Air transportation big data operation safety monitoring and early warning management platform

Abstract

The invention discloses an air transportation big data operation safety monitoring and early warning management platform, and relates to the technical field of air data processing. A distributed micro-service architecture is adopted, and the system comprises a data acquisition layer, a data integration layer, a model construction layer, an application service layer and a display layer. Wherein the data acquisition layer is used for acquiring data in an air transportation process; the data integration layer is used for cleaning, converting and integrating data in the air transportation process; the model building layer is used for building a data-driven universal model and an industry model; the application service layer provides safety monitoring, early warning, recording, evaluation and situation analysis functions based on a model and data; and the display layer displays the monitoring result, the early warning information and the situation analysis content through a visualization technology. According to the embodiment of the invention, by integrating various data in the air transportation process, real-time acquisition, processing, analysis and early warning of the data are realized, a data island is broken, and the safety and efficiency of air transportation are improved.

Description

Technical Field

[0001] This application belongs to the technical field of air data processing, and particularly relates to a big data operation safety monitoring and early warning management platform for air transportation. Background Art

[0002] In the field of air transportation, with the continuous increase in the number of flights and the increasing complexity of the air transportation system, traditional safety monitoring and management methods have been difficult to meet the safety requirements of modern air transportation.

[0003] Air transportation safety management faces challenges such as scattered data sources and serious information silos. Multiple departments such as airports, airlines, and air traffic control each hold part of the data, making it difficult to form a comprehensive understanding of the safety situation. At the same time, there are technical difficulties in the real-time collection, cleaning, and integration of massive heterogeneous data, which affects data quality and analysis effects. In addition, traditional safety management methods are often passive and reactive, lacking the ability to provide forward-looking early warnings of potential risks. How to timely detect safety hazards and take preventive measures in the complex and changeable air transportation environment has become a key problem to be solved urgently.

[0004] On the other hand, the intuitive display and effective communication of the safety situation also face challenges. How to present a large amount of professional data and analysis results to managers in a simple and easy-to-understand manner to support rapid decision-making is also a difficult point. Finally, how to effectively accumulate and spread knowledge while ensuring system security and improve the overall safety management level is also an important issue in air transportation safety management. These challenges together constitute the core technical problems of air transportation safety situation awareness. Summary of the Invention

[0005] The purpose of this application is to provide a big data operation safety monitoring and early warning management platform for air transportation, which integrates various types of data in the air transportation process, realizes the real-time collection, processing, analysis, and early warning of data, breaks data silos, and improves the safety and efficiency of air transportation.

[0006] To achieve the above object, an embodiment of this application provides a big data operation safety monitoring and early warning management platform for air transportation, which adopts a distributed microservice architecture and includes a data collection layer, a data integration layer, a model construction layer, an application service layer, and a display layer;

[0007] Among them, the data collection layer of the air transportation big data operation safety monitoring and early warning management platform is used to collect data during the air transportation process; the data integration layer of the air transportation big data operation safety monitoring and early warning management platform cleans, transforms, and integrates the data during the air transportation process; the model construction layer of the air transportation big data operation safety monitoring and early warning management platform establishes data-driven general models and industry models; the application service layer of the air transportation big data operation safety monitoring and early warning management platform provides functions of safety monitoring, early warning, recording, evaluation, and situation analysis based on the models and data; the display layer of the air transportation big data operation safety monitoring and early warning management platform displays the monitoring results, early warning information, and content of situation analysis through visualization technology.

[0008] According to the above method of the embodiment of the present application, the following additional technical features may also be included:

[0009] Further, the data during the air transportation process collected by the data collection layer of the air transportation big data operation safety monitoring and early warning management platform includes flight plans, dynamics, and resource usage data obtained in real time through the A-CDM system interface, real-time and future weather forecast data obtained through the meteorological system API, and vehicle real-time position and status information obtained using the vehicle positioning system SDK.

[0010] Further, the data integration layer of the air transportation big data operation safety monitoring and early warning management platform realizes the convergence and integration of data through the industrial Internet platform, and establishes a data quality monitoring mechanism to monitor and give early warnings to the data collection process in real time.

[0011] Further, the model construction layer of the air transportation big data operation safety monitoring and early warning management platform establishes a security situation analysis model based on the data during the air transportation process collected. By setting early warning indicators and thresholds, early warning information is sent out in a timely manner when abnormalities occur; weather, aircraft stand, and runway data are accessed to establish an operation situation analysis model, which processes and analyzes the operation data in real time, calculates key operation indicators, and establishes operation early warning rules.

[0012] Further, the security monitoring and early warning functions of the application service layer of the air transportation big data operation safety monitoring and early warning management platform monitor the security situation and operation situation of the airport in real time. When abnormalities occur, early warning information is immediately sent out, and it supports notifying relevant personnel through means such as text messages, emails, and / or APP push.

[0013] Further, through the situation analysis function of the application service layer of the air transportation big data operation safety monitoring and early warning management platform, the security situation and operation situation are comprehensively analyzed to form a situation analysis result, and through the display layer, the situation analysis result is displayed using visualization technology.

[0014] Furthermore, through the knowledge management and training functions of the application service layer of the air transportation big data operation safety monitoring and early warning management platform, the knowledge and experience of safety management are integrated to provide employees with online training and learning resources. The training effect is evaluated through data analysis, and personalized training plans are formulated according to the learning situation of employees.

[0015] Furthermore, the air transportation big data operation safety monitoring and early warning management platform realizes system security guarantee through data encryption and desensitization, access control and security audit. Sensitive data is encrypted to ensure the security of data transmission and storage. An access control mechanism is established to allocate different access permissions according to the roles and permissions of users. The operation logs of the system are recorded and audited, and security incidents are discovered and handled.

[0016] Adopting the air transportation big data operation safety monitoring and early warning management platform provided by the embodiments of the present application has the following beneficial technical effects compared with the prior art:

[0017] The air transportation big data operation safety monitoring and early warning management platform of the embodiments of the present application can collect and analyze data in the air transportation process in real time, and realize real-time monitoring and early warning of the safety status. This greatly improves the efficiency of safety management, enables managers to discover and handle potential safety hazards in time, and reduces the probability of safety accidents.

[0018] By establishing data-driven general models and industry models, the embodiments of the present application can set early warning indicators and thresholds, and send early warning information in time when abnormalities occur. This early warning mechanism can discover potential safety risks in advance, provide sufficient time for managers to take countermeasures, and avoid the occurrence of safety accidents.

