maximum baggage capacity handled by nodes of 28, a flight departure time of 100, and a baggage check-in time of 66. The calculated path delay assessment value for this path is 39.81. The path length of accessible path P2 is 50, the conveyor belt speed is 1.60, the current number of bags is 8, the number of bags arriving at the node is 7, the maximum baggage capacity of the node is 30, the flight departure time is 101, the baggage check-in time is 68, and the corresponding path delay assessment value is 41.38. The path length of accessible path P3 is 55, the conveyor belt speed is 1.40, the current number of bags is 12, the number of bags arriving at the node is 5, the maximum baggage capacity of the node is 26, the flight departure time is 104, the baggage check-in time is 70, and the calculated path delay assessment value is 52.00. The path length of accessible path P4 is 48, the conveyor belt speed is 1.50, the current number of bags is 9, the number of bags arriving at the node is 6, the maximum baggage capacity of the node is 27, the flight departure time is 105, the baggage check-in time is 71, and the corresponding path delay assessment value is 43.39. The path length of the passable path P5 is 52, the conveyor belt speed is 1.45, the current number of bags on the path is 11, the number of bags arriving at the node is 7, the maximum baggage capacity that the node can handle is 29, the flight departure time is the 107th, the baggage check-in time is the 73rd, and the calculated path delay assessment value is 47.50.

[0039] Table 1 Path Delay Evaluation Data Table

[0040]

[0041] like Fig. 2The chart shown is a bar chart analyzing path delay assessment values, displaying the distribution of path delay assessment values ​​for five passable paths within the current scheduling cycle, and classifying path status according to a set path delay threshold. In the chart, green represents normal paths, red represents congested paths, and the blue dashed line represents the reference baseline for the path delay threshold. As can be seen from the chart, the path delay assessment values ​​for passable paths P1, P2, and P4 are 39.81, 41.38, and 43.39 respectively, all below the path delay threshold, and are therefore classified as normal paths. The path delay assessment values ​​for paths P3 and P5 are 52.00 and 47.50 respectively, exceeding the path delay threshold, and are marked as congested paths within the current scheduling cycle. This chart helps to intuitively identify path scheduling availability, providing a visual basis for scheduling optimization and path selection.

[0042] This implementation scheme constructs a sequence of passageways from the baggage check-in entrance to the flight loading area, integrating path length, conveyor belt speed, current number of baggage items on the path, number of baggage items arriving at nodes, maximum baggage capacity handled at nodes, flight departure time, and baggage check-in time to achieve dynamic quantification of path delay assessment values. Responding to the new demands of modern air logistics for transportation efficiency, resource allocation, and refined process management, this scheme effectively improves the accuracy and stability of path operation status identification, providing efficient and reliable structured input support for subsequent path selection and task scheduling.

[0043] Specifically, the steps for selecting passable normal paths from the travel path sequence based on the evaluation results and outputting a set of normal paths are as follows: Real-time comparison of path delay evaluation values ​​and path delay thresholds. The path delay evaluation value is jointly determined by path length, conveyor belt speed, current number of bags on the path, number of bags arriving at nodes, maximum baggage capacity handled by nodes, flight departure time, and baggage check-in time. If the path delay evaluation value is less than the path delay threshold, it is marked as a normal path, and the corresponding path number, path structure, and current status are recorded. All normal paths are extracted, and a set of normal paths is constructed as the initial input for candidate paths. If the path delay evaluation value is greater than or equal to the path delay threshold, it is marked as a congested path, and the trend of path delay evaluation value changes is recorded. The scheduling of this path is suspended. A fixed scheduling cycle is set, and the path delay evaluation value is updated periodically based on the latest collected airport baggage transportation data. During the update process, the node processing status and historical evaluation records of the current path are simultaneously called, and the path label is dynamically updated according to the updated path delay evaluation value, realizing the periodic correction and identification of path usage status.

[0044] This implementation plan achieves dynamic identification of normal and congested routes by constructing a route status labeling mechanism based on route delay assessment values. This mechanism updates route labels within a fixed scheduling cycle, addressing the higher demands of modern air logistics for route efficiency and scheduling response accuracy in complex operational scenarios. It effectively improves the real-time accuracy of route selection, enhances the automation capabilities of route status identification and label maintenance in airport baggage handling scheduling, and provides stable data support for subsequent scheduling adaptation assessment value calculation and candidate route construction.

