Report generation method and device, equipment and storage medium

Abstract

The invention discloses a report generation method and device, equipment and a storage medium, and relates to the technical field of air traffic management, and the method comprises the steps: obtaining the current navigation data and meteorological data of a target aircraft, and constructing corresponding target data based on the navigation data and meteorological data; the navigation data comprises radar data and flight plan data of a target aircraft; determining the flight conflict probability of the target aircraft according to the target data through a preset conflict probability prediction model; the preset conflict probability prediction model is constructed based on a long and short term memory network; determining a conflict risk level of the target aircraft based on the flight conflict probability of the target aircraft and preset historical conflict data; and generating a conflict report of the target aircraft based on the flight conflict probability and the conflict risk level. Through deep fusion of the large language model and air traffic control field knowledge, a more comprehensive conflict analysis basis can be provided, automatic report generation is realized, and the accuracy of conflict detection is significantly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of air traffic management, and particularly to a report generation method, device, equipment, and storage medium. Background Art

[0002] With the continuous growth of global air transportation volume, the complexity and safety pressure faced by air traffic control (ATC) are increasing day by day. Traditional air traffic conflict detection and reporting rely on manual analysis, with insufficient real-time performance, making it difficult to handle massive dynamic data. Moreover, the multi-source data fusion ability is weak, and the report generation efficiency is low, thus affecting the accuracy of conflict judgment.

[0003] In recent years, large language models have powerful natural language understanding, logical reasoning, and multi-modal data processing capabilities, and have shown significant advantages in fields such as healthcare and finance. However, applying them to air traffic control conflict report generation still faces challenges. Therefore, how to use large language models to achieve air traffic conflict detection is an issue to be solved in this field. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a report generation method, device, equipment, and storage medium. By deeply integrating large language models with air traffic control domain knowledge, more comprehensive conflict analysis basis can be provided, and report generation can be automated, significantly improving the accuracy of conflict detection. The specific solutions are as follows:

[0005] In a first aspect, the present application provides a report generation method, including:

[0006] Obtain the current navigation data and meteorological data of the target aircraft, and construct corresponding target data based on the navigation data and the meteorological data; the navigation data includes radar data and flight plan data of the target aircraft;

[0007] Determine the flight conflict probability of the target aircraft according to the target data through a preset conflict probability prediction model; the preset conflict probability prediction model is constructed based on a long short-term memory network;

[0008] Determine the conflict risk level of the target aircraft based on the flight conflict probability of the target aircraft and preset historical conflict data;

[0009] Generate a conflict report for the target aircraft based on the flight conflict probability and the conflict risk level.

[0010] Optionally, the constructing corresponding target data based on the navigation data and the meteorological data includes:

[0011] Obtain the navigation data and the meteorological data of the target aircraft, and perform format conversion on the navigation data and the meteorological data based on a preset data format;

[0012] Based on a preset time alignment standard and a space alignment standard, perform spatio-temporal alignment on the navigation data and the meteorological data after format conversion to obtain the corresponding target data.

[0013] Optionally, the determining the flight conflict probability of the target aircraft by a preset conflict probability prediction model based on the target data includes:

[0014] Encode the target data through a preset encoder in the preset conflict probability prediction model to obtain encoded data;

[0015] Determine the association features between different target aircraft according to the encoded data, and determine the attention weights of the association features;

[0016] Utilize a preset graph attention network in the preset conflict probability prediction model to determine the flight conflict probability of the target aircraft based on the association features and the attention weights.

[0017] Optionally, in the process of determining the flight conflict probability of the target aircraft by a preset conflict probability prediction model based on the target data, it further includes:

[0018] Utilize a long short-term memory network in the preset conflict probability model to predict the target navigation trajectory of the target aircraft within a preset time period based on the target data;

[0019] Perform similarity matching based on the historical navigation trajectory in the preset historical conflict data and the target navigation trajectory to obtain a corresponding matching result;

[0020] Correspondingly, the determining the flight conflict probability of the target aircraft includes:

[0021] Determine the flight conflict probability of the target aircraft according to the association features, the attention weights, and the matching result.

