A method, apparatus, equipment and medium for processing digital health data in airport operations.

Abstract

This application discloses a method, apparatus, equipment, and medium for processing digital health data of airport operations, relating to the field of airport operation management technology, and is used to solve technical problems such as poor dynamic quantification capabilities and risk prediction and intervention capabilities in existing technologies. The method includes: in the data analysis layer, determining the Airport Operational Health (AOH) index at each level of a preset three-level index system based on processed airport operation data; wherein the preset three-level index system includes equipment-level, regional-level, and global-level; in the prediction and early warning closed-loop layer, using the global-level AOH index for trend prediction to determine whether there is a risk at the airport; if a risk is determined, an intervention process is triggered. Therefore, this application can achieve real-time quantitative assessment and proactive decision-making of airport operation status through the three-level index system and predictive intervention technologies.

Description

Technical Field

[0001] This application relates to the field of airport operation management technology, and in particular to a method, apparatus, equipment and medium for processing digital health data of airport operations. Background Technology

[0002] Currently, airport operation management mainly relies on distributed monitoring systems, such as flight management systems, passenger security screening systems, and baggage sorting systems. For these distributed monitoring systems, traditional technologies often use static index assessments, post-event statistical reports, and isolated system monitoring to evaluate airport operations. However, these traditional technologies clearly have the following problems:

[0003] (1) Lack of multi-level dynamic quantification capability: The existing airport operation assessment relies on a static index system. Therefore, it cannot reflect the dynamic evolution of the airport's operational health status in real time. In particular, the quantification accuracy is insufficient in high-density operation scenarios, making it difficult to support refined decision-making.

[0004] (2) Lack of scenario adaptability: The existing index weights rely on fixed weights set by human experience. Therefore, in special scenarios such as severe weather and peak passenger flow, the fixed weight allocation cannot highlight the health impact of key areas, causing the health index to deviate from the actual operating status, reducing the reference value for decision-making, and especially unable to cope with the priority adjustment needs of emergencies.

[0005] (3) Lack of risk prediction and intervention capabilities: The existing monitoring system relies on post-event statistical reports. Therefore, it cannot predict operational risks through time series models, nor can it automatically trigger resource scheduling intervention, resulting in a lag in risk response and making it difficult to upgrade the management model from "passive response" to "proactive prevention". Summary of the Invention

[0006] The main purpose of this application is to provide a method, apparatus, equipment and medium for processing digital health of airport operations, in order to solve the technical problems of poor dynamic quantification capabilities and risk prediction and intervention capabilities in existing technologies.

[0007] On the one hand, a method for processing digital health of airport operations is provided, the method comprising:

[0008] In the data analysis layer, based on the processed airport operation data, the Airport Operation Health (AOH) index for each level in the preset three-level index system is determined; wherein, the preset three-level index system includes equipment level, regional level and global level, the regional level AOH index is obtained based on the equipment level AOH index, and the global level AOH index is obtained based on the regional level AOH index;

[0009] In the prediction and early warning closed-loop layer, the global AOH index is used to predict trends and determine whether there are risks at the airport;

[0010] If a risk is identified at the airport, an intervention process is triggered.

[0011] Optionally, the step of determining the Airport Operational Health (AOH) index for each level of the preset three-level index system based on the processed airport operation data includes:

[0012] The threshold interval mapping method is used to evaluate various airport operating parameters and obtain multiple AOH indices at the equipment level. The operating parameters include taxiing time, number of shuttle buses, number of aircraft stands occupied, check-in queuing time, security check queuing time, passenger saturation, number of people queuing for taxis, parking space occupancy rate, and traffic flow.

[0013] For any given preset area, multiple AOH indices at the device level under that preset area are weighted and aggregated using a fixed weight to obtain the AOH index of that preset area; wherein, the preset area includes the flight area, the terminal area, and the public area;

[0014] A global AOH index is obtained by weighting and aggregating the AOH indices of each preset region using dynamic weights; wherein the dynamic weights are dynamically adjusted by adjustment strategies matched from the rule base.

[0015] Optionally, the step of weighting and aggregating the AOH indices of each preset region using dynamic weights to obtain a global AOH index includes:

[0016] Determine whether a preset event has occurred; wherein the preset events include severe weather, peak passenger flow, and equipment malfunction;

[0017] If a preset event is determined to occur, then a corresponding adjustment strategy is matched from the rule base based on the preset event.

[0018] The initial weights of each preset region are dynamically adjusted according to the adjustment strategy to obtain the adjusted weights of each preset region.

[0019] Normalize the adjusted weights of each preset region to obtain the dynamic weights of each preset region.

[0020] By using the dynamic weights of each preset region, the AOH index of each preset region is weighted and aggregated to obtain the global AOH index.

[0021] Optionally, the step of using a global-level AOH index for trend prediction to determine whether an airport poses a risk includes:

[0022] The global historical AOH index sequence and real-time feature vector are input into the trained LSTM model to predict trends and obtain the predicted health index value.

[0023] Determine whether the predicted health index value is less than a preset health index threshold;

[0024] If the predicted health index value is determined to be less than the preset health index threshold, then the airport is determined to be at risk.

[0025] Optionally, the step of triggering the intervention process includes:

[0026] For any preset region, determine whether the AOH index of the preset region is less than a preset region-level index threshold;

[0027] If it is determined that the AOH index of any preset region is less than the preset region-level index threshold, then the corresponding intervention measures are matched from the action library;

[0028] According to the intervention measures, intervention is triggered in any of the preset areas.

[0029] Optionally, after triggering the intervention process, the method further includes:

[0030] In the data analysis layer, the AOH index at each level of the preset three-level index system is redefined based on the reprocessed airport operation data.

