Multi-type meteorological risk course influence analysis and evaluation method

Abstract

The invention relates to the technical field of route management, in particular to a route influence analysis and evaluation method for multiple types of meteorological risks. Comprising the following steps that S100, input typhoon and volcanic ash related navigation notification messages are obtained and analyzed, meteorological key information is extracted, the meteorological key information comprises the meteorological occurrence position, the influence intensity and the moving trend, and the meteorological key information is converted into structural data; s200, according to the structured meteorological key information and the corresponding meteorological motion characteristics, constructing dynamic spatial position models under a plurality of different time dimensions in the future, and predicting the spatial distribution range of the meteorology in each time period through the dynamic spatial position models under the different time dimensions; and S300, acquiring space coordinate data of a target route, performing space conflict detection on the space coordinate data of the route and the dynamic space model under each time dimension, and identifying and outputting route segment information influenced by weather according to a conflict detection result.

Description

Technical Field

[0001] This invention relates to the field of route management technology, specifically to a method for analyzing and assessing the impact of multiple types of meteorological risks on routes. Background Technology

[0002] In the field of aviation safety, accurately assessing the potential impact of severe weather such as typhoons and volcanic ash on flight routes is a core element in ensuring flight safety and improving operational efficiency. However, the assessment methods and technical systems currently widely used in the industry suffer from a series of fundamental problems that urgently need to be addressed, severely restricting their effectiveness and reliability in practical applications. Existing technologies typically exhibit several disconnected modes. The most traditional and widely relied-upon method is the manual experience-based interpretation. Dispatchers or pilots are required to directly confront a large number of text-based NOTAMs, such as SIGMET or METAR messages, while simultaneously combining static weather forecast charts from various sources, relying on their personal professional knowledge and past experience to infer the potential impact of weather on scheduled routes. The core flaw of this approach lies in its heavy reliance on individual subjective judgment and the lack of objective and unified quantitative analysis standards, leading to potentially significant differences in assessment results for the same weather conditions among different personnel. At the same time, manual processing of massive amounts of unstructured text information is extremely slow and inefficient. When faced with complex scenarios such as typhoon season or large-scale volcanic eruptions with a wide range of meteorological factors, it is almost impossible to conduct rapid and comprehensive analysis and judgment. It is very easy to miss risks due to fatigue or negligence.

[0003] In addition, some relatively advanced systems attempt to use basic visualization overlay techniques, which involves simply overlaying raster images released by meteorological forecasting agencies, such as typhoon track forecast maps, with electronic aeronautical charts. While this method is an improvement over pure text reading, its limitations remain significant. First, it essentially remains at the level of visual observation and subjective judgment, unable to perform precise spatial calculations and logical reasoning. The system cannot automatically and accurately calculate the specific geometrical intersection of flight paths and meteorological impact areas, thus failing to answer crucial questions such as the specific affected flight segments, the extent of the impact, and the precise start and end times of the impact. Second, this model suffers from very poor timeliness. When meteorological data is updated, the analysis results often fail to update automatically, typically requiring manual reloading of data, re-overlaying of layers, and repeated visual comparisons. This lag creates a significant time difference between the information relied upon by decision-makers and the rapidly evolving actual weather situation, making it impossible to capture the dynamic risk changes brought about by the movement and development of meteorological systems. Summary of the Invention

[0004] The technical problem solved by this invention is to provide a method for analyzing and assessing the impact of multiple types of meteorological risks on flight routes, which can dynamically identify and capture the dynamic risk changes brought about by the movement and development of meteorological systems.

[0005] The basic solution provided by this invention is a method for analyzing and assessing the impact of multiple types of meteorological risks on flight routes, characterized by the following steps: S100. Obtain and parse the input typhoon and volcanic ash related navigation notice messages, extract key meteorological information, including the location of meteorological occurrence, intensity of impact, and movement trend, and convert the key meteorological information into structured data. S200. Based on structured key meteorological information and corresponding meteorological motion characteristics, construct dynamic spatial location models for multiple different time dimensions in the future, and predict the spatial distribution range of meteorology in each time period through dynamic spatial location models for different time dimensions. S300. Obtain the spatial coordinate data of the target route, perform spatial conflict detection between the spatial coordinate data of the route and the dynamic spatial model under each time dimension, and identify and output the information of the flight segment affected by the weather based on the conflict detection results. S400: When a new navigation message is received, S100-S300 are re-executed to update the information of the flight segments affected by the weather and generate an assessment report including the route identifier, the period of weather impact, and the degree of impact.

