Airport geographic data dynamic update method and system based on digital twin technology

Abstract

This application discloses a method and system for dynamically updating airport geographic data based on digital twin technology. The method includes: defining multi-dimensional tags for airport geographic data and a data acquisition device deployment strategy that matches them; completing the collection of airport geographic data corresponding to different tag combinations according to the deployment strategy; transmitting the collected airport geographic data in real time through a constructed communication network architecture; defining QoS levels that match different tag combinations, and allocating network resources in real time to the airport geographic data corresponding to different tag combinations; completing real-time airport geographic data fusion through a three-engine data fusion architecture built into the cloud for airport geographic data transmitted to the cloud; setting a multi-strategy collaborative update mechanism to complete the real-time update of airport geographic data, generate updated airport geographic data, and feed it back to the digital twin system. This application can achieve real-time and comprehensive data collection and real-time dynamic updating of airport geographic data.

Description

Technical Field

[0001] The present application relates to the technical field of airport geographic data analysis and update, and specifically to a method and system for dynamically updating airport geographic data based on digital twin technology. Background Art

[0002] With the rapid development of IoT and digital twin technologies, the application of geographic information systems (GIS) is becoming increasingly widespread across various fields. The use of GIS is crucial in airport management. Real-time, dynamically updated geographic data can effectively improve airport operational efficiency, ensure safety, and optimize resource allocation. Many airports are now using GIS for management, enabling them to better plan flight arrivals and departures, passenger flow, and venue resource utilization.

[0003] Existing airport geographic data collection and updating systems primarily utilize two common methods: one is regular manual inspections, where staff periodically conduct on-site inspections and record data in various areas of the airport. This method captures relatively detailed data, covering the actual conditions of each area. The other is the use of a static sensor network, which implements a degree of automated data collection by deploying fixed sensor nodes in certain areas of the airport, relying on the sensors' inherent capabilities to collect relevant geographic data.

[0004] Clearly, these existing technologies have significant flaws. Manual inspections are inefficient, requiring significant manpower and time, and offer limited real-time performance, failing to reflect dynamic changes in airport geographic data. Static sensor networks, however, struggle to fully cover every area of ​​an airport due to the limited distribution and number of sensor nodes, and their data processing and analysis capabilities are also limited. Therefore, existing technologies generally fall short in both real-time and comprehensive data collection, making it difficult to achieve real-time, dynamic updates of geographic data. Summary of the Invention

[0005] In order to achieve real-time and comprehensive data collection and real-time dynamic update of airport geographic data, this application provides a method and system for dynamic update of airport geographic data based on digital twin technology.

[0006] In a first aspect, the present application provides a method for dynamically updating airport geographic data based on digital twin technology, comprising:

[0007] Define multi-dimensional tags for airport geographic data, define data collection device deployment strategies that match tag combinations containing different dimensions, and complete the collection of airport geographic data corresponding to different tag combinations according to the matched data collection device deployment strategies; the multi-dimensionality includes: spatial dimension, type dimension, and dynamic attribute dimension; the data collection device deployment strategy includes: data collection device type selection and deployment density;

[0008] The collected airport geographic data is transmitted in real time via a constructed communication network architecture; the constructed communication network architecture has multiple communication network layers, and data transmission is performed according to the preset communication network layers matched with different tag combinations; QoS levels that match different tag combinations are defined, and network resources are allocated in real time to the airport geographic data corresponding to the different tag combinations according to the QoS levels matched with the different tag combinations, with airport geographic data with higher QoS levels being given higher priority in network resource allocation;

[0009] For airport geographic data transmitted to the cloud, real-time airport geographic data fusion is achieved through the cloud's built-in three-engine data fusion architecture, combined with the corresponding tag combinations of the airport geographic data. The three-engine data fusion architecture includes: a spatial engine, a temporal engine, and a relational engine. A multi-strategy collaborative update mechanism is set up to complete the real-time update of the airport geographic data based on the fused airport geographic data in accordance with the multi-strategy collaborative update mechanism, generating real-time updated airport geographic data. The multi-strategy collaborative update mechanism includes a basic data-driven update mechanism, an event-driven update mechanism, a cycle-driven update mechanism, and a prediction-driven update mechanism.

[0010] The real-time updated airport geographic data is fed back to the digital twin system built based on the airport to achieve real-time dynamic update of the airport geographic data.

[0011] By adopting the above solution, a deployment strategy for data collection devices with multi-dimensional tags and matching is defined to improve the comprehensiveness and effectiveness of data collection; a communication network architecture with multiple communication network layers is constructed, and preset layered transmission data is matched according to different dimensional tag combinations, and network resources are allocated according to QoS levels to improve the real-time and stability of data transmission; the cloud-based three-engine data fusion architecture is used in combination with tag combinations to complete data fusion, thereby improving the accuracy of data fusion and assisting subsequent data updates; a multi-strategy collaborative update mechanism is set up for data updates, realizing real-time dynamic updates of airport geographic data.

[0012] Preferably, the data acquisition device type selection in the data acquisition device deployment strategy that defines and matches the tag combination including different dimensions includes: at least one data acquisition device selected from satellite positioning, radar, drone, sensor, UWB indoor positioning, optical fiber, and camera device;

[0013] The deployment density decision in the data collection device deployment strategy defined to match the label combination containing different dimensions includes: using a deep learning algorithm to obtain the correlation strength between multiple label combinations, and comparing it with a first preset correlation strength to determine multiple label combinations with strong correlation relationships, and comparing it with a second preset correlation strength to determine multiple label combinations with medium correlation relationships or low correlation relationships; the first preset correlation strength is greater than the second preset correlation strength; for multiple label combinations with strong correlation relationships, overlapping deployment or co-location of data collection devices are selected for corresponding airport geographic data, and synchronous collection is performed; for multiple label combinations with medium correlation relationships, adjacent deployment of data collection devices are selected for corresponding airport geographic data, and asynchronous collection is performed; for multiple label combinations with low correlation relationships, data collection devices need to be independently deployed for corresponding airport geographic data.

[0014] By adopting the above solution, deep learning algorithms are used to determine label combinations with different association strengths, and different data collection device deployment and collection methods are adopted according to the association strength. The data collection layout is rationally planned and resource allocation is optimized to ensure that airport geographic data can be collected comprehensively and accurately, which helps to realize real-time dynamic updates of airport geographic data.