[0031] In the prediction and early warning closed-loop layer, the newly determined global AOH index is used again for trend prediction to obtain a new health index prediction value;

[0032] The new health index predictions and corresponding interventions are recorded as an intervention log, and the rule base is updated accordingly.

[0033] Optionally, before determining the AOH index for each level in the preset three-level index system based on the processed airport operation data, the method further includes:

[0034] In the data acquisition layer, data is collected from multiple airport management systems included in the data source layer to obtain raw airport operation data;

[0035] In the data governance layer, the original airport operation data is processed to obtain the processed airport operation data; wherein, the processing includes removing invalid values, data filtering, and data standardization.

[0036] On the one hand, an airport operation digital health processing device is provided, the device comprising:

[0037] The health index determination unit is used in the data analysis layer to determine the airport operation health (AOH) index at each level of a preset three-level index system based on the processed airport operation data. The preset three-level index system includes equipment level, regional level, and global level. The regional level AOH index is obtained based on the equipment level AOH index, and the global level AOH index is obtained based on the regional level AOH index.

[0038] The trend prediction and intervention unit is used to predict trends using the global AOH index in the prediction and early warning closed loop layer to determine whether there is a risk at the airport.

[0039] The trend prediction and intervention unit is also used to trigger an intervention process if it is determined that there is a risk at the airport.

[0040] On one hand, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the methods described above.

[0041] On the one hand, a storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement any of the methods described above.

[0042] Compared with the prior art, the beneficial effects of this application are as follows:

[0043] In this application, when conducting management assessments of airport operations, firstly, in the data analysis layer, the Airport Operational Health (AOH) index at each level of a pre-defined three-level index system can be determined based on the processed airport operation data. This pre-defined three-level index system includes equipment-level, regional-level, and global-level indices. The regional-level AOH index is obtained based on the equipment-level AOH index, and the global-level AOH index is obtained based on the regional-level AOH index. Then, in the prediction and early warning closed-loop layer, the global-level AOH index can be directly used for trend prediction to determine whether the airport faces risks. Furthermore, if the airport is determined to have risks, an intervention process can be triggered.

[0044] Based on this, this application utilizes a three-tiered indicator system (equipment-regional-global) to form a progressive airport quantitative model. This model breaks through the limitations of traditional static assessments, achieving real-time quantification of airport operational health status from 0 to 100 points for the first time. It supports millisecond-level situational awareness, providing precise data support for refined decision-making in complex scenarios and significantly improving the scientific nature and timeliness of airport operation management. Furthermore, since a global-level AOH index is used for trend prediction and automatic intervention triggering logic, predictive intervention can be achieved, significantly reducing the incidence of operational risks, improving resource utilization efficiency and passenger service experience, and promoting the transformation of airport management towards proactive prevention. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0046] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of this application;

[0047] Figure 2 A schematic diagram of an airport operation digital health processing method provided in an embodiment of this application;

[0048] Figure 3 A schematic diagram of a three-level index system provided in an embodiment of this application;

[0049] Figure 4 An overall architecture diagram of airport operation digital health processing provided in this application embodiment;

[0050] Figure 5 A schematic diagram of a predictive intervention closed loop provided in an embodiment of this application;

[0051] Figure 6 A schematic diagram of the dynamic weight adjustment mechanism provided in the embodiments of this application;

[0052] Figure 7 This is a schematic diagram of an airport operation digital health processing device provided in an embodiment of this application.

[0053] The diagram is labeled as follows: 10-Airport Operations Digital Health Processing Equipment, 101-Processor, 102-Memory, 103-I / O Interface, 104-Database, 70-Airport Operations Digital Health Processing Device, 701-Health Index Determination Unit, 702-Trend Prediction and Intervention Unit, 703-Data Acquisition and Processing Unit. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. Unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that shown here.

[0055] Currently, airport operation management mainly relies on distributed monitoring systems, such as flight management systems, passenger security screening systems, and baggage sorting systems. For these distributed monitoring systems, traditional technologies often use static index assessments, post-event statistical reports, and isolated system monitoring to evaluate airport operations. However, these traditional technologies clearly have the following problems:

[0056] (1) Lack of multi-level dynamic quantification capability: The existing airport operation assessment relies on a static index system. Therefore, it cannot reflect the dynamic evolution of the airport's operational health status in real time. In particular, the quantification accuracy is insufficient in high-density operation scenarios, making it difficult to support refined decision-making.

[0057] (2) Lack of scenario adaptability: The existing index weights rely on fixed weights set by human experience. Therefore, in special scenarios such as severe weather and peak passenger flow, the fixed weight allocation cannot highlight the health impact of key areas, causing the health index to deviate from the actual operating status, reducing the reference value for decision-making, and especially unable to cope with the priority adjustment needs of emergencies.

[0058] (3) Lack of risk prediction and intervention capabilities: The existing monitoring system relies on post-event statistical reports. Therefore, it cannot predict operational risks through time series models, nor can it automatically trigger resource scheduling intervention, resulting in a lag in risk response and making it difficult to upgrade the management model from "passive response" to "proactive prevention".

[0059] Based on this, this application provides an airport operation digital health processing method. In this method, firstly, in the data analysis layer, the airport operation health (AOH) index at each level of a preset three-level index system can be determined based on the processed airport operation data. The preset three-level index system includes equipment-level, regional-level, and global-level. The regional-level AOH index is obtained based on the equipment-level AOH index, and the global-level AOH index is obtained based on the regional-level AOH index. Then, in the prediction and early warning closed-loop layer, the global-level AOH index can be directly used for trend prediction to determine whether there is a risk at the airport. Furthermore, if it is determined that there is a risk at the airport, an intervention process can be triggered. Based on this, this application utilizes a three-tiered indicator system (equipment-regional-global) to form a progressive airport quantitative model. This model breaks through the limitations of traditional static assessments, achieving real-time quantification of airport operational health status from 0 to 100 points for the first time. It supports millisecond-level situational awareness, providing precise data support for refined decision-making in complex scenarios and significantly improving the scientific nature and timeliness of airport operation management. Furthermore, since a global-level AOH index is used for trend prediction and automatic intervention triggering logic, predictive intervention can be achieved, significantly reducing the incidence of operational risks, improving resource utilization efficiency and passenger service experience, and promoting the transformation of airport management towards proactive prevention.