[0006] The principle and advantages of this invention lie in the parsing of raw NOTAM (Notice to Airmen) messages, transforming unstructured text information into structured data that machines can understand. Then, using this structured meteorological data, based on the mobile and changing nature of weather, it predicts where weather phenomena might occur in the near future, constructing these predictions into a series of models with defined spatial ranges and temporal sequences. Next, the specific flight path data of the planned aircraft is compared with these predicted meteorological spatial models, and calculations are performed to check for overlaps, thereby identifying which parts of the flight path are likely to encounter bad weather. Finally, the entire system incorporates an automatic update mechanism; once the latest weather report is received, the entire analysis process is re-run to ensure that the results are always based on the most up-to-date information.

[0007] Compared to existing technologies, this new method transforms the complex process that previously relied on manual reading, experience, and subjective judgment into a standardized, automated computer workflow. It goes beyond simply displaying meteorological data; it accurately calculates when and where flight routes and weather conditions might conflict, and it closely monitors changes in weather conditions, providing the latest analysis results in real time. This significantly improves the accuracy, efficiency, and timeliness of flight route risk analysis, offering more reliable protection for aviation safety.

[0008] Furthermore, S100 includes the following steps: S110. Perform data cleaning and standardize the format of the input NOTAM (Notification of Navigation) messages; S120. Using a natural language processing model, meteorological entity information is identified from the NOTAM (Notice to Airmen) message. The meteorological entity information includes geographic location entities, intensity description entities, and trend description entities. S130. Based on the preset meteorological domain knowledge engine, perform semantic association analysis on the identified meteorological entity information to extract the meteorological occurrence location, impact intensity, and movement trend; S140. Convert the obtained key meteorological information into structured data and store it.

[0009] First, the original reports, which contained inconsistent formats and redundant information, were cleaned and organized to prepare for subsequent analysis. Then, a natural language processing model was used to identify which words represented geographical locations, which described intensity, and which indicated direction and speed of movement from the sentences of the reports. Next, a pre-defined meteorological knowledge engine was used to correlate and interpret these previously identified fragmented information segments according to meteorological logic; for example, "moving northeast" and "30 kilometers per hour" were combined into a clear trend vector. Finally, all the accurately interpreted information was converted into a unified structured data format.

[0010] This solution addresses the challenge of machine-understanding the semantics of weather reports, overcoming the inefficiency and error-prone nature of traditional methods that rely entirely on manual interpretation or simple keyword matching. Through intelligent semantic parsing, it can more accurately extract key elements from the reports, laying a solid and reliable data foundation for subsequent modeling and analysis, and fundamentally improving the quality of the entire system's input data.

[0011] Furthermore, S200 includes the following steps: S210. Based on the type identifier in the meteorological key information, call the corresponding meteorological kinematic model. For typhoons, call the trajectory prediction model based on numerical weather prediction; for volcanic ash, call the diffusion model based on atmospheric diffusion equation. S220. Using the location of the meteorological event as the initial location, perform geometric extrapolation based on the movement trend to generate meteorological impact areas for the next 6 hours, 12 hours, 24 hours, and 72 hours; wherein, for typhoons, the meteorological impact area includes the range of impact heights extrapolated based on their intensity and structure; for volcanic ash, the meteorological impact area includes the height layers at which different concentrations are distributed extrapolated based on the vertical diffusion law of the atmosphere. S230. The meteorological impact areas for each time period are constructed into a set of vector polygons or a set of three-dimensional spatial geometries with geographic coordinate labels and associated vertical height range information, forming the dynamic spatial location model.