[0022] Optionally, the predicting the target navigation trajectory of the target aircraft within a preset time period based on the target data includes:

[0023] Predict the navigation trajectory of the target aircraft within the preset time period a preset number of times based on the target data to obtain a corresponding number of initial navigation trajectories;

[0024] Fit the initial navigation trajectories to obtain the target navigation trajectory of the target aircraft within the preset time period.

[0025] Optionally, after determining the conflict risk level of the target aircraft, the method further includes:

[0026] Generating a number of corresponding conflict resolution suggestions based on the conflict risk level of the target aircraft, and determining the suggestion priorities of the conflict resolution suggestions;

[0027] Correspondingly, generating a conflict report for the target aircraft based on the flight conflict probability and the conflict risk level, including:

[0028] Generating the conflict report for the target aircraft based on the flight conflict probability, the conflict risk level, each conflict resolution suggestion, and the corresponding suggestion priority.

[0029] Optionally, determining the suggestion priorities of the conflict resolution suggestions includes:

[0030] Constructing an aircraft conflict simulation scenario corresponding to each conflict resolution suggestion based on the current navigation data and meteorological data of the target aircraft;

[0031] Simulating each conflict resolution suggestion using the aircraft conflict simulation scenario to obtain the conflict resolution success rate corresponding to each conflict resolution suggestion, and determining the suggestion priority of each conflict resolution suggestion according to the conflict resolution success rate.

[0032] In a second aspect, the present application provides a report generation device, including:

[0033] A data generation module, configured to obtain the current navigation data and meteorological data of a target aircraft, and construct corresponding target data based on the navigation data and the meteorological data; the navigation data includes radar data and flight plan data of the target aircraft;

[0034] A probability determination module, configured to determine the flight conflict probability of the target aircraft according to the target data through a preset conflict probability prediction model; the preset conflict probability prediction model is constructed based on a long short-term memory network;

[0035] A level determination module, configured to determine the conflict risk level of the target aircraft based on the flight conflict probability of the target aircraft and preset historical conflict data;

[0036] A report generation module, configured to generate a conflict report for the target aircraft based on the flight conflict probability and the conflict risk level.

[0037] In a third aspect, the present application provides an electronic device, which includes a processor and a memory; wherein, the memory is used to store a computer program, and the computer program is loaded and executed by the processor to implement the foregoing report generation method.

[0038] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program, and when the computer program is executed by a processor, the foregoing report generation method is implemented.

[0039] The present application can first obtain the navigation data and meteorological data of the target aircraft, including the radar data and flight plan data of the target aircraft, and construct corresponding target data based on the navigation data and meteorological data. Then, a preset conflict probability prediction model constructed based on a long short-term memory network is used to determine the flight conflict probability of the target aircraft according to the target data, and based on the flight conflict probability of the target aircraft and preset historical conflict data, the conflict risk level of the target aircraft is determined, so as to generate a conflict report for the target aircraft based on the flight conflict probability and the conflict risk level. By deeply integrating the large language model with the knowledge in the field of air traffic control, the present application can integrate various data, provide a more comprehensive basis for conflict analysis, and automate report generation, reduce manual intervention, improve the report generation efficiency and consistency, and significantly improve the accuracy of conflict detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings according to the provided drawings without creative efforts.

[0041] Figure 1 It is a flowchart of a report generation method provided by the present application;

[0042] Figure 2 It is a schematic diagram of the system architecture of a report generation system provided by the present application;

[0043] Figure 3 It is a flowchart of a specific method for determining the flight conflict probability provided by the present application;

[0044] Figure 4 It is a schematic diagram of the structure of a report generation device provided by the present application;

[0045] Figure 5 It is a structural diagram of an electronic device provided by the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0047] With the continuous growth of global air traffic volume, the complexity and safety pressure faced by air traffic control are increasing day by day. Traditional air traffic conflict detection and reporting rely on manual analysis, lacking real-time performance, being difficult to handle massive dynamic data, having weak multi-source data fusion capabilities, and low report generation efficiency, thus affecting the accuracy of conflict judgment. However, in this application, by deeply integrating large language models with air traffic control domain knowledge, various data can be fused, providing a more comprehensive basis for conflict analysis, automating report generation, reducing manual intervention, improving report generation efficiency, and significantly enhancing the accuracy of conflict detection.

