Space-time knowledge enhanced dynamic optimization method for urban multi-level low-altitude airspace functional area

Abstract

The embodiment of the invention provides a spatial-temporal knowledge enhanced dynamic optimization method for urban multi-level low-altitude airspace functional areas. The method comprises the following steps: acquiring low-altitude airspace basic data; mapping the data into a grid structure composed of a plurality of voxel units to generate an initial airspace data model; utilizing a knowledge graph framework to structurally describe low-altitude entity nodes and semantic relationships thereof to obtain entity node semantic information; constructing a low-altitude airspace rule base; dividing the low-altitude airspace according to the low-altitude airspace rule base; performing nonlinear subdivision on the initial airspace data model by adopting a nonlinear voxel subdivision algorithm to obtain a low-altitude airspace grid layering model, and endowing the entity node semantic information to a voxel unit of the low-altitude airspace grid layering model; and dynamically collecting real-time data, and dynamically optimizing the low-altitude airspace grid hierarchical model. In this way, integrated optimization of dynamic adjustment of the functional area and real-time updating of multi-source data can be achieved.

Description

Technical Field

[0001] The present invention generally relates to the field of low-altitude airspace modeling and dynamic regulation, and more specifically, to a method for dynamic optimization of urban multi-level low-altitude airspace functional zones enhanced with spatiotemporal knowledge. Background Art

[0002] With the rapid development of smart cities, low-altitude airspace has gradually become an important part of the intelligent transportation system, showing great potential in environmental monitoring, emergency response and resource allocation. However, low-altitude airspace has complex multivariate system characteristics, including topography, building distribution and dynamic meteorological conditions (such as wind speed, humidity, temperature), etc. Its dynamicity and diversity pose severe challenges to traditional modeling techniques.

[0003] Currently, low-altitude airspace modeling usually relies on static terrain data (such as digital elevation model DEM) and building distribution (such as three-dimensional model CityGML). These methods can provide airspace descriptions at fixed times.

[0004] However, in complex urban environments, low-altitude airspace usually needs to be subdivided into multiple functional zones (such as no-fly zones, buffer zones, and navigation zones), and multi-level divisions are combined with different altitude levels (such as ground activity layer, low-altitude flight layer, and high-altitude operation layer). However, existing methods often lack the ability to adapt to real-time environmental changes, and it is difficult to achieve integrated optimization of dynamic adjustment of functional zones and real-time update of multi-source data. Summary of the invention

[0005] According to an embodiment of the present invention, a collaborative hierarchical modeling scheme for urban multi-level low-altitude airspace networks enhanced with spatiotemporal knowledge is provided. This scheme can perform a refined representation of multi-dimensional information of low-altitude airspace in a complex urban environment, and achieve dynamic optimization and adjustment through knowledge reasoning, providing an intelligent solution for airspace resource management.

[0006] In a first aspect of the present invention, a method for dynamic optimization of urban multi-level low-altitude airspace functional areas enhanced with spatiotemporal knowledge is provided. The method comprises: Acquire low-altitude airspace basic data, wherein the low-altitude airspace basic data includes terrain data, building data, dynamic environment data and airspace rule information within the low-altitude airspace; Mapping the low-altitude airspace basic data to a grid structure composed of a plurality of voxel units to generate an initial airspace data model; Define low-altitude entity nodes and semantic relationships between low-altitude entity nodes; use the knowledge graph framework to structure the description of low-altitude entity nodes and their semantic relationships to obtain entity node semantic information; Constructing a low-altitude airspace rule base; the low-altitude airspace rule base includes airspace function zoning rules, dynamic environmental impact rules, and risk area adjustment rules; according to the low-altitude airspace rule base, the low-altitude airspace is divided into a low-speed traffic area, a high-speed traffic area, and a buffer no-fly area; The initial airspace data model is nonlinearly partitioned by a nonlinear voxel partitioning algorithm to obtain a low-altitude airspace grid hierarchical model, and entity node semantic information is assigned to the voxel unit of the low-altitude airspace grid hierarchical model; Dynamically collect real-time data, update the dynamic attribute values ​​of voxel units according to the real-time data, and dynamically optimize the low-altitude airspace grid layered model.

