Airport resource scheduling analysis method based on big data platform

Abstract

The invention relates to the technical field of digital data processing, in particular to an airport resource scheduling analysis method based on a big data platform, and the method comprises the steps: collecting real-time flight information; the collected flight information is preprocessed; calculating the number of vehicles needing to be scheduled based on the number of people in the preprocessed flight information; searching a nearby target vehicle based on the parking position of flight allocation; generating a scheduling path based on the searched target vehicle and the parking position; and the target vehicle moves based on the scheduling path and monitors the moving state of the vehicle in real time. Through the above steps, the airport can effectively manage and schedule the resources thereof, reduce the waiting time of passengers, and improve the overall operation efficiency of the airport.

Description

Technical Field

[0001] The present invention relates to the technical field of digital data processing, and in particular to an airport resource scheduling analysis method based on a big data platform. Background Art

[0002] Airport passenger transport vehicle dispatch refers to the process of effectively managing and arranging various means of transportation used to transport passengers within the airport. These means of transportation mainly include shuttle buses, luggage carts, barrier-free service vehicles, and VIP shuttle vehicles. Efficient and reasonable dispatch can not only ensure the fast and convenient movement of passengers from the terminal to the apron or from the arrival area to the parking lot, but also improve the overall service quality of the airport.

[0003] The existing method is mainly to manually mobilize vehicles according to the flight operation situation, which has low work efficiency and requires people to wait for a long time. Summary of the invention

[0004] The purpose of the present invention is to provide an airport resource scheduling analysis method based on a big data platform, aiming to reduce passenger waiting time and improve the overall operating efficiency of the airport.

[0005] To achieve the above-mentioned purpose, the present invention provides an airport resource scheduling analysis method based on a big data platform, including collecting real-time flight information;

[0006] Pre-process the collected flight information;

[0007] Calculate the number of vehicles to be dispatched based on the number of passengers in the pre-processed flight information;

[0008] Search nearby target vehicles based on the flight assigned parking location;

[0009] Generate a dispatch path based on the searched target vehicle and parking location;

[0010] The target vehicle moves based on the dispatch path and monitors the vehicle's movement status in real time.

[0011] The flight information includes the flight number, airline, departure place, destination, actual departure time and actual arrival time.

[0012] The specific steps of collecting real-time flight information include:

[0013] Establish data exchange agreements with airlines and air traffic control departments;

[0014] Access the flight schedule information provided by the airline and read the corresponding flight information.

[0015] The specific steps of preprocessing the collected flight information include:

[0016] Clean up the wrong data in flight information;

[0017] Format flight information to clear erroneous data.

[0018] The specific steps of calculating the number of vehicles to be dispatched based on the number of people in the pre-processed flight information include:

[0019] Extracting estimated passenger number information and baggage information from flight information;

[0020] Match vehicle type based on passenger number information and luggage information;

[0021] Predict the proportion of passengers using airport shuttles based on historical data;

[0022] Calculate the number of vehicles required based on the vehicle utilization ratio, the number of passengers on the flight, and the passenger capacity of each vehicle;

[0023] Schedule vehicle dispatch based on flight arrival times.

[0024] The specific steps of predicting the proportion of passengers using airport shuttle buses based on historical data include:

[0025] Extracting vehicle usage characteristics related to the proportion of passengers using shuttle buses, wherein the vehicle usage characteristics include the number of passengers, flight arrival time, and weather;

[0026] Divide the feature dataset into training set and test set;

[0027] The support vector machine model is trained using the training set;

[0028] Use the test set data to verify the predictive performance of the model;

[0029] The support vector machine model is used to predict the proportion of passengers on future flights who will use shuttle buses, and the predicted proportion of buses used is obtained.

[0030] The specific steps of searching for a target vehicle nearby based on the parking location assigned by the flight include:

[0031] Determine the specific location where the aircraft will stop based on flight information;

[0032] Determine the type of vehicle that needs to be dispatched;

[0033] Obtain the current location of the vehicle through GPS positioning and tracking technology;

[0034] Based on the parking location, search for available vehicles within a preset range;

[0035] Assign the nearest available vehicle to the designated location based on the parking position and the type of vehicle required.

[0036] The specific steps of generating a dispatch path based on the searched target vehicle and parking location include:

[0037] Obtain the determined parking location coordinates, collect the current location coordinates and vehicle type of the target vehicle;

[0038] Obtain the airport's map data from the airport's internal map database;

[0039] The Dijkstra algorithm is applied to calculate the optimal path from the starting point to the end point under the set constraints to obtain the scheduling path.

