Map-based position information display method and system

Abstract

The invention belongs to the field of flight navigation, particularly relates to a position information display method and system based on a map, and aims to solve the problem that in the prior art, a static grid division and separated prediction model is adopted, so that system misalignment is easily caused. The method comprises the following steps: in response to a position display request of airborne equipment, determining a to-be-displayed target area and a scene semantic type; constructing a multi-objective collaborative optimization function according to the scene semantic type, and obtaining an optimal grid division parameter by solving the optimization function; dividing the target area into a plurality of target grids according to the optimal grid division parameters, and constructing a space-time relation graph; predicting an access probability and access intensity by using a pre-trained space-time diagram neural network model; and according to the access probability and the access intensity, sequentially loading map information of each target grid in the airborne equipment. According to the method, the performance and efficiency of map information loading are effectively improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of flight navigation, and in particular relates to a method and system for displaying position information based on a map. Background Art

[0002] Currently, onboard map information loading systems generally employ a combination of static meshing and separate prediction models. In the meshing phase, the target area is typically mechanically segmented according to fixed-size rules (such as equally spaced latitude and longitude grids or recursive quadtree partitioning), without taking into account the semantic characteristics of different scenes. Prediction models, on the other hand, often employ independent spatial graph networks or temporal models.

[0003] The above technical solutions have limitations in practical applications. Static meshing and separate prediction models will cause the coordination of spatiotemporal features to fail, leading to inaccurate system performance in dynamic environments. Specifically, the static rules of the meshing process cannot adapt to changes in scene semantics, the separate spatial model ignores cross-regional migration patterns, and the temporal model cannot respond to the geographical diffusion effects of sudden disturbances. This ultimately leads to resource mismatch in loading decisions. For example, in key navigation areas (such as airport approach airspace), there is a risk of information loss due to prediction bias, while low-value areas (such as uninhabited hills) continue to occupy more than 60% of video memory resources, seriously restricting the aircraft's real-time obstacle avoidance capabilities and route planning efficiency. Summary of the Invention

[0004] To address the aforementioned problem in the prior art, namely, the technical problem that the prior art uses static meshing and a separate prediction model when loading onboard map information, causing a failure in the coordination of spatiotemporal features, thereby resulting in inaccurate performance in dynamic environments, the present invention proposes a map-based location information display method, comprising: In response to a position display request from an airborne device, determining a target area to be displayed and a scene semantic type corresponding to the target area; Constructing a multi-objective collaborative optimization function based on the scene semantic type, and obtaining optimal grid partitioning parameters by solving the optimization function, wherein the constraint objectives of the optimization function include a complexity minimization objective and a redundancy minimization objective. The complexity minimization objective is used to ensure that the computational load of the onboard equipment is lower than a preset threshold; the redundancy minimization objective is used to minimize duplicate caching of map information between adjacent grids; Dividing the target area into a plurality of target grids according to the optimal grid division parameters, and constructing a spatiotemporal relationship graph of the plurality of target grids in combination with map information of the target area; Based on the spatiotemporal relationship graph, a pre-trained spatiotemporal graph neural network model is used to predict the access probability and access intensity of each target grid within a preset future time period. The spatiotemporal graph neural network model is a memory-enhanced spatiotemporal metagraph network with a built-in inference engine and a multi-level memory pool. The inference engine is used to dynamically generate model parameters based on the scene semantic type of the target area. The multi-level memory pool is used to integrate real-time flight tracks and historical event features, and to impose constraints based on preset aviation rules to output prediction results that meet the constraints. According to the access probability and access intensity, map information of each target grid is sequentially loaded into the onboard device.

[0005] In some preferred embodiments, responding to the position display request of the onboard device and determining the target area to be displayed and the scene semantic type corresponding to the target area includes: Receive the display request sent by the airborne equipment, and parse the latitude and longitude range, altitude parameters and display scale contained in the request; Determine a three-dimensional space boundary according to the latitude and longitude range and the altitude layer parameter, wherein the three-dimensional space boundary includes a horizontal range boundary and a vertical height boundary; The target area is determined according to the three-dimensional space boundary and the display scale.

[0006] In some preferred embodiments, the method for obtaining the scene semantic type includes: Call the preset geographic information database to extract the distribution characteristics of land objects and airspace attributes in the target area; According to the feature distribution characteristics and airspace attributes, the scene semantic type corresponding to the target area is determined, and the scene semantic type includes an urban airspace type, an airway corridor type, and a special control area type.

[0007] In some preferred embodiments, constructing a multi-objective collaborative optimization function according to the scene semantic type, and solving the multi-objective collaborative optimization function by