[0007] Furthermore, it also includes: After obtaining the basic data of low-altitude airspace, outliers in the dynamic environment data are eliminated, and missing information of terrain data and building data is supplemented.

[0008] Furthermore, the initial airspace data model includes a plurality of voxel units, each voxel unit is a cube, and the voxel unit is used to correspond to a position in the low-altitude airspace and carry attributes of the position.

[0009] Further, the low-altitude entity node includes static attributes and dynamic attributes; The semantic relationship between the low-altitude entity nodes includes: proximity relationship, influence relationship and inclusion relationship.

[0010] Furthermore, the nonlinear voxel partitioning algorithm is used to perform nonlinear partitioning on the initial airspace data model to obtain a low-altitude airspace grid layered model, including: Determine a nonlinear partitioning basis according to the low-altitude airspace rule base; Adjusting the voxel side length according to the nonlinear segmentation basis, segmenting the corresponding area of ​​the initial spatial domain data model according to the voxel side length to obtain a segmentation result; The segmentation results are layered according to the low-altitude airspace rule base to obtain a low-altitude airspace grid layered model.

[0011] Furthermore, it also includes: Morton coding is used to convert the spatial position of each voxel unit into a one-dimensional code.

[0012] Further, the updating of the dynamic attribute value of the voxel unit according to the real-time data includes: The low-altitude entity nodes and their semantic relationships in the entity node semantic information are updated by real-time data, and logical reasoning is performed according to the low-altitude airspace rule base to obtain the reasoning result of the spatiotemporal knowledge graph; Assign the dynamic attributes of the inference results to the voxel units.

[0013] In a second aspect of the present invention, a device for collaborative hierarchical modeling of urban multi-level low-altitude airspace networks enhanced with spatiotemporal knowledge is provided. The device comprises: A data acquisition module is used to acquire low-altitude airspace basic data, wherein the low-altitude airspace basic data includes terrain data, building data, dynamic environment data and airspace rule information within the low-altitude airspace; A data model generation module is used to map the low-altitude airspace basic data into a grid structure composed of a plurality of voxel units to generate an initial airspace data model; The semantic acquisition module is used to define the low-altitude entity nodes and the semantic relationships between the low-altitude entity nodes; the knowledge graph framework is used to structurally describe the low-altitude entity nodes and their semantic relationships to obtain the semantic information of the entity nodes; A rule base construction module is used to construct a low-altitude airspace rule base; the low-altitude airspace rule base includes airspace function zoning rules, dynamic environmental impact rules and risk area adjustment rules; according to the low-altitude airspace rule base, the low-altitude airspace is divided into a low-speed traffic area, a high-speed traffic area and a buffer no-fly area; A semantic assignment module is used to perform nonlinear segmentation on the initial airspace data model using a nonlinear voxel segmentation algorithm to obtain a low-altitude airspace grid hierarchical model, and assign entity node semantic information to the voxel unit of the low-altitude airspace grid hierarchical model; The optimization module is used to dynamically collect real-time data, update the dynamic attribute values ​​of the voxel units according to the real-time data, and dynamically optimize the low-altitude airspace grid layered model.

[0014] In a third aspect of the present invention, an electronic device is provided. The electronic device has at least one processor; and a memory connected to the at least one processor in communication; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the method of the first aspect of the present invention.

[0015] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and other features, advantages and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein: Figure 1A flow chart showing a method for dynamic optimization of multi-level low-altitude airspace functional areas in a city enhanced by spatiotemporal knowledge according to an embodiment of the present invention is shown; Figure 2 A flow chart of a low-altitude airspace grid hierarchical model according to an embodiment of the present invention is shown; Figure 3 A block diagram of a device for collaborative hierarchical modeling of a multi-level low-altitude airspace network in a city enhanced by spatiotemporal knowledge according to an embodiment of the present invention is shown; Figure 4 A block diagram of an exemplary electronic device capable of implementing embodiments of the present invention is shown.