[0040] The specific steps of moving the target vehicle based on the scheduling path and monitoring the moving state of the vehicle in real time include:

[0041] Check whether the vehicle is in a drivable state. Check items include battery power, tire pressure, and brake system;

[0042] Start the vehicle to move according to the dispatched path;

[0043] Use the on-board GPS positioning system to track the vehicle's location in real time.

[0044] The airport resource scheduling analysis method based on a big data platform of the present invention comprises: collecting real-time flight information; preprocessing the collected flight information; calculating the number of vehicles to be scheduled based on the number of people in the preprocessed flight information; searching for nearby target vehicles based on the parking location assigned by the flight; generating a scheduling path based on the searched target vehicle and the parking location; the target vehicle moves based on the scheduling path and monitors the movement status of the vehicle in real time. By using the Internet of Things technology and the sensor network, information from various data sources such as airlines, air traffic control systems and airports is collected, including the expected arrival and departure time of flights, aircraft models, number of passengers, etc. The collected data is cleaned to remove invalid or erroneous data points to ensure the accuracy of subsequent analysis. Data standardization unifies the formats and units of data from different sources for further analysis. The preprocessed flight information is analyzed, and the number of shuttle buses and luggage trucks required is calculated based on factors such as the number of passengers and luggage volume of each flight. Considering the special circumstances that may occur during peak hours, a certain number of vehicles are reserved as spare resources. The location of each dispatchable vehicle is determined by GPS positioning technology. According to the parking location of the flight, the shortest path algorithm or the distance-based sorting algorithm is used to quickly find the nearest and available vehicle. The optimal driving route is planned for each vehicle through Geographic Information System (GIS) software combined with the airport map data. Taking into account other obstacles or restrictions that may exist in the airport, the route is dynamically adjusted to avoid congested areas. After receiving the dispatch instruction, the vehicle drives to the designated location along the predetermined route. Using on-board sensors and communication technology, the location, speed and status of the vehicle are continuously monitored to ensure the smooth completion of the dispatch task. During the operation of the vehicle, if an emergency (such as road closure) is encountered, the system can adjust the route in real time to ensure dispatch efficiency.

[0045] Through the above steps, the airport can effectively manage and dispatch its resources, reduce passenger waiting time, and improve the overall operational efficiency of the airport. In addition, this method can also be extended to include baggage handling, cargo transportation and other aspects, further improving the airport's service quality and customer satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 It is a flow chart of the airport resource scheduling and analysis method based on the big data platform of the first embodiment of the present invention.

[0048] Figure 2 FIG. 4 is a flow chart of collecting real-time flight information according to the first embodiment of the present invention.

[0049] Figure 3 This is a flowchart of preprocessing collected flight information according to the first embodiment of the present invention.

[0050] Figure 4 This is a flow chart of calculating the number of vehicles to be dispatched based on the number of passengers in pre-processed flight information according to the first embodiment of the present invention.

[0051] Figure 5 This is a flow chart of predicting the proportion of passengers using airport shuttle buses based on historical data according to the first embodiment of the present invention.

[0052] Figure 6 The flowchart of searching for a nearby target vehicle based on a parking position assigned by a flight according to the first embodiment of the present invention.

[0053] Figure 7 It is a flowchart of generating a dispatch path based on the searched target vehicle and parking position according to the first embodiment of the present invention.

[0054] Figure 8 It is a flow chart of the target vehicle moving based on the scheduling path and monitoring the moving state of the vehicle in real time according to the first embodiment of the present invention. DETAILED DESCRIPTION

[0055] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0056] First embodiment

[0057] See also Figures 1 to 8 The present invention provides an airport resource scheduling analysis method based on a big data platform, comprising:

[0058] S101 collects real-time flight information;

[0059] The goal of this phase is to obtain the latest data about a specific flight, which is vital for passengers, airlines, and aviation authorities. The flight information includes flight number, airline, origin, destination, actual departure time, and actual arrival time.

[0060] Flight number is a unique number that identifies a specific flight. Airline is the name of the airline operating the flight. Origin is the airport from which the flight departs. Destination is the airport to which the flight lands. Actual departure time is the time the aircraft actually leaves the ground. Actual arrival time is the time the aircraft actually lands at the destination airport.

[0061] The specific steps include:

[0062] S201 Establish data exchange agreements with airlines and air traffic control departments;

[0063] Negotiate with airlines and air traffic management departments to determine the specific details of data exchange so that the corresponding data can be obtained. Then clarify key parameters such as data format, transmission frequency, update cycle, etc. Formalize the data sharing agreement to lay the legal foundation for subsequent data exchange.