[0048] See Figure 1 As shown, an embodiment of the present invention discloses a report generation method, including:

[0049] Step S11: Obtain the current navigation data and meteorological data of the target aircraft, and construct corresponding target data based on the navigation data and the meteorological data; the navigation data includes the radar data and flight plan data of the target aircraft.

[0050] In this embodiment, as Figure 2 shown, first, a multi-source data integration and preprocessing module can be used to integrate multi-source data and generate standardized inputs. Specifically, the current navigation data and meteorological data of the target aircraft can be obtained, and corresponding target data can be constructed based on the navigation data and meteorological data. It can be understood that the above-mentioned navigation data includes the radar data (aircraft position, speed, altitude) and flight plan data (route, takeoff and landing time) of the target aircraft, the meteorological data includes relevant data such as wind speed and turbulence, and historical conflict cases can also be obtained simultaneously to further improve the accuracy of flight conflict probability determination in combination with historical conflict cases. It should be noted that the preset conflict probability prediction model in this embodiment is a model obtained by fine-tuning a pre-trained large model using LoRA (Low-Rank Adaptation) technology and injecting air traffic control domain knowledge (such as safety interval rules, route structure). Injecting air traffic control rules through LoRA technology helps to solve the problem of insufficient domain adaptation of general models. And the preset conflict probability prediction model also includes a pre-designed hybrid input layer, which supports the joint embedding of text (flight plan), numerical values (radar data), and images (meteorological cloud maps, track maps) through multi-modal data and domain adaptation.

[0051] And in the above process, after obtaining the navigation data and meteorological data of the target aircraft, the format of the navigation data and meteorological data can be converted based on a preset data format, and the navigation data and meteorological data after format conversion can be aligned in time and space based on preset time alignment standards and space alignment standards to obtain corresponding target data, so as to realize the cleaning and format unification of the original data, and integrate multi-source information through time-space alignment technology to improve data standardization.

[0052] Step S12: Determine the flight conflict probability of the target aircraft according to the target data through a preset conflict probability prediction model; the preset conflict probability prediction model is constructed based on a long short-term memory network.

[0053] In this embodiment, a preset conflict probability prediction model can be constructed in advance based on a long short-term memory network. Specifically, a conflict probability prediction model can be constructed based on an improved Transformer architecture, combined with four-dimensional trajectory prediction (three-dimensional space + time), and the model can be trained in combination with professional domain knowledge, so as to determine the flight conflict probability of the target aircraft according to the target data through the preset conflict probability prediction model.

[0054] Step S13: Determine the conflict risk level of the target aircraft based on the flight conflict probability of the target aircraft and preset historical conflict data.

[0055] In this embodiment, the conflict risk level of the target aircraft can be determined based on the flight conflict probability of the target aircraft and preset historical conflict data. As Figure 2 shown, the risk assessment sub-module can integrate the safety separation standards of the International Civil Aviation Organization (ICAO), the experience rules of air traffic controllers, and historical conflict data to establish a multi-dimensional risk scoring system, so as to output the conflict risk level (for example: low, medium, high) and the corresponding confidence level.

[0056] Step S14: Generate a conflict report for the target aircraft based on the flight conflict probability and the conflict risk level.

[0057] In this embodiment, based on the flight conflict probability and the conflict risk level, a conflict report of the target aircraft can be generated. It should be noted that after determining the conflict risk level of the target aircraft, a number of corresponding conflict resolution suggestions can also be generated based on the conflict risk level of the target aircraft, and the suggestion priorities of each conflict resolution suggestion are determined. Correspondingly, when generating the conflict report of the target aircraft, specifically, the conflict report of the target aircraft can be generated based on the flight conflict probability, the conflict risk level, each conflict resolution suggestion, and the corresponding suggestion priorities. And in a specific embodiment, when determining the suggestion priorities of each conflict resolution suggestion, first, based on the current navigation data and meteorological data of the target aircraft, an aircraft conflict simulation scenario corresponding to each conflict resolution suggestion is constructed, and then the aircraft conflict simulation scenario is used to simulate each conflict resolution suggestion to obtain the conflict resolution success rate corresponding to each conflict resolution suggestion, and the suggestion priorities of each conflict resolution suggestion are determined according to the conflict resolution success rate.