[0017] Among them, 400 is an electronic device, 401 is a computing unit, 402 is a ROM, 403 is a RAM, 404 is a bus, 405 is an I / O interface, 406 is an input unit, 407 is an output unit, 408 is a storage unit, and 409 is a communication unit. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0020] In the present invention, the initial airspace data model is generated by low-altitude airspace basic data; the knowledge graph framework is used to structurally describe low-altitude entity nodes and their semantic relationships to obtain entity node semantic information; low-altitude airspace is divided into low-altitude airspace according to the low-altitude airspace rule library; the initial airspace data model is nonlinearly partitioned by a nonlinear voxel partitioning algorithm to obtain a low-altitude airspace grid hierarchical model, and the entity node semantic information is assigned to the voxel unit of the low-altitude airspace grid hierarchical model. In this way, the dynamic adjustment of functional areas and the integrated optimization of real-time updating of multi-source data are realized.

[0021] Figure 1 A flow chart of a method for dynamic optimization of urban multi-level low-altitude airspace functional zones enhanced by spatiotemporal knowledge according to an embodiment of the present invention is shown.

[0022] The method includes: S101. Acquire low-altitude airspace basic data, where the low-altitude airspace basic data includes terrain data, building data, dynamic environment data and airspace rule information within the low-altitude airspace.

[0023] In this embodiment, terrain data, building data, dynamic environment data and airspace rule information are unified into the global geographic coordinate system (WGS84, World Geodetic System-1984 Coordinate System) to ensure the consistency of data spatial reference.

[0024] Specifically, static data includes terrain data and building data. Terrain data includes digital elevation model (DEM, Digital Elevation Model) and digital terrain model (DTM, Digital Terrain Model). Building data includes three-dimensional building models (CityGML (General Data Model of City Template, City Geography MarkupLanguage), BIM (Building Information Modeling)), which are used to record the height, purpose and geometric boundaries of buildings. Dynamic environmental data includes low-altitude aircraft sensor data such as wind speed, humidity, and temperature. Airspace rule information includes polygonal boundary information of low-speed traffic areas, high-speed traffic areas, and buffer no-fly zones.

[0025] In this embodiment, it also includes: After obtaining the basic data of low-altitude airspace, outliers in the dynamic environment data are eliminated; and missing information of terrain data and building data is completed, such as: attribute values ​​of terrain data or buildings (such as height information of some buildings).

[0026] Specifically, outliers in dynamic environment data are eliminated by defining outliers as erroneous data points that deviate from the normal range or regularity. This embodiment quantifies them as data points that deviate from the average value by more than 3 standard deviations based on statistical analysis methods. In this case, outliers are replaced by linear interpolation methods. For terrain data, IDW (Inverse Distance Weight) is used for spatial interpolation, and for building information, the neighboring area inference method is used for information completion.

[0027] The normal range refers to the range in which the data value should be located at a certain time or in a certain area based on historical data, industry standards or physical limitations. For example, if the normal wind speed range in the low-altitude airspace of a city is 0-20m / s, if a data point with a wind speed of 50 m / s appears, it means that the data point may be abnormal. Regular errors refer to deviations caused by systematic problems in measurement equipment, transmission processes or calculation methods.

[0028] Eliminating outliers in dynamic environmental data and filling in missing information in terrain data and building data can help improve data quality, optimize modeling and prediction, enhance the reliability of decision support, and ensure the accuracy of subsequent analysis.

[0029] S102, mapping the low-altitude airspace basic data to a grid structure composed of a plurality of voxel units to generate an initial airspace data model.

[0030] Specifically, the terrain data, building data and dynamic environment data are mapped into a unified grid structure using spatial overlay analysis technology.