[0019] Through the situation analysis and display function, the embodiments of the present application can comprehensively analyze the safety situation and operation situation, form the situation analysis result, and display it in the form of charts, maps, etc. through visualization technology. This enables managers to intuitively understand the safety situation and operation situation of the air transportation process and provide support for decision-making.

[0020] Through the knowledge management and training functions, the embodiments of the present application can integrate the knowledge and experience of safety management and provide employees with online training and learning resources. This not only improves the safety awareness and skill level of employees, but also evaluates the training effect through data analysis, and formulates personalized training plans according to the learning situation of employees, further improving the safety management ability of employees.

[0021] The embodiments of the present application achieve system security guarantee through methods such as data encryption and desensitization, access control, and security auditing, ensuring the security of the transmission and storage of sensitive data. At the same time, an access control mechanism is established to allocate different access permissions according to the roles and permissions of users, effectively preventing data leakage and illegal access. Brief Description of the Drawings

[0022] Figure 1 The block diagram of the operation security monitoring and early warning management platform for air transportation big data according to the embodiments of the present application is shown. Detailed Embodiments

[0023] To make the above objects, features, and advantages of the present application more obvious and understandable, the following describes the detailed embodiments of the present application in conjunction with the drawings. It can be understood that the specific embodiments described herein are only used to explain the present application, rather than limiting the present application. Additionally, it should be noted that for the sake of description, only parts related to the present application rather than all structures are shown in the drawings. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0024] The terms "including" and "having" and any variations thereof in the present application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or devices.

[0025] Referring to "embodiments" in the present application means that specific features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of the present application. The phrase appears in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described in the present application can be combined with other embodiments.

[0026] As Figure 1 shown, the embodiments of the present application provide an operation security monitoring and early warning management platform for air transportation big data, adopting a distributed microservice architecture. By splitting the system into multiple independent microservices, each microservice is responsible for a specific business function, and the microservices interact through a lightweight communication mechanism. This architecture has advantages such as high flexibility, strong scalability, and good fault tolerance. For example, when a certain microservice fails, it will not affect the operation of the entire system, and other microservices can continue to provide services. At the same time, each microservice can be independently scaled up or down according to actual needs to improve resource utilization efficiency.

[0027] Among them, the data acquisition layer in the embodiments of this application is responsible for collecting raw data related to air transportation from various data sources. Through devices such as sensors, cameras, and RFID readers deployed at different locations such as airports, airplanes, and air traffic control, multi-dimensional data such as aircraft position, speed, altitude, engine parameters, airport weather conditions, and passenger information are collected in real time. The collected data is preliminarily processed and filtered through an Internet of Things gateway, and then transmitted to the data integration layer through a secure and reliable network.

[0028] The data integration layer receives the raw data from the data acquisition layer, performs data cleaning, transformation, association, and fusion, and integrates the scattered and heterogeneous data into a unified and standardized data format, laying a foundation for subsequent data analysis and mining. For example, coordinate system conversion and time synchronization are performed on aircraft position data from different sources, and airport weather data is associated with aircraft status data to generate comprehensive description information of the flight environment. During the data integration process, data quality inspection and abnormal data processing are also required to ensure the accuracy and integrity of the data.

[0029] Based on the integrated data, the model construction layer constructs various machine learning models and knowledge graphs for the identification, prediction, and risk assessment of aviation safety events. For example, by training historical flight data, an aircraft fault prediction model is constructed, and based on the real-time collected aircraft status data, the health status and remaining life of each aircraft component are predicted. Another example is that through the correlation analysis of airport operation data and weather data, a flight delay prediction model is constructed to predict possible flight delays in advance and provide decision support for airport resource scheduling.

[0030] Based on the intelligent models generated by the model construction layer, the application service layer develops various application services for air transportation safety management, such as aircraft health management, flight risk assessment, and intelligent airport resource scheduling. These application services provide data and algorithm support to the presentation layer through API interfaces. For example, the aircraft health management service can monitor various parameter indicators of the aircraft in real time, give an immediate warning when abnormalities are found, and provide maintenance suggestions. The flight risk assessment service can comprehensively analyze factors such as aircraft status, crew experience, and route weather before the aircraft takes off, evaluate the flight risk level, and prompt risk points that may need attention.

[0031] The presentation layer presents the data and analysis results provided by the application service layer to aviation transportation managers and decision-makers clearly and intuitively through a friendly visual interface, providing them with real-time safety situation awareness and decision-making assistance. For example, it displays the positions, statuses, flight plans, and surrounding weather conditions of all aircraft on-site in real-time on a large screen, and marks warning information with different colors. When a user selects a certain warning event, the system automatically pops up a detailed information window, showing the type, level, cause analysis, and handling suggestions of the event, etc. Managers can make quick responses and decisions based on this.

[0032] Specifically, the data acquisition layer is used to collect various types of data during the aviation transportation process. The data acquisition layer is the foundation of the entire platform, and it is responsible for obtaining raw data from various data sources. In the field of aviation transportation, the data sources are very extensive and diverse, including airport operation data, flight dynamic data, meteorological data, passenger information data, etc. For example, flight schedule timetables and actual takeoff and landing times can be collected through the airport's Flight Information Display System (FIDS); real-time aircraft position information can be collected through the air traffic control system at the airport tower; weather condition data of the airport and air routes can be collected through meteorological radars and satellite cloud images of the meteorological department; passenger check-in, security check, and boarding flow data can be collected through check-in counters and boarding gates. In addition, various equipment operation status data of the airport and aircraft can also be collected through Internet of Things sensors, such as the operating speed of the baggage conveyor belt, the docking status of the boarding bridge, and the opening and closing status of the aircraft cabin door. By comprehensively collecting various types of data, a solid data foundation is laid for subsequent data integration, analysis, and application. The data integration layer cleans, transforms, and integrates the collected data. Given that there are many data source channels for aviation transportation data and there are differences in data formats and standards between different systems, it is necessary to process the raw data in the data integration layer to ensure the accuracy, consistency, and availability of the data.

[0033] First is data cleaning, which requires identifying and correcting "dirty data" such as missing values, outliers, and duplicate values. For example, eliminating flight altitude data beyond a reasonable range and uniformly converting data with inconsistent time formats. Secondly is data transformation, which requires converting data from different sources into a unified data model and format. For example, correlating flight schedule data and passenger check-in data to form complete flight information data. Finally is data integration, which requires summarizing and correlating data scattered in different systems and departments, breaking data silos, and realizing data sharing and exchange. For instance, integrating flight dynamic data with airport resource data can analyze the relationship between flight delays and shortages of resources such as boarding gates and baggage carousels; integrating flight data with meteorological data can analyze the impact of bad weather on flight regularity. The processing process of the data integration layer can be implemented using ETL (Extract, Transform, Load) tools, which can improve the efficiency and quality of data integration through a visual operation interface and flexible data mapping functions.