[0064] S202 accesses the flight schedule information provided by the airline and reads the corresponding flight information.

[0065] Connect with airline systems through API (application programming interface) or other technical means. Pull the latest flight schedule information from the airline server regularly.

[0066] Convert received data into a format that is easy to process. Save flight information in a database for later use. Check data for completeness and accuracy to ensure information is reliable.

[0067] S102 pre-processes the collected flight information;

[0068] The specific steps include:

[0069] S301 cleans up the wrong data in the flight information;

[0070] Remove or correct data items that are inaccurate, incomplete, or non-compliant. Use algorithms or rules to check for outliers in the data, such as unreasonable departure or arrival times, non-existent flight numbers, etc. Correct correctable data, such as input errors or inconsistent formats. Delete data items that cannot be corrected, such as records with serious missing information. Ensure that each record is unique and remove duplicate records. Ensure that all fields follow the same format and standards, for example, the representation of dates and times should be consistent.

[0071] S302 formats the flight information to remove erroneous data.

[0072] Ensure that all fields are in a unified standard format, such as flight number, airline code, airport code, etc. Convert date and time fields to a unified format, such as YYYY-MM-DD HH:MM:SS. Ensure that the data type of each field is correct, such as converting text-type numbers to numeric types. For missing fields, decide whether to fill in default values ​​or predictive filling based on the specific situation. Add additional information to each record, such as data source, last updated time, etc., to track the history of data changes.

[0073] S103 calculates the number of vehicles to be dispatched based on the number of passengers in the pre-processed flight information;

[0074] The specific steps include:

[0075] S401 extracts estimated passenger number information and baggage information from the flight information;

[0076] Extract key data from flight information for subsequent vehicle dispatch planning. Extract the number of passengers per flight, which is usually provided by the airline. Estimate the total luggage volume based on the number of passengers, taking into account the checked and carry-on luggage that passengers may carry.

[0077] S402 matches the vehicle type according to the passenger number information and the luggage information;

[0078] Choose the right type of vehicle to meet the needs of your passengers. You can determine the minimum capacity requirement of the vehicle based on the number of passengers. Consider the luggage storage space of the vehicle to ensure that it can accommodate the luggage of all passengers. Choose the right vehicle type based on the capacity and space requirements, such as minibus, large bus, etc.

[0079] S403 predicts the proportion of passengers using airport shuttle buses based on historical data;

[0080] The specific steps include:

[0081] S501 extracts vehicle usage characteristics related to the proportion of passengers using shuttle buses, where the vehicle usage characteristics include the number of passengers, flight arrival time, and weather;

[0082] Extract features related to the proportion of passengers using shuttle buses from historical data, including the number of passengers, flight arrival time, weather, etc.

[0083] S502 divides the feature data set into a training set and a test set;

[0084] The collected historical data is randomly divided into two parts, one for training the machine learning model and the other for evaluating the performance of the model.

[0085] S503 trains the support vector machine model using the training set;

[0086] Use the training set data to train the support vector machine model and adjust the model parameters to obtain the best fit.

[0087] S504 uses the test set data to verify the prediction performance of the model;

[0088] Use the test set data to evaluate the predictive ability of the model, including indicators such as accuracy and recall.

[0089] S505 uses a support vector machine model to predict the proportion of passengers on future flights using shuttle buses to obtain a predicted bus usage ratio.

[0090] Apply the model to new flight data to predict the proportion of future passengers using shuttles.

[0091] S404 calculates the required number of vehicles based on the vehicle utilization ratio, the number of passengers on the flight, and the passenger capacity of each vehicle;

[0092] Determine the number of vehicles that need to be dispatched.

[0093] The calculation formula is:

[0094] Number of vehicles required = (number of passengers × vehicle utilization ratio) / passenger capacity of each vehicle

[0095] S405: Formulate vehicle dispatching time according to the flight arrival time.

[0096] Arrange vehicles to arrive in advance based on the actual arrival time of the flight. Reserve a certain buffer time to take into account possible delays or advances of flights. Rationally allocate vehicle resources to avoid waste caused by over-scheduling.

[0097] S104 searches for a nearby target vehicle based on the parking location assigned by the flight;

[0098] The specific steps include:

[0099] S601 determines the specific location where the aircraft will stop based on the flight information;

[0100] Get the parking position information of each flight from the flight information system. Make sure the parking position information is up to date and consistent with the actual parking position.