[0012] For different types of meteorological phenomena, the most suitable prediction model based on their physical laws is used for dynamic simulation. Specifically, for typhoons, a trajectory prediction model based on atmospheric physics and numerical calculation methods is used; for volcanic ash, a diffusion model describing how the material spreads with the wind in the atmosphere is used. Using the current location and movement trend of the meteorological event obtained from message parsing as the starting point for the model input, and then, like simulating a physical process, calculating step by step along its direction of movement and considering its motion characteristics, the extent to which the meteorological impact will expand at several key time points in the future, such as 6 hours, 12 hours, 24 hours, and 72 hours, is determined, distinguishing between the core area with the strongest destructive force and the relatively weaker peripheral areas. Finally, these calculated areas effective at different times are clearly represented using vector polygons with geographic coordinates, forming a dynamic model sequence that evolves over time.

[0013] Beyond simple circular markers or static forecast maps, the use of predictive models transforms weather risk forecasts from static snapshots of a single moment into a continuous picture showcasing its dynamic future development. This capability enables the anticipation of risks much further in advance, allowing for more proactive decision-making rather than reactive responses to already altered weather conditions.

[0014] Furthermore, S300 includes the following steps: S310. Import the three-dimensional spatial coordinate data of the flight path containing flight altitude layer information; S320. For each preset time node, the three-dimensional data of the flight route is spatiotemporally overlaid with the meteorological dynamic spatial model at the same time node. S330. Using a spatial conflict detection algorithm, determine segment by segment whether the flight path intersects with the meteorological influence area in both horizontal and vertical dimensions. S340. When a flight segment intersects with a meteorological impact area, the risk index is calculated based on the intensity of the impact of the meteorological impact area and the vertical height of the crossing, and the segment is marked as a meteorological impact segment.

[0015] The concept of three-dimensional space is introduced to perform conflict detection that better reflects actual flight conditions. The imported flight path data must include flight altitude information, so the flight path in the computer is not a two-dimensional line, but a trajectory with altitude in three-dimensional space. During analysis, for each pre-set future time point, the system precisely compares the spatial position of this three-dimensional flight path trajectory with a three-dimensional meteorological impact area model at the same time point. Using specialized spatial calculation algorithms, each segment of the flight path is checked segment by segment to see if it simultaneously enters the meteorological impact danger zone in both the horizontal and vertical directions.

[0016] This significantly improves the precision and accuracy of risk assessment. Traditional two-dimensional analysis cannot determine whether an aircraft can safely fly over a weather zone by changing altitude, while this method, through three-dimensional analysis, can identify risks that appear to overlap on a planar map but can actually be safely avoided by the aircraft by climbing or descending. It can also more accurately assess those truly unavoidable, high-risk flight segments, thus providing a more precise and reliable basis for flight decisions.

[0017] Furthermore, S400 includes the following steps: S410: Continuously receive NOTAM messages. When a new NOTAM message is received, identify whether the rate of change of key meteorological information exceeds a preset threshold. If it exceeds the preset threshold, trigger an update event. S420: Execute the S100-S300 response update event, update the dynamic spatial position model using the new NOTAM message and re-perform spatial conflict detection; S430. Based on the detection results, incrementally update the weather-affected flight segments and generate a new assessment report. The assessment report includes the route identifier, spatial coordinates of the risky flight segment, the predicted start and end times of weather impact, the risk level, and the corresponding weather confidence level.

[0018] A closed-loop system of intelligent response and incremental updates was established. It continuously monitors the input of NOTAM (Notices to Airmen) messages, but instead of blindly recalculating everything upon receiving new information, it first determines whether the information change brought by the new message is significant enough. Using key meteorological information, such as the rate of change of position or intensity, the system automatically triggers the entire update process—from parsing and modeling to analysis—only when this change exceeds a preset threshold, signifying a significant change in weather conditions. The system uses the latest message data to re-predict the movement and extent of weather events and re-detect flight path conflicts. When generating new assessment reports, it employs an incremental update strategy, updating only the information for flight segments whose status has changed due to weather conditions, rather than completely rewriting the entire system.

[0019] By setting a threshold for the rate of change, meaningless calculations caused by minor fluctuations in meteorological information are avoided, saving computing resources. The automatically triggered mechanism ensures that users can always obtain the latest analysis results without manual intervention, achieving true real-time risk monitoring. This intelligent dynamic updating capability allows the entire system to closely follow rapidly evolving weather conditions, providing continuous, timely, and efficient risk warning services for aviation operations.