[0015] Preferably, it also includes:

[0016] For the collected airport geographic data, determine the quality index of the airport geographic data collected in real time according to the airport geographic data quality index calculation rules;

[0017] Construct a data acquisition dynamic adjustment algorithm; input the label combination corresponding to the real-time collected airport geographic data and the quality index of the real-time collected airport geographic data into the data acquisition dynamic adjustment algorithm to obtain the data acquisition device deployment density adjustment strategy and the acquisition frequency adjustment strategy; the input layer of the data acquisition dynamic adjustment algorithm includes: the label combination corresponding to the real-time collected airport geographic data and the quality index of the collected airport geographic data; the decision layer includes: the label combination association modeling layer based on the graph neural network and the reinforcement learning strategy optimization layer; the output layer is the data acquisition device deployment density adjustment strategy and the acquisition frequency adjustment strategy; the training generation is completed using the label combination corresponding to the historically collected airport geographic data and the quality index of the real-time collected airport geographic data, as well as the historically selected data acquisition device deployment density adjustment strategy and the acquisition frequency adjustment strategy as training data;

[0018] According to the data acquisition device deployment density adjustment strategy and acquisition frequency adjustment strategy, the density and acquisition frequency of the deployed data acquisition devices are dynamically adjusted.

[0019] By adopting the above scheme, a dynamic adjustment algorithm for data collection is constructed. Combined with the label combination and quality indicators corresponding to the airport geographic data, the data collection device deployment density adjustment strategy and the collection frequency adjustment strategy are obtained and applied to improve the efficiency and quality of data collection.

[0020] Preferably, the multiple communication networks are designed with three-level network layers, namely edge layer, convergence layer and core layer, and the edge computing center of the edge layer is used to filter and compress the collected airport geographic data, including: filtering data according to preset event triggering rules based on matching different label combinations, and the preset event triggering rules include: retaining only the airport geographic data corresponding to the preset label combination that exceeds the preset quality index threshold; using the convergence layer to perform data aggregation and protocol conversion on the collected airport geographic data; and using the core layer to directly transmit the collected airport geographic data to the cloud.

[0021] By adopting the above solution, the edge computing center of the edge layer is used to filter data according to the preset event trigger rules, only retaining the data corresponding to the preset label combination that exceeds the preset quality indicator threshold, removing unnecessary data, and reducing the amount of data for subsequent processing; the convergence layer is used to aggregate data and convert protocols to facilitate unified processing and transmission of data; the core layer is used to transmit data directly to the cloud to achieve efficient data upload, which jointly improves the efficiency and effectiveness of data transmission.

[0022] Preferably, the real-time allocation of network resources for airport geographic data corresponding to different tag combinations includes:

[0023] Obtain the network status of the current communication network architecture in real time, including network load and link quality values;

[0024] Based on the network status of the current communication network architecture, determine whether the network load is greater than the preset network load; if not, directly allocate the remaining network resources according to the QoS level; if so, use the dynamic QoS scheduling model based on reinforcement learning to obtain the optimal network resource allocation strategy and allocate network resources according to the optimal network resource allocation strategy; the dynamic QoS scheduling model based on reinforcement learning is set up including a label combination of airport geographic data, a state space of network load and link quality values, an action space including bandwidth allocation adjustment, transmission link switching, and activation or disabling of redundant links, and a reward function with parameters including delay compliance rate, packet loss rate penalty and energy consumption; wherein, the bandwidth allocation of different levels of the network is set with a bandwidth allocation ratio limit range interval; using historical status data, action data and reward data as training data, the training and generation of the dynamic QoS scheduling model based on reinforcement learning are completed.

[0025] By adopting the above solution, the network status of the communication network architecture can be obtained in real time. When the network load is not too heavy, the remaining network resources are allocated according to the QoS level to ensure the orderly allocation of resources under normal circumstances. When the network load is too heavy, the dynamic QoS scheduling model based on reinforcement learning is used to obtain the optimal network resource allocation strategy, optimize resource allocation, and ensure the stable transmission of airport geographic data.

[0026] Preferably, the airport geographic data transmitted to the cloud is integrated with the three-engine data fusion architecture built into the cloud and the corresponding tag combination of the airport geographic data to complete the real-time airport geographic data fusion, including:

[0027] Using spatial engine fusion calculations, complete the spatial coordinate standardization and spatial relationship reasoning of the collected airport geographic data to obtain a standardized spatial data set;

[0028] Using time engine fusion calculations, we complete the time series synchronization and time series feature extraction of the collected airport geographic data to obtain a time series aligned data set;

[0029] Using the relational engine fusion calculation, the label combination association weight matrix and causal relationship reasoning results of the collected airport geographic data are completed to obtain the association enhanced data set;

[0030] Based on the fusion calculation results of the three engines, the weight of the airport geographic data is determined through a QoS-driven weight fusion algorithm, and real-time airport geographic data fusion is completed based on the determined airport geographic data weight. This includes: mapping the initial weight of the QoS level based on the label combination of the airport geographic data; setting the basic weight of each engine, and determining the final weight of each airport geographic data according to the weight of each engine and the initial weight of the QoS level mapping, and performing normalization processing.

[0031] By adopting the above solution, the results of the three-engine fusion calculations are integrated, and the weight of the airport geographic data is determined in coordination with the QoS-driven weight fusion algorithm and the data deduplication mechanism to complete real-time airport geographic data fusion, thereby improving the accuracy of airport geographic data updates and assisting in subsequent data updates.

[0032] Preferably, the multi-strategy collaborative update mechanism is set up, and based on the fused airport geographic data, the real-time update of the airport geographic data is completed according to the multi-strategy collaborative update mechanism, and the generation of the real-time updated airport geographic data includes:

[0033] For the basic data-driven update mechanism, the preset type of fused airport geographic data is compared with the existing airport geographic data in the digital twin model to determine whether the comparison result is greater than the preset difference of the fused airport geographic data. If the comparison result is greater than the preset difference, the existing airport geographic data in the digital twin model is updated;

[0034] For the event-driven update mechanism, the preset events and trigger conditions are clearly defined, and the fused airport geographic data is analyzed using deep learning algorithms to identify whether a preset event has been triggered. Based on the triggered preset event, the associated airport geographic data is determined and the corresponding airport geographic data is updated.