[0031] In this embodiment, the initial airspace data model includes a plurality of voxel units, each voxel unit is a cube, and the voxel unit is used to correspond to a position in the low-altitude airspace and carries the attributes of the position.

[0032] The voxel unit is a three-dimensional voxel unit: the entire target airspace is divided into regular three-dimensional voxel units, where the horizontal unit is longitude and latitude and the vertical unit is 10 meters.

[0033] Specifically, mapping the low-altitude airspace basic data to a grid structure composed of a number of voxel units means matching the terrain data and building data to the voxel units through a unified geographic coordinate, and then mapping the dynamic environment data and airspace control rules to the voxel units through the IDW point interpolation method, wherein the dynamic environment data and airspace control rules are usually point data.

[0034] The specific process of matching terrain data and building data to voxel units and then mapping dynamic environment data and airspace control rules to voxel units through the IDW point interpolation method is as follows: (1) Based on the terrain data, fill the ground height information of each voxel unit into the corresponding voxel unit.

[0035] (2) Based on the building data, the building information (such as height) within each voxel unit is mapped to the corresponding voxel; (3) For dynamic environmental data (such as wind speed), use the IDW interpolation method to interpolate these point data into the voxel units of the spatial grid; (4) Use the IDW interpolation method to map airspace control rules (such as low-speed traffic areas and buffer no-fly zones) to voxel units.

[0036] The initial airspace data model provides a detailed spatial representation of the low-altitude airspace, covering information such as terrain, buildings and controlled areas, providing a basis for subsequent airspace management and risk assessment.

[0037] S103. Define low-altitude entity nodes and semantic relationships between low-altitude entity nodes; use the knowledge graph framework to structure the description of low-altitude entity nodes and their semantic relationships to obtain entity node semantic information.

[0038] Specifically, low-altitude entity nodes include terrain nodes (such as digital elevation model nodes), building nodes (such as building height nodes), and dynamic environment nodes (such as wind speed nodes). Structured description refers to the structured description of the above low-altitude entity nodes and their semantic relationships through a knowledge graph framework (such as RDF (Resource Description Framework) / OWL (Web Ontology Language)) to form a triple <low-altitude entity, relationship, low-altitude entity>, such as "<building A, contained in, buffer no-fly zone B>".

[0039] This embodiment realizes the semantic description and dynamic reasoning of airspace stratification through low-altitude entity nodes and their semantic relationships. In addition, the low-altitude entity nodes and their semantic relationships are structured through the knowledge graph, realizing semantic data integration, so that airspace stratification not only relies on geometric models, but also has semantic expression capabilities.

[0040] In this embodiment, the low-altitude entity nodes include static attributes and dynamic attributes; the semantic relationships between the low-altitude entity nodes include: proximity relationships, influence relationships, and inclusion relationships.

[0041] Specifically, static attributes include location and geometric shape; dynamic attributes include wind speed and risk level; static attributes and dynamic attributes are used to express the basic elements in the airspace and their dynamic characteristics.

[0042] In this embodiment, the semantic relationship between low-altitude entity nodes includes: Proximity relationship, for example: the distance between a building and the boundary of the flight area is between 50 meters and 200 meters, indicating that the building is spatially adjacent to the flight area.

[0043] Influence relationships, for example, the impact of wind speed nodes on the risk level of the top area of ​​a building.

[0044] Containment relationships, such as a rule constraint that a specific area belongs to a buffered no-fly zone.

[0045] The knowledge graph establishes a semantic entity relationship network by defining the static and dynamic attributes of low-altitude entity nodes, and combines the rule engine to infer and update dynamic environmental data, such as dynamically adjusting regional risk levels or functional zoning according to changes in wind speed.

[0046] S104, constructing a low-altitude airspace rule base; the low-altitude airspace rule base includes airspace function zoning rules, dynamic environmental impact rules and risk area adjustment rules; according to the low-altitude airspace rule base, the low-altitude airspace is divided into a low-speed traffic area, a high-speed traffic area and a buffer no-fly zone.