[0058] Specifically, as Figure 2 shown, the conflict resolution suggestions (such as altitude adjustment, course change, speed control, etc.) can be generated through the decision support sub-module, and the suggestion priorities are optimized through reinforcement learning. Then, the report generation and visualization module automatically generates a structured report according to the ICAO standard format. The report includes but is not limited to conflict time, location, risk level, suggested measures, and historical similar cases. After that, the generated report can be displayed using a preset three-dimensional flight track visualization interface to support the interactive analysis of air traffic controllers. In this way, by integrating ICAO rules, air traffic controller experience, and historical data, a multi-dimensional risk scoring system is established, which can further improve the accuracy of report generation.

[0059] In this embodiment, first, the navigation data and meteorological data including the radar data and flight plan data of the target aircraft can be obtained, and the corresponding target data is constructed based on the navigation data and meteorological data. Then, the preset conflict probability prediction model based on the long short-term memory network determines the flight conflict probability of the target aircraft according to the target data, and based on the flight conflict probability of the target aircraft and the preset historical conflict data, the conflict risk level of the target aircraft is determined, so as to generate a conflict report of the target aircraft based on the flight conflict probability and the conflict risk level. Through the above technical solution, this embodiment can deeply integrate the large language model with the knowledge in the field of air traffic control, can integrate text, numerical, and image data, provide a more comprehensive basis for conflict analysis, and automatically generate a report that meets the ICAO standard format, reduce manual intervention, improve the report generation efficiency and consistency, and significantly improve the accuracy of conflict detection.

[0060] Based on the previous embodiment, it can be known that the present application can deeply integrate the large language model with the knowledge in the field of air traffic control to automatically generate reports. Next, the process of determining the flight conflict probability during report generation will be elaborated in detail in this embodiment. Refer to Figure 3 As shown, an embodiment of the present application discloses a method for determining flight conflict probability, including:

[0061] Step S21: Encode the target data through a preset encoder in a preset conflict probability prediction model to obtain encoded data.

[0062] In this embodiment, the preset conflict probability prediction model also introduces an attention mechanism to dynamically capture the spatio-temporal associations (such as route intersections, speed differences) between aircraft. Specifically, first, the time series data of each aircraft can be encoded through the preset encoder in the preset conflict probability prediction model, and corresponding hidden states can be generated.

[0063] Step S22: Determine the association features between different target aircraft according to the encoded data, and determine the attention weights of the association features.

[0064] In this embodiment, the association features between different target aircraft can be determined according to the encoded data, and the attention weights of the association features can be determined. That is to say, through the attention mechanism of the model in this embodiment, combined with the spatio-temporal features (position, speed difference) of the aircraft, the association weights between the aircraft can be calculated.

[0065] Step S23: Use the preset graph attention network in the preset conflict probability prediction model to determine the flight conflict probability of the target aircraft based on the association features and the attention weights.

[0066] In this embodiment, the preset graph attention network in the preset conflict probability prediction model can be used to determine the flight conflict probability of the target aircraft based on the association features and the attention weights. In this process, a graph attention network or a Transformer architecture can be used to aggregate relevant information, decode and generate future trajectories, and optimize the model parameters through training. Specifically, in the process of determining the flight conflict probability of the target aircraft, a long short-term memory network (LSTM) in the preset conflict probability model can be used to predict the target navigation trajectory of the target aircraft within a preset time period based on the target data, and perform similarity matching based on the historical navigation trajectory and the target navigation trajectory in the preset historical conflict data to obtain corresponding matching results, and then determine the flight conflict probability of the target aircraft according to the association features, the attention weights, and the matching results.