[0035] In view of the periodic driving mechanism, the airport geographic data with time-varying patterns is clearly identified, and the update cycle of the corresponding airport geographic data is set accordingly. The task scheduling system is used to automatically generate data update tasks according to the set cycle. When the update cycle arrives, the corresponding airport geographic data is automatically collected and calculated according to the data update task, and the corresponding airport geographic data is updated.

[0036] According to the prediction-driven update mechanism, the airport geographic data for a period of time in the future is predicted, and the prediction results are compared with the corresponding preset airport geographic data thresholds. If the prediction results exceed the preset airport geographic data thresholds, the data is updated based on the predicted airport geographic data.

[0037] By adopting the above solution and utilizing a multi-strategy collaborative update strategy, multi-dimensional data updates can be completed, ensuring real-time updates of airport geographic data and ensuring data timeliness and accuracy.

[0038] In a second aspect, the present application provides a system for dynamically updating airport geographic data based on digital twin technology, comprising:

[0039] The airport geographic data collection module is used to define multi-dimensional tags for airport geographic data and define data collection device deployment strategies that match tag combinations containing different dimensions; the module completes the collection of airport geographic data corresponding to different tag combinations according to the matching data collection device deployment strategies; the multi-dimensional tags include: spatial dimension, type dimension, and dynamic attribute dimension; the data collection device deployment strategies include: data collection device type selection and deployment density;

[0040] An airport geographic data transmission module is used to transmit collected airport geographic data in real time through a constructed communication network architecture; the constructed communication network architecture is provided with multiple communication network layers, and data transmission is performed according to the preset communication network layers matched with different tag combinations; QoS levels that match different tag combinations are defined, and network resources are allocated in real time to the airport geographic data corresponding to the different tag combinations based on the QoS levels matched with the different tag combinations, with airport geographic data with higher QoS levels being given higher priority in network resource allocation;

[0041] The airport geographic data analysis module is used to integrate the airport geographic data transmitted to the cloud into real-time airport geographic data through a three-engine data fusion architecture built into the cloud, combining the corresponding tags of the airport geographic data. The three-engine data fusion architecture includes a spatial engine, a temporal engine, and a relational engine. A multi-strategy collaborative update mechanism is set up to update the airport geographic data in real time based on the integrated airport geographic data, generating real-time updated airport geographic data in accordance with the multi-strategy collaborative update mechanism. The multi-strategy collaborative update mechanism includes a basic data-driven update mechanism, an event-driven update mechanism, a cycle-driven update mechanism, and a prediction-driven update mechanism.

[0042] The airport geographic data update module is used to feed back the real-time updated airport geographic data to the digital twin system built based on the airport to achieve real-time dynamic update of the airport geographic data.

[0043] By adopting the above solution, multi-dimensional tags are defined for airport geographic data and data collection is carried out according to the data collection device deployment strategy, thereby improving the pertinence and comprehensiveness of data collection. The three-engine data fusion architecture is combined with the tag combination for data fusion, and a multi-strategy collaborative update mechanism is set up to complete the multi-dimensional data update, which improves the accuracy of data analysis and update. The updated data is fed back to the digital twin system, realizing the real-time dynamic update of airport geographic data and improving the efficiency and safety of airport management.

[0044] In a third aspect, the present application provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the method as described above.

[0045] In a fourth aspect, the present application provides a computer device, which includes a memory, a processor, and a program stored and executable on the memory, and the program implements the steps of the above method when executed by the processor.

[0046] In summary, this application has the following beneficial effects:

[0047] Data collection is carried out by defining multi-dimensional tags and matching data collection device deployment strategies, and data is transmitted in real time through the constructed communication network architecture. The data is updated through the cloud-based three-engine data fusion architecture and multi-strategy collaborative update mechanism, and then fed back to the digital twin system, realizing real-time dynamic updates of airport geographic data and ensuring the timeliness of the data. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a flowchart of the method for dynamically updating airport geographic data based on digital twin technology in a specific embodiment;

[0049] Figure 2 It is a structural diagram of the airport geographic data dynamic update system based on digital twin technology described in a specific embodiment. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0051] like Figure 1 As shown, the embodiment of the present application discloses a dynamic update of airport geographic data based on digital twin technology, including data collection, data transmission, data analysis, data update and other links; wherein, data collection is completed by defining multi-dimensional tags of airport geographic data and the corresponding data collection device deployment strategy, and the constructed communication network architecture is used for data transmission. In the cloud, with the help of a three-engine data fusion architecture and a multi-strategy collaborative update mechanism, data analysis and data update are completed. Finally, the updated data is fed back to the digital twin system built based on the airport, realizing the real-time dynamic update of airport geographic data and effectively improving the timeliness and comprehensiveness of the data. The specific update steps include:

[0052] S1. Define the multi-dimensional tags of airport geographic data and the corresponding data collection device deployment strategy.

[0053] Specifically, in this embodiment, the multi-dimensional labeling of airport geographic data covers spatial dimensions, type dimensions, and dynamic attribute dimensions. The spatial dimension is divided into five layers: air (aerial layer), sky (sky-based layer), ground (ground layer), underground (underground layer), and indoor and outdoor. The type dimension is divided into basic geographic information data (such as topography, land and vegetation, and other natural resources), operational management information data (such as flight takeoffs and landings, personnel flow, and equipment status), safety management information data (such as personnel density, firefighting facility locations, and contraband detection results), and environmental data (such as temperature and humidity, wind speed and direction, and noise decibels). The dynamic attribute dimension is divided into timestamp, collection frequency (high frequency / low frequency), data status (raw / cleaned / aggregated), and confidence level.

[0054] Based on the multi-dimensional tags of airport geographic data, data acquisition device deployment strategies that match the airport geographic data corresponding to different dimensional tag combinations are defined, including but not limited to the type selection of data acquisition devices and the deployment density of data acquisition devices. Each tag combination is assigned a matching data acquisition device deployment strategy. The data acquisition device type selection includes at least one of satellite positioning, radar, drone, sensor, UWB indoor positioning, optical fiber, and camera devices. Some tag combinations are assigned a matching data acquisition device deployment strategy as shown in Table 1 below:

[0055] Table 1

[0056]

[0057] Among them, the data of each dimension in the label combination can be specific to the specific value under the corresponding dimension.