[0047] In this embodiment, the low-altitude airspace is divided by guiding the knowledge graph, which can then be used for the hierarchical optimization of the initial airspace data model.

[0048] Specifically, the low-altitude airspace rule base includes: (1) Airspace functional zoning rules: describe the functional zoning of the airspace (such as low-speed traffic area, high-speed traffic area and buffer no-fly zone) and its dynamic adjustment conditions. For example, if the wind speed in the buffer zone exceeds the threshold (generally 10m / s), it will be adjusted to a buffer no-fly zone; if the distance to sensitive buildings is less than 500m, it will be adjusted to a buffer no-fly zone.

[0049] (2) Dynamic environmental impact rules: reflect the impact of the dynamic environment (such as wind speed and humidity) on airspace risks. For example, if the wind speed is > 10m / s and the humidity is > 90% or adjacent to a buffer zone, the regional risk level is increased to "high risk".

[0050] (3) Risk zone adjustment rules are used to dynamically assess regional risks and adjust zoning functions according to risk levels. For example, if the regional risk level reaches "high risk", access will be restricted or the buffer zone will be expanded.

[0051] In this embodiment, the division of low-altitude airspace includes: (1) Low-speed traffic areas, such as: , and the building distance is <50 meters.

[0052] (2) High-speed traffic areas, such as: , and the building density is less than 10 buildings / km 2 .

[0053] (3) Buffer no-fly zone, for example: 50m < distance to the no-fly zone boundary < 200m, and wind speed > 15m / s.

[0054] In this embodiment, the structured representation of the rule base is to use a knowledge graph framework (such as RDF / OWL) to represent the rules. The constructed rule base includes but is not limited to those shown in Table 1: Table 1 Rule Description condition implement No-fly zone setting <500 meters from sensitive buildings Area marked as "buffered no-fly zone" Wind speed influence If wind speed > 10m / s and adjacent to buffer zone Raise the regional risk level to "high risk" Low-speed traffic zone division Height range is between 20m and 50m; Building distance <50m Area marked as "Slow Traffic Area" High-speed traffic area division <![CDATA[The height range is between 50 meters and 150 meters; the building density < 10 buildings / km 2 > Area marked as "High Speed ​​Traffic Area" Buffer no-fly zone division Between 50m and 200m from the no-fly zone boundary; wind speed > 15m / s Area marked as "Buffered No-Fly Zone" Humidity Effect Humidity> 90% Reduce regional access priority Risk Diffusion High risk duration > 10 minutes Expand the buffer zone Priority Adjustment Area designated as an emergency mission area Raise the regional access priority to "priority mission" level Impact of building density <![CDATA[Building density > 50 buildings / km 2 and building height > 30 m]]> The area is marked as "complex construction area" and the priority of regional access is reduced Neighboring facility protection Distance to key facilities (such as airports, bridges) <300 meters Marked as "sensitive area", and the access priority of the area is increased to "priority protection" level S105, using a nonlinear voxel partitioning algorithm to perform nonlinear partitioning on the initial airspace data model to obtain a low-altitude airspace grid hierarchical model, and assigning entity node semantic information to the voxel units of the low-altitude airspace grid hierarchical model.

[0055] Specifically, a nonlinear voxel segmentation algorithm is used to perform nonlinear segmentation and digital encoding on the initial airspace to generate a refined voxel grid, achieving high-precision numerical representation of any position. Then, through dynamic reasoning of the knowledge graph, semantic information (such as the functional zoning of the airspace and the regional risk level) is given to the voxel unit to optimize the properties and structure of the hierarchical model, and finally a low-altitude airspace grid hierarchical model is obtained.

[0056] In this embodiment, if Figure 2 As shown, the nonlinear voxel partitioning algorithm is used to perform nonlinear partitioning on the initial airspace data model to obtain a low-altitude airspace grid layered model, including: S201. Determine a nonlinear partitioning basis according to the low-altitude airspace rule base.

