An air space safety management and risk early warning prevention and control method and system

Abstract

The application discloses a kind of airspace safety management and risk early warning prevention and control method and system, it is related to space-time information processing technical field, including, unmanned aerial vehicle flight data, meteorological data and low-altitude environment data are collected and preprocessed, generate space-time data stream, space-time data stream is mapped to space grid system, generate and include the initial grid sequence of multilevel space resolution;Based on target density, meteorological disturbance and space constraint change information, the semantic entropy value of each grid unit in initial grid sequence is calculated, form weighted grid sequence, based on weighted grid sequence, according to preset threshold rule, grid level is dynamically adjusted, generate dynamic grid structure.The application constructs semantic entropy driven dynamic grid resolution adjustment mechanism and trajectory continuous reconstruction method based on prediction compensation, improves the adaptive ability of space-time data fusion under low-altitude complex environment and the continuity and accuracy of flight trajectory control.

Description

Technical Field

[0001] This invention relates to the field of spatiotemporal information processing technology, and in particular to a method and system for airspace safety management and risk early warning and prevention. Background Technology

[0002] With the rapid development of the low-altitude economy and the application of unmanned aerial vehicles (UAVs), spatial positioning and management technologies based on satellite navigation systems are gradually becoming an important foundation for the digital governance of low-altitude airspace. Among these technologies, spatial grid systems, through multi-level discretization of geospatial representation, achieve a unified mapping from continuous space to a discrete grid structure, providing standardized data structure support for spatial indexing, trajectory recording, and regional division of low-altitude targets. Building upon this, fusion processing methods combining multi-source spatiotemporal data are increasingly being applied to low-altitude operational monitoring and decision support, enabling the expression and analysis of the operational status of low-altitude targets within a unified spatial framework, thereby improving the structured and systematic level of spatial information processing.

[0003] However, in real-world, complex low-altitude environments, the dynamic nature of target motion, meteorological conditions, and spatial constraints means that existing grid representation methods based on fixed resolution or static hierarchical division still have room for improvement in terms of accuracy and adaptability in spatially sensitive areas. Furthermore, during continuous trajectory data acquisition, factors such as communication delays, sensor errors, and environmental occlusion can lead to localized gaps or breaks in the data. Traditional methods typically rely on interpolation or rule-based completion for repair, and their ability to represent trajectory continuity in complex, multi-source coupled scenarios still has room for improvement. In addition, the quantitative expression mechanism for the degree of influence of different factors during multi-source data fusion needs further enhancement to improve the ability to characterize the uncertainties of low-altitude environments. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a method for airspace safety management and risk early warning and prevention, which solves the problem of inconsistency between multi-source low-altitude spatiotemporal data fusion modeling and trajectory continuous control.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a method for airspace safety management and risk early warning and prevention, comprising, Collect UAV flight data, meteorological data, and low-altitude environmental data and preprocess them to generate a spatiotemporal data stream. Map the spatiotemporal data stream to a spatial grid system to generate an initial grid sequence containing multiple levels of spatial resolution. Based on the target density, meteorological disturbance and spatial constraint change information, the semantic entropy value of each grid cell in the initial grid sequence is calculated to form a weighted grid sequence. Based on the weighted grid sequence, the grid level is dynamically adjusted according to the preset threshold rule to generate a dynamic grid structure. The continuous trajectory points of the UAV are mapped onto a dynamic grid structure to generate a grid trajectory sequence arranged in chronological order. When the grid trajectory sequence breaks, prediction compensation is performed based on the historical grid trajectory sequence and semantic entropy weights to generate a continuous grid trajectory stream. Low-altitude flight control status information is then output based on the continuous grid trajectory stream.

[0007] As a preferred embodiment of the airspace safety management and risk early warning and prevention method of the present invention, the step of collecting UAV flight data, meteorological data and low-altitude environmental data and preprocessing them to generate a spatiotemporal data stream includes the following steps: Collect position data, speed data, altitude data and timestamp information generated during the flight of the UAV, and obtain basic flight trajectory data through airborne positioning equipment; Collect meteorological and environmental data, including wind speed, wind direction, air pressure, and visibility parameters; Collect low-altitude environmental constraint data, including no-fly zone information, obstacle distribution information, and airspace control rule information; The collected UAV flight data, meteorological data, and low-altitude environmental data are processed for time alignment and spatial coordinate unification, and then integrated according to the time scale to generate a spatiotemporal data stream.