[0058] In addition, considering that the degree of correlation between tag combinations can represent the different degrees of correlation between the corresponding airport geographic data, it is possible to choose to complete the dynamic deployment of data acquisition devices based on the correlation of multi-dimensional tag combinations. By calculating the degree of correlation between tag combinations, it is assisted to set the deployment density according to actual needs; for example: overlapping or co-locating sensors in high-correlation areas and increasing the density, and adopting the lowest coverage density in areas with low redundancy requirements and combining it with external data supplements, thereby achieving a balance between the comprehensiveness, real-timeness and cost-effectiveness of data collection, and completing the optimized matching setting of data acquisition device deployment.

[0059] Specific deployment density decisions include obtaining the strength of association between multiple label combinations. Specifically, various methods can be used to calculate the association between label combinations, such as using deep learning algorithms to build a neural network model and collecting multiple label combinations with historical expert annotations for model training. Alternatively, correlation analysis can be used to determine the applicable scenarios for different label combinations, and corresponding methods such as the Pearson correlation coefficient (for label combinations that conform to a linear relationship) or mutual information entropy (for label combinations that conform to a nonlinear relationship) can be used to determine the strength of association between different label combinations.

[0060] The obtained correlation strengths between multiple tag combinations are compared with a first preset correlation strength to identify tag combinations with strong correlations (greater than the first preset correlation strength), a second preset correlation strength to identify tag combinations with moderate correlations (less than the first preset correlation strength and greater than the second preset correlation strength), and a second preset correlation strength to identify tag combinations with weak correlations (less than the second preset correlation strength). The first preset correlation strength is greater than the second preset correlation strength. For tag combinations with strong correlations, the corresponding airport geographic data must be collected using overlapping (e.g., vertically overlapping) or co-located (co-located) data collection devices, with synchronous collection. For tag combinations with moderate correlations, the corresponding airport geographic data must be collected using adjacent data collection devices, with asynchronous collection. For tag combinations with weak correlations, the corresponding airport geographic data must be collected using independent data collection devices. For example, the correlation strength between "drone activity in airspace" (air-high frequency-safety) and "runway incursion alarm" (ground-real-time-safety) is 0.82, indicating a strong correlation. The sensors (drone radar + runway camera) are co-located, with a synchronized collection frequency of 5Hz.

[0061] The final deployment density calculation formula includes:

[0062]

[0063] Among them, deployment density refers to the deployment density of data collection devices that need to be deployed overlappingly or co-located. The real-time level of airport geographic data corresponding to different dimensional label combinations can be determined based on historical data.

[0064] S2. The collected airport geographic data is transmitted in real time through the constructed communication network architecture.

[0065] To adapt to the high-density and highly dynamic airport geographic data transmission, the tag combination is deeply bound with the network transmission strategy to form a "tag resolution-network layer, QoS classification-data transmission" design. The specific settings include:

[0066] The constructed communication network architecture has multiple communication network layers, which can adaptively transmit airport geographic data with different network requirements through different communication network layers. Different label combinations can reflect different network requirements of data, such as: ground-operational-real-time. Corresponding to low-latency network requirements, the data transmission network requirements corresponding to the label combination can be obtained in advance, and then the label combination and network layer matching rules can be defined. According to the preset communication network layers matched with different label combinations, data transmission is carried out, thereby meeting the latency, reliability and bandwidth requirements of each airport geographic data.

[0067] In this embodiment, the communication network architecture is designed as a three-level network layer consisting of an edge layer, an aggregation layer, and a core layer to ensure end-to-end latency and reliability. Specifically, the edge computing center of the edge layer (such as an MEC server, an industrial gateway, etc.) is used to perform data filtering and data compression on the collected airport geographic data to complete data transmission. To further ensure the low-latency transmission of valid data, some local decisions are made directly to reduce the amount of data transmission. For example, when the edge computing center of the edge layer performs data filtering, it will perform data filtering according to preset event triggering rules based on matching different label combinations. Among them, the preset event triggering rules include retaining only airport geographic data corresponding to preset label combinations that exceed preset quality indicator thresholds. The aggregation layer (connecting edge nodes via optical fiber / microwave links and deploying aggregation routers) is used to aggregate and convert the collected airport geographic data to complete data transmission. The core layer (connecting to cloud data centers and supporting network slicing) is used to directly transmit the collected airport geographic data to the cloud. Some label combinations and network layer matching rules are shown in Table 2 below:

[0068] Table 2

[0069]

[0070] A corresponding QoS strategy can be designed for each tag combination. Based on the developed QoS strategy, the real-time, reliability, and bandwidth requirements of data transmission can be met. Specifically, QoS levels that match different tag combinations are defined, such as the first level, second level, third level, and fourth level. The tag combinations that match the above four levels in order correspond to the real-time requirements and reliability requirements of airport geographic data transmission, and the lower the bandwidth requirements. Based on the QoS levels that match different tag combinations, network resources are allocated to the airport geographic data corresponding to different tag combinations in real time. The higher the QoS level, the more priority is given to allocating network resources to the airport geographic data. The QoS levels that match some tag combinations are shown in Table 3 below:

[0071] Table 3

[0072]

[0073] To achieve better network resource allocation, in this embodiment, the real-time allocation of network resources for airport geographic data corresponding to different tag combinations includes: obtaining the network status of the current communication network architecture in real time, including network load and link quality (packet loss rate and latency) values ​​and energy consumption;

[0074] Based on the network status of the current communication network architecture, determine whether the network load exceeds the preset network load, such as 70%. If not, directly allocate the remaining network resources or statically reserve resources according to the QoS level, that is, set priority queues according to the QoS level and allocate network resources in order of priority, such as reserving 20% ​​bandwidth for the first level, 15% bandwidth for the second level, and sharing the remaining bandwidth below the third level. If so, utilize a dynamic QoS scheduling model based on reinforcement learning, input the label combination and real-time network status, obtain the optimal network resource allocation strategy, and allocate network resources according to the optimal network resource allocation strategy. The dynamic QoS scheduling model based on reinforcement learning is configured with a state space, an action space, and a reward function. The state space configuration includes the label combination of airport geographic data, network status (network load and link quality value), and energy consumption. The action space configuration includes the action space for bandwidth allocation adjustment, transmission link switching, and the activation or disabling of redundant links. The reward function configuration parameters include the delay compliance rate, packet loss rate penalty, and energy consumption. The specific formula includes: The packet loss rate penalty is a penalty function set according to the packet loss rate value. In addition, to take into account the characteristics and needs of each network layer, for example, the edge layer may require higher bandwidth and lower latency, while the core layer focuses more on data stability and high-speed exchange capabilities; through reasonable algorithm design and parameter settings, it can be ensured that resource allocation does not conflict with the basic functions of each network layer. For example, the bandwidth allocation of different network layers is set with a bandwidth allocation ratio limit range.