[0057] In this embodiment, nonlinear partitioning refers to dividing the continuous three-dimensional space into a voxel grid composed of cubic units. The voxel unit is the smallest spatial representation unit, and each voxel carries static and dynamic properties.

[0058] Specifically, the basis for nonlinear subdivision is: through an adaptive subdivision strategy, the resolution of the grid unit is dynamically adjusted according to the spatial complexity (such as terrain undulation, building density), that is, in areas with low spatiotemporal complexity such as low-speed traffic areas and buffered no-fly zones, larger voxel units are generated to reduce calculation and model complexity; in areas with high spatiotemporal complexity such as high-speed traffic areas, smaller voxel units are generated to improve accuracy, that is, the subdivision accuracy of high-speed traffic areas is finer.

[0059] S202, traversing each voxel unit of the initial spatial data model, adjusting the voxel side length according to the nonlinear segmentation basis, segmenting the corresponding area of ​​the initial spatial data model according to the voxel side length, and obtaining a segmentation result.

[0060] Specifically, the voxel side length for: ; in, is the low-resolution voxel side length (e.g. 10 meters), is the high-resolution voxel side length (e.g. 1 meter).

[0061] S203, stratifying the segmentation results according to the low-altitude airspace rule library to obtain a low-altitude airspace grid stratification model.

[0062] Specifically, according to the division heights of the low-speed traffic area, the high-speed traffic area and the buffer no-fly area determined by the low-altitude airspace rule base, the segmentation results are layered to obtain a low-altitude airspace grid layered model.

[0063] In this embodiment, the semantic information of the entity node includes: functional zoning (low-speed traffic area, high-speed traffic area and buffer no-fly zone), risk information (risk level, risk source, risk duration), dynamic environmental attributes (wind speed, wind direction, humidity, temperature, visibility), static attributes (terrain height, building height, building density, infrastructure proximity), etc.

[0064] Specifically, the voxel unit also includes: using Morton coding to convert the spatial position of each voxel unit into a one-dimensional code for fast retrieval, update and query of voxel information.

[0065] By adopting a nonlinear voxel partitioning algorithm to partition the initial airspace data model, the low-altitude airspace grid model can provide a detailed airspace representation based on the actual characteristics and dynamic changes of the airspace.

[0066] S106, dynamically collect real-time data, update the dynamic attribute value of the voxel unit according to the real-time data, and dynamically optimize the low-altitude airspace grid layered model.

[0067] Specifically, the low-altitude airspace grid hierarchical model is dynamically optimized, including: dynamically optimizing each functional area in the low-altitude airspace grid hierarchical model, including expanding or shrinking the boundaries of functional areas, merging or refining partitions, to obtain a dynamically optimized low-altitude airspace network model.

[0068] In this embodiment, updating the dynamic attribute value of the voxel unit according to the real-time data includes: The low-altitude entity nodes and their semantic relationships in the entity node semantic information are updated by real-time data, and logical reasoning is performed according to the low-altitude airspace rule base to obtain the reasoning result of the spatiotemporal knowledge graph; Assign the dynamic attributes of the inference results to the voxel units.

[0069] Specifically, real-time data includes real-time environmental data and real-time flight sensor data. The dynamic attributes of the reasoning results include functional partitioning, risk level, etc.

[0070] Dynamic attribute updates make airspace management more flexible and responsive. As environmental conditions change (such as weather changes, airspace control area adjustments, etc.), real-time updates of the dynamic attribute values ​​of voxel units allow the airspace management system to make timely adjustments to meet the needs of aircraft and airspace resources.

[0071] According to the embodiments of the present invention, compared with the prior art, the present invention has the following advantages: By constructing a spatiotemporal knowledge graph and systematically describing spatial entities and their semantic relationships, dynamic reasoning and adjustment of airspace functional zoning are achieved, so that the airspace functional zoning can respond to environmental changes, changes in flight requirements and emergency situations in real time, thereby improving the flexibility and adaptability of the airspace management system.