[0020] Furthermore, S430 includes the following steps: S431. Collect conflict detection results, including the set of spatial coordinates of the affected flight segments, the predicted start and end times of the weather impact, the calculated risk index, and associate the key meteorological information that triggered this update event with its confidence level. S432. Assemble the collected data into a structured evaluation report according to a preset template. The evaluation report shall include at least the following: Report header information includes the report generation time, a unique report identifier, and the corresponding flight route identifier; Meteorological overview: including weather type, current core location, movement trend, data source, and overall confidence level; Risk Segment Details List: Each weather-affected segment creates a record item, including the spatial coordinates of the risk segment, the predicted start and end times of weather impact, the risk level, and the specific weather intensity and vertical altitude layer encountered within the segment; Overall Risk Summary: Based on all risky flight segments, the highest risk level, total distance of flight segments affected by weather, and estimated total duration of weather impact are calculated for the entire route; S433. Create a number for the assessment report generated this time, and compare it with the previous version of the report. If the set of affected flight segments or the risk level changes, mark it as a critical update and output the final assessment report. Attached Figure Description

[0021] Figure 1 This is a flowchart illustrating an embodiment of the method for analyzing and assessing the impact of various types of meteorological risks on flight routes according to the present invention. Detailed Implementation

[0022] The following detailed description illustrates the specific implementation method: The basic implementation examples are as follows: Figure 1 As shown: A method for analyzing and assessing the impact of various types of meteorological risks on flight routes, characterized by the following steps: S100. Obtain and parse the input typhoon and volcanic ash related navigation notice messages, extract key meteorological information, including the location of meteorological occurrence, intensity of impact, and movement trend, and convert the key meteorological information into structured data. S200. Based on structured key meteorological information and corresponding meteorological motion characteristics, construct dynamic spatial location models for multiple different time dimensions in the future, and predict the spatial distribution range of meteorology in each time period through dynamic spatial location models for different time dimensions. S300. Obtain the spatial coordinate data of the target route, perform spatial conflict detection between the spatial coordinate data of the route and the dynamic spatial model under each time dimension, and identify and output the information of the flight segment affected by the weather based on the conflict detection results. S400: When a new navigation message is received, S100-S300 are re-executed to update the information of the flight segments affected by the weather and generate an assessment report including the route identifier, the period of weather impact, and the degree of impact.

[0023] The system analyzes raw NOTAM (Notice to Airmen) messages, transforming unstructured text into machine-understandable structured data. Then, using this structured meteorological data, and considering the mobile and changing nature of weather, it predicts where weather phenomena might occur in the near future, constructing these predictions into a series of models with defined spatial ranges and temporal sequences. Next, the system compares the aircraft's planned flight path data with these predicted meteorological spatial models, calculating and checking for overlaps to identify which parts of the flight path are likely to encounter bad weather. Finally, the entire system incorporates an automatic update mechanism; upon receiving the latest weather report, it re-runs the entire analysis process to ensure the results are always based on the most up-to-date information.

[0024] Compared to existing technologies, this new method transforms the complex process that previously relied on manual reading, experience, and subjective judgment into a standardized, automated computer workflow. It goes beyond simply displaying meteorological data; it accurately calculates when and where flight routes and weather conditions might conflict, and it closely monitors changes in weather conditions, providing the latest analysis results in real time. This significantly improves the accuracy, efficiency, and timeliness of flight route risk analysis, offering more reliable protection for aviation safety.

[0025] S100 includes the following steps: S110. Perform data cleaning and standardize the format of the input NOTAM (Notification of Navigation) messages; S120. Using a natural language processing model, meteorological entity information is identified from the NOTAM (Notice to Airmen) message. The meteorological entity information includes geographic location entities, intensity description entities, and trend description entities. S130. Based on the preset meteorological domain knowledge engine, perform semantic association analysis on the identified meteorological entity information to extract the meteorological occurrence location, impact intensity, and movement trend; S140. Convert the obtained key meteorological information into structured data and store it.