[0060] After introducing the design concept of the embodiments of this application, the following is a brief introduction to the application scenarios to which the technical solutions of the embodiments of this application can be applied. It should be noted that the application scenarios described below are only for illustrating the embodiments of this application and are not intended to limit the scope. In specific implementation, the technical solutions provided by the embodiments of this application can be flexibly applied according to actual needs.

[0061] like Figure 1 The diagram shown is an application scenario illustration provided by an embodiment of this application. This application scenario may include an airport operation digital health processing device 10.

[0062] The airport operation digital health processing device 10 can be used for health diagnosis and risk prediction of airport operations. For example, it can be an in-vehicle computer, a personal computer (PC), a server, or a laptop. The airport operation digital health processing device 10 may include one or more processors 101, memory 102, I / O interfaces 103, and a database 104. Specifically, the processor 101 can be a central processing unit (CPU) or a digital processing unit, etc. The memory 102 can be volatile memory, such as random-access memory (RAM); the memory 102 can also be non-volatile memory, such as read-only memory, flash memory, hard disk drive (HDD), or solid-state drive (SSD); or the memory 102 can be any other medium capable of carrying or storing desired program code in the form of instructions or data structures that can be accessed by a computer, but is not limited thereto. The memory 102 can be a combination of the above-mentioned memories. The memory 102 can store some program instructions of the airport operation digital health processing method provided in the embodiments of this application. When these program instructions are executed by the processor 101, they can be used to implement the steps of the airport operation digital health processing method provided in the embodiments of this application, so as to solve the technical problems of poor dynamic quantification capability and risk prediction intervention capability in the prior art. The database 104 can be used to store various operating parameters, raw airport operation data, processed airport operation data, AOH indices at all levels, and intervention logs involved in the scheme provided in the embodiments of this application.

[0063] In this embodiment, the airport operation digital health processing device 10 can obtain airport operation management instructions through the I / O interface 103. Then, the processor 101 of the airport operation digital health processing device 10 will solve the technical problems existing in the prior art, such as poor dynamic quantification capability and risk prediction intervention capability, according to the program instructions of the airport operation digital health processing method provided in this embodiment in the memory 102. In addition, various operating parameters, raw airport operation data, processed airport operation data, AOH indices at all levels, and intervention logs can be stored in the database 104.

[0064] Of course, the methods provided in the embodiments of this application are not limited to... Figure 1 The application scenarios shown can also be used in other possible scenarios, and this application embodiment does not impose any limitations. Figure 1The functions that the various devices in the application scenarios shown can achieve will be described in subsequent method embodiments, and will not be elaborated on here. Below, the methods of the embodiments of this application will be described in conjunction with the accompanying drawings.

[0065] like Figure 2 The diagram shown is a flowchart of an airport operation digital health processing method provided in an embodiment of this application. This method can... Figure 1 The airport operates digital health processing equipment 10 to perform this process. The specific process is described below.

[0066] Step 201: In the data analysis layer, based on the processed airport operation data, determine the Airport Operation Health (AOH) index for each level in the preset three-level index system.

[0067] In this application, as Figure 3 The diagram illustrates a three-level index system provided in this application. The preset three-level index system includes equipment-level, regional-level, and global-level indices. The regional-level Airport Operation Health (AOH) index is obtained based on the equipment-level AOH index, and the global-level AOH index is obtained based on the regional-level AOH index. Therefore, this application can provide a complete assessment system for airport operation management from micro to macro levels through a hierarchical abstraction from equipment-level, regional-level to global-level, and achieve precise quantification of airport operation health status.

[0068] To achieve real-time quantitative assessment and proactive decision-making regarding airport operational status, this application adopts a hierarchical design approach for the overall airport assessment, such as... Figure 4 The diagram shown is an overall architecture diagram of airport operation digital health processing provided in this application embodiment, which consists of six parts from bottom to top: data source layer, data acquisition layer, data governance layer, data analysis layer, data application layer, and prediction and early warning closed loop layer.

[0069] Based on this, before determining the AOH index for each level of the pre-set three-level index system according to the processed airport operation data, such as Figure 4 As shown, various preparatory work is also required for the data source layer, data acquisition layer, and data governance layer.

[0070] Specifically, firstly, in the data source layer, 21 heterogeneous data systems, such as the flight management system, passenger security check system, baggage sorting system, and parking management system, can be integrated. These heterogeneous data systems cover real-time streaming data (e.g., shuttle bus GPS coordinates) and historical data (e.g., aircraft stand occupancy records).

[0071] Then, in the data acquisition layer, data can be collected from multiple airport management systems included in the data source layer to obtain raw airport operation data. During the acquisition process, the data from each management system can be classified and processed. For example, the real-time acquisition module can obtain second-level data (real-time streaming data) through ESB / MQ, while the non-real-time acquisition module can synchronize historical data periodically through WebService. All data is decoupled and transmitted through message middleware to ensure high concurrency processing capabilities.

[0072] Next, in the data governance layer, the raw airport operation data can be deeply processed to obtain processed airport operation data. This processing includes data validation to remove invalid values ​​(e.g., abnormal passenger numbers due to video obstruction), data filtering according to business rules (e.g., data from specific airlines), and data standardization to unify units and formats (e.g., converting queue times to minutes per person). Then, the processed airport operation data can be categorized and stored according to five major themes: operation, service, security, transportation, and logistics, for easy retrieval.