[0008] As a preferred embodiment of the airspace safety management and risk early warning and prevention method of the present invention, the step of mapping spatiotemporal data streams to a spatial grid system to generate an initial grid sequence containing multiple levels of spatial resolution includes the following steps: Based on the preset spatial grid division rules, spatial index mapping processing is performed on the spatiotemporal data stream to establish a correspondence between continuous spatiotemporal data and preset grid spatial units; Based on the preset spatial grid hierarchical division mechanism, the spatial units are expanded by multi-scale grid encoding to generate corresponding multi-level grid representation results; The grid codes at different spatial resolution levels are organized and associated in chronological order to form a spatiotemporal grid sequence with a hierarchical structure. An initial grid representation system is constructed based on spatiotemporal grid sequences, enabling the initial grid sequences to simultaneously characterize the macroscopic distribution features and microscopic local details of low-altitude space.

[0009] As a preferred embodiment of the airspace safety management and risk early warning and control method of the present invention, the step of calculating the semantic entropy value of each grid cell in the initial grid sequence based on target density, meteorological disturbance and spatial constraint change information to form a weighted grid sequence includes the following steps: For each grid cell in the initial grid sequence, determine the target distribution characteristics, the degree of environmental disturbance change, and the intensity of spatial constraint influence within its corresponding spatial range; The distribution characteristics of the target, the degree of change of environmental disturbance, and the intensity of the influence of spatial constraints are standardized and quantified to obtain the quantitative values ​​of each factor; The semantic entropy value of the corresponding grid cell is obtained by fusing the quantified values ​​of each factor based on the preset weight coefficients. The semantic entropy value is used as the weight value of the grid cell, and the initial grid sequence is identified based on the weight value to form a weighted grid sequence.

[0010] As a preferred embodiment of the airspace safety management and risk early warning and prevention method of the present invention, the step of dynamically adjusting the grid level according to a preset threshold rule based on a weighted grid sequence to generate a dynamic grid structure includes the following steps: The weight value of each grid cell is compared with a preset threshold range to determine the spatial hierarchy adjustment direction of each grid cell; When the weight value of each grid cell is greater than the preset threshold, the spatial level corresponding to that grid cell is refined to improve the spatial representation accuracy. When the weight value of each grid cell is less than the preset threshold lower limit, the spatial level corresponding to that grid cell is merged to reduce the spatial representation complexity. Based on the spatial hierarchy adjustment results of each grid cell, the grid spatial structure is reconstructed to generate a dynamically changing grid structure.

[0011] As a preferred embodiment of the airspace safety management and risk early warning and prevention method of the present invention, the step of mapping continuous trajectory points of the UAV onto a dynamic grid structure to generate a grid trajectory sequence arranged in chronological order includes the following steps: The continuous trajectory data of the UAV during flight is spatially matched with the dynamic grid structure so that each trajectory position point corresponds to its grid cell. Based on the temporal order of the trajectory data, the temporal relationship of each trajectory point in the grid cell is determined; When multiple consecutive trajectory points are mapped to the same grid cell, they are merged into the same grid access record, and the corresponding time sequence information is retained; When a trajectory point crosses different grid cells, the connection relationship between the grid cells is established according to their spatial migration order. Based on grid access records and grid connection relationships, a grid trajectory sequence arranged in chronological order is generated.