[0072] By introducing nonlinear voxel technology, the airspace is discretized into refined multi-level grid units, and the multi-scale numerical representation of the airspace is realized in combination with dynamic environmental data. Through multi-scale numerical representation, it is possible to perform refined processing according to the actual complexity of the airspace, and use grids of different precisions for risk assessment in different airspace areas. Refined grids can accurately represent regional features such as urban dense areas, buildings, obstacles, etc., while coarse grids can be used for wide open areas. Fine grids can accurately identify small-scale risk factors, such as buildings, wind speed, etc.; in simpler areas, using coarser grids can reduce computational complexity. In this way, it can ensure that airspace features of different scales can be properly represented, improving the accuracy of the airspace model.

[0073] (3) By deeply integrating the knowledge graph and the voxel model, the present invention not only has the ability to accurately represent static geographic information, but also can respond to dynamic environmental data in real time, providing a new path for the refined management and intelligent regulation of airspace.

[0074] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described order of actions, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0075] The above is an introduction to a method embodiment. The following is a further explanation of the scheme of the present invention through a device embodiment having the same inventive concept as the method in the aforementioned embodiment.

[0076] like Figure 3 As shown, the device 300 includes: The data acquisition module 310 is used to acquire low-altitude airspace basic data, where the low-altitude airspace basic data includes terrain data, building data, dynamic environment data and airspace rule information within the low-altitude airspace.

[0077] The data model generation module 320 is used to map the low-altitude airspace basic data into a grid structure composed of a number of voxel units to generate an initial airspace data model.

[0078] The semantic acquisition module 330 is used to define low-altitude entity nodes and semantic relationships between low-altitude entity nodes; use the knowledge graph framework to structure the description of low-altitude entity nodes and their semantic relationships to obtain entity node semantic information.

[0079] The rule base construction module 340 is used to construct a low-altitude airspace rule base; the low-altitude airspace rule base includes airspace functional zoning rules, dynamic environmental impact rules and risk area adjustment rules; according to the low-altitude airspace rule base, the low-altitude airspace is divided into low-speed traffic areas, high-speed traffic areas and buffer no-fly areas.

[0080] The semantic assignment module 350 is used to perform nonlinear segmentation on the initial airspace data model using a nonlinear voxel segmentation algorithm to obtain a low-altitude airspace grid hierarchical model, and assign entity node semantic information to the voxel units of the low-altitude airspace grid hierarchical model.

[0081] The optimization module 360 ​​is used to dynamically collect real-time data, update the dynamic attribute value of the voxel unit according to the real-time data, and dynamically optimize the low-altitude airspace grid layered model.

[0082] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0083] In the technical solution of the present invention, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0084] According to an embodiment of the present invention, the present invention further provides an electronic device.

[0085] Figure 4 A schematic block diagram of an electronic device 400 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0086] The electronic device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0087] Multiple components in the electronic device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the electronic device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0088] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 401 performs the various methods and processes described above, such as methods S101 to S106. For example, in some embodiments, methods S101 to S106 may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the methods S101 to S106 described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to execute methods S101 - S106 in any other appropriate manner (eg, by means of firmware).

[0089] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0090] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0091] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0092] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for dynamic optimization of urban multi-level low-altitude airspace functional areas enhanced by spatiotemporal knowledge, characterized in that: include: Acquire low-altitude airspace basic data, wherein the low-altitude airspace basic data includes terrain data, building data, dynamic environment data and airspace rule information within the low-altitude airspace; Mapping the low-altitude airspace basic data to a grid structure composed of a plurality of voxel units to generate an initial airspace data model; Define low-altitude entity nodes and semantic relationships between low-altitude entity nodes; use the knowledge graph framework to structure the description of low-altitude entity nodes and their semantic relationships to obtain entity node semantic information; Constructing a low-altitude airspace rule base; the low-altitude airspace rule base includes airspace function zoning rules, dynamic environmental impact rules, and risk area adjustment rules; according to the low-altitude airspace rule base, the low-altitude airspace is divided into a low-speed traffic area, a high-speed traffic area, and a buffer no-fly area; The initial airspace data model is nonlinearly partitioned by a nonlinear voxel partitioning algorithm to obtain a low-altitude airspace grid hierarchical model, and entity node semantic information is assigned to the voxel unit of the low-altitude airspace grid hierarchical model; Dynamically collect real-time data, update the dynamic attribute values ​​of voxel units according to the real-time data, and dynamically optimize the low-altitude airspace grid layered model.