[0073] Furthermore, after the preparation work is completed, the AOH index at each level of the preset three-level index system can be determined directly in the data analysis layer based on the processed airport operation data.

[0074] Step 202: In the prediction and early warning closed-loop layer, the global AOH index is used to predict trends and determine whether there is a risk at the airport.

[0075] Specifically, such as Figure 5 The diagram illustrates a predictive intervention loop provided in this application. First, a global-level historical AOH index sequence and real-time feature vectors can be input into a trained Long Short-Term Memory (LSTM) network model for trend prediction to obtain a predicted health index value. For example, a global-level historical AOH index sequence (e.g., [85, 83, 82, 80, 79]) and real-time features (e.g., a 20% increase in check-in queues and a 15% increase in shuttle bus demand) from the past hour can be input into the trained LSTM model. This trained LSTM model contains 128 memory units and can capture long-term dependencies in the time series through a gating mechanism to output the predicted AOH value for the next 30 minutes. Furthermore, in this application, the prediction process of the trained LSTM model can be represented by the following prediction calculation formula:

[0076]

[0077] in, This is a predicted health index value for the next 30 minutes. is the global historical AOH index sequence, is the real-time feature vector.

[0078] Then, it can be determined whether the predicted value of the health index is less than the preset health index threshold.

[0079] Finally, if it is determined that the predicted value of the health index is less than the preset health index threshold, it can be determined that there is a risk at the airport. For example, if the predicted value of the health index is 78.5 points and the preset health index threshold is 80 points, then it can be determined that there is a risk at the airport, thereby achieving early risk identification. On the contrary, if it is determined that the predicted value of the health index is not less than the preset health index threshold, the airport will continue to be monitored.

[0080] Step 203: If it is determined that there is a risk at the airport, trigger the intervention process.

[0081] In this application, in order to reduce the incidence of operation risks, when it is predicted that there is a risk at the airport, intervention can be triggered. That is, the intervention trigger engine can match intervention measures according to the prediction results and the status of the regional index.

[0082] Specifically, for any preset area, it can be determined whether the AOH index of any preset area is less than the preset area-level index threshold.

[0083] Then, if it is determined that the AOH index of any preset area is less than the preset area-level index threshold, the corresponding intervention measures can be matched from the action library. For example, when the AOH index of the terminal area is less than 75 points and the predicted value of the health index is less than the preset health index threshold, the corresponding intervention measures (such as dispatching more shuttle buses to remote positions, opening the standby security inspection channel T2-03, pushing self-service check-in notifications to passengers, etc.) can be automatically matched from the action library. And in this application, the rule matching logic of the action library can be represented by the following formula:

[0084]

[0085] Among them, is the preset health index threshold (for example, 80 points), is the preset area-level index threshold (for example, 75 points).

[0086] Finally, according to the intervention measures, trigger intervention for any preset area. For example, according to the intervention measures, a dispatching instruction (such as license plate number Sichuan A12345) can be sent to the ground crew department through the Flight Operation Business Coordination System (OBCS), and resource scheduling can be executed. At the same time, the security inspection system is controlled to automatically open the T2-03 channel to achieve millisecond-level response.

[0087] In one possible implementation, in order to upgrade the management model from passive response to proactive prevention, this application can also monitor the intervention effect in real time and form a feedback loop after the intervention process is triggered.

[0088] Specifically, after triggering the intervention process, airport operation data can be reacquired and further processed. Then, in the data analysis layer, the AOH index at each level of the preset three-level index system can be redefined based on the reprocessed airport operation data. Next, in the prediction and early warning closed-loop layer, the newly determined global AOH index can be used again for trend prediction to obtain new health index prediction values. Finally, the new health index prediction values ​​and corresponding intervention measures can be recorded as intervention logs, and the rule base can be updated simultaneously.

[0089] For example, taking shuttle bus scheduling as an example, 5 minutes after the intervention is triggered, the check-in queuing time for shuttle buses decreases to 18 minutes, its AOH index is 92, and the shuttle bus response time is shortened to 3 minutes. The re-predicted AOH index rises to 82 points, and the intervention log is recorded (e.g., time is 8:35, action is to dispatch more shuttle buses, effect is AOH +3.5). At the same time, the shuttle bus scheduling priority in the rule base is updated by 10%. In this application, the scheduling optimization formula can be expressed as follows:

[0090]

[0091] in, The updated weights for each running parameter, The original weights of each operating parameter, The learning rate (e.g., 0.1). For the intervention effect (e.g., +3.5).

[0092] As can be seen, the predictive intervention closed loop of this application can achieve a management upgrade from "post-event statistics" to "pre-event prediction and in-event intervention" through the collaborative work of the LSTM model and the automatic intervention engine. Moreover, this closed-loop mechanism can predict operational risks 30 minutes in advance and automatically trigger resource scheduling, thereby significantly reducing the occurrence rate of operational risks and improving resource utilization efficiency and passenger service experience.

[0093] In one possible implementation, a dynamic weight adjustment mechanism is also designed in this application to improve scene adaptability.

[0094] Specifically, when determining the AOH index at each level of the preset three-level index system based on the processed airport operation data, the threshold interval mapping method can be used to evaluate various airport operation parameters to obtain multiple AOH indices at the equipment level. Among these, the operation parameters include taxiing time (the difference between the actual takeoff time and pushback time of a flight), number of shuttle buses (the number of vehicles parked simultaneously in the remote gate area), and number of gate occupancy (the actual number of gates occupied at the current time point) in the flight area; check-in queuing time (the average time from queuing to check-in) in the terminal area; security check queuing time (the time from passing through pre-security check to the start of security check) and passenger saturation (the ratio of real-time passenger count to theoretical maximum capacity); and taxi queueing numbers (the number of passengers queuing in the platform area), parking space occupancy ratio (the ratio of used parking spaces in the parking garage to total parking spaces) and traffic flow (the number of vehicles passing through the main road per unit time) in the public area.