[0034] Specifically, the model construction layer establishes data-driven general models and industry models. The model construction layer uses big data processing technologies and machine learning algorithms to analyze and model various types of data collected during the air transportation process. Through learning and training on historical data, a prediction model that can reflect the safety status of air transportation is established. For example, a flight safety risk assessment model based on factors such as meteorological data, flight delay situations, and airport operation parameters can be established. Through this model, the current flight safety risk level can be evaluated in real time, providing a basis for safety monitoring and early warning. Another example is that an equipment health status assessment model based on data such as equipment operation parameters and fault history records can be established. Through this model, the performance trends and potential fault risks of key equipment can be grasped, providing decision-making support for equipment maintenance and renewal. When constructing industry models, fully consider the business characteristics and safety management requirements in the field of air transportation, incorporate business scenarios such as flight quality monitoring, air defense safety management, and operation risk analysis, and form an industry model system that comprehensively covers all aspects of air transportation safety management. Through continuous data accumulation and algorithm optimization, continuously improve the accuracy and practicality of the models, laying a solid foundation for safety monitoring and early warning.

[0035] Specifically, the application service layer provides functions of security monitoring, early warning, recording, evaluation, and situation analysis based on models and data. The application service layer is the core of the aviation security monitoring and early warning platform, comprehensively utilizing various models and data to achieve all-round and multi-level security monitoring and early warning. In terms of security monitoring, through the collection and analysis of real-time operation data, with the help of machine learning algorithms and pre-trained security assessment models, the entire flight operation process is monitored, and abnormal conditions and potential risks during the flight operation are promptly detected, triggering corresponding early warning mechanisms. For example, through the real-time monitoring of data such as aircraft attitude parameters and engine operating status, once a situation deviating from the normal range is detected, relevant personnel are immediately warned to take countermeasures to avoid accidents. In terms of security early warning, based on various monitoring data and security assessment results, with the help of intelligent early warning models and knowledge bases, potential safety hazards and risk factors are identified and alerted in advance. For example, through the comprehensive analysis of information such as airport weather conditions, flight schedules, and airspace control, potential flight delays, route conflicts, etc. are predicted, and emergency response plans and scheduling plans are formulated in advance to minimize operation risks. The security recording function provides data support for post-event security assessment and problem tracing by completely and accurately recording key data in each link of the flight, such as the execution of flight plans, crew operation behaviors, and aircraft system working status. These recorded data can also be used as important materials for optimizing security models and improving early warning rules. The security assessment function comprehensively uses various data and models to evaluate the aviation transportation security situation from different dimensions, including overall security level assessment, single-item security index assessment, key risk assessment, etc., providing an objective basis for security management decisions. For example, through the analysis and evaluation of data such as flight operation records, air defense security incidents, and passenger complaints, a security performance report of the airline is formed, weak links in security management are identified, and targeted improvement measures are formulated. The situation analysis function is based on a global perspective, comprehensively analyzing the security situation of the aviation transportation system, including air defense security situation, flight quality trend, operation risk distribution, etc., providing a macro reference for security supervision and decision-making. For example, by integrating and analyzing security incident data at specific airports and routes, regional security risk characteristics are identified, which helps relevant departments formulate targeted supervision policies and security guarantee measures.

[0036] Specifically, the core of the presentation layer lies in the presentation of information, with the goal of transforming complex data into a user-friendly graphical interface. The purpose of doing so is to enable airport managers to quickly understand the airport's operating status and make decisions based on intuitive information. Its advantage is to abstract complex back-end data, enabling users to efficiently obtain key information, thereby optimizing the management process and improving the quality of decision-making. Visualization technology is the key technical means of the presentation layer. It includes the application of various charts. For example, line charts are used to show the trends of certain indicators over time, bar charts are used to compare data differences between different categories, and pie charts intuitively reflect the proportion of each part in the overall. There are also maps. For example, based on geographical information, a heat map of each area of the airport is drawn, which can clearly show the passenger flow distribution or high-incidence areas of security incidents. Its advantage lies in leveraging the high sensitivity of the human visual processing ability to graphics to achieve rapid and effective data transmission. Its significance is that it can turn data into an easy-to-understand story, which is more attractive and persuasive than a simple numerical report. The display of monitoring results is one of the basic functions of the presentation layer. For example, multiple cameras may be installed at the security checkpoints of the airport to monitor the passenger flow in real time, with the aim of promptly deploying security personnel to avoid passenger congestion. Suppose the camera monitors that the average number of people passing through Security Checkpoint A per minute in the past hour is 50 and shows an upward trend. This information can be updated in real time on the monitoring screen in the form of a bar chart. The principle is to intuitively reflect the current number of people through the height of the bar chart and predict possible peaks. The technical effect is to help managers quickly capture traffic changes and make decisions on quickly adjusting the personnel allocation. The advantage of doing so is that by combining real-time monitoring data and chart presentation, it can greatly improve the response speed and efficiency of on-site management. The display of warning information is to ensure that information is effectively and promptly noticed. For example, if the temperature in a certain area is abnormal and the sensor detects that the temperature of a certain key device exceeds the normal operating threshold, the system can trigger a warning mechanism. On the large screen of the airport's real-time security situation display platform, the corresponding area will be displayed in flashing red to indicate a dangerous emergency, and yellow can represent a warning warning. Detailed explanations can also be provided in the warning box, including the specific location of the device, the current temperature value, and the preset safety threshold. The purpose is to enable managers to immediately notice possible risks so as to take timely countermeasures to ensure safe production. The advantage of doing so lies in its visual salience, which can ensure that warning information stands out among numerous data and achieve the effect of effectively preventing the occurrence of security incidents. The display of situation analysis is more complex and involves the comprehensive processing and analysis of multiple data sources. For example, by integrating multi-dimensional information such as the monitoring camera data of each area of the airport, historical passenger flow data, special event records, and holiday events, through data processing and machine learning, a prediction model is established, and then the situation of a specific area in a future time period is given. After data prediction and analysis through algorithms, a complex prediction chart with trend lines and confidence intervals is generated.This chart predicts the peak passenger flow period that may occur in the next hour. There will be multiple time series lines represented by different colors on this graph. Each line represents an influencing factor (such as holidays, special events). The combined effect of these lines forms the final passenger flow forecast result. And use specific symbols to remind administrators during the predicted peak period. Its significance lies in that it is not just a simple listing of data, but through the inherent connection between data, it reveals the deep laws of airport operations and predicts potential problems and trends. Its advantage is that it can provide more refined and forward-looking management methods. The purpose of this is to enable managers to be ready before things happen, thereby improving the overall level of management.