[0067] Moreover, when predicting the target flight trajectory of the target aircraft based on the target data, specifically, the flight trajectory of the target aircraft within a preset time period can be predicted a preset number of times based on the target data to obtain a corresponding number of initial flight trajectories, and then the initial flight trajectories are fitted to obtain the target flight trajectory of the target aircraft within the preset time period.

[0068] Based on the above technical solution, the preset conflict probability prediction model in this embodiment can predict the aircraft flight trajectory conflict through a four-dimensional trajectory conflict prediction algorithm. Specifically, it can predict the aircraft trajectory for the next 15 minutes based on a long short-term memory network, quantify the prediction uncertainty by combining Monte Carlo simulation, and introduce the dynamic time warping (DTW) algorithm to match the predicted trajectory with the historical conflict pattern. In this way, by combining LSTM, Monte Carlo simulation, DTW, and the attention mechanism, a four-dimensional trajectory prediction model that can both predict the trajectory and effectively identify conflicts is constructed. At the same time, the computational efficiency and scalability of the model can be ensured, making it applicable to real-time or near-real-time air traffic control systems. Specifically, the model distillation can be used to compress the large model parameters through real-time inference optimization technology to meet the real-time inference requirements of edge computing devices, and a dynamic adjustment mechanism for conflict alarm thresholds is designed to automatically optimize the detection sensitivity according to the airspace complexity. For example: Scenario 1: There are 3 aircraft in the airspace with similar speeds (low complexity) → threshold = 50 → only detect obvious conflicts; Scenario 2: There are 15 aircraft in the airspace with large speed differences (high complexity) → threshold = 10 → high-sensitivity detection of potential risks. In this way, by combining trajectory prediction and Monte Carlo simulation, the foresight and accuracy of conflict detection are significantly improved.

[0069] Based on the above technical solution, combined with the above embodiments, first, data such as radar, flight plan, and meteorology can be integrated to generate a standardized input vector, then the potential conflict points are predicted through a four-dimensional trajectory model, the risk probability is calculated to achieve conflict prediction, and then the conflict level and influence range are determined by combining domain rules and historical data for risk assessment. Then, the optimal resolution strategy is output based on reinforcement learning, the implementation effect of the strategy is simulated, and a report that complies with ICAO specifications is automatically generated and pushed to the controller terminal. Some specific embodiments are as follows:

[0070] Embodiment 1: System training process

[0071] 1. Data preparation:

[0072] Collect radar data (1 million records), flight plans (500,000 records), and historical conflict cases (2,000 cases) within a certain airspace in one year; and label the spatio-temporal characteristics of conflict events (such as relative speed, closest point of approach (CPA), and vertical separation).

[0073] 2. Model Training:

[0074] Adopt a mixed-precision training strategy, use the NVIDIA A100 GPU cluster for acceleration, and combine the loss function with cross-entropy (conflict classification) and mean squared error (risk score regression) for model training.

[0075] 3. Model Optimization:

[0076] Improve the robustness of the model to abnormal data through adversarial training; and deploy the model on a cloud server for real-time inference testing, and dynamically adjust the threshold according to the false alarm rate.

[0077] Example 2: Real-time Conflict Handling Scenario

[0078] 1. Data Input:

[0079] Radar data shows that two aircraft, A (heading 300°, altitude FL350) and B (heading 120°, altitude FL330), are approaching; the flight plan shows that the two aircraft will pass through the same route intersection in 5 minutes.

[0080] 2. Conflict Prediction:

[0081] The four-dimensional trajectory model predicts that the CPA of the two aircraft is 1.8 nautical miles (below the safety separation of 3 nautical miles), the conflict probability is 92%, and then the risk assessment module outputs a high risk level and recommends immediate intervention.

[0082] 3. Decision Support:

[0083] The system generates three suggestions: ① Aircraft A descends to FL320; ② Aircraft B turns left by 10°; ③ Both aircraft decelerate by 5% simultaneously; evaluate the success rate of conflict resolution for each strategy through the reinforcement learning module (95%, 88%, and 90% respectively), and recommend the priority ① > ③ > ②.