2. The method according to claim 1, characterized in that Also includes: After obtaining the basic data of low-altitude airspace, outliers in dynamic environmental data are eliminated; And complete the missing information of terrain data and building data.

3. The method according to claim 1, characterized in that The initial airspace data model includes a plurality of voxel units, each voxel unit is a cube, and the voxel unit is used to correspond to a position in the low-altitude airspace and carry the attributes of the position.

4. The method according to claim 1, characterized in that: The low-altitude entity node includes static attributes and dynamic attributes; The semantic relationship between the low-altitude entity nodes includes: proximity relationship, influence relationship and inclusion relationship.

5. The method according to claim 1, characterized in that The nonlinear voxel partitioning algorithm is used to perform nonlinear partitioning on the initial airspace data model to obtain a low-altitude airspace grid layered model, including: Determine a nonlinear partitioning basis according to the low-altitude airspace rule base; Adjusting the voxel side length according to the nonlinear segmentation basis, segmenting the corresponding area of ​​the initial spatial domain data model according to the voxel side length to obtain a segmentation result; The segmentation results are layered according to the low-altitude airspace rule base to obtain a low-altitude airspace grid layered model.

6. The method according to claim 3, characterized in that Also includes: Morton coding is used to convert the spatial position of each voxel unit into a one-dimensional code.

7. The method according to claim 1, characterized in that The updating of the dynamic attribute value of the voxel unit according to the real-time data comprises: The low-altitude entity nodes and their semantic relationships in the entity node semantic information are updated by real-time data, and logical reasoning is performed according to the low-altitude airspace rule base to obtain the reasoning result of the spatiotemporal knowledge graph; Assign the dynamic attributes of the inference results to the voxel units.

8. A spatiotemporal knowledge-enhanced urban multi-level low-altitude airspace network collaborative hierarchical modeling device, characterized in that: include: A data acquisition module is used to acquire low-altitude airspace basic data, wherein the low-altitude airspace basic data includes terrain data, building data, dynamic environment data and airspace rule information within the low-altitude airspace; A data model generation module is used to map the low-altitude airspace basic data into a grid structure composed of a plurality of voxel units to generate an initial airspace data model; The semantic acquisition module is used to define the low-altitude entity nodes and the semantic relationships between the low-altitude entity nodes; the knowledge graph framework is used to structurally describe the low-altitude entity nodes and their semantic relationships to obtain the semantic information of the entity nodes; A rule base construction module is used to construct a low-altitude airspace rule base; the low-altitude airspace rule base includes airspace function zoning rules, dynamic environmental impact rules and risk area adjustment rules; according to the low-altitude airspace rule base, the low-altitude airspace is divided into a low-speed traffic area, a high-speed traffic area and a buffer no-fly area; A semantic assignment module is used to perform nonlinear segmentation on the initial airspace data model using a nonlinear voxel segmentation algorithm to obtain a low-altitude airspace grid hierarchical model, and assign entity node semantic information to the voxel unit of the low-altitude airspace grid hierarchical model; The optimization module is used to dynamically collect real-time data, update the dynamic attribute values ​​of the voxel units according to the real-time data, and dynamically optimize the low-altitude airspace grid layered model.

9. An electronic device comprising at least one processor; and a memory connected in communication with the at least one processor; characterized in that: The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

Images