[0037] Furthermore, the data collection layer has three main data sources: A-CDM system, meteorological system and vehicle positioning system. Among them, the A-CDM system, namely the airport collaborative decision-making system, is a comprehensive information platform for airport operation management. The A-CDM system brings together key operational data from various units of the airport, including air traffic control, airlines, ground services and other departments. By obtaining flight plan data through the A-CDM system interface, you can learn basic information such as the estimated departure time, estimated arrival time, aircraft model, origin, and destination of the flight. The dynamic data of the flight is the information that is continuously updated during the actual execution of the flight, mainly reflecting the real-time status information of the flight. Through this system, you can query the actual departure time, actual arrival time, and current status of the flight in real time, such as "planned", "takeoff", "delayed", "cancelled", etc. Resource usage data refers to the usage of various resources in the airport, such as parking spaces, boarding gates, check-in counters, baggage carousels, etc., and whether these resources are idle. Through this system, we can obtain specific information about which parking space is occupied by which flight, whether the boarding gate is free, etc. This information reflects the current and future flight schedule information, the status and stage information during the operation, and the current situation of the resources involved in the airport operation. For example, the schedule information of a flight includes "Flight number MU123, scheduled departure time 10:00, scheduled arrival time 12:00, aircraft type Boeing 737, departure point Beijing Capital Airport, destination Shanghai Hongqiao Airport". The current status of a flight is "takeoff", and its previous status is "boarding". When the status is updated to "takeoff", the status of relevant information such as the runway and parking space in the airport will be modified at the same time. The A-CDM system mainly uses the message queue mechanism and interface form to provide the above data to the outside. Through the A-CDM system interface, we can learn about the schedule of a flight in detail, and provide comprehensive decision support for the operation guarantee of the airport. The purpose of this is to open up the whole process of flight operation guarantee through A-CDM and improve the efficiency and safety of airport operation.

[0038] Meteorological data plays a crucial role in airline operations. Severe weather often causes abnormal situations such as flight delays, cancellations, and diversions, which in turn affect flight safety and normalcy. Therefore, real-time monitoring and accurate forecasting of weather conditions enable airlines to detect and formulate corresponding measures as early as possible, which is a prerequisite for the smooth implementation of flight guarantee tasks. Real-time weather data reflects the current weather conditions at the airport and its surrounding areas. Weather data can be collected through various meteorological sensors deployed at the airport, but it is mainly supported by systems provided by the meteorological department. Through these professional systems, it can be specifically learned that the current temperature at the airport is 25 degrees Celsius, the wind speed is 5 meters per second, the wind direction is northeast, and the visibility is 10 kilometers. These values have an impact on aircraft takeoff and landing. In addition to real-time weather conditions, future weather forecast data provides guidance for subsequent operation plans. By accessing real-time weather and forecast weather information through the meteorological system API, that is, the application programming interface, corresponding preparations can be made in advance to reduce the possibility of large-scale flight delays. The API of the meteorological system can be called, and the information sent by the other party can be received in the form of data services. Through the API, the hourly weather conditions in the specified area for the next 24 hours can be detailedly understood. What kind of severe weather will occur at which time periods in the future. After obtaining these data, by comparing and analyzing them with flight data, it can be found which flights may have greater risks in the future. Through the above mechanism, risks can be arranged and avoided as early as possible, and the efficiency of airline operations can be improved. Obtaining meteorological data can provide information support for subsequent arrangements of operation guarantee plans. The purpose of doing this is to obtain the status and trend of the meteorological environment, evaluate the possible impact of the meteorological environment on the normal operation of flights, ensure the normal and safe operation of flights as much as possible under extremely adverse meteorological conditions, respond to and dispose of the risks brought by special weather in advance, and ensure that flights can complete transportation safely and smoothly.

[0039] The real-time location and status information of vehicles is crucial for airport ground operation management. Vehicles include special vehicles that provide various ground service support for flights at the airport, such as refueling trucks, shuttle trucks, tractors, de-icing trucks, etc. The location of the vehicle can be used as a reference for scheduling, and the spatial distribution of each vehicle can be understood and obtained in a timely manner to facilitate the efficiency of work assignment, save operating costs for the airport, and avoid waste of transportation resources. The status can help understand the current working status and real-time busyness of the vehicle. Intelligent scheduling can be carried out according to the spatial distribution of special vehicles at the airport to avoid uneconomical operation behaviors such as clustered parking of vehicles in some areas or long-distance scheduling. The airport can measure and plan the procurement scale of special vehicles at the airport according to actual conditions to ensure that each vehicle is fully utilized. At the same time, the service efficiency of service personnel in a certain area can be reversely assessed through the vehicle operation trajectory. Using the vehicle positioning system software development kit, the positioning status of each vehicle at the airport can be obtained, the specific location and current working status of the vehicle can be seen on the monitoring page, and the operation trajectory information of each vehicle can be queried over the past period of time. The obtained vehicle positioning data can reflect the spatial distribution and operation status of various transportation capacities at the airport. The purpose of this is to improve the operational efficiency of the airport's transport capacity, coordinate and deploy transport support personnel in a timely manner, avoid wasting the support resources of the entire airport, and enable each area to configure support resources as needed.

[0040] The embodiment of the present application integrates the flight schedule, flight dynamics and resource occupancy information of the A-CDM system, the real-time and future forecast data of the meteorological system, and the position status information of the vehicle positioning system for comprehensive correlation application. For example, the scheduled departure time of a certain flight is 10 a.m., and the weather forecast data shows that there will be thunderstorms around the airport during this period. Through the vehicle positioning system, it can be found that the support vehicle performing the flight support task is occupied by other flight support tasks. Based on the above integrated data, it can be inferred that this flight cannot obtain support resources on time, and will not take off on time due to the influence of thunderstorm weather. This will cause the actual departure time of the flight to be changed to 10:40, and the boarding gate used by the flight plan needs to be adjusted. At the same time, it will also cause all subsequent flight plans using this boarding gate and these support vehicles to be adjusted. And it is necessary to publish these change information through various channels as soon as possible, and deliver the information to passengers as soon as possible. In this way, airport managers can understand the operation support resources and constraints of each flight in advance, facilitate the global optimal operation scheduling plan, and avoid adverse effects on the travel of civil aviation passengers.