[0045] Specifically, the steps for constructing a candidate path set by calling the normal path set and filtering the feasible paths of the current task from those duplicated in the normal path set are as follows: For each baggage transportation task to be scheduled, the number of times the current task has been delayed in the past cycle is counted and written into the task scheduling log along with the task number, recorded as the scheduling wait count; the starting processing point number of the current task and the loading processing point number corresponding to the target flight are determined, and all feasible paths between them are extracted based on the path graph structure information, recording the path number and node sequence; the normal path set is called to retrieve paths with path delay evaluation values ​​lower than the path delay threshold, and the feasible paths of the current task are compared and filtered with the duplicate paths in the normal path set to construct a candidate path set, and key data such as the path length, conveyor belt speed, number of baggage on the current path, and number of baggage arriving at the node are recorded, providing the input path set for the subsequent calculation of the scheduling adaptation evaluation value.

[0046] In this implementation plan, by calling the normal path set and combining the starting processing point number and the loading processing point number to extract the passable path, a candidate path set matching the current transportation task is constructed. With the support of scheduling waiting times, path number, path length, conveyor belt speed, current path baggage number and node arrival baggage number, targeted constraints for scheduling path selection are realized, providing a data entry with a closed structure for the accurate calculation of scheduling adaptation evaluation value and path optimization allocation.

[0047] Specifically, the steps for analyzing the scheduling priority of candidate paths are as follows: Based on real-time airport baggage transportation data and path delay assessment values, analyze the scheduling priority of candidate paths; add one to the number of scheduling waits and divide by the path delay assessment value, combining the path number and historical scheduling records to obtain a path scheduling compensation term, reflecting the corrective impact of the current task on the frequency of path usage; subtract baggage check-in time from flight departure time and add a minimum term, taking the reciprocal of this value to construct a task urgency factor, used to characterize the degree of constraint of remaining task time on path selection; divide the conveyor belt speed by the path length, combining with the path structure stability label to obtain a unit transportation efficiency factor, measuring the operational efficiency of the path per unit distance; multiply the path scheduling compensation term, the task urgency factor, and the unit transportation efficiency factor to obtain a scheduling fit assessment value, which is used as the core indicator for candidate path ranking and optimal allocation.

[0048] The specific formula for calculating the scheduling adaptation evaluation value is as follows:

[0049] ;

[0050] In the formula, P represents the scheduling adaptation evaluation value, W represents the number of scheduling wait times, D represents the path delay evaluation value, and T represents the flight departure time. Let S represent baggage check-in time, S represent conveyor belt speed, L represent path length, and ε represent minterms.

[0051] In this embodiment, Table 2 is a scheduling adaptation evaluation value data table, which records in detail the path status parameters and scheduling adaptation evaluation value calculation results of the five candidate paths in the current scheduling cycle. Specifically, candidate path H1 has a scheduling wait count of 0, a path delay evaluation value of 14.47, a flight departure time of 2324, a baggage check-in time of 2159, a conveyor belt speed of 3.48, and a path length of 16, resulting in a calculated scheduling adaptation evaluation value of 9.11; candidate path H2 has a scheduling wait count of 1, a path delay evaluation value of 19.82, a flight departure time of 2077, a baggage check-in time of 1862, a conveyor belt speed of 2.47, and a path length of 22, resulting in a calculated value of 8.12; candidate path H3 has a scheduling wait count of 0, a path delay evaluation value of 22.40, a flight departure time of 2648, and a path delay evaluation value of 22.40. The baggage check-in time is 2357, the conveyor belt speed is 3.09, the path length is 19, and the corresponding scheduling adaptation evaluation value is 6.54; the path parameters of candidate path H4 include 0 scheduling wait times, a path delay evaluation value of 14.56, a departure time of 3115, a check-in time of 2969, a conveyor belt speed of 3.36, a path length of 21, and a scheduling adaptation evaluation value of 7.53; the parameters of candidate path H5 are: 1 scheduling wait time, a path delay evaluation value of 22.28, a flight departure time of 2043, a check-in time of 1867, a conveyor belt speed of 3.45, a path length of 25, and a calculated scheduling adaptation evaluation value of 6.73.