[0012] As a preferred embodiment of the airspace safety management and risk early warning and control method of the present invention, the step of predicting and compensating for a continuous grid trajectory flow based on historical grid trajectory sequences and semantic entropy weights when a break occurs in the grid trajectory sequence, and outputting low-altitude flight control status information based on the continuous grid trajectory flow, includes the following steps: When the temporal continuity of the grid trajectory sequence is interrupted or the spatial jump anomaly occurs, the trajectory interval where the break occurs is determined; Based on the recorded grid access order in the historical grid trajectory sequence and the semantic entropy weight of the corresponding grid cell, a correlation analysis is performed on the trajectory evolution trend before and after the fracture interval. Based on the correlation analysis results, the missing grid trajectories within the fracture interval are completed to generate a continuous grid trajectory sequence; Based on continuous grid trajectory sequences, a continuous motion representation of UAVs in low-altitude space is constructed, generating a continuous grid trajectory flow; Based on the matching relationship between continuous grid trajectory flow and preset control rules, corresponding low-altitude flight control status information is generated.

[0013] Secondly, this invention provides an airspace safety management and risk early warning and prevention system, comprising, The multi-source spatiotemporal acquisition module collects UAV flight data, meteorological data, and low-altitude environmental data, and performs preprocessing to generate a spatiotemporal data stream; The grid mapping construction module maps spatiotemporal data streams to a spatial grid system, generating an initial grid sequence with multi-level spatial resolution. The semantic entropy weight calculation module calculates the semantic entropy value of the grid based on the target density, meteorological disturbance and spatial constraint change information, and generates a weighted grid sequence; The dynamic grid adjustment module adaptively adjusts the grid hierarchy based on semantic entropy weights to form a dynamically changing grid structure. The trajectory grid mapping module maps continuous trajectory points of the UAV to a dynamic grid structure, generating a grid trajectory sequence arranged in chronological order; The trajectory compensation and control module performs predictive compensation to generate a continuous grid trajectory flow when the trajectory sequence is broken, and outputs low-altitude flight control status information.

[0014] Thirdly, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the airspace security management and risk warning and prevention method as described in the first aspect of the present invention.

[0015] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the airspace security management and risk warning and prevention method as described in the first aspect of the present invention.

[0016] The beneficial effects of this invention are as follows: By collecting UAV flight data, meteorological data, and low-altitude environmental data and performing spatiotemporal consistency preprocessing, a unified spatiotemporal data stream is generated and mapped to a spatial grid system to form a multi-level initial grid sequence. This achieves a standardized spatial expression of multi-source heterogeneous information in the low-altitude environment, providing a unified data foundation for subsequent spatial analysis. By calculating semantic entropy values ​​based on target density, meteorological disturbances, and spatial constraint changes, and constructing a weighted grid sequence, a quantitative characterization of the uncertainty and spatial risk distribution in the low-altitude environment is achieved, enhancing the grid expression's responsiveness to complex environmental changes. Furthermore, by adaptively reconstructing the grid hierarchy through a dynamic threshold adjustment mechanism based on semantic entropy weights, a dynamic grid structure is generated, enabling adaptive adjustment of spatial resolution with environmental changes and improving the spatial expression accuracy and adaptability in complex scenarios. Finally, by mapping UAV trajectories to the dynamic grid structure and performing predictive compensation based on historical trajectories and semantic entropy weights in the event of trajectory breakage, a continuous grid trajectory stream is generated, achieving trajectory continuity recovery and behavior reconstruction, thus improving the continuous perception and control decision support capabilities during low-altitude flight. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of airspace safety management and risk early warning and prevention methods.

[0019] Figure 2 This is a schematic diagram of an airspace safety management and risk early warning and prevention system.

[0020] Figure 3 A flowchart for generating a continuous grid trajectory flow. Detailed Implementation

[0021] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0022] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0023] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0024] Reference Figures 1-3 As an embodiment of the present invention, this embodiment provides a method for airspace safety management and risk early warning and prevention, including the following steps: Collect and preprocess UAV flight data, meteorological data, and low-altitude environmental data to generate a spatiotemporal data stream. Map the spatiotemporal data stream to a spatial grid system to generate an initial grid sequence containing multiple levels of spatial resolution.