[0084] 4. Report Generation:

[0085] Automatically generate a bilingual Chinese-English report, including the conflict timestamp, 3D trajectory comparison chart, and implementation steps of the recommended measures.

[0086] Through the above technical solution, in this embodiment, by deeply integrating the large language model with the knowledge in the field of air traffic control, a conflict report generation system for air traffic control based on a large model is provided. The core processing module of the large model adopts an improved Transformer architecture, combines four-dimensional trajectory prediction with the attention mechanism, and the corresponding four-dimensional trajectory model adopts a prediction algorithm that combines LSTM and Monte Carlo simulation. Thus, by integrating multi-source data and constructing a domain-specific model, real-time detection, intelligent analysis, and automated report generation of conflicts are achieved, improving air traffic control efficiency and safety. Moreover, on the premise of ensuring real-time performance, the accuracy of conflict detection and the effectiveness of decision support are significantly improved, and it has broad application prospects. By further combining communication technologies such as 5G (5th Generation Mobile Communication Technology), data sharing and collaborative decision-making among multiple control centers can be realized.

[0087] See Figure 4 As shown, this embodiment of the present application also discloses a report generation device, including:

[0088] A data generation module 11, configured to obtain the current navigation data and meteorological data of the target aircraft, and construct corresponding target data based on the navigation data and the meteorological data; the navigation data includes the radar data and flight plan data of the target aircraft;

[0089] A probability determination module 12, configured to determine the flight conflict probability of the target aircraft according to the target data through a preset conflict probability prediction model; the preset conflict probability prediction model is constructed based on a long short-term memory network;

[0090] A level determination module 13, configured to determine the conflict risk level of the target aircraft based on the flight conflict probability of the target aircraft and preset historical conflict data;

[0091] A report generation module 14, configured to generate a conflict report of the target aircraft based on the flight conflict probability and the conflict risk level.

[0092] In this embodiment, the navigation data and meteorological data of the target aircraft, including the radar data and flight plan data of the target aircraft, can be obtained, and corresponding target data can be constructed based on the navigation data and meteorological data. Then, according to the target data, the flight conflict probability of the target aircraft can be determined by a preset conflict probability prediction model constructed based on a long short-term memory network, and based on the flight conflict probability of the target aircraft and preset historical conflict data, the conflict risk level of the target aircraft can be determined, so as to generate a conflict report for the target aircraft based on the flight conflict probability and the conflict risk level. In this way, by deeply integrating the large language model with the knowledge in the field of air traffic control, various data can be integrated, providing a more comprehensive basis for conflict analysis, and automating report generation, reducing manual intervention, improving the efficiency and consistency of report generation, and significantly improving the accuracy of conflict detection.

[0093] In some specific embodiments, the data generation module 11 specifically includes:

[0094] A data conversion unit, configured to obtain the navigation data and the meteorological data of the target aircraft, and perform format conversion on the navigation data and the meteorological data based on a preset data format;

[0095] A data alignment unit, configured to perform spatio-temporal alignment on the navigation data and the meteorological data after format conversion based on a preset time alignment standard and a space alignment standard, so as to obtain the corresponding target data.

[0096] In some specific embodiments, the probability determination module 12 specifically includes:

[0097] A data encoding unit, configured to encode the target data through a preset encoder in the preset conflict probability prediction model to obtain encoded data;

[0098] A weight determination unit, configured to determine the association features between different target aircraft according to the encoded data, and determine the attention weights of the association features;

[0099] A probability prediction unit, configured to use a preset graph attention network in the preset conflict probability prediction model to determine the flight conflict probability of the target aircraft based on the association features and the attention weights.