[0101] S602 determines the type of vehicle that needs to be dispatched;

[0102] Review the vehicle type determined in step S402 to ensure that the selected vehicle can meet the requirements of the number of passengers and luggage. Finally determine the type of vehicle to be dispatched

[0103] S603 obtains the current location of the vehicle through GPS positioning and tracking technology;

[0104] Ensure that all vehicles are equipped with GPS devices and connected to the central dispatch system. Regularly receive vehicle location data from GPS devices and update the real-time location of vehicles. Record the location history of all vehicles for subsequent analysis and tracking.

[0105] S604 searches for available vehicles within a preset range based on the parking location;

[0106] Search for available vehicles near the parking space. Define a preset search range, such as a radius around the parking space. Filter out vehicles within the preset range from all vehicles. Make sure the selected vehicles are available, i.e. not occupied by other tasks.

[0107] S605 allocates the nearest available vehicle to the designated location according to the parking space and the required vehicle type.

[0108] Assign the most suitable vehicle to the flight. Calculate the distance between all eligible vehicles and the parking stand. Select the closest vehicle of the matching type. Send a dispatch instruction to the selected vehicle to instruct it to go to the designated parking stand. Plan the optimal driving route for the vehicle to ensure that it can reach the parking stand in time.

[0109] S105 generates a dispatching path based on the searched target vehicle and parking location;

[0110] The specific steps include:

[0111] S701 obtains the determined parking position coordinates, and collects the current position coordinates and vehicle type of the target vehicle;

[0112] Ensure that the dispatch system has accurate coordinate information of the origin (current location of the vehicle) and destination (parking space) as well as the vehicle type.

[0113] The exact coordinates of the parking position are obtained from step S601.

[0114] The GPS positioning data of the target vehicle is obtained from step S603 to obtain the current position coordinates of the vehicle.

[0115] The vehicle type is confirmed in step S602 for subsequent possible path restriction considerations.

[0116] S702 obtains map data of the airport from a map database within the airport;

[0117] Obtain map data such as the airport's internal road network layout. Specifically, you can access the airport's internal map database, which contains all the airport's roads, buildings, parking spaces and other geographic information. Parse the acquired map data and convert it into a data structure that can be processed by a computer, such as the nodes and edges in the data structure.

[0118] S703: Apply the Dijkstra algorithm to calculate the best path from the starting point to the end point under the set constraint conditions to obtain a scheduling path.

[0119] Calculate the best path from the target vehicle's current position to the parking space.

[0120] Set constraints based on airport rules and actual conditions, for example:

[0121] Access restrictions by vehicle type (certain areas are restricted to certain types of vehicles only).

[0122] Road capacity (some sections may have speed limits or be closed to traffic).

[0123] Impact of special events (construction areas, temporary road closures, etc.).

[0124] The parking space is used as the target node and the current position of the target vehicle is used as the starting point. The Dijkstra algorithm is applied to find the shortest path from the starting point to the target node in the map data, taking into account the above constraints. If there are multiple feasible paths, the selection can be further optimized according to specific criteria, such as giving priority to roads with smooth traffic and avoiding congested areas.

[0125] The calculated optimal path is used as the scheduling path, including information such as the specific driving route, estimated driving time, and estimated arrival time.

[0126] S106 The target vehicle moves based on the scheduling path and monitors the movement status of the vehicle in real time.

[0127] The specific steps include:

[0128] S801 Checks whether the vehicle is in a drivable state, including battery power, tire pressure, and brake system;

[0129] Make sure the vehicle is in good working order and can safely follow the scheduled route. Confirm that the vehicle battery has enough power to complete the trip. If it is low, you need to charge or replace the battery. Check that the pressure of all tires is within the normal range to ensure that the tires can withstand the expected load and ensure stable driving. Test the responsiveness and effectiveness of the braking system to ensure that it can stop in time in an emergency.

[0130] S802 starts the vehicle to move according to the dispatched path;

[0131] According to the previously planned dispatch path, start the vehicle and start moving. Upload the dispatch path generated in step S105 to the vehicle's navigation system. After completing all safety checks, start the vehicle and start driving along the planned path according to the navigation instructions. According to the airport regulations and the vehicle's functions, select the appropriate driving mode (such as automatic driving or manual driving).

[0132] S803 uses the onboard GPS positioning system to track the vehicle's location in real time.