[0025] Specifically, it collects position data, speed data, altitude data, and timestamp information generated during the drone's flight, and obtains basic flight trajectory data through onboard positioning equipment; Collect meteorological and environmental data, including wind speed, wind direction, air pressure, and visibility parameters; Collect low-altitude environmental constraint data, including no-fly zone information, obstacle distribution information, and airspace control rule information; The collected UAV flight data, meteorological data, and low-altitude environmental data are processed for time alignment and spatial coordinate unification, and then integrated according to the time scale to generate a spatiotemporal data stream.

[0026] By collecting flight data, meteorological data, and environmental constraint data, and performing time alignment and spatial coordinate unification processing, a unified spatiotemporal data stream is generated, realizing the fusion expression of multi-source heterogeneous data under a unified spatiotemporal benchmark, and providing a standardized data foundation for subsequent low-altitude situation analysis and control.

[0027] Furthermore, based on the preset spatial grid division rules, spatial index mapping processing is performed on the spatiotemporal data stream to establish a correspondence between continuous spatiotemporal data and preset grid spatial units; The spatial index mapping process extracts spatial coordinate information from each data point in the spatiotemporal data stream, performs hierarchical encoding conversion according to preset spatial grid division rules, determines its corresponding grid unit, and realizes the mapping from continuous space to discrete grid space.

[0028] Based on the preset spatial grid hierarchical division mechanism, the spatial units are expanded by multi-scale grid encoding to generate corresponding multi-level grid representation results; The multi-scale grid coding unfolding, based on the hierarchical recursive rules of spatial grid coding, subdivides grid units level by level to generate grid coding sets at different spatial scales, forming a multi-level spatial resolution expression structure.

[0029] The grid codes at different spatial resolution levels are organized and associated in chronological order to form a spatiotemporal grid sequence with a hierarchical structure. An initial grid representation system is constructed based on spatiotemporal grid sequences, enabling the initial grid sequences to simultaneously characterize the macroscopic distribution features and microscopic local detail features of low-altitude space. The initial grid representation system is constructed based on a multi-level spatiotemporal grid sequence. The high-level grid is used to represent the overall distribution characteristics of low-altitude space, and the low-level grid is used to represent the detailed characteristics of local space, thus constructing a unified initial grid representation system.

[0030] By spatially indexing and mapping spatiotemporal data streams based on preset spatial grid partitioning rules, the correspondence between continuous spatiotemporal data and discrete grid spatial units is constructed, providing a unified spatial representation basis for low-altitude targets. By encoding and expanding spatial units at multiple scales according to the hierarchical partitioning mechanism of the spatial grid system, layered representation at different spatial scales is achieved, enhancing the hierarchical resolution capability of spatial information. By organizing and associating multi-resolution grid codes according to chronological order, a hierarchical spatiotemporal grid sequence is formed, realizing the structured and continuous representation of spatiotemporal information and improving the organization and traceability capabilities of low-altitude spatiotemporal data. By constructing an initial grid representation system based on multi-level spatiotemporal grid sequences, the grid sequence simultaneously possesses the ability to express macroscopic spatial distribution and microscopic local details, improving the completeness and refinement of spatial situational awareness in complex low-altitude environments.

[0031] Based on the target density, meteorological disturbances and spatial constraint change information, the semantic entropy value of each grid cell in the initial grid sequence is calculated to form a weighted grid sequence. Based on the weighted grid sequence, the grid level is dynamically adjusted according to the preset threshold rule to generate a dynamic grid structure.

[0032] Specifically, for each grid cell in the initial grid sequence, the target distribution characteristics, the degree of environmental disturbance change, and the intensity of spatial constraint influence within its corresponding spatial range are determined; The distribution characteristics of the target, the degree of change of environmental disturbance, and the intensity of the influence of spatial constraints are standardized and quantified to obtain the quantitative values ​​of each factor; The standardized quantification process normalizes the target distribution characteristics, the degree of environmental disturbance change, and the intensity of spatial constraint influence, so that different types of data can be expressed on a unified numerical scale, forming standardized quantified values.

[0033] The semantic entropy value of the corresponding grid cell is obtained by fusing the quantified values ​​of each factor based on the preset weight coefficients. The fusion calculation involves linearly summing each standardized quantized value based on a preset weighting coefficient to characterize the degree of uncertainty of each factor on the state of the grid cell, and generating a semantic entropy value to describe the complexity of the grid space.