[0052] Table 2. Scheduling Adaptation Evaluation Values

[0053]

[0054] like Fig. 3 The figure shows the ranking of candidate path scheduling adaptation evaluation values, displaying the ranking results of the scheduling adaptation evaluation values ​​of 5 candidate paths within the current scheduling period. The horizontal axis represents the candidate path number, and the vertical axis represents the corresponding scheduling adaptation evaluation value P. The higher the value, the stronger the path's adaptability to the current transportation task. As can be seen from the figure, candidate path H1 has the highest scheduling adaptation evaluation value of 9.11, ranking first; followed by H2 and H4, with evaluation values ​​of 8.12 and 7.53 respectively; H5 and H3 have relatively lower scheduling adaptation evaluation values ​​of 6.73 and 6.54 respectively. During the task scheduling optimization process, the system will prioritize paths with higher scheduling adaptation evaluation values ​​to undertake the current transportation task, thereby achieving optimal allocation of path resources. This provides intuitive support for the path ranking mechanism and assists in the implementation of a path scheduling strategy driven by evaluation values.

[0055] In this implementation plan, a scheduling adaptation evaluation value calculation mechanism is constructed with scheduling waiting times, path delay evaluation values, flight departure times, baggage check-in times, conveyor belt speeds, and path lengths as inputs. This mechanism enables a multi-factor comprehensive characterization of candidate path scheduling priorities, improves the accuracy of path ranking and task matching, and provides a quantifiable decision-making basis for subsequent path optimization and allocation.

[0056] Specifically, the steps for optimizing and allocating candidate paths, generating scheduling instructions, and recording transportation task execution logs are as follows: The scheduling suitability evaluation values ​​of paths in the candidate path set are sorted from highest to lowest. Combining the path number with the historical task allocation frequency, the path with the highest scheduling suitability evaluation value is selected as the execution path for the current transportation task, thus achieving optimal path allocation. If multiple paths in the candidate path set have the same scheduling suitability evaluation value, based on a joint path ranking strategy that integrates Markov decision processes and queuing network models, the historical sequences of node waiting times and scheduling waiting times corresponding to the path are invoked to construct the ranking input state. Each path is modeled as a node in the queuing system, and the path is simulated using a Markov state transition method. The evolution of the scheduling state, combined with queue delay characteristics and state value function, outputs a joint path ranking score and performs secondary ranking selection. If the candidate path set for the current task is empty, the task is marked as an unscheduled task, its scheduling wait count is incremented, and the task number and path requirement information are retained in the scheduling buffer queue. Path selection is retried in the next scheduling cycle. For transportation tasks with completed path allocation, scheduling instructions are generated. The scheduling instructions include the task number, selected path number, starting processing point number, target processing point number, path delay evaluation value, scheduling time, and scheduling fit evaluation value. These instructions are written to the transportation task execution log to drive subsequent transportation execution and support data backtracking for the execution feedback mechanism.

[0057] In this implementation scheme, a scheduling adaptation evaluation value sorting mechanism is introduced, and a secondary path sorting strategy is constructed by integrating Markov decision process and queuing network model. This enables joint modeling of variables such as scheduling waiting times, node waiting times, and path delay evaluation values. In the event of scheduling conflicts, the accuracy of path selection is improved, providing dynamic and robust scheduling logic for transportation task allocation. Furthermore, a structured scheduling feedback chain is established by generating scheduling instructions and recording transportation task execution logs.

[0058] Specifically, the steps for extracting data from the transportation task execution log, establishing a path execution feedback dataset, and quantifying the deviation of the path during actual execution are as follows: After the baggage transportation task is completed, the actual transportation time of the task and the node waiting time of each transportation processing point in the path are collected. Combined with the task number, the actual execution status of the current task within the scheduling cycle is recorded, and the actual transportation time and average node waiting time are obtained as direct observations of the path's operational status. Data from the transportation task execution log, including the selected path number, path delay assessment value, scheduling time, and scheduling adaptation assessment value, is extracted and fused with the actual transportation time and average node waiting time to establish a path execution feedback dataset. Based on the path execution feedback dataset, the path is quantified. The deviation between scheduling predictions and execution results is assessed as follows: The actual transport time minus the path delay assessment value, divided by the path delay assessment value plus a minimum term, is used to construct a scheduling deviation factor, which measures the magnitude of the error in scheduling prediction in terms of timeliness. The node waiting time, the current number of baggage items on the path, and the number of baggage items arriving at the node are added together to form the path comprehensive load term, reflecting the degree of concentrated use of path resources. The path comprehensive load term is divided by the maximum baggage handling capacity of the node plus a minimum term to obtain a load normalization factor, used to eliminate the impact of differences in service capacity across different paths. The scheduling deviation factor and the load normalization factor are added together to obtain the path execution deviation assessment value, which serves as a key evaluation indicator in the feedback phase, supporting subsequent path status updates and parameter corrections.