[0041] Furthermore, in the embodiments of the present application, the industrial Internet platform is used to achieve efficient data aggregation and integration, and a data quality monitoring mechanism is adopted to monitor and give early warnings to the data collection process in real time to ensure the accuracy, consistency, and reliability of the data. The industrial Internet platform plays a crucial role in the data integration layer. It is like an efficient information hub that aggregates data scattered in various formats in different corners into a unified data stream. This process is not just a simple accumulation of data but rather a series of complex and delicate operations that make the data orderly and usable. First of all, the platform needs to have strong data compatibility. This means that regardless of the data source, whether it is flight dynamic information in the A-CDM system, real-time weather data provided by the meteorological system, or vehicle location feedback from the vehicle positioning system, the industrial Internet platform can "understand" them. This depends on a variety of pre-set data interface protocols and conversion mechanisms on the platform.

[0042] For example, in the face of different database types, the platform may use ETL (Extract, Transform, Load) tools to extract data and convert the data into a unified data format within the platform by writing scripts adapted to different data sources. During the data aggregation process, the data quality monitoring mechanism begins to play a role. This mechanism is like a "guardian" of data quality, monitoring every link of data collection in real time. Data quality monitoring not only focuses on the data itself but also includes the monitoring of the data collection process. For example, if a large amount of data is missing or there are outliers in the data collected by a certain sensor due to a fault or signal interference, the data quality monitoring system can quickly detect this anomaly. For example, rules can be set: if a key indicator data, such as the temperature value read by a temperature sensor, is continuously missing for more than 5 time points, or the deviation between the estimated departure time and the actual departure time of a flight exceeds 30 minutes, the system will immediately issue a warning. This is not just a simple data comparison but a comprehensive application of a complex rule engine and anomaly detection algorithms.

[0043] The system validates each piece of incoming data through preset data quality rules. For example, the system checks the integrity of the data to ensure that no key fields are missing; checks the consistency of the data to ensure that the same information from different sources is consistent; checks the accuracy of the data by comparing historical data and business logic to discover and correct errors in the data; and also checks the timeliness of the data to ensure that the data can arrive and be updated on time. Once data quality issues are found, such as incorrect data formats, missing data, or data values outside the reasonable range, the monitoring mechanism will immediately trigger an alert. These alert messages can be sent via SMS, email, or integrated into the platform's alarm system to notify relevant data managers or operations engineers in a timely manner. The purpose of the alert is to enable a quick response to troubleshoot and fix the problem. For example, after receiving an alert, the staff may immediately check the status of the data source, such as whether the sensor is working properly, whether the interface service is responding, and whether the network connection is stable, or manually correct the incorrect data entries and record the problem logs and solutions in the system to form a knowledge base to avoid similar problems from occurring again. This can effectively prevent the spread and accumulation of problem data and reduce the impact on subsequent data analysis and model building. At a deeper level, this data quality monitoring mechanism not only discovers problems passively, but also supports the continuous improvement of data quality. By analyzing the alert information and tracking historical data, systematic problems in the data collection and processing process can be discovered, and then the data collection strategy and integration process can be optimized. For example, if it is found through analysis that a particular type of data often experiences delays, perhaps due to the inefficiency of the data transmission protocol, then a more efficient protocol can be considered. In this way, the accuracy, consistency, and reliability of the data are ensured, providing a high-quality data foundation for subsequent model building and application services. Each value and every fluctuation in the data can potentially become a key feature for the model to learn, helping the model to more accurately identify potential security risks and operation bottlenecks, triggering the warning mechanism according to the set rules to avoid potential accidents, and at the same time helping the business department to adjust resource allocation in a timely manner and improve operational efficiency.

[0044] Furthermore, the analysis model construction layer focuses on the security situation analysis model based on security data, with emphasis on the setting of warning indicators and thresholds. It analyzes the operation situation analysis model that accesses data such as weather, aircraft positions, and runways. The core is the calculation of key operation indicators and the establishment of operation warning rules. Specific example content: The establishment of the security situation analysis model first requires the definition and understanding of security data. Security data covers multiple aspects such as aircraft status, personnel operations, environmental factors, and management processes. For example, data such as the speed, altitude, and distance from obstacles during aircraft taxiing are crucial for evaluating flight safety. Also, the workload, fatigue level, and operation accuracy of tower personnel directly affect air traffic safety. In model construction, these complex and multi-dimensional security data need to be converted into quantifiable indicators. The extensiveness of security data collection is one of the keys to this business scenario. In the security field of airport operations, data sources are diverse, including not only various information systems but also data collected by various hardware. For another example, the judgment of various weather phenomena such as the magnitude of rainfall, the severity of icing, the time, location, and trend of thunderstorm weather, and snowfall weather, etc., all need to form real-time operation rules for safety through the collected data, so as to guide specific flight operations, vehicle driving, and aircraft position allocation. This can not only provide data basis for the airport management to make judgments and analyses but also provide necessary and effective information support for the relevant competent departments in the national security field. These security warning rules and security thresholds can be generated in real time and accurately, which can greatly improve efficiency and play an important role in effectively dealing with various airport security risks. In terms of data, in the event scenario of an aircraft approaching and landing, the real-time data information from the equipment on the runway and the facilities on both sides of the runway provides a basis for judging whether the landing is safe. The comprehensiveness of the collection of this security data also determines the reliability of later analysis. There is also the timely analysis of security data such as the real-time video of the cameras on the runway. These data can timely guide the degree of risk of aircraft landing and give an alarm reminder of whether the landing is safe in a timely manner. This process also involves the aggregation of a large amount of real-time data, video stream data, analysis data, a large amount of hardware facility data, and the collection of a large amount of management system data, which is an exponential expansion of the data volume.

[0045] The data also includes the discovery time of security hazards, the location of the discovered security hazards, the level of risk security events, the aspects and links involved, and the associated impacts, etc. From the security field, early warnings, rectification opinions, and implementation progress can be given in a timely manner.