[0100] In some specific embodiments, the probability determination module 12 further includes:

[0101] A trajectory prediction sub-module, configured to use the long short-term memory network in the preset conflict probability model to predict the target navigation trajectory of the target aircraft within a preset time period based on the target data;

[0102] A trajectory matching sub-module, configured to perform similarity matching based on the historical navigation trajectory in the preset historical conflict data and the target navigation trajectory, so as to obtain a corresponding matching result;

[0103] Correspondingly, the probability determination module 12 specifically includes:

[0104] A probability determination unit, configured to determine the flight conflict probability of the target aircraft according to the association feature, the attention weight, and the matching result.

[0105] In some specific embodiments, the trajectory prediction sub-module specifically includes:

[0106] A trajectory prediction unit, configured to perform a preset number of predictions on the navigation trajectory of the target aircraft within the preset time period based on the target data, so as to obtain a corresponding number of initial navigation trajectories;

[0107] A trajectory fitting unit, configured to fit the initial navigation trajectories to obtain the target navigation trajectory of the target aircraft within the preset time period.

[0108] In some specific embodiments, the report generation device further includes:

[0109] A priority determination module, configured to generate a corresponding number of conflict resolution suggestions based on the conflict risk level of the target aircraft, and determine the suggestion priority of each conflict resolution suggestion;

[0110] Correspondingly, the report generation module 14 specifically includes:

[0111] A report generation unit, configured to generate a conflict report of the target aircraft based on the flight conflict probability, the conflict risk level, each conflict resolution suggestion, and the corresponding suggestion priority.

[0112] In some specific embodiments, the priority determination module specifically includes:

[0113] A scenario simulation unit, configured to construct an aircraft conflict simulation scenario corresponding to each conflict resolution suggestion based on the current navigation data and the meteorological data of the target aircraft;

[0114] A priority determination unit, configured to simulate each conflict resolution suggestion by using the aircraft conflict simulation scenario to obtain the conflict resolution success rate corresponding to each conflict resolution suggestion, and determine the suggestion priority of each conflict resolution suggestion according to the conflict resolution success rate.

[0115] Furthermore, an embodiment of the present application also discloses an electronic device, Figure 5It is a structural diagram of an electronic device 20 shown according to an exemplary embodiment, and the content in the figure should not be considered as any limitation on the scope of use of this application.

[0116] Figure 5 This is a schematic structural diagram of an electronic device 20 provided in an embodiment of this application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. Among them, the memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the report generation method disclosed in any of the foregoing embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0117] In this embodiment, the power supply 23 is used to provide operating voltages for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of this application, and no specific limitation is imposed on it here; the input / output interface 25 is used to obtain external input data or output data to the outside, and its specific interface type can be selected according to specific application needs, and no specific limitation is made here.

[0118] In addition, the memory 22, as a carrier for resource storage, may be a read-only memory, a random access memory, a magnetic disk, or an optical disc, etc., and the resources stored thereon may include an operating system 221, a computer program 222, etc., and the storage method may be temporary storage or permanent storage.

[0119] Among them, the operating system 221 is used to manage and control each hardware device and the computer program 222 on the electronic device 20, and it may be Windows Server, Netware, Unix, Linux, etc. In addition to the computer program that can be used to complete the report generation method executed by the electronic device 20 disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs that can be used to complete other specific tasks.

[0120] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the report generation method disclosed above. For the specific steps of this method, reference may be made to the corresponding content disclosed in the foregoing embodiments, and details will not be repeated here.

[0121] In the present specification, the various embodiments are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the embodiments, reference can be made to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple. For the relevant parts, reference can be made to the description in the method section.

[0122] Those skilled in the art can further realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0123] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be directly implemented by hardware, software modules executed by a processor, or a combination of the two. The software modules can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0124] Finally, it should also be noted that in this document, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising a..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element.

[0125] The above has introduced the technical solutions provided by this application in detail. Specific examples are used herein to elaborate on the principles and implementation manners of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, based on the idea of this application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. A report generation method, characterized in that, Including: Obtain the current navigation data and meteorological data of the target aircraft, and construct corresponding target data based on the navigation data and the meteorological data; the navigation data includes radar data and flight plan data of the target aircraft; Determine the flight conflict probability of the target aircraft according to the target data through a preset conflict probability prediction model; the preset conflict probability prediction model is constructed based on a long short-term memory network; Determine the conflict risk level of the target aircraft based on the flight conflict probability of the target aircraft and preset historical conflict data; Generate a conflict report for the target aircraft based on the flight conflict probability and the conflict risk level.