[0026] First, the original reports, which contained inconsistent formats and redundant information, were cleaned and organized to prepare for subsequent analysis. Then, a natural language processing model was used to identify which words represented geographical locations, which described intensity, and which indicated direction and speed of movement from the sentences of the reports. Next, a pre-defined meteorological knowledge engine was used to correlate and interpret these previously identified fragmented information segments according to meteorological logic; for example, "moving northeast" and "30 kilometers per hour" were combined into a clear trend vector. Finally, all the accurately interpreted information was converted into a unified structured data format.

[0027] This solution addresses the challenge of machine-understanding the semantics of weather reports, overcoming the inefficiency and error-prone nature of traditional methods that rely entirely on manual interpretation or simple keyword matching. Through intelligent semantic parsing, it can more accurately extract key elements from the reports, laying a solid and reliable data foundation for subsequent modeling and analysis, and fundamentally improving the quality of the entire system's input data.

[0028] S200 includes the following steps: S210. Based on the type identifier in the meteorological key information, call the corresponding meteorological kinematic model. For typhoons, call the trajectory prediction model based on numerical weather prediction; for volcanic ash, call the diffusion model based on atmospheric diffusion equation. S220. Using the location of the meteorological event as the initial location, perform geometric extrapolation based on the movement trend to generate meteorological impact areas for the next 6 hours, 12 hours, 24 hours, and 72 hours; wherein, for typhoons, the meteorological impact area includes the range of impact heights extrapolated based on their intensity and structure; for volcanic ash, the meteorological impact area includes the height layers at which different concentrations are distributed extrapolated based on the vertical diffusion law of the atmosphere. S230. The meteorological impact areas for each time period are constructed into a set of vector polygons or a set of three-dimensional spatial geometries with geographic coordinate labels and associated vertical height range information, forming the dynamic spatial location model.

[0029] For different types of meteorological phenomena, the most suitable prediction model based on their physical laws is used for dynamic simulation. Specifically, for typhoons, a trajectory prediction model based on atmospheric physics and numerical calculation methods is used; for volcanic ash, a diffusion model describing how the material spreads with the wind in the atmosphere is used. Using the current location and movement trend of the meteorological event obtained from message parsing as the starting point for the model input, and then, like simulating a physical process, calculating step by step along its direction of movement and considering its motion characteristics, the extent to which the meteorological impact will expand at several key time points in the future, such as 6 hours, 12 hours, 24 hours, and 72 hours, is determined, distinguishing between the core area with the strongest destructive force and the relatively weaker peripheral areas. Finally, these calculated areas effective at different times are clearly represented using vector polygons with geographic coordinates, forming a dynamic model sequence that evolves over time.

[0030] Beyond simple circular markers or static forecast maps, the use of predictive models transforms weather risk forecasts from static snapshots of a single moment into a continuous picture showcasing its dynamic future development. This capability enables the anticipation of risks much further in advance, allowing for more proactive decision-making rather than reactive responses to already altered weather conditions.

[0031] S300 includes the following steps: S310. Import the three-dimensional spatial coordinate data of the flight path containing flight altitude layer information; S320. For each preset time node, the three-dimensional data of the flight route is spatiotemporally overlaid with the meteorological dynamic spatial model at the same time node. S330. Using a spatial conflict detection algorithm, determine segment by segment whether the flight path intersects with the meteorological influence area in both horizontal and vertical dimensions. S340. When a flight segment intersects with a meteorological impact area, the risk index is calculated based on the intensity of the impact of the meteorological impact area and the vertical height of the crossing, and the segment is marked as a meteorological impact segment.

[0032] The concept of three-dimensional space is introduced to perform conflict detection that better reflects actual flight conditions. The imported flight path data must include flight altitude information, so the flight path in the computer is not a two-dimensional line, but a trajectory with altitude in three-dimensional space. During analysis, for each pre-set future time point, the system precisely compares the spatial position of this three-dimensional flight path trajectory with a three-dimensional meteorological impact area model at the same time point. Using specialized spatial calculation algorithms, each segment of the flight path is checked segment by segment to see if it simultaneously enters the meteorological impact danger zone in both the horizontal and vertical directions.