[0059] The specific formula for calculating the path execution deviation evaluation value is as follows:

[0060] ;

[0061] In the formula, E represents the path execution deviation evaluation value. This represents the actual transportation time, where D represents the estimated route delay. denoted by , N represents the number of bags on the current path, R represents the number of bags arriving at the node, C represents the maximum number of bags the node can handle, and ε represents the minima.

[0062] In this implementation plan, a path execution feedback dataset is constructed with actual transportation time, average node waiting time, path delay assessment value, current path baggage number, number of baggage arriving at nodes, and maximum baggage capacity of nodes as core variables. This enables quantitative modeling of the deviation between scheduling prediction and execution results. The path execution deviation assessment value is constructed as a feedback indicator, forming a quantitative feedback basis for the path status after task execution, and providing closed-loop support for subsequent path delay assessment value correction and node parameter update.

[0063] Specifically, based on the quantification results, the runtime evaluation value of the travel path and the processing capacity configuration of the processing points are adjusted. The adjustment results are used as the basis for updating path selection and task scheduling. The specific steps of constructing a closed-loop scheduling mechanism are as follows: Real-time comparison of the path execution deviation evaluation value and the execution deviation threshold, combined with the current path number and the corresponding task execution log, determines the degree of deviation in path scheduling performance; when the path execution deviation evaluation value is greater than or equal to the execution deviation threshold, the path delay evaluation value of the path is corrected and improved in the next evaluation cycle, while recording the number of corrections and historical fluctuation range of the path to suppress frequent selection of the path; when the path execution deviation evaluation value is less than the execution deviation threshold, the original path delay evaluation value of the path is maintained, and its historical evaluation records are retained for trend monitoring. The process involves several steps. First, if the waiting time of a processing point in a path exceeds the node waiting time threshold for three consecutive scheduling cycles, that processing point is marked as an overloaded node. Simultaneously, the node's processing status label is updated, and its maximum baggage capacity is reduced in subsequent scheduling cycles. At the end of each scheduling cycle, the path delay assessment is updated based on the updated maximum baggage capacity and real-time collected airport baggage transportation data, including path length, conveyor belt speed, current path baggage count, and the number of baggage arriving at the node. During the update process, the path structure and processing point numbers are preserved to ensure consistency in scheduling logic. The updated path delay assessment is then used as input for calculating the scheduling adaptation assessment and path sorting in the next cycle, forming a closed-loop mechanism of scheduling-execution-feedback-update.

[0064] In this implementation scheme, a path delay assessment correction mechanism is constructed, triggered by the path execution deviation assessment value. Combined with a dynamic adjustment strategy for node waiting time and maximum baggage handling capacity, this mechanism enables periodic repair of path scheduling performance and node operational status, enhancing the automation of path status modeling and input correction. Addressing the complex requirements of modern air logistics in terms of scheduling accuracy and operational robustness, the path delay assessment value is updated after the scheduling cycle ends and used as the basis for calculating the scheduling adaptation assessment value, forming a closed-loop structure of scheduling-execution-feedback-update, thus improving the real-time performance of scheduling inputs and the adaptive capability of path status.