2. The report generation method according to claim 1, wherein The constructing corresponding target data based on the navigation data and the meteorological data includes: Obtain the navigation data and the meteorological data of the target aircraft, and perform format conversion on the navigation data and the meteorological data based on a preset data format; Perform spatio-temporal alignment on the navigation data and the meteorological data after format conversion based on a preset time alignment standard and a space alignment standard to obtain the corresponding target data.

3. The report generation method according to claim 1, characterized in that, The determining the flight conflict probability of the target aircraft according to the target data through a preset conflict probability prediction model includes: Encode the target data through a preset encoder in the preset conflict probability prediction model to obtain encoded data; Determine the association features between different target aircraft according to the encoded data, and determine the attention weights of the association features; Use a preset graph attention network in the preset conflict probability prediction model to determine the flight conflict probability of the target aircraft based on the association features and the attention weights.

4. The report generation method according to claim 3, wherein During the process of determining the flight conflict probability of the target aircraft according to the target data through a preset conflict probability prediction model, it further includes: Use a long short-term memory network in the preset conflict probability model to predict the target navigation trajectory of the target aircraft within a preset time period based on the target data; Perform similarity matching on the historical navigation trajectory in the preset historical conflict data and the target navigation trajectory to obtain a corresponding matching result; Correspondingly, the determining the flight conflict probability of the target aircraft includes: Determine the flight conflict probability of the target aircraft according to the association features, the attention weights and the matching result.

5. The report generation method according to claim 4, wherein The predicting the target navigation trajectory of the target aircraft within a preset time period based on the target data includes: Predict the navigation trajectory of the target aircraft within the preset time period a preset number of times based on the target data to obtain a corresponding number of initial navigation trajectories; Fit the initial navigation trajectories to obtain the target navigation trajectory of the target aircraft within the preset time period.

6. The report generation method according to any one of claims 1 to 5, characterized in that, After determining the conflict risk level of the target aircraft, it further includes: Generate corresponding conflict resolution suggestions based on the conflict risk level of the target aircraft, and determine the suggestion priorities of the conflict resolution suggestions; Correspondingly, generating a conflict report for the target aircraft based on the flight conflict probability and the conflict risk level includes: Generating the conflict report for the target aircraft based on the flight conflict probability, the conflict risk level, each conflict resolution suggestion, and the corresponding suggestion priority.

7. The report generation method according to claim 6, wherein Determining the suggestion priority of each conflict resolution suggestion includes: Based on the current navigation data and meteorological data of the target aircraft, constructing an aircraft conflict simulation scenario corresponding to each conflict resolution suggestion; Using the aircraft conflict simulation scenario to simulate each conflict resolution suggestion to obtain the conflict resolution success rate corresponding to each conflict resolution suggestion, and determining the suggestion priority of each conflict resolution suggestion according to the conflict resolution success rate.

8. A report generation device, characterized in that, Including: A data generation module, configured to obtain the current navigation data and meteorological data of the target aircraft, and construct corresponding target data based on the navigation data and the meteorological data; the navigation data includes the radar data and flight plan data of the target aircraft; A probability determination module, configured to determine the flight conflict probability of the target aircraft according to the target data through a preset conflict probability prediction model; the preset conflict probability prediction model is constructed based on a long short-term memory network; A level determination module, configured to determine the conflict risk level of the target aircraft based on the flight conflict probability of the target aircraft and preset historical conflict data; A report generation module, configured to generate a conflict report for the target aircraft based on the flight conflict probability and the conflict risk level.

9. An electronic device, characterized in that, The electronic device includes a processor and a memory; wherein, the memory is used to store a computer program, and the computer program is loaded and executed by the processor to implement the report generation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, For saving a computer program, the computer program, when executed by a processor, implements the report generation method according to any one of claims 1 to 7.

Images