[0095] Furthermore, these equipment-level AOH (Away From Home) indices need to be standardized and scored from 0 to 100 points to facilitate cross-dimensional comparisons. For example, the corresponding scoring formula for check-in queuing time is as follows:

[0096]

[0097] In addition, in this application, the average value of the remaining dimensions is calculated after removing the dimensions with the highest scores from the multi-dimensional indicators to ensure that the scores reflect the actual operational pressure.

[0098] Then, for any given preset area, multiple AOH indices at the device level under that preset area can be weighted and aggregated using fixed weights to obtain the AOH index for that preset area; where the preset areas include the flight area, terminal area, and public area. For example, taking the flight area as an example, the corresponding AOH index calculation formula for the flight area is as follows:

[0099]

[0100] Where A is the AOH index of the flight area; B is the AOH index of taxiing time; C is the AOH index of the number of shuttle buses; and D is the AOH index of the number of locomotives occupied.

[0101] Finally, a global AOH index can be obtained by weighting and aggregating the AOH indices of each preset region using dynamic weights; the dynamic weights are dynamically adjusted by adjustment strategies matched from the rule base. In this application, the global AOH index can be represented by the following dynamic weighting mechanism calculation formula:

[0102]

[0103] in, The AOH index for the i-th preset region; This represents the dynamic weight of the i-th preset region. Furthermore, the dynamic weight can be dynamically adjusted based on the adjustment strategy matched from the rule base by the event; for example, severe weather will increase the weight of the flight zone by 30%.

[0104] Therefore, this application can use this three-level progressive structure to ensure the accurate capture of micro parameters and achieve a comprehensive assessment of the macro situation, thus providing a scientific basis for the quantification of airport operational health.

[0105] In one possible implementation, the dynamic weight adjustment mechanism of this application adopts an event-driven design, automatically adjusting the health index weights by detecting changes in business scenarios in real time, ensuring that the AOH index always reflects the current core operational contradictions. Figure 6 The diagram shown is a schematic of a dynamic weight adjustment mechanism provided in an embodiment of this application. This mechanism solves the problem that traditional fixed weights cannot adapt to dynamic scenarios, enabling the health index to accurately assess the airport's operational status even under special circumstances such as severe weather or peak passenger traffic.

[0106] Specifically, when using dynamic weights to weight and aggregate the AOH indices of various preset areas to obtain a global AOH index, the airport operating environment can first be monitored in real time through multi-source data interfaces to determine whether preset events have occurred (i.e., event detection). Preset events include severe weather (such as a fog warning with visibility below 500 meters), peak passenger traffic (such as check-in area exceeding 80% of theoretical capacity), and equipment malfunctions (such as baggage carousel shutdown). For example, taking a fog event as an example, the visibility parameter of 300 meters can be obtained from the air traffic control system, identified as a "severe weather" event type, and the key parameter {visibility: 300m} can be extracted to provide a basis for subsequent weight adjustments.

[0107] Then, if a preset event is detected, the corresponding adjustment strategy can be matched from the rule base according to the preset event; that is, when a preset event is detected, the weight adjustment process is automatically triggered.

[0108] Next, the initial weights of each preset area can be dynamically adjusted according to the adjustment strategy to obtain the adjusted weights for each preset area. For example, when a severe weather event is identified, the following weight adjustment rules can be automatically executed: the weight of the flight area increases by 30% (because ground operations are most affected), the weight of the terminal area decreases by 10% (passenger flow is relatively controllable), and the weight of the public area decreases by 20% (the impact on external traffic is secondary). Thus, the original weights [flight area 0.4, terminal area 0.4, public area 0.2] become [0.52, 0.36, 0.16] after rule adjustment. In addition, since this rule design is based on business experience, it can be ensured that the weight changes conform to the actual operational impact.

[0109] Then, to ensure the total weights equal to 1, this application can also normalize the adjusted weights of each preset region to obtain the dynamic weights of each preset region. The calculation process is as follows: first, the adjusted weights are summed, and then the dynamic weights are calculated using the following normalization formula:

[0110]

[0111] For example, the adjusted weights for the flight area and terminal area are 0.52, 0.36, and 0.16, respectively. Using the normalization formula described above, the final dynamic weights for the flight area, terminal area, and public area are 0.5, 0.35, and 0.15, respectively. Clearly, this application ensures the scientific rationality of the weight allocation through normalization and avoids calculation deviations caused by weight adjustments.

[0112] Finally, the AOH indices of each preset region can be weighted and aggregated according to the dynamic weights of each preset region to obtain the global AOH index.

[0113] For example, in a foggy scenario, the AOH index for equipment in the flight area drops to 65 due to increased taxiing time, while the AOH index for shuttle bus quantity remains at 85. Using the new dynamic weights, the flight area AOH index is calculated as 65 × 0.5 + 85 × 0.5 = 75. The AOH indices for the terminal area and public area remain at 74 and 88 respectively, but the weight changes adjust their contribution. Therefore, the final global AOH index is updated to 75 × 0.5 + 74 × 0.35 + 88 × 0.15 = 76.3, which more accurately reflects the impact of severe weather on flight area operations compared to the previous score of 81. The entire process is completed automatically within 30 seconds without manual intervention, ensuring that the health index remains consistent with the current core operational challenges.