[0065] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0066] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. An airport transportation route optimization and scheduling management system based on big data, characterized in that, include: The airport baggage transportation data acquisition and preprocessing module is used to collect multi-source data from airport transportation route maps, sensor networks, baggage check-in systems and flight scheduling systems in real time, extract airport baggage transportation data from the multi-source data, and preprocess the airport baggage transportation data. The path delay assessment and normal path filtering module is used to construct a sequence of passage paths based on airport baggage transportation paths, assess the operational status of each passage path in the sequence of passage paths based on preprocessed airport baggage transportation data, filter out passable normal paths from the sequence of passage paths based on the assessment results, and output a set of normal paths. The transportation task scheduling and route selection module calls the normal path set, filters the feasible paths of the current task and the paths that overlap with the normal path set, constructs a candidate path set, analyzes the scheduling priority of the candidate paths, completes the optimal allocation of the candidate paths, generates scheduling instructions, and records the transportation task execution log. The transportation execution feedback and route status update module is used to extract data from the transportation task execution log, establish a route execution feedback dataset, quantify the deviation of the route during actual execution, adjust the runtime evaluation value of the route and the processing capacity configuration of the processing point based on the quantification results, and use the adjustment results as the basis for updating route optimization and task scheduling to build a closed-loop scheduling mechanism. The specific steps for extracting data from the transportation task execution log, establishing a path execution feedback dataset, and quantifying the degree of deviation of the path during actual execution are as follows: Based on the path execution feedback dataset, the deviation between the scheduling prediction and the execution result is quantified: the actual transportation time minus the path delay assessment value, divided by the sum of the path delay assessment value and the minimum term, and the absolute value is taken to obtain the scheduling deviation factor; the node waiting time, the current number of baggage on the path, and the number of baggage arriving at the node are added together to obtain the path comprehensive load term; the path comprehensive load term is divided by the maximum baggage capacity of the node and the minimum term is added to obtain the load normalization factor; the scheduling deviation factor and the load normalization factor are added together to obtain the path execution deviation assessment value. The specific formula for calculating the path execution deviation evaluation value is as follows: ； In the formula, E represents the path execution deviation evaluation value. This represents the actual transportation time, where D represents the estimated route delay. Let N represent the average waiting time of the node, R represent the number of bags on the current path, C represent the maximum number of bags that the node can handle, and ε represent the minimum term. The specific steps for adjusting the runtime evaluation value of the travel path and the processing capacity configuration of the processing points based on the quantification results, and using the adjustment results as the basis for updating path optimization and task scheduling, to construct a closed-loop scheduling mechanism are as follows: The system compares the path execution deviation assessment value with the execution deviation threshold in real time, and combines the current path number with the corresponding task execution log to determine the degree of deviation in path scheduling performance. When the path execution deviation assessment value is greater than or equal to the execution deviation threshold, the path delay assessment value of the path is corrected and improved in the next assessment cycle. At the same time, the number of corrections and the historical fluctuation range of the path are recorded to prevent the path from being frequently selected. When the path execution deviation assessment value is less than the execution deviation threshold, the original path delay assessment value of the path is maintained, and its historical assessment records are retained for trend monitoring. When the node waiting time of a certain processing point in the path exceeds the node waiting time threshold in three consecutive scheduling cycles, the processing point is marked as an overloaded node, the processing status label of the node is updated, and the maximum baggage capacity of the node is reduced in subsequent scheduling cycles. At the end of each scheduling cycle, the path delay assessment value is updated based on the updated maximum baggage handling capacity of the nodes and real-time airport baggage transportation data. During the update process, the path structure and processing point number are retained simultaneously to ensure the consistency of the scheduling logic. The updated path delay assessment value is used as the input basis for the calculation of the scheduling adaptation assessment value and path sorting in the next cycle, forming a closed-loop mechanism of scheduling-execution-feedback-update.

2. The airport transportation route optimization and scheduling management system based on big data according to claim 1, characterized in that: The specific steps for extracting airport baggage transportation data from multi-source data, including real-time airport transportation route maps, sensor networks, baggage handling systems, and flight scheduling systems, are as follows: By performing structured analysis on the airport transportation route map, the connection relationships and numbering information of each transportation processing point are extracted; the sensor network is simultaneously accessed to periodically read the real-time values ​​of conveyor belt speed and the number of bags on the current route; baggage check-in time and corresponding processing point identifiers are obtained from the baggage check-in system; at the same time, the mapping relationship between flight departure time and baggage target segment is extracted from the flight scheduling system; the above multi-source data are aligned according to a unified timestamp format to extract airport baggage transportation data including route length, conveyor belt speed, number of bags on the current route, number of bags arriving at nodes, maximum baggage capacity handled by nodes, flight departure time, and baggage check-in time.

3. The airport transportation route optimization and scheduling management system based on big data according to claim 1, characterized in that: The specific steps for preprocessing airport baggage transportation data are as follows: Outlier detection and correction algorithms are used to identify outliers in path length and conveyor belt speed, eliminating data drift caused by erroneous data entry. A sliding window median filtering algorithm is used to denoise airport baggage transportation data, smoothing out data jumps caused by system jitter and instantaneous repeated recording by sensors. The Z-score standardization method is used to statistically standardize airport baggage transportation data. Decimal scaling normalization is used to uniformly adjust the range of airport baggage transportation data, achieving normalization of airport baggage transportation data.