[0075] The dynamic QoS scheduling model based on reinforcement learning mainly uses historical state data, action data, and reward data as training data to complete the training and generate a dynamic QoS scheduling model based on reinforcement learning. Specifically, it includes: collecting historical state data, action data, and reward data, and performing necessary preprocessing; initializing the reinforcement learning model, including the state space, action space, and reward function; training the model, selecting actions based on the current state, and observing the new state and reward obtained after executing the action; and using the reinforcement learning algorithm to update the strategy or value function in the model based on the collected experience data (i.e., the state-action-reward sequence).

[0076] S3. Complete data fusion for the airport geographic data transmitted to the cloud and perform data updates based on the fused data.

[0077] In order to achieve accurate processing and timely updating of airport geographic data, it is necessary to use cloud-based data analysis algorithms for data analysis, including data alignment, data fusion, etc., to assist in subsequent multi-dimensional data updates and improve data processing and update efficiency.

[0078] For the airport geographic data transmitted to the cloud, the cloud's built-in three-engine data fusion architecture combines the corresponding tags of the airport geographic data to complete the real-time airport geographic data fusion. In this embodiment, the three-engine data fusion architecture includes: spatial engine, time engine and relational engine. Specifically, the fusion steps include:

[0079] First, using spatial engine fusion calculations, the spatial coordinate standardization and spatial relationship reasoning of the collected airport geographic data are completed to obtain a standardized spatial data set. This includes: unifying the coordinate system, converting the collected airport geographic data (such as GPS coordinates, drone LiDAR point clouds, and satellite remote sensing images) to the airport's unified coordinate system; performing spatial interpolation, and interpolating sparse data (such as rainfall data from airport weather stations) to generate a continuous spatial grid. The specific interpolation formulas include:

[0080]

[0081] Where, is the weight coefficient, The system uses known point data and performs spatial relationship reasoning, including labeling data based on airport geographic fences (such as runways, taxiways, and restricted areas). For example, when a drone trajectory crosses a runway fence, it labels it an "airspace intrusion" event. It also clusters similar data (such as airport vehicle GPS data) to identify hotspots. It also obtains standardized spatial datasets, including airport geographic data in a unified coordinate system and corresponding spatial labels.

[0082] Secondly, the time engine fusion calculation is used to complete the time series synchronization and time series feature extraction of the collected airport geographic data to obtain a time series aligned data set; this includes: aligning the collected airport geographic data (such as: ADS-B collects data once per second, and the camera collects data every 1 / 30 second) to a unified timestamp, using linear interpolation and other methods to fill the data, aggregating data according to a fixed time window (such as 1 minute) (for example: summarizing all flight takeoff and landing events within 1 minute as the "flight density" indicator), and generating time series slices; extracting time series features, such as calculating the mean, variance, and trend, marking abnormal data (such as periodic fluctuation data), and further predicting the data corresponding to the key features to obtain a portion of future data. Finally, a time series aligned data set is obtained, including: airport geographic data slices under a unified timestamp and corresponding time series features.

[0083] Then, the relational engine is used to fusion calculate and complete the label combination association weight matrix and causal relationship reasoning results of the collected airport geographic data to obtain the association enhanced data set; including: using a graph neural network to map the label combination into graph nodes, the edge weight represents the association strength, input node features (labels), edge features (temporal and spatial overlap), and output node embedding vectors (association weights between nodes); or using a Bayesian network to construct a conditional probability table between label combinations and identify causal relationships; using Granger causality test technology to verify the causal relationship between time series, obtain the causal relationship graph between the label combination and the airport geographic data, and finally obtain the association enhanced data set, including: the association weight matrix and causal relationship graph between the airport geographic data.

[0084] Finally, the three-engine fusion calculation results are integrated, and the weight of the airport geographic data is determined through a QoS-driven weight fusion algorithm. Based on the determined weight of the airport geographic data, real-time airport geographic data fusion is completed. The specific steps include:

[0085] The three-engine fusion calculation results are determined in real time, such as: the obtained standardized spatial data set: {A, B, D...}, the time-series aligned data set: {B, C, D...}, and the associated enhanced data: {A, D...}, where letters such as A and B represent each airport geographic data point after fusion. The QoS level corresponding to each data point uses the highest level of the data point before fusion or re-determines the QoS level according to QoS requirements, such as: A is the first level, B is the second level, C is the third level, and D is the fourth level.

[0086] Initial weights for QoS level mapping based on the tag combination of airport geographic data; for example, the initial weights for the first, second, third, and fourth levels are set to 1.5, 1.2, 1.0, and 0.8, respectively;

[0087] Set the basic weight of each engine, such as 0.4 for the spatial engine, 0.3 for the temporal engine, and 0.3 for the relational engine. Determine the final weight of each airport's geographic data based on the weight of each engine and the initial weight of the QoS level mapping and perform normalization. The specific formula includes: , such as: the sum of the engine weights of A is 0.4+0.3=0.7, The weight is 1.5, and the final weight is 1.05; similarly, B is 1.2, C is 0.3, and D is 0.24; finally, normalization is performed to obtain the corresponding weight of each data point, such as: 0.376, 0.430, 0.108, 0.086 to complete the data point fusion.

[0088] For the airport geographic data that has completed the data fusion processing, data updates are performed. In order to complete the multi-dimensional data basis, a multi-strategy collaborative update mechanism is set up. Based on the fused airport geographic data, the real-time update of the airport geographic data is completed in accordance with the multi-strategy collaborative update mechanism to generate real-time updated airport geographic data; the updated airport geographic data is stored in the database, and information such as the update time and operator is recorded for version management. In this embodiment, the multi-strategy collaborative update mechanism includes a basic data driven update mechanism, an event driven update mechanism, a cycle driven update mechanism, and a prediction driven update mechanism. Specifically, each update mechanism is elaborated in detail as follows:

[0089] For the basic data-driven update mechanism, the preset type of fused airport geographic data is compared with the existing airport geographic data in the digital twin model to determine whether the comparison result is greater than the preset difference of the fused airport geographic data. If the comparison result is greater than, the existing airport geographic data in the digital twin model is updated; the preset type can be set in advance manually, such as: the airport's building layout data (building layout data of different terminals), which is compared with the building layout data constructed in the digital twin model. If it is determined that there is a preset difference in the building layout data, the building layout data in the digital twin model is updated.