[0034] The semantic entropy value is used as the weight value of the grid cell, and the initial grid sequence is identified based on the weight value to form a weighted grid sequence.

[0035] By extracting target distribution characteristics, environmental disturbance changes, and spatial constraint influence intensity from each grid cell in the initial grid sequence, a unified characterization of the multi-factor influence characteristics of low-altitude space is achieved, providing basic data support for grid state analysis. Standardized quantification of these multi-source influencing factors enables comparable expression of information across different dimensions, improving the standardization of multi-factor collaborative analysis. Semantic entropy values ​​are generated by fusing the quantification results based on preset weight coefficients, achieving a comprehensive representation of the spatial uncertainty and complexity of grid cells and enhancing the ability to identify sensitive areas of low-altitude environmental change. By using semantic entropy values ​​as weights to identify the initial grid sequence, differentiated expression of grid state is achieved, forming a weighted grid sequence with spatial differences, providing a basis for subsequent dynamic grid adjustments.

[0036] Furthermore, the weight value of each grid cell is compared with a preset threshold range to determine the spatial hierarchy adjustment direction of each grid cell; When the weight value of each grid cell is greater than the preset threshold, the spatial level corresponding to that grid cell is refined to improve the spatial representation accuracy. When the weight value of each grid cell is less than the preset threshold lower limit, the spatial level corresponding to that grid cell is merged to reduce the spatial representation complexity. Based on the spatial hierarchy adjustment results of each grid cell, the grid spatial structure is reconstructed to generate a dynamically changing grid structure.

[0037] By comparing the weight values ​​of each grid cell with a preset threshold range, the intensity of spatial changes in different grid cells is determined, providing a basis for subsequent spatial structure adjustments. Grid cells with weight values ​​exceeding the upper threshold are subjected to spatial hierarchy refinement, improving the accuracy of local spatial representation and enhancing the spatial resolution capability for highly variable regions. Grid cells with weight values ​​below the lower threshold are subjected to spatial hierarchy merging, reducing spatial representation complexity and optimizing overall grid representation efficiency. The grid spatial structure is reconstructed based on the hierarchical adjustment results of different grid cells, forming a dynamically changing grid structure, thus improving the adaptive adjustment capability and representation consistency of the spatial structure in complex low-altitude environments.

[0038] The continuous trajectory points of the UAV are mapped onto a dynamic grid structure to generate a grid trajectory sequence arranged in chronological order. When the grid trajectory sequence breaks, prediction compensation is performed based on the historical grid trajectory sequence and semantic entropy weights to generate a continuous grid trajectory stream. Low-altitude flight control status information is then output based on the continuous grid trajectory stream.

[0039] Specifically, the continuous trajectory data of the UAV during flight is spatially matched with the dynamic grid structure so that each trajectory position point corresponds to its grid cell. Based on the temporal order of the trajectory data, the temporal relationship of each trajectory point in the grid cell is determined; When multiple consecutive trajectory points are mapped to the same grid cell, they are merged into the same grid access record, and the corresponding time sequence information is retained; When a trajectory point crosses different grid cells, the connection relationship between the grid cells is established according to their spatial migration order. Based on grid access records and grid connection relationships, a grid trajectory sequence arranged in chronological order is generated.

[0040] By spatially matching continuous UAV trajectory data with a dynamic grid structure, the correspondence between trajectory position points and grid cells is constructed, thus providing a foundation for the spatial discrete representation of low-altitude motion states. By determining the temporal relationship within grid cells based on the chronological order of trajectory data, the temporal dimension organization of trajectory behavior is achieved, enhancing the temporal consistency of trajectory representation. By merging continuous trajectory points falling into the same grid cell and retaining temporal order information, redundant trajectory information is structurally compressed, thereby improving data representation efficiency. By establishing grid migration connection relationships for trajectory points spanning different grid cells, the spatial migration path is structurally represented, enhancing the traceability of trajectory spatial evolution relationships. Finally, based on grid access records and grid connection relationships, a grid trajectory sequence arranged in chronological order is generated, achieving the structured reconstruction and continuous representation capability of low-altitude flight trajectories.