[0046] The early warning mechanism of the security situation analysis model can specifically be the early warning of runway incursion events. Set a runway incursion distance threshold. For example, when it is detected that the distance between an unauthorized object and the runway is less than the safety threshold, such as 50 meters, the system determines that there is a potential runway incursion risk. On this basis, the system can set different early warning levels. For example, when the distance is between 50 meters and 100 meters, a yellow early warning is triggered to alert relevant personnel; when the distance is less than 50 meters, a red early warning is triggered, indicating that the situation is urgent and immediate action is required. The data support for such safety thresholds is also a very important technical aspect. Once the red early warning is triggered, the system will immediately notify relevant personnel such as tower controllers and runway safety officers through means such as audible and visual alarms and text messages to quickly handle potential runway incursion events and avoid accidents. Another benefit of this early warning mechanism is that such early warnings can effectively prevent similar accidents and emergencies.

[0047] In terms of the operation situation analysis model, modeling and analysis can be carried out for the key indicator of flight punctuality rate. The calculation of the flight punctuality rate involves the comparison of the actual departure time and the planned departure time of the flight. First, through system docking, the real-time departure information of each flight can be collected. The specific data of the flight punctuality rate can also include the actual departure time and arrival time of the flight. Suppose there are 300 scheduled departure flights at an airport throughout the day. After comparing the actual departure time and arrival time of each flight at the airport throughout the day with the flight plan time pre-entered in the system through a data model, the result is compared in real time to obtain 45 delayed flights, and the flight punctuality rate is obtained as 85%. At the same time, external factors affecting the flight punctuality rate need to be considered, such as weather conditions. When the airport meteorological data shows bad weather such as thunderstorms and fog, the real-time release rate of the airport will change accordingly according to information such as weather warning data. These changes play a very important guiding role in safety assessment. The system can set different weather conditions, perform data correlation calculations for each system through interfaces, deduce the data of the flight plan and make timely adjustments. Through this situation, the flight delay rate caused by bad weather can be reduced. And through historical data analysis, the flight punctuality rates of different months and different routes can be statistically analyzed, and the trend of future flight punctuality rates can be predicted. For example, June is a season with frequent thunderstorms, and the estimated proportion value of flights that need to be delayed due to being affected during these periods is preset for comparison with the actual situation.

[0048] The utilization rate of aircraft positions is also an important indicator that needs attention. It can be detailedly divided into inner-field and outer-field positions, or can be distinguished according to the service capacity range of positions, divided into positions that can accept the landing and support of all aircraft types, or positions that can only accept the landing and support of some types of aircraft. At the same time, it is also necessary to consider whether it is a position for berthing and maintenance, or a dedicated position for cargo aircraft, or a jet bridge position for boarding gates, etc. The utilization rate of positions involves the reasonable allocation of airport resources, and this aspect is related to the specific operation. Taking an airport as an example, it has 100 positions. Through real-time data collection, the system can count the number of positions that are currently occupied. Assuming that 80 positions are currently occupied, the utilization rate of positions is 80%. Further analysis shows that the system can count the average occupancy time of each position and find that some positions are idle for a long time. For example, these positions cannot be used by Boeing 737 passenger aircraft, while some other positions are used too frequently. Therefore, advance planning is needed to adjust services such as the docking of Boeing 737 aircraft expected to arrive and depart to positions that can meet this type. According to these analysis results, it can be improved by pre-planning the position arrangement, thereby being able to significantly increase the utilization rate of positions and the service guarantee for docking aircraft.

[0049] Based on this, the system can establish early warning rules. When the utilization rate of positions exceeds 90%, a yellow early warning is triggered to prompt the dispatcher to pay attention to the situation of position resources; when the utilization rate of positions exceeds 95%, a red early warning is triggered, indicating that the position resources are tense and immediate position adjustment or other measures need to be taken, such as temporarily adjusting a remote position to a near position to ensure the normal operation of flights. In terms of technical effects, reasonable position arrangement and dispatching can maximize the use of each position, ensure the normal operation of as many aircraft as possible, reduce the waiting time, and improve safety.

[0050] Furthermore, the embodiments of the present application monitor the security status of the airport in real time, which is like the nervous system of the airport and needs to work highly sensitively and continuously. For example, the airport can be regarded as a huge city, in which there are countless cameras, sensors and other monitoring devices. These devices work around the clock, just like the eyes and ears of the city, observing and listening to every corner at any time. The cameras can identify abnormal behaviors, such as someone trying to climb over the fence or loitering in the restricted area, and the sensors can detect whether dangerous goods enter the airport or whether the plane deviates from the normal route during landing. The images and data captured by these devices in real time will be immediately transmitted to the data center for analysis. For example, on a certain day, a suitcase was left unclaimed for a long time and was abandoned in a corner of the waiting hall. The X-ray machine at the security checkpoint found that the image of this suitcase was very suspicious. This information was immediately transmitted to the security monitoring center. Through the high-definition camera, security personnel can see the appearance of the suitcase and the surrounding situation, and the image analysis software in the monitoring center will analyze the behaviors of the people captured by the camera to observe whether someone deliberately avoids this suitcase or shows abnormal nervousness nearby. The purpose of security monitoring is not only to detect abnormal situations, but more importantly, to identify whether these abnormalities indicate real dangers so as to take countermeasures, which is similar to making advance predictions to reduce security accidents and improve safety and reliability. The monitoring of the operation situation is a comprehensive physical examination of the airport operation efficiency.