[0090] For the event-driven update mechanism, pre-set events and trigger conditions are clearly defined. Deep learning algorithms are then used to analyze the fused airport geographic data to identify whether a pre-set event has been triggered. Based on the triggered pre-set event, the associated airport geographic data is determined and updated accordingly. For example, pre-set events include flight takeoff and landing, equipment failure, and crowd gathering, with corresponding trigger conditions: the presence of a flight on the runway with flight parameters within the pre-set takeoff and landing parameter range, equipment parameters exceeding the corresponding parameter threshold, and crowd density exceeding the pre-set density. A deep learning algorithm is then used to analyze the fused airport geographic data to identify whether a pre-set event has been triggered. Different neural network models can be trained for different pre-set events to identify the corresponding events. Statistical analysis is performed on historical pre-set event updates corresponding to the occurrence of these events to determine the airport geographic data associated with the triggered pre-set event. For example, when a flight takeoff and landing event occurs, associated data such as flight dynamics, stand occupancy status, and ground traffic guidance data are updated. The fused airport geographic data is retrieved to obtain the associated airport geographic data and update the corresponding airport geographic data.

[0091] For the periodic driving mechanism, the airport geographic data with time-varying patterns are clearly defined, and the corresponding update cycles of the corresponding airport geographic data are set. For example, the passenger flow data in the terminal is updated every hour, and the airport indoor equipment operating status data is summarized and updated every day; the task scheduling system is used to automatically generate data update tasks according to the set cycle; when the update cycle arrives, the corresponding airport geographic data is automatically collected and calculated according to the data update task, and the corresponding airport geographic data is updated; in addition, before the update, the collected and calculated data are quality verified to check the integrity, accuracy and consistency of the data; if there are problems with the data, corrections or re-collection and recalculation are carried out.

[0092] According to the prediction-driven update mechanism, airport geographic data for a period of time in the future is predicted. Specifically, key predicted airport geographic data can be set, such as: predicted future flight traffic, passenger traffic peak hours, equipment failure probability, etc., and the predicted results are compared with the corresponding preset airport geographic data thresholds. If the predicted results exceed the preset airport geographic data thresholds, indicating that there is a significant impact on airport operations, safety, etc., the data will be updated based on the predicted airport geographic data.

[0093] S4. Feedback the real-time updated airport geographic data to the digital twin system built based on the airport to achieve real-time dynamic update of the airport geographic data.

[0094] In a specific embodiment, to further ensure the comprehensiveness, accuracy, and timeliness of the collected airport geographic data, the deployment strategy of the data collection device can be dynamically adjusted based on the quality indicators of the collected geographic data. The method further includes:

[0095] For the collected airport geographic data, the quality indicators of the airport geographic data collected in real time are determined according to the airport geographic data quality indicator calculation rules; among them, the airport geographic data quality indicators include delay value and confidence level, which can be obtained by weighted calculation.

[0096] Construct a dynamic adjustment algorithm for data collection; input the label combination corresponding to the airport geographic data collected in real time and the quality index of the airport geographic data collected in real time into the dynamic adjustment algorithm for data collection to obtain the data collection device deployment density adjustment strategy and the collection frequency adjustment strategy.

[0097] Specifically, the constructed data collection dynamic adjustment algorithm chooses to adopt an RL model, the input layer of which includes: the label combination corresponding to the airport geographic data collected in real time and the quality index of the collected airport geographic data, the decision layer includes: the label combination association modeling layer based on the graph neural network and the reinforcement learning strategy optimization layer, and the output layer is the data collection device deployment density adjustment strategy and the collection frequency adjustment strategy; wherein, the label combination association modeling layer based on the graph neural network uses the input label combination corresponding to the real-time collected airport geographic data as the graph node, calculates the association strength between the label combinations as the association strength through mutual information entropy or Bayesian network, and outputs the association matrix of the label combination; the reinforcement learning strategy optimization layer sets the state space, including: the association matrix of the label combination and the quality index of the airport geographic data collected in real time; sets the action space, including: adjusting the data collection device deployment density, the collection frequency adjustment strategy, and whether to activate the redundant data collection device strategy; sets the reward function parameters, including: data integrity, data real-time, and the cost of activating redundant data collection devices.

[0098] Specifically, the constructed data acquisition dynamic adjustment algorithm completes training generation by using the label combination corresponding to the historically collected airport geographic data, the quality index of the real-time collected airport geographic data, and the historically selected data acquisition device deployment density adjustment strategy and acquisition frequency adjustment strategy as training data;

[0099] According to the data acquisition device deployment density adjustment strategy and acquisition frequency adjustment strategy, the density and acquisition frequency of the deployed data acquisition devices are dynamically adjusted.

[0100] like Figure 2 As shown, this embodiment discloses a system for dynamically updating airport geographic data based on digital twin technology, specifically including:

[0101] The airport geographic data collection module 101 is configured to define multi-dimensional tags for airport geographic data and define data collection device deployment strategies that match tag combinations containing different dimensions; the collection of airport geographic data corresponding to different tag combinations is completed according to the matched data collection device deployment strategies; the multi-dimensional tags include: spatial dimension, type dimension, and dynamic attribute dimension; the data collection device deployment strategies include: data collection device type selection and deployment density;

[0102] The airport geographic data transmission module 102 is used to transmit the collected airport geographic data in real time through a constructed communication network architecture; the constructed communication network architecture has multiple communication network layers, and data transmission is performed according to the preset communication network layers matched with different tag combinations; QoS levels that match different tag combinations are defined, and network resources are allocated in real time to the airport geographic data corresponding to the different tag combinations based on the QoS levels matched with the different tag combinations, with airport geographic data with higher QoS levels being given higher priority in network resource allocation;

[0103] The airport geographic data analysis module 103 is used to perform real-time airport geographic data fusion based on the airport geographic data transmitted to the cloud through a three-engine data fusion architecture built into the cloud, combined with the corresponding tag combinations of the airport geographic data; the three-engine data fusion architecture includes: a spatial engine, a temporal engine, and a relational engine; a multi-strategy collaborative update mechanism is set up to perform real-time updates of the airport geographic data based on the fused airport geographic data in accordance with the multi-strategy collaborative update mechanism, thereby generating real-time updated airport geographic data; the multi-strategy collaborative update mechanism includes a basic data-driven update mechanism, an event-driven update mechanism, a cycle-driven update mechanism, and a prediction-driven update mechanism;

[0104] The airport geographic data update module 104 is used to feed back the real-time updated airport geographic data to the digital twin system built based on the airport to achieve real-time dynamic update of the airport geographic data.