[0041] Furthermore, when the temporal continuity of the grid trajectory sequence is interrupted or spatial jump anomalies occur, the trajectory interval where the break occurs is determined; The process of determining the trajectory interval where the break occurs involves performing continuity detection on the temporal information and spatial grid encoding of adjacent trajectory units in the grid trajectory sequence. When the time interval is abnormal or a non-adjacent jump occurs in the spatial grid, the trajectory is determined to be broken, and the break interval is located.

[0042] Based on the recorded grid access order in the historical grid trajectory sequence and the semantic entropy weight of the corresponding grid cell, a correlation analysis is performed on the trajectory evolution trend before and after the fracture interval. Based on the correlation analysis results, the missing grid trajectories within the fracture interval are completed to generate a continuous grid trajectory sequence; The missing grid trajectories within the fractured interval are completed by interpolating and reconstructing the missing trajectories within the fractured interval based on the historical trajectory evolution path and the current grid spatial adjacency relationship, thereby generating a continuous grid trajectory sequence.

[0043] Based on continuous grid trajectory sequences, a continuous motion representation of UAVs in low-altitude space is constructed, generating a continuous grid trajectory flow; Based on the matching relationship between continuous grid trajectory flow and preset control rules, corresponding low-altitude flight control status information is generated.

[0044] By identifying and determining the fractured trajectory intervals through temporal discontinuity interruptions or spatial jump anomalies in the grid trajectory sequence, the structured localization of trajectory continuity anomalies is achieved, providing a clear scope for subsequent repair. Correlation analysis of trajectory evolution trends before and after the fracture interval is conducted based on the access order and semantic entropy weights of historical grid trajectory sequences, enabling the inference of the continuity of trajectory spatial evolution patterns and providing behavioral constraints for missing trajectory recovery. By completing the missing grid trajectories within the fracture interval based on the correlation analysis results, the continuity of trajectory data is reconstructed, enhancing the complete representation of low-altitude motion processes. A continuous grid trajectory flow is constructed based on the completed continuous grid trajectory sequence, achieving a unified spatiotemporal representation of UAV motion states and enhancing the consistency and analyzability of trajectory representation. Finally, by matching the continuous grid trajectory flow with preset control rules to generate low-altitude flight control status information, the rule-based constraint expression of low-altitude flight behavior and control decision support are achieved, improving low-altitude flight safety management and situational awareness capabilities.

[0045] This embodiment also provides an airspace safety management and risk early warning and prevention system, including: The multi-source spatiotemporal acquisition module collects UAV flight data, meteorological data, and low-altitude environmental data, and performs preprocessing to generate a spatiotemporal data stream; The grid mapping construction module maps spatiotemporal data streams to a spatial grid system, generating an initial grid sequence with multi-level spatial resolution. The semantic entropy weight calculation module calculates the semantic entropy value of the grid based on the target density, meteorological disturbance and spatial constraint change information, and generates a weighted grid sequence; The dynamic grid adjustment module adaptively adjusts the grid hierarchy based on semantic entropy weights to form a dynamically changing grid structure. The trajectory grid mapping module maps continuous trajectory points of the UAV to a dynamic grid structure, generating a grid trajectory sequence arranged in chronological order; The trajectory compensation and control module performs predictive compensation to generate a continuous grid trajectory flow when the trajectory sequence is broken, and outputs low-altitude flight control status information.

[0046] This embodiment also provides a computer device applicable to the airspace safety management and risk warning and prevention method, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the airspace safety management and risk warning and prevention method proposed in the above embodiment.