4. The airport transportation route optimization and scheduling management system based on big data according to claim 1, characterized in that: The specific steps for constructing a transit route sequence based on airport baggage transport routes and evaluating the operational status of each transit route in the transit route sequence based on preprocessed airport baggage transport data are as follows: In the airport baggage transportation route, several physical transportation processing points are set up. Each transportation processing point is used to perform baggage sorting, transfer and handover operations, and a node number is assigned to each transportation processing point. Multiple consecutive transportation processing points are connected in sequence to construct a passage route sequence from the check-in entrance to the flight loading area. Based on the preprocessed airport baggage transportation data, the operational status of each passable route is evaluated: the route length is divided by the conveyor belt speed to obtain the basic transportation time. Add the current number of baggage items to the number of baggage items arriving at the node, then divide by the maximum baggage capacity that the node can handle plus the sum of the minimum items to obtain the processing load time; add the basic transportation time to the processing load time to obtain the total transportation and processing time. Subtract baggage check-in time from flight departure time, add natural constant, and take the logarithm. Take the reciprocal of this logarithm and add one to obtain the urgency adjustment factor. Multiply the total time term by the urgency adjustment factor to obtain the path delay assessment value.

5. The airport transportation route optimization and scheduling management system based on big data according to claim 1, characterized in that: The specific steps for filtering passable normal paths from the sequence of travel paths based on the evaluation results and outputting a set of normal paths are as follows: The path delay assessment value and the path delay threshold are compared in real time. If the path delay assessment value is less than the path delay threshold, it is marked as a normal path, all normal paths are extracted, and a normal path set is constructed. If the path delay assessment value is greater than or equal to the path delay threshold, it is marked as a congested path, and the scheduling and use of the path are suspended. Set a fixed scheduling cycle, update the path delay assessment value regularly based on the latest collected airport baggage transportation data, and dynamically update the path label according to the updated path delay assessment value.

6. The airport transportation route optimization and scheduling management system based on big data according to claim 1, characterized in that: The specific steps for constructing a candidate path set by calling the normal path set, filtering out paths that are duplicates of the current task's feasible paths in the normal path set, and constructing the candidate path set are as follows: For each baggage transport task to be scheduled, count the number of times the current task has been delayed in the past cycle, and record it as the scheduling wait count; determine the starting processing point number of the current task and the loading processing point number corresponding to the target flight, and extract all passable paths between the two; call the normal path set, filter the passable paths of the current task and the paths that are repeated in the normal path set, and construct a candidate path set.

7. The airport transportation route optimization and scheduling management system based on big data according to claim 1, characterized in that: The specific steps for analyzing the scheduling priority of candidate paths are as follows: Based on real-time airport baggage transportation data and path delay assessment values, the scheduling priority of candidate paths is analyzed: the scheduling waiting count is incremented by one and then divided by the path delay assessment value to obtain the path scheduling compensation term; the flight departure time is subtracted from the baggage check-in time and a minimum term is added, and the reciprocal of this value is taken to obtain the task urgency factor; the conveyor belt speed is divided by the path length to obtain the unit transportation efficiency factor; the path scheduling compensation term, the task urgency factor, and the unit transportation efficiency factor are multiplied to obtain the scheduling adaptation assessment value.

8. The airport transportation route optimization and scheduling management system based on big data according to claim 1, characterized in that: The specific steps for completing the optimal allocation of candidate paths, generating scheduling instructions, and recording the transportation task execution log are as follows: The candidate path set is sorted from highest to lowest scheduling fit evaluation value, and the path with the highest scheduling fit evaluation value is selected as the execution path for the current transportation task, thus achieving optimal path allocation. If there are multiple paths with the same scheduling fit evaluation value in the candidate path set, a joint path sorting strategy based on the fusion of Markov decision process and queuing network model is used. The historical sequence of node waiting time and scheduling waiting count for the corresponding path is called to construct the sorting input state, and the current state transition probability and expected delay structure of each path are output for secondary sorting selection. If the candidate path set for the current task is empty, the task is marked as an unscheduled task, its scheduling waiting count is incremented by one, and it is retained until the next scheduling cycle to retry path selection. The transportation task with completed path allocation generates scheduling instructions to drive subsequent transportation execution; and writes the task number, selected path number, starting and target processing point numbers, path delay evaluation value, scheduling time and scheduling adaptation evaluation value into the transportation task execution log.

9. The airport transportation route optimization and scheduling management system based on big data according to claim 1, characterized in that: The specific steps for extracting data from transportation task execution logs, establishing a path execution feedback dataset, and quantifying the degree of deviation of the path during actual execution also include: After the baggage transportation task is completed, the actual transportation time and the waiting time of each transportation processing point in the route are collected to obtain the actual transportation time and the average waiting time of each node; data is extracted from the transportation task execution log and a path execution feedback dataset is established with the actual transportation time and the average waiting time of each node.

Images