[0051] Through various sensors and data interfaces, the system can obtain key information such as flight takeoff and landing information, runway and taxiway usage, and apron occupancy status in real time. For example, on a busy morning, due to foggy weather, multiple flights were delayed. The system connected to the meteorological data interface, obtained the information that the visibility at the airport was below the takeoff and landing standards in real time, and combined with the flight schedule to calculate the number of affected flights and the estimated delay time. At the same time, the system also detected that the apron occupancy rate was too high, and incoming flights would have no apron available. This information was immediately obtained by the operation staff. Using the real-time collected operation data, the system can calculate key indicators such as flight punctuality rate and taxiing time. For example, through statistical analysis, it was found that the average taxiing time of flights in the recent week increased by 5 minutes compared with usual, and it was concentrated in the morning peak period. Further analysis of the taxiing route found that it was mainly due to the insufficient number of open taxiways, resulting in aircraft queuing. This information was immediately reported to the tower, and the tower then opened some less frequently used taxiways through scheduling to speed up the turnover of taxiways and improve the push-out efficiency of flights. Real-time update of flight information and provision of reasonable apron positions, timely resolution of safety and non-safety incidents to improve the work efficiency of the airport and the flight operation guarantee level. Once an anomaly is detected, an early warning message is immediately sent, which means that through preset safety and operation parameters, if the real-time monitoring information is detected not to meet the preset information, the system triggers an alarm, generates an alarm report and notifies the designated personnel for timely handling. The system is built-in with rich safety operation analysis and early warning models, and relevant alarm thresholds are set. Here, taking safety as an example, it is set that when a large number of unqualified events suspected of dangerous goods continuously occur at a certain security checkpoint within a unit time, an alarm is issued. Suppose at a certain security checkpoint, within 5 minutes, more than 2 passengers' bags are detected with lighters, which exceeds the set safety threshold. The background conducts modeling analysis and processing through the set analysis model, determines that this is an abnormal situation, generates an early warning information report, pushes the event to the site for inspection, and reports the information. These early warning reports are reminded to the on-duty personnel through on-site equipment to check whether an emergency or non-safe situation has occurred. For example, when the background management personnel check the report, they find that several security checks for flights to the northwest on the same day are not passed, and the dangerous goods found are detonators. This is probably a certain degree of danger, and this information is reported to the public security department for further processing. Multiple notification methods ensure that information can be quickly and accurately conveyed to the hands of every relevant person. The purpose of supporting the integration of multiple notification methods is to achieve a more efficient information reach efficiency. For example, when the system detects that there is a foreign object intrusion in the flight area and there is a risk of bird strike, the system immediately marks the safety status of the relevant area as a warning.Meanwhile, this piece of information is immediately sent to the APP of the on-duty personnel on site for voice alarm and red-letter prompt, informing them of what kind of emergency situation may occur in which area. The on-duty personnel on site must immediately go to handle and check, and conduct review or closure. The system will push the relevant detailed detection information to the work email boxes of the person in charge of the day's operation and the on-site disposal personnel in the form of a report. And relevant managers will be reminded to check the email in the form of a text message.

[0052] Furthermore, the situation analysis and display function is an important part of the airport safety operation monitoring and early warning system. Through the comprehensive analysis of a large amount of safety and operation data, the system can comprehensively evaluate the safety situation and operation status of the airport, and present the analysis results in an intuitive way, providing strong support for management decision-making. In terms of safety situation analysis, the system comprehensively considers various safety risk factors of the airport, such as aircraft failures, runway foreign objects, extreme weather, human errors, etc., and establishes a multi-dimensional safety assessment model. Using big data analysis technology, it processes and correlates various safety data in real time, and dynamically evaluates the safety risk level of the airport. For example, when the number of runway foreign object alarms suddenly increases within a short period of time, the system can judge that the risk level of runway foreign objects has increased, and prompt the management personnel to pay attention through a red warning sign. In terms of operation situation analysis, the system focuses on core operation indicators such as flight punctuality rate, departure punctuality rate, and apron utilization rate. Through the integrated analysis of data such as flight schedules, apron resource tables, and aircraft dispatching information, the system can calculate various operation indicators in real time and compare them with historical data of the same period to intuitively display the change trend of the operation situation. When an abnormal fluctuation occurs in a certain indicator, the system can automatically mark a warning and generate an analysis report to help management personnel quickly locate the cause of the problem. The visual display of the situation analysis results is another highlight of the situation analysis and display function. The system adopts advanced visualization technology to convert complex analysis results into simple and intuitive charts and maps for presentation, greatly reducing the difficulty of information acquisition. In the overall situation overview large screen, the overall safety situation and operation situation of the airport are displayed in real time in the form of a dashboard, and red, yellow, and green warning signs are set. Management personnel can clearly understand the overall situation of the airport and quickly respond to emergencies. In addition, the visual display also supports multi-dimensional data drilling and correlation analysis. Users can select conditions such as time range and area range according to needs to deeply analyze the safety operation situation in a specific period or area. And when users find an abnormality in a certain area on the overall situation overview large screen, they can directly call up the real-time monitoring video of that area through the drilling function to understand the on-site situation in the first time and improve the efficiency of emergency disposal. In short, through the data-driven analysis model and user-friendly visual design, the situation analysis and display function enables airport managers to comprehensively and intuitively understand the airport safety operation situation, effectively improve the safety management level and operation efficiency, and escort the smooth operation of the airport.

[0053] Furthermore, the core of the knowledge management and training function in the application service layer lies in the efficient utilization of existing resources, the stimulation of employees' potential, and ultimately the continuous optimization of the entire airport operation safety. First of all, integrating the knowledge and experience related to safety management can be understood as constructing a huge and dynamically updated knowledge base, systematically collecting, classifying, tagging, and storing all aspects of airport safety operations, such as rules and regulations, operation procedures, emergency plans, accident case analyses, etc. For example, in terms of safety regulations, the knowledge base should contain all the latest safety regulations issued by the Civil Aviation Administration and be organized by chapter. For operation procedures, the knowledge base includes all the operation SOPs (standard operation procedures) that employees need to follow in each position, accompanied by flowcharts, such as the baggage handling process, the operation process of vehicles in the airfield, the emergency medical rescue service specifications, etc., and also records historical accident lessons. All of these will exist in the system in electronic form, and employees can quickly find the required content through keyword search, such as entering the keyword "special vehicles" in the knowledge base, or by browsing the hierarchical directory, ensuring the comprehensiveness and usability of the information. In addition, it is necessary to ensure the timely update of the knowledge base to keep it updated in real time with the latest regulations and cases.

[0054] Secondly, providing online training and learning resources is a practical process of transforming knowledge into employees' capabilities. The system can utilize the achievements of the previous knowledge base construction and convert them into various training and learning resources. This requires us to not only provide traditional reading materials but also apply advanced online education technologies. For example, we can develop web-based multimedia courses, which include interactive learning modules such as animated simulations with voice explanations, quizzes interspersed with multiple-choice questions, and various learning materials. The platform can also embed training modules supported by virtual reality (VR) or augmented reality (AR) technologies. Through these scenarios, the training effect can be effectively guaranteed. Taking the cargo handling training course as an example, the system details the dangerous goods handling process, safety handling rules for special goods (such as large-sized goods and dangerous goods), and practical operation videos through videos and texts. Employees can use the VR scenario simulator to repeatedly practice dealing with emergencies. This enables employees to learn knowledge in a more immersive way and strengthen the consolidation effect in practice. Further, using data analysis to evaluate the training effect is a key link in measuring the input-output ratio of training. The system should track the learning trajectories of each employee, including which courses they have completed, test scores for each part, learning duration, number of practice operations, etc. Through the collection and analysis of these data, the effectiveness of the training courses can be evaluated, the proficiency of individuals in certain operations or knowledge can be evaluated, the difficulties in training can be found, the questions that trainees often answer wrongly can be identified, and the nodes where they stay too long in the course can be found. These data are all valuable feedback. For example, in a training on the operating procedures of the baggage sorting system, most employees scored low in the module related to the emergency handling process of the equipment, and the average answering time was 10% higher than normal, and they stayed too long at this point. This indicates that everyone is relatively weak in this aspect. At this time, we can consider increasing the teaching hours in this area and also conducting more exercises and simulations on this part in the future.