[0033] This significantly improves the precision and accuracy of risk assessment. Traditional two-dimensional analysis cannot determine whether an aircraft can safely fly over a weather zone by changing altitude, while this method, through three-dimensional analysis, can identify risks that appear to overlap on a planar map but can actually be safely avoided by the aircraft by climbing or descending. It can also more accurately assess those truly unavoidable, high-risk flight segments, thus providing a more precise and reliable basis for flight decisions.

[0034] The S400 includes the following steps: S410: Continuously receive NOTAM messages. When a new NOTAM message is received, identify whether the rate of change of key meteorological information exceeds a preset threshold. If it exceeds the preset threshold, trigger an update event. S420: Execute the S100-S300 response update event, update the dynamic spatial position model using the new NOTAM message and re-perform spatial conflict detection; S430. Based on the detection results, incrementally update the weather-affected flight segments and generate a new assessment report. The assessment report includes the route identifier, spatial coordinates of the risky flight segment, the predicted start and end times of weather impact, the risk level, and the corresponding weather confidence level.

[0035] A closed-loop system of intelligent response and incremental updates was established. It continuously monitors the input of NOTAM (Notices to Airmen) messages, but instead of blindly recalculating everything upon receiving new information, it first determines whether the information change brought by the new message is significant enough. Using key meteorological information, such as the rate of change of position or intensity, the system automatically triggers the entire update process—from parsing and modeling to analysis—only when this change exceeds a preset threshold, signifying a significant change in weather conditions. The system uses the latest message data to re-predict the movement and extent of weather events and re-detect flight path conflicts. When generating new assessment reports, it employs an incremental update strategy, updating only the information for flight segments whose status has changed due to weather conditions, rather than completely rewriting the entire system.

[0036] By setting a threshold for the rate of change, meaningless calculations caused by minor fluctuations in meteorological information are avoided, saving computing resources. The automatically triggered mechanism ensures that users can always obtain the latest analysis results without manual intervention, achieving true real-time risk monitoring. This intelligent dynamic updating capability allows the entire system to closely follow rapidly evolving weather conditions, providing continuous, timely, and efficient risk warning services for aviation operations.

[0037] S430 includes the following steps: S431. Collect conflict detection results, including the set of spatial coordinates of the affected flight segments, the predicted start and end times of the weather impact, the calculated risk index, and associate the key meteorological information that triggered this update event with its confidence level. S432. Assemble the collected data into a structured evaluation report according to a preset template. The evaluation report shall include at least the following: Report header information includes the report generation time, a unique report identifier, and the corresponding flight route identifier; Meteorological overview: including weather type, current core location, movement trend, data source, and overall confidence level; Risk Segment Details List: Each weather-affected segment creates a record item, including the spatial coordinates of the risk segment, the predicted start and end times of weather impact, the risk level, and the specific weather intensity and vertical altitude layer encountered within the segment; Overall Risk Summary: Based on all risky flight segments, the highest risk level, total distance of flight segments affected by weather, and estimated total duration of weather impact are calculated for the entire route; S433. Create a number for the assessment report generated this time, and compare it with the previous version of the report. If the set of affected flight segments or the risk level changes, mark it as a critical update and output the final assessment report.

[0038] The above are merely embodiments of the present invention. Commonly known structures and characteristics are not described in detail here. Those skilled in the art are aware of all common technical knowledge in the field prior to the application date or priority date, are aware of all existing technologies in that field, and have the ability to apply conventional experimental methods prior to that date. Those skilled in the art can, under the guidance of this application, improve and implement this solution in combination with their own capabilities. Some typical known structures or methods should not be obstacles for those skilled in the art to implement this application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention. These should also be considered within the scope of protection of the present invention, and will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.

Claims

1. A method for analyzing and evaluating the impact of a route on multi-type weather risks, characterized in that: The method comprises the following steps: S100, acquiring and parsing an input typhoon or volcanic ash related navigation notice message, extracting meteorological key information including a meteorological occurrence position, an influence intensity and a movement trend, and converting the meteorological key information into structured data; S200, constructing a dynamic spatial position model in multiple different time dimensions in the future according to the structured meteorological key information and corresponding meteorological movement characteristics, and predicting a spatial distribution range of the meteorological phenomenon in each time period through the dynamic spatial position model in different time dimensions; S300, acquiring spatial coordinate data of a target route, performing spatial conflict detection on the spatial coordinate data of the route and the dynamic spatial model in each time dimension, and identifying and outputting a meteorologically affected route section information according to a conflict detection result; S400, when a new navigation message is received, re-executing S100-S300, updating the meteorologically affected route section information, and generating an evaluation report including a route identifier, a meteorologically affected time period and an influence degree.