[0114] In another possible implementation, such as Figure 4 As shown, after calculating the AOH index at each level, value output can also be realized at the data application layer. For example, the comprehensive quantification of the three-level indicators (0-100 points) can be completed through the AOH index assessment, the operating status can be displayed in real time through the visual cockpit (refer to the "cockpit" function of the AOH platform), and the OBCS command can be automatically pushed through the alarm management module when the threshold is exceeded. Specific Implementation Example 1:

[0116] This paper mainly introduces the construction and calculation of dynamic health quantification models.

[0117] For example, during the morning peak hours (8:00-9:00) at Tianfu Airport, firstly, real-time raw airport operation data can be obtained through multi-source data collection. Specifically, flight data from the raw airport operation data comes from the information integration system, showing that flight CA1234's scheduled departure time is 8:15 and the actual taxiing time is 25 minutes; passenger data is provided by the video analysis system, detecting a real-time number of 120 people in Air China's C island check-in area, while the departure system simultaneously shows 115 passengers checking in at the same area; resource data is obtained through the apron intelligent dispatch system, showing 8 shuttle buses parked in the remote gate area 46-51.

[0118] Then, these raw airport operation data can be cleaned to remove abnormal frames (such as a sudden increase in the number of people caused by video occlusion), and the GPS coordinates of the shuttle bus can be matched with the remote gate area through spatiotemporal alignment, and standardized into a unified unit (such as converting passenger queuing time into minutes / person).

[0119] Next, we will introduce the calculation of the AOH index at the equipment level, using check-in queuing time as an example. Specifically, we can first score according to preset threshold rules: when the time is in the range of 0-20 minutes, the AOH index decreases linearly from 100 points to 90 points, for example, 2.1 minutes of time corresponds to 99 points; when the time is in the range of 20-25 minutes, the AOH index decreases from 90 points to 80 points, for example, 23 minutes of time corresponds to 84 points. Similarly, the AOH index of taxiing time in the airfield scores 75 points due to a delay of 25 minutes, and the AOH index of the number of shuttle buses scores 85 points due to reasonable parking.

[0120] The regional AOH index is calculated through weighted aggregation. The AOH index of the flight area is a combination of taxi time score and shuttle bus number score with dynamic weights (e.g., 75×0.4 + 85×0.6 = 81). The indices of the terminal area and public area are calculated in the same way.

[0121] The final global AOH index is obtained by weighted summation of regional AOH indices, with initial weights allocated as follows: 40% for the flight area, 40% for the terminal area, and 20% for the public area. After normalization, a comprehensive health score is output. The entire calculation process is completed in milliseconds, reflecting the airport's operational health status in real time and providing quantitative decision-making support for the command center. Specific Implementation Example 2:

[0123] The main focus is on the scene-adaptive weight adjustment mechanism.

[0124] For example, when Tianfu Airport receives a "fog alert" (visibility 300 meters) from the air traffic control system at 8:30, the following event-driven weight adjustment process can be initiated immediately.

[0125] First, the event type is identified as "severe weather," and the key parameter of visibility of 300 meters is extracted, triggering the preset weight adjustment rules.

[0126] Then, based on the preset weight adjustment rules (the weight of the flight area needs to be increased by 30% under severe weather conditions, the weight of the terminal area needs to be decreased by 10%, and the weight of the public area needs to be decreased by 20%), the original weights of each area (flight area 0.4, terminal area 0.4, public area 0.2) are dynamically adjusted to 0.52, 0.36, and 0.16 respectively.

[0127] Next, to ensure that the total weight is 1, the adjusted weights can be normalized, resulting in a final weight of 0.5 for the flight area, 0.35 for the terminal area, and 0.15 for the public area.

[0128] Finally, after the weights are updated, the AOH index for each area can be recalculated. At this point, the equipment-level AOH index under the flight area drops to 65 due to taxiing time caused by fog, while the shuttle bus quantity score remains at 85. Based on this, the flight area AOH index can be calculated as 65 × 0.5 + 85 × 0.5 = 75 using the updated dynamic weights. The terminal area and public area indices maintain their original scores of 74 and 88 respectively, but the weight changes adjust their contributions.

[0129] The final global AOH index was updated to 75×0.5 + 74×0.35 + 88×0.15 = 76.3, which, compared to the previous score of 81, more accurately reflects the impact of severe weather on flight operations. The entire process was completed within 30 seconds without human intervention, ensuring that the health index remains consistent with the current core operational challenges and improving decision-making sensitivity. Specific Implementation Example 3:

[0131] The introduction mainly focuses on the triggering and execution of predictive intervention engines.

[0132] Specifically, in predictive intervention scenarios, firstly, a trained LSTM model can be used to analyze health index trends. For example, the global AOH index sequence (85, 83, 82, 80, 79) from the past hour and real-time feature vectors (check-in queues increased by 20%, shuttle bus demand increased by 15%) can be input into the trained LSTM model.

[0133] Then, after calculation by the LSTM layer (128 units), the predicted AOH index value of 78.5 points for the next 30 minutes is output. Based on this, the predicted AOH index value of 78.5 points can be compared with the preset threshold of 80 points. Since 78.5 < 80, the intervention rule engine is automatically triggered.

[0134] Next, the intervention rule engine can match intervention measures (such as dispatching additional shuttle buses to remote positions, opening the standby security check channel T2-03, pushing self-service check-in notifications to passengers, etc.) from the action library based on the condition that the AOH index in the terminal area is lower than 75 points.

[0135] Then, dispatch instructions (such as license plate number Sichuan A12345) can be sent to the ground crew department through OBCS, and at the same time, the security check system is controlled to automatically open the T2-03 channel.

[0136] Five minutes after the intervention, the queuing time for check-in decreased to 18 minutes (score 92), and the response time of the shuttle bus was shortened to 3 minutes. The predicted value of the AOH index recovered to 82 points, and an intervention log was recorded (time: 8:35, action: dispatching additional shuttle buses, effect: AOH + 3.5). At the same time, the dispatching priority of the shuttle bus in the rule library was updated to increase by 10%. The entire process from prediction to execution of the closed loop took 2 minutes, achieving an upgrade in the management mode from passive response to proactive prevention.