[0047] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0048] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the airspace safety management and risk warning and control method proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0049] In summary, this invention achieves standardized spatial representation of multi-source heterogeneous information in the low-altitude environment by: collecting UAV flight data, meteorological data, and low-altitude environmental data and performing spatiotemporal consistency preprocessing to generate a unified spatiotemporal data stream; mapping this data to a spatial grid system to form a multi-level initial grid sequence, providing a unified data foundation for subsequent spatial analysis; calculating semantic entropy values ​​based on target density, meteorological disturbances, and spatial constraint changes, and constructing a weighted grid sequence to quantitatively characterize the uncertainty and spatial risk distribution of the low-altitude environment, enhancing the grid representation's responsiveness to complex environmental changes; further, adaptively reconstructing the grid hierarchy through a dynamic threshold adjustment mechanism based on semantic entropy weights to generate a dynamic grid structure, achieving adaptive adjustment of spatial resolution with environmental changes, improving the accuracy and adaptability of spatial representation in complex scenarios; and finally, mapping UAV trajectories to the dynamic grid structure and performing predictive compensation based on historical trajectories and semantic entropy weights in the event of trajectory breakage to generate a continuous grid trajectory stream, achieving trajectory continuity recovery and behavior reconstruction, and improving the continuous perception and control decision support capabilities during low-altitude flight.

[0050] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for airspace safety management and risk early warning and prevention, characterized in that: include, Collect UAV flight data, meteorological data, and low-altitude environmental data and preprocess them to generate a spatiotemporal data stream. Map the spatiotemporal data stream to a spatial grid system to generate an initial grid sequence containing multiple levels of spatial resolution. Based on the target density, meteorological disturbance and spatial constraint change information, the semantic entropy value of each grid cell in the initial grid sequence is calculated to form a weighted grid sequence. Based on the weighted grid sequence, the grid level is dynamically adjusted according to the preset threshold rule to generate a dynamic grid structure. The continuous trajectory points of the UAV are mapped onto a dynamic grid structure to generate a grid trajectory sequence arranged in chronological order. When the grid trajectory sequence breaks, prediction compensation is performed based on the historical grid trajectory sequence and semantic entropy weights to generate a continuous grid trajectory stream. Low-altitude flight control status information is then output based on the continuous grid trajectory stream.

2. The airspace safety management and risk early warning and prevention method as described in claim 1, characterized in that: The process of collecting and preprocessing UAV flight data, meteorological data, and low-altitude environmental data to generate a spatiotemporal data stream includes the following steps: Collect position data, speed data, altitude data and timestamp information generated during the flight of the UAV, and obtain basic flight trajectory data through airborne positioning equipment; Collect meteorological and environmental data, including wind speed, wind direction, air pressure, and visibility parameters; Collect low-altitude environmental constraint data, including no-fly zone information, obstacle distribution information, and airspace control rule information; The collected UAV flight data, meteorological data, and low-altitude environmental data are processed for time alignment and spatial coordinate unification, and then integrated according to the time scale to generate a spatiotemporal data stream.

3. The airspace safety management and risk early warning and prevention method as described in claim 2, characterized in that: The process of mapping spatiotemporal data streams to a spatial grid system to generate an initial grid sequence containing multiple levels of spatial resolution includes the following steps: Based on the preset spatial grid division rules, spatial index mapping processing is performed on the spatiotemporal data stream to establish a correspondence between continuous spatiotemporal data and preset grid spatial units; Based on the preset spatial grid hierarchical division mechanism, the spatial units are expanded by multi-scale grid encoding to generate corresponding multi-level grid representation results; The grid codes at different spatial resolution levels are organized and associated in chronological order to form a spatiotemporal grid sequence with a hierarchical structure. An initial grid representation system is constructed based on spatiotemporal grid sequences, enabling the initial grid sequences to simultaneously characterize the macroscopic distribution features and microscopic local details of low-altitude space.

4. The airspace safety management and risk early warning and prevention method as described in claim 3, characterized in that: The step of calculating the semantic entropy value of each grid cell in the initial grid sequence based on target density, meteorological disturbance, and spatial constraint change information to form a weighted grid sequence includes the following steps: For each grid cell in the initial grid sequence, determine the target distribution characteristics, the degree of environmental disturbance change, and the intensity of spatial constraint influence within its corresponding spatial range; The distribution characteristics of the target, the degree of change of environmental disturbance, and the intensity of the influence of spatial constraints are standardized and quantified to obtain the quantitative values ​​of each factor; The semantic entropy value of the corresponding grid cell is obtained by fusing the quantified values ​​of each factor based on the preset weight coefficients. The semantic entropy value is used as the weight value of the grid cell, and the initial grid sequence is identified based on the weight value to form a weighted grid sequence.