[0133] Monitor the location of the vehicle in real time to ensure that the vehicle is moving along the planned route and can respond to emergencies in a timely manner. Use the on-board GPS positioning system to record the actual location of the vehicle to ensure the accuracy and real-time nature of the data. Send the location data to the central monitoring system or dispatch center through wireless communication technology (such as 4G / LTE, Wi-Fi, etc.). After receiving the location data, the central monitoring system displays the vehicle location in real time and compares it with the planned path. If deviations are found or special circumstances are encountered, the dispatcher can adjust the path or take other measures in time. If the vehicle deviates from the planned path or a fault warning occurs, the system will immediately issue an alarm, and the operator can make corresponding arrangements based on the actual situation, such as replanning the path or dispatching a maintenance team.

[0134] What is disclosed above is only a preferred embodiment of the present invention, and it certainly cannot be used to limit the scope of rights of the present invention. Ordinary technicians in this field can understand that all or part of the processes of the above embodiment and equivalent changes made according to the claims of the present invention still fall within the scope of the invention.

Claims

1. Airport resource scheduling analysis method based on big data platform, It is characterized in that Includes: collecting real-time flight information; Pre-process the collected flight information; Calculate the number of vehicles to be dispatched based on the number of passengers in the pre-processed flight information; Search nearby target vehicles based on the flight assigned parking location; Generate a dispatch path based on the searched target vehicle and parking location; The target vehicle moves based on the dispatch path and monitors the vehicle's movement status in real time.

2. The airport resource scheduling analysis method based on a big data platform according to claim 1, characterized in that: The flight information includes flight number, airline, departure place, destination, actual departure time and actual arrival time.

3. The airport resource scheduling analysis method based on a big data platform as claimed in claim 2 is characterized in that: The specific steps of collecting real-time flight information include: Establish data exchange agreements with airlines and air traffic control departments; Access the flight schedule information provided by the airline and read the corresponding flight information.

4. The airport resource scheduling analysis method based on a big data platform as claimed in claim 3 is characterized in that: The specific steps of preprocessing the collected flight information include: Clean up the wrong data in flight information; Format flight information to clear erroneous data.

5. The airport resource scheduling analysis method based on a big data platform as claimed in claim 4 is characterized in that: The specific steps of calculating the number of vehicles to be dispatched based on the number of people in the pre-processed flight information include: Extracting estimated passenger number information and baggage information from flight information; Match vehicle type based on passenger number information and luggage information; Predict the proportion of passengers using airport shuttles based on historical data; Calculate the number of vehicles required based on the vehicle utilization ratio, the number of passengers on the flight, and the passenger capacity of each vehicle; Schedule vehicle dispatch based on flight arrival times.

6. The airport resource scheduling analysis method based on a big data platform as claimed in claim 5, characterized in that: The specific steps of predicting the proportion of passengers using airport shuttle buses based on historical data include: Extracting vehicle usage characteristics related to the proportion of passengers using shuttle buses, wherein the vehicle usage characteristics include the number of passengers, flight arrival time, and weather; Divide the feature dataset into training set and test set; The support vector machine model is trained using the training set; Use the test set data to verify the predictive performance of the model; The support vector machine model is used to predict the proportion of passengers on future flights who will use shuttle buses, and the predicted proportion of buses used is obtained.

7. The airport resource scheduling analysis method based on a big data platform according to claim 6 is characterized in that: The specific steps of searching for a target vehicle near a parking location based on flight allocation include: Determine the specific location where the aircraft will stop based on flight information; Determine the type of vehicle that needs to be dispatched; Obtain the current location of the vehicle through GPS positioning and tracking technology; Based on the parking location, search for available vehicles within a preset range; Assign the nearest available vehicle to the designated location based on the parking position and the type of vehicle required.

8. The airport resource scheduling analysis method based on a big data platform according to claim 7, characterized in that: The specific steps of generating a dispatching path based on the searched target vehicle and parking location include: Obtain the determined parking location coordinates, collect the current location coordinates and vehicle type of the target vehicle; Obtain the airport's map data from the airport's internal map database; The Dijkstra algorithm is applied to calculate the optimal path from the starting point to the end point under the set constraints to obtain the scheduling path.

9. The airport resource scheduling analysis method based on a big data platform as claimed in claim 8, characterized in that: The specific steps of moving the target vehicle based on the scheduling path and monitoring the moving state of the vehicle in real time include: Check whether the vehicle is in a drivable state. Check items include battery power, tire pressure, and brake system; Start the vehicle to move according to the dispatched path; Use the on-board GPS positioning system to track the vehicle's location in real time.

Images