[0105] In a specific embodiment, the system further includes: an airport geographic data collection optimization module 105, which is used to determine the quality index of the airport geographic data collected in real time according to the airport geographic data quality index calculation rules for the collected airport geographic data; construct a data collection dynamic adjustment algorithm; input the label combination corresponding to the real-time collected airport geographic data and the quality index of the real-time collected airport geographic data into the data collection dynamic adjustment algorithm to obtain a data collection device deployment density adjustment strategy and a collection frequency adjustment strategy; the input layer of the data collection dynamic adjustment algorithm includes: the label combination corresponding to the real-time collected airport geographic data and the quality index of the collected airport geographic data; the decision layer includes: a label combination association modeling layer based on a graph neural network and a reinforcement learning strategy optimization layer; the output layer is the data collection device deployment density adjustment strategy and the collection frequency adjustment strategy; training generation is completed using the label combination corresponding to the historically collected airport geographic data and the quality index of the real-time collected airport geographic data, as well as the historically selected data collection device deployment density adjustment strategy and the collection frequency adjustment strategy as training data; based on the obtained data collection device deployment density adjustment strategy and the collection frequency adjustment strategy, the density and collection frequency of the deployed data collection devices are dynamically adjusted.

[0106] The embodiment of the present application also discloses a computer-readable storage medium.

[0107] Specifically, the computer-readable storage medium stores a computer program that can be loaded by a processor and execute the above-mentioned airport geographic data dynamic update method based on digital twin technology. The computer-readable storage medium includes, for example: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk and other media that can store program codes.

[0108] The embodiment of the present application also discloses a computer device.

[0109] Specifically, the computer device includes a memory and a processor, and the memory stores a computer program that can be loaded by the processor and execute the above-mentioned airport geographic data dynamic update method based on digital twin technology.

[0110] The above are all preferred embodiments of the present application and are not intended to limit the scope of protection of this application. Unless otherwise stated, any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features. In other words, unless otherwise stated, each feature is merely an example of a series of equivalent or similar features.

Claims

1. A method for dynamically updating airport geographic data based on digital twin technology, characterized in that: include: Define multi-dimensional tags for airport geographic data and define data collection device deployment strategies that match tag combinations containing different dimensions; Complete the collection of airport geographic data corresponding to different tag combinations according to the matching data collection device deployment strategy; the multiple dimensions include: spatial dimension, type dimension and dynamic attribute dimension; the data collection device deployment strategy includes: data collection device type selection and deployment density; The collected airport geographic data is transmitted in real time via a constructed communication network architecture; the constructed communication network architecture has multiple communication network layers, and data transmission is performed according to the preset communication network layers matched with different tag combinations; QoS levels that match different tag combinations are defined, and network resources are allocated in real time to the airport geographic data corresponding to the different tag combinations according to the QoS levels matched with the different tag combinations, with airport geographic data with higher QoS levels being given higher priority in network resource allocation; For airport geographic data transmitted to the cloud, real-time airport geographic data fusion is achieved through the cloud's built-in three-engine data fusion architecture, combined with the corresponding tag combinations of the airport geographic data. The three-engine data fusion architecture includes: a spatial engine, a temporal engine, and a relational engine. A multi-strategy collaborative update mechanism is set up to complete the real-time update of the airport geographic data based on the fused airport geographic data in accordance with the multi-strategy collaborative update mechanism, generating real-time updated airport geographic data. The multi-strategy collaborative update mechanism includes a basic data-driven update mechanism, an event-driven update mechanism, a cycle-driven update mechanism, and a prediction-driven update mechanism. The real-time updated airport geographic data is fed back to the digital twin system built based on the airport to achieve real-time dynamic update of the airport geographic data.

2. The method for dynamically updating airport geographic data based on digital twin technology according to claim 1 is characterized in that: The data acquisition device type selection in the data acquisition device deployment strategy that defines and matches the tag combination including different dimensions includes: at least one data acquisition device selected from satellite positioning, radar, drone, sensor, UWB indoor positioning, optical fiber, and camera device; The deployment density decision in the data collection device deployment strategy defined to match the label combination containing different dimensions includes: using a deep learning algorithm to obtain the correlation strength between multiple label combinations, and comparing it with a first preset correlation strength to determine multiple label combinations with strong correlation relationships, and comparing it with a second preset correlation strength to determine multiple label combinations with medium correlation relationships or low correlation relationships; the first preset correlation strength is greater than the second preset correlation strength; for multiple label combinations with strong correlation relationships, overlapping deployment or co-location of data collection devices are selected for corresponding airport geographic data, and synchronous collection is performed; for multiple label combinations with medium correlation relationships, adjacent deployment of data collection devices are selected for corresponding airport geographic data, and asynchronous collection is performed; for multiple label combinations with low correlation relationships, data collection devices need to be independently deployed for corresponding airport geographic data.

3. The method for dynamically updating airport geographic data based on digital twin technology according to claim 1 is characterized in that: Also includes: For the collected airport geographic data, determine the quality index of the airport geographic data collected in real time according to the airport geographic data quality index calculation rules; Construct a data collection dynamic adjustment algorithm; input the label combination corresponding to the real-time collected airport geographic data and the quality index of the real-time collected airport geographic data into the data collection dynamic adjustment algorithm to obtain a data collection device deployment density adjustment strategy and a collection frequency adjustment strategy; The input layer of the data acquisition dynamic adjustment algorithm includes: label combinations corresponding to the real-time collected airport geographic data and quality indicators of the collected airport geographic data; the decision layer includes: a label combination association modeling layer based on a graph neural network and a reinforcement learning strategy optimization layer; the output layer includes a data acquisition device deployment density adjustment strategy and a collection frequency adjustment strategy; training generation is completed using the label combinations corresponding to the historically collected airport geographic data, the quality indicators of the real-time collected airport geographic data, and the historically selected data acquisition device deployment density adjustment strategy and collection frequency adjustment strategy as training data; According to the data acquisition device deployment density adjustment strategy and acquisition frequency adjustment strategy, the density and acquisition frequency of the deployed data acquisition devices are dynamically adjusted.