[0137] In summary, this application has the following advantages:

[0138] (1) Improved dynamic quantification ability: Since this application constructs a three-level index system (equipment level - area level - global level) and a dynamic weight generation algorithm, and forms a progressive quantification model by collecting real-time equipment operation data (such as the number of parked shuttle buses), area health index (such as the taxiing efficiency in the flight area), and the global AOH comprehensive index, it breaks through the limitations of traditional static evaluation, and for the first time realizes the real-time quantification of the airport operation health status from 0 to 100 points, supports millisecond-level situation awareness, provides accurate data support for refined decision-making in complex scenarios, and significantly improves the scientificity and timeliness of airport operation management.

[0139] (2) Improved scene adaptability: This application designs a dynamic weight adaptability mechanism based on the weight adjustment rule driven by events. When specific events such as bad weather and passenger peaks are detected, the index weights can be automatically adjusted (such as the weight of the flight area is increased by 30% under bad weather), and the contribution degree of the area health index is dynamically balanced through a preset weight formula. Therefore, it can effectively solve the defect that fixed weights cannot adapt to dynamic operation scenarios, ensure that the health index always reflects the current core contradiction, and improve the decision-making sensitivity and resource allocation rationality in key scenarios.

[0140] (3) Improved predictive intervention capability: This application integrates a health index trend prediction model with automatic intervention triggering logic, and uses the LSTM time series algorithm to predict the operational risk in the next 30 minutes. When the predicted AOH index falls below the threshold, resource scheduling instructions (such as increasing shuttle buses and expanding security checkpoints) can be automatically triggered to achieve predictive intervention. Therefore, it can be upgraded from "post-event statistics" to a closed-loop management model of "pre-event prediction-in-event intervention", which significantly reduces the incidence of operational risks, improves resource utilization efficiency and passenger service experience, and promotes the transformation of airport management towards proactive prevention.

[0141] Based on the same inventive concept, embodiments of this application provide an airport operation digital health processing device 70, such as... Figure 7 As shown, the airport's digital health processing unit 70 includes:

[0142] The health index determination unit 701 is used in the data analysis layer to determine the airport operation health (AOH) index at each level of the preset three-level index system based on the processed airport operation data. The preset three-level index system includes equipment level, regional level and global level. The regional level AOH index is obtained based on the equipment level AOH index, and the global level AOH index is obtained based on the regional level AOH index.

[0143] The trend prediction and intervention unit 702 is used to perform trend prediction using the global AOH index in the prediction and early warning closed loop layer to determine whether there is a risk at the airport.

[0144] The trend prediction and intervention unit 702 is also used to trigger the intervention process if a risk is determined to exist at the airport.

[0145] Optionally, the health index determination unit 701 is also used for:

[0146] The threshold interval mapping method is used to evaluate various airport operating parameters and obtain multiple AOH indices at the equipment level. Among them, the operating parameters include taxi time, number of shuttle buses, number of aircraft stands occupied, check-in queuing time, security check queuing time, passenger saturation, number of taxis in queue, parking space occupancy rate and traffic flow.

[0147] For any given preset area, multiple AOH indices at the device level under that preset area are weighted and aggregated using fixed weights to obtain the AOH index for that preset area; wherein, the preset areas include the flight area, terminal area and public area;

[0148] A weighted aggregation of AOH indices for each preset region is performed using dynamic weights to obtain a global AOH index; the dynamic weights are dynamically adjusted by adjustment strategies matched from the rule base.

[0149] Optionally, the health index determination unit 701 is also used for:

[0150] Determine whether a preset event has occurred; preset events include severe weather, peak passenger flow, and equipment malfunction.

[0151] If a preset event is determined to occur, the corresponding adjustment strategy is matched from the rule base based on the preset event.

[0152] The initial weights of each preset region are dynamically adjusted according to the adjustment strategy to obtain the adjusted weights of each preset region.

[0153] Normalize the adjusted weights of each preset region to obtain the dynamic weights of each preset region.

[0154] By using the dynamic weights of each preset region, the AOH index of each preset region is weighted and aggregated to obtain the global AOH index.

[0155] Optionally, the trend prediction and intervention unit 702 is also used for:

[0156] The global historical AOH index sequence and real-time feature vector are input into the trained LSTM model to predict trends and obtain the predicted health index value.

[0157] Determine whether the predicted health index value is less than the preset health index threshold;

[0158] If the predicted health index value is determined to be less than the preset health index threshold, then the airport is deemed to be at risk.

[0159] Optionally, the trend prediction and intervention unit 702 is also used for:

[0160] For any given preset region, determine whether the AOH index of that preset region is less than a preset region-level index threshold;

[0161] If the AOH index of any preset region is determined to be less than the preset region-level index threshold, then the corresponding intervention measures are matched from the action library;

[0162] Based on the intervention measures, trigger intervention in any preset area.

[0163] Optionally, the trend prediction and intervention unit 702 is also used for:

[0164] In the data analysis layer, the AOH index at each level of the preset three-level index system is redefined based on the reprocessed airport operation data.

[0165] In the prediction and early warning closed-loop layer, the newly determined global AOH index is used again for trend prediction to obtain a new health index prediction value;

[0166] New health index predictions and corresponding interventions are recorded in the intervention log, and the rule base is updated accordingly.

[0167] Optionally, the airport operation digital health processing unit 70 also includes a data acquisition and processing unit for:

[0168] In the data acquisition layer, data is collected from multiple airport management systems included in the data source layer to obtain raw airport operation data;

[0169] In the data governance layer, the raw airport operation data is processed to obtain processed airport operation data; the processing includes removing invalid values, data filtering, and data standardization.