5. The airspace safety management and risk early warning and prevention method as described in claim 4, characterized in that: The process of dynamically adjusting the grid levels based on a weighted grid sequence according to a preset threshold rule to generate a dynamic grid structure includes the following steps: The weight value of each grid cell is compared with a preset threshold range to determine the spatial hierarchy adjustment direction of each grid cell; When the weight value of each grid cell is greater than the preset threshold, the spatial level corresponding to that grid cell is refined to improve the spatial representation accuracy. When the weight value of each grid cell is less than the preset threshold lower limit, the spatial level corresponding to that grid cell is merged to reduce the spatial representation complexity. Based on the spatial hierarchy adjustment results of each grid cell, the grid spatial structure is reconstructed to generate a dynamically changing grid structure.

6. The airspace safety management and risk early warning and prevention method as described in claim 5, characterized in that: The process of mapping continuous trajectory points of the UAV onto a dynamic mesh structure to generate a time-ordered sequence of mesh trajectories includes the following steps: The continuous trajectory data of the UAV during flight is spatially matched with the dynamic grid structure so that each trajectory position point corresponds to its grid cell. Based on the temporal order of the trajectory data, the temporal relationship of each trajectory point in the grid cell is determined; When multiple consecutive trajectory points are mapped to the same grid cell, they are merged into the same grid access record, and the corresponding time sequence information is retained; When a trajectory point crosses different grid cells, the connection relationship between the grid cells is established according to their spatial migration order. Based on grid access records and grid connection relationships, a grid trajectory sequence arranged in chronological order is generated.

7. The airspace safety management and risk early warning and prevention method as described in claim 6, characterized in that: When a break occurs in the grid trajectory sequence, prediction compensation is performed based on historical grid trajectory sequences and semantic entropy weights to generate a continuous grid trajectory stream, and low-altitude flight control status information is output based on the continuous grid trajectory stream, including the following steps: When the temporal continuity of the grid trajectory sequence is interrupted or the spatial jump anomaly occurs, the trajectory interval where the break occurs is determined; Based on the recorded grid access order in the historical grid trajectory sequence and the semantic entropy weight of the corresponding grid cell, a correlation analysis is performed on the trajectory evolution trend before and after the fracture interval. Based on the correlation analysis results, the missing grid trajectories within the fracture interval are completed to generate a continuous grid trajectory sequence; Based on continuous grid trajectory sequences, a continuous motion representation of UAVs in low-altitude space is constructed, generating a continuous grid trajectory flow; Based on the matching relationship between continuous grid trajectory flow and preset control rules, corresponding low-altitude flight control status information is generated.

8. An airspace safety management and risk early warning and control system, based on the airspace safety management and risk early warning and control method according to any one of claims 1 to 7, characterized in that: include, The multi-source spatiotemporal acquisition module collects UAV flight data, meteorological data, and low-altitude environmental data, and performs preprocessing to generate a spatiotemporal data stream; The grid mapping construction module maps spatiotemporal data streams to a spatial grid system, generating an initial grid sequence with multi-level spatial resolution. The semantic entropy weight calculation module calculates the semantic entropy value of the grid based on the target density, meteorological disturbance and spatial constraint change information, and generates a weighted grid sequence; The dynamic grid adjustment module adaptively adjusts the grid hierarchy based on semantic entropy weights to form a dynamically changing grid structure. The trajectory grid mapping module maps continuous trajectory points of the UAV to a dynamic grid structure, generating a grid trajectory sequence arranged in chronological order; The trajectory compensation and control module performs predictive compensation to generate a continuous grid trajectory flow when the trajectory sequence is broken, and outputs low-altitude flight control status information.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the airspace safety management and risk warning and prevention method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the airspace safety management and risk warning and prevention method according to any one of claims 1 to 7.

Images