4. The method for dynamically updating airport geographic data based on digital twin technology according to claim 3 is characterized in that: The multiple communication network layers are designed with three-level network layers: edge layer, convergence layer and core layer. The edge computing center of the edge layer is used to filter and compress the collected airport geographic data, including: data filtering according to preset event triggering rules based on matching different label combinations, and the preset event triggering rules include: only retaining airport geographic data corresponding to preset label combinations that exceed preset quality index thresholds; using the convergence layer to aggregate and convert the collected airport geographic data; and using the core layer to directly transmit the collected airport geographic data to the cloud.

5. The method for dynamically updating airport geographic data based on digital twin technology according to claim 1 is characterized in that: The real-time allocation of network resources for airport geographic data corresponding to different tag combinations includes: Obtain the network status of the current communication network architecture in real time, including network load and link quality values; Based on the network status of the current communication network architecture, determine whether the network load is greater than the preset network load; if not, directly allocate the remaining network resources according to the QoS level; if so, use the dynamic QoS scheduling model based on reinforcement learning to obtain the optimal network resource allocation strategy and allocate network resources according to the optimal network resource allocation strategy; the dynamic QoS scheduling model based on reinforcement learning is set up including a label combination of airport geographic data, a state space of network load and link quality values, an action space including bandwidth allocation adjustment, transmission link switching, and activation or disabling of redundant links, and a reward function with parameters including delay compliance rate, packet loss rate penalty and energy consumption; wherein, the bandwidth allocation of different levels of the network is set with a bandwidth allocation ratio limit range interval; using historical status data, action data and reward data as training data, the training and generation of the dynamic QoS scheduling model based on reinforcement learning are completed.

6. The method for dynamically updating airport geographic data based on digital twin technology according to claim 1 is characterized in that: The airport geographic data transmitted to the cloud is integrated with the cloud's built-in three-engine data fusion architecture, and the corresponding tags of the airport geographic data are combined to complete the real-time airport geographic data fusion, including: Using spatial engine fusion calculations, complete the spatial coordinate standardization and spatial relationship reasoning of the collected airport geographic data to obtain a standardized spatial data set; Using time engine fusion calculations, we complete the time series synchronization and time series feature extraction of the collected airport geographic data to obtain a time series aligned data set; Using the relational engine fusion calculation, the label combination association weight matrix and causal relationship reasoning results of the collected airport geographic data are completed to obtain the association enhanced data set; Based on the fusion calculation results of the three engines, the weight of the airport geographic data is determined through a QoS-driven weight fusion algorithm, and real-time airport geographic data fusion is completed based on the determined airport geographic data weight. This includes: mapping the initial weight of the QoS level based on the label combination of the airport geographic data; setting the basic weight of each engine, and determining the final weight of each airport geographic data according to the weight of each engine and the initial weight of the QoS level mapping, and performing normalization processing.

7. The method for dynamically updating airport geographic data based on digital twin technology according to claim 1 is characterized in that: The multi-strategy collaborative update mechanism is set up to complete the real-time update of the airport geographic data based on the fused airport geographic data according to the multi-strategy collaborative update mechanism, and the generated real-time updated airport geographic data includes: For the basic data-driven update mechanism, the preset type of fused airport geographic data is compared with the existing airport geographic data in the digital twin model to determine whether the comparison result is greater than the preset difference of the fused airport geographic data. If the comparison result is greater than the preset difference, the existing airport geographic data in the digital twin model is updated; For the event-driven update mechanism, the preset events and trigger conditions are clearly defined, and the fused airport geographic data is analyzed using deep learning algorithms to identify whether a preset event has been triggered. Based on the triggered preset event, the associated airport geographic data is determined and the corresponding airport geographic data is updated. In view of the periodic driving mechanism, the airport geographic data with time-varying patterns is clearly identified, and the update cycle of the corresponding airport geographic data is set accordingly. The task scheduling system is used to automatically generate data update tasks according to the set cycle. When the update cycle arrives, the corresponding airport geographic data is automatically collected and calculated according to the data update task, and the corresponding airport geographic data is updated. According to the prediction-driven update mechanism, the airport geographic data for a period of time in the future is predicted, and the prediction results are compared with the corresponding preset airport geographic data thresholds. If the prediction results exceed the preset airport geographic data thresholds, the data is updated based on the predicted airport geographic data.

8. A dynamic update system for airport geographic data based on digital twin technology, characterized by: include: The airport geographic data collection module is used to define multi-dimensional tags for airport geographic data and define data collection device deployment strategies that match tag combinations containing different dimensions; Complete the collection of airport geographic data corresponding to different tag combinations according to the matching data collection device deployment strategy; the multiple dimensions include: spatial dimension, type dimension and dynamic attribute dimension; the data collection device deployment strategy includes: data collection device type selection and deployment density; An airport geographic data transmission module is used to transmit collected airport geographic data in real time through a constructed communication network architecture; the constructed communication network architecture is provided with multiple communication network layers, and data transmission is performed according to the preset communication network layers matched with different tag combinations; QoS levels that match different tag combinations are defined, and network resources are allocated in real time to the airport geographic data corresponding to the different tag combinations based on the QoS levels matched with the different tag combinations, with airport geographic data with higher QoS levels being given higher priority in network resource allocation; The airport geographic data analysis module is used to integrate the airport geographic data transmitted to the cloud into real-time airport geographic data through a three-engine data fusion architecture built into the cloud, combining the corresponding tags of the airport geographic data. The three-engine data fusion architecture includes a spatial engine, a temporal engine, and a relational engine. A multi-strategy collaborative update mechanism is set up to update the airport geographic data in real time based on the integrated airport geographic data, generating real-time updated airport geographic data in accordance with the multi-strategy collaborative update mechanism. The multi-strategy collaborative update mechanism includes a basic data-driven update mechanism, an event-driven update mechanism, a cycle-driven update mechanism, and a prediction-driven update mechanism. The airport geographic data update module is used to feed back the real-time updated airport geographic data to the digital twin system built based on the airport to achieve real-time dynamic update of the airport geographic data.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

10. A computer device, characterized in that: The computer device includes a memory, a processor, and a program stored and executable on the memory, and when the program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images