[0055] Finally, formulating a personalized training plan based on the learning situation of employees is the guarantee for achieving individualized teaching and precise improvement. Data is not only used for evaluation but also to formulate more targeted learning content according to the strengths and weaknesses of each trainee. For example, for those employees who frequently make mistakes in emergency incident handling response training, the system can mark their error points and automatically push relevant enhanced learning plans, including materials for re-studying the operation manual, case studies of similar incident handling processes, and targeted simulation operation exercises. For those who deal with data for a long time, some chart-based and visualized materials can be focused on being pushed to assist in strengthening understanding. In addition, for employees with strong learning abilities and who can quickly accept new knowledge, the system can also provide more advanced courses so that they can quickly master more professional skills. Such data analysis is objective and targeted advice based on data. Such a training method is not like simply releasing information unidirectionally, but an interactive and circular teaching model. It can improve the technical level of employees and also greatly enhance the management efficiency of the enterprise.

[0056] In order to ensure the system security of the aviation transportation big data operation safety monitoring and early warning management platform, the embodiments of this application have taken various security guarantee measures. First, sensitive data is encrypted to ensure its security during transmission and storage. Symmetric encryption algorithms such as AES or asymmetric encryption algorithms such as RSA can be used to encrypt sensitive data. For example, for data containing passengers' personal information, the AES-256-bit encryption algorithm can be used, with a key length of 256 bits, the encryption mode using the CBC mode, and the padding method being PKCS7. In this way, even if the data is intercepted, it cannot be decrypted to obtain sensitive information without the key.

[0057] Secondly, a strict access control mechanism is established to allocate different access rights according to the roles and permissions of users. The Role-Based Access Control (RBAC) model can be adopted to divide users into different roles, such as system administrators, security administrators, operation and maintenance personnel, etc. Each role has different permissions. For example, system administrators have the highest permissions and can access all functions and data of the system; security administrators can only access functions and data related to security management; ordinary users can only access specific authorized functions and data. Through strict access control, unauthorized users can be prevented from accessing sensitive data and functions, reducing the risks of data leakage and system intrusion. Finally, the operation logs of the system are recorded and audited to detect and handle security incidents in a timely manner. A centralized log management system can be used to collect, store, and analyze logs distributed on different servers and applications in a unified manner. The log content should include key information such as user ID, IP address, operation time, operation type, operation object, etc. Through real-time monitoring and analysis of the logs, suspicious operations and abnormal behaviors can be detected in a timely manner. When a security incident is discovered, the time, location, and responsible person of the incident can be quickly located, and corresponding handling measures can be taken, such as disconnecting suspicious connections, freezing accounts, and tracing data operations. A perfect security audit function can minimize the impact of security incidents and provide strong evidence for post-event accountability. In short, data encryption, access control, and security audit are the three key measures to ensure the security of the operation safety monitoring and early warning management platform system for air transportation big data. By adopting industry-standard encryption algorithms, establishing a strict access control system, and improving the security audit mechanism, the security of the system can be guaranteed in all aspects, providing a solid foundation for the stable operation of the platform.

[0058] It should be noted that in this application, the terms "including", "comprising", or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device including a series of elements not only includes those elements but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article, or device. Without further limitations, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article, or device including that element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of this application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may also be added, omitted, or combined. Additionally, the features described with reference to certain examples may be combined in other examples.

[0059] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative rather than restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them fall within the protection scope of the present application.

Claims

1. An aviation transportation big data operation safety monitoring and early warning management platform, characterized in that: The platform adopts a distributed microservice architecture, including a data collection layer, a data integration layer, a model building layer, an application service layer, and a display layer; Among them, the data collection layer is used to collect data in the air transportation process; the data integration layer cleans, converts and integrates the data in the air transportation process; the model building layer establishes data-driven general models and industry models; the application service layer provides safety monitoring, early warning, recording, evaluation and situation analysis functions based on models and data; the display layer displays the monitoring results, early warning information and situation analysis content through visualization technology.

2. The aviation transportation big data operation safety monitoring and early warning management platform according to claim 1, characterized in that: The data collected by the data collection layer during the air transportation process include flight plans, dynamics and resource usage data obtained in real time through the A-CDM system interface, real-time and future weather forecast data obtained through the meteorological system API, and real-time vehicle location and status information obtained using the vehicle positioning system SDK.

3. The aviation transportation big data operation safety monitoring and early warning management platform according to claim 1, characterized in that: The data integration layer realizes data aggregation and integration through the industrial Internet platform, and establishes a data quality monitoring mechanism to conduct real-time monitoring and early warning of the data collection process.

4. The aviation transportation big data operation safety monitoring and early warning management platform according to claim 1, characterized in that: The model building layer establishes a safety situation analysis model based on the data collected during the air transportation process, and issues warning information in a timely manner when an abnormality occurs by setting warning indicators and thresholds; accesses weather, aircraft positions and runway data, establishes an operation situation analysis model, processes and analyzes operation data in real time, calculates key operation indicators and establishes operation warning rules.

5. The aviation transportation big data operation safety monitoring and early warning management platform according to claim 4, characterized in that: The security monitoring and early warning functions of the application service layer can monitor the security and operation status of the airport in real time, issue early warning information immediately when an abnormality occurs, and support notification of relevant personnel via SMS, email and / or APP push.

6. The aviation transportation big data operation safety monitoring and early warning management platform according to claim 4, characterized in that: The situation analysis function of the application service layer is used to comprehensively analyze the security situation and the operation situation to form a situation analysis result, and the situation analysis result is displayed through the display layer using visualization technology.

7. The aviation transportation big data operation safety monitoring and early warning management platform according to claim 1, characterized in that: Through the knowledge management and training functions of the application service layer, the knowledge and experience of security management are integrated, online training and learning resources are provided to employees, the training effect is evaluated through data analysis, and personalized training plans are formulated according to the learning situation of employees.

8. The aviation transportation big data operation safety monitoring and early warning management platform according to claim 1, characterized in that: The platform achieves system security through data encryption and desensitization, access control and security auditing, encrypts sensitive data to ensure the security of data transmission and storage, establishes an access control mechanism, assigns different access rights according to user roles and permissions, records and audits the system's operation logs, and discovers and handles security incidents.

Images