[0170] The airport operates a digital health processing unit 70 which can be used for execution Figures 2-6 The method executed by the airport operation digital health processing device in the illustrated embodiment can be referenced for understanding the functions that each functional module of the airport operation digital health processing device 70 can achieve. Figures 2-6 The embodiments shown are described in detail below.

[0171] In some possible implementations, various aspects of the methods provided in this application can also be implemented as a program product comprising program code that, when run on a computer device, causes the computer device to perform the steps of the methods according to the various exemplary embodiments of this application described above. For example, the computer device may perform actions such as... Figures 2-6 The method performed by the airport's digital health processing device in the illustrated embodiment.

[0172] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks. Alternatively, if the integrated units of this application are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to the prior art, can be embodied in the form of software products. These computer software products are stored in a storage medium and include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0173] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0174] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. An airport operations digital health processing method, characterized by, The method comprises: In the data analysis layer, various operation parameters of the airport are evaluated by using a threshold interval mapping method to obtain a plurality of AOH indexes at the equipment level; for any one preset area, the plurality of AOH indexes at the equipment level under the any one preset area are weighted and aggregated by using a fixed weight to obtain an AOH index of the any one preset area; the AOH indexes of the various preset areas are weighted and aggregated by using a dynamic weight to obtain an AOH index at the global level; wherein the operation parameters comprise taxiing time, number of transfer vehicles, number of gate occupancies, check-in queuing time, security check queuing time, passenger saturation, number of taxi queuing passengers, parking space occupancy ratio and traffic volume; the preset areas comprise a flight area, a terminal area and a public area; and the dynamic weight is dynamically adjusted by an adjustment strategy matched from a rule base; In the prediction and early warning closed loop layer, the AOH index at the global level is used for trend prediction to determine whether the airport is at risk; If it is determined that the airport is at risk, an intervention process is triggered.

2. The method of claim 1, wherein, The step of using the dynamic weight to weight and aggregate the AOH indexes of the various preset areas to obtain the AOH index at the global level comprises: Determining whether a preset event occurs; wherein the preset event comprises adverse weather, passenger peak and equipment failure; If it is determined that the preset event occurs, a corresponding adjustment strategy is matched from the rule base according to the preset event; The initial weight of each preset area is dynamically adjusted according to the adjustment strategy to obtain the adjusted weight of each preset area; The adjusted weight of each preset area is normalized to obtain the dynamic weight of each preset area; The AOH indexes of each preset area recalculated are weighted and aggregated by using the dynamic weight of each preset area to obtain the AOH index at the global level.

3. The method of claim 1, wherein, The step of using the AOH index at the global level for trend prediction to determine whether the airport is at risk comprises: The historical AOH index sequence at the global level and the real-time feature vector are input into a trained LSTM model for trend prediction to obtain a health index prediction value; It is determined whether the health index prediction value is less than a preset health index threshold value; If it is determined that the health index prediction value is less than the preset health index threshold value, it is determined that the airport is at risk.

4. The method of claim 1, wherein, The step of triggering the intervention process comprises: For any one preset area, it is determined whether the AOH index of the any one preset area is less than a preset area level index threshold value; If it is determined that the AOH index of the any one preset area is less than the preset area level index threshold value, a corresponding intervention measure is matched from an action library; According to the intervention measure, the any one preset area is intervened.

5. The method of claim 1, wherein, After triggering the intervention process, the method further comprises: In the data analysis layer, the AOH indexes at various levels in the preset three-level index system are re-determined according to the re-processed airport operation data; In the prediction and early warning closed loop layer, the newly determined AOH index at the global level is re-used for trend prediction to obtain a new health index prediction value; The new health index prediction value and the corresponding intervention measure are recorded as an intervention log, and the rule base is updated.

6. The method of claim 1, wherein, Before determining the AOH indexes of each level in the preset three-level index system according to the processed airport operation data, the method further comprises: In the data acquisition layer, data acquisition is performed on the plurality of airport management systems included in the data source layer to obtain original airport operation data; In the data governance layer, the original airport operation data is processed to obtain the processed airport operation data; wherein the processing comprises eliminating invalid values, data filtering and data standardization.

7. An airport operations digital health processing apparatus, characterized by, The device comprises: A health index determination unit configured to, in the data analysis layer, evaluate various operation parameters of the airport by using a threshold interval mapping method to obtain a plurality of AOH indexes at the equipment level; for any one preset area, the plurality of AOH indexes at the equipment level under the any one preset area are aggregated by using a fixed weight to obtain an AOH index of the any one preset area; the AOH indexes of each preset area are aggregated by using a dynamic weight to obtain an AOH index at a global level; wherein the operation parameters comprise taxiing time, number of transfer vehicles, number of gate occupancies, check-in queue time, security check queue time, passenger saturation, number of taxi queue, parking occupancy ratio and traffic flow; the preset areas comprise a flight area, a terminal area and a public area; the dynamic weight is dynamically adjusted by an adjustment strategy matched from a rule base; A trend prediction and intervention unit configured to, in the prediction and early warning closed loop layer, perform trend prediction by using the AOH index at the global level to determine whether the airport has risks; The trend prediction and intervention unit is further configured to, if it is determined that the airport has risks, trigger an intervention process.

8. An electronic device, comprising: The device comprises: A memory configured to store program instructions; A processor configured to call the program instructions stored in the memory and execute the method according to any one of claims 1-6 according to the obtained program instructions.

9. A storage medium, characterized by The storage medium stores computer executable instructions, and the computer executable instructions are used to make the computer execute the method according to any one of claims 1-6. The storage medium stores computer executable instructions, and the computer executable instructions are used to make the computer execute the method according to any one of claims 1-6.

Images