2. The method of claim 1, wherein the method further comprises: The S100 comprises the following steps: S110, performing data cleaning and uniform formatting on the input navigation notice message; S120, identifying meteorological entity information from the navigation notice message by using a natural language processing model, the meteorological entity information including a geographical position entity, an intensity description entity and a trend description entity; S130, performing semantic correlation analysis on the identified meteorological entity information according to a preset meteorological field knowledge engine, and extracting a meteorological occurrence position, an influence intensity and a movement trend; S140, converting the parsed meteorological key information into structured data for storage. 3.The method of claim 2, wherein: The S200 comprises the following steps: S210, calling a corresponding meteorological kinematic model according to a type identifier in the meteorological key information, calling a trajectory prediction model based on numerical weather prediction for a typhoon, and calling a diffusion model based on an atmospheric diffusion equation for volcanic ash; S220, taking the meteorological occurrence position as an initial position, geometrically extrapolating according to the movement trend, and generating meteorological influence areas in time sequences of 6 hours, 12 hours, 24 hours and 72 hours in the future; wherein for a typhoon, the meteorological influence area includes an influence height range deduced based on its intensity and structure; and for volcanic ash, the meteorological influence area includes height layers in which different concentrations are distributed, deduced based on atmospheric vertical diffusion rules; S230, constructing the meteorological influence areas in each time period into a vector polygon set or a three-dimensional spatial geometric body set with geographical coordinate labels and associated vertical height range information, forming the dynamic spatial position model.

4. The method of claim 3, wherein the method further comprises: The S300 comprises the following steps: S310, importing route three-dimensional spatial coordinate data including flight height layer information; S320, for each preset time node, performing spatio-temporal superposition of the route three-dimensional data and the meteorological dynamic spatial model at the same time node; S330, judging whether the route exists intersection with the meteorological influence area in horizontal range and vertical height through a spatial conflict detection algorithm, and judging the route section by section. S340, when there is a flight segment intersecting with the weather impact area, calculate the risk index according to the impact intensity of the weather impact area it is located in and the vertical height it crosses, and mark it as a weather-affected flight segment.

5. The method of claim 4, wherein the method further comprises: determining a plurality of weather risk types; and determining a plurality of weather risk levels for each of the plurality of weather risk types. The S400 includes the following steps: S410, continuously receive flight notification messages, and when a new flight notification message is received, identify whether the change rate of weather key information exceeds a preset threshold, and when the preset threshold is exceeded, trigger an update event; S420, execute S100-S300 to respond to the update event, update the dynamic spatial position model with the new flight notification message and re-perform spatial conflict detection; S430, according to the detection result, incrementally update the weather-affected flight segment, and generate a new evaluation report, the evaluation report including flight route identification, risk flight segment spatial coordinates, predicted weather-affected start and end time, risk level and corresponding weather confidence.

6. The method of claim 5, wherein the method further comprises: The S430 includes the following steps: S431, collect conflict detection results, including the spatial coordinate set of the weather-affected flight segment, the predicted weather-affected start and end time, the calculated risk index, and the weather key information triggering this update event and its confidence; S432, assemble the collected data into a structured evaluation report according to a preset template, the evaluation report content including at least: Report header information: including report generation time, unique report identifier, corresponding flight route identification; Weather profile: including weather type, current core position, movement trend, data source and overall confidence; Risk flight segment detail list: each weather-affected flight segment creates a record item, including the spatial coordinates of the risk flight segment, the predicted weather-affected start and end time, the risk level, and the specific weather intensity and the vertical height layer affected in the flight segment; Overall risk summary: based on all risk flight segments, statistics of the highest risk level, total weather-affected flight segment distance and total weather-affected time; S433, create a number for the evaluation report generated this time, and compare it with the previous version of the report, if the affected flight segment set or the risk level changes, mark it as a key update, and output the final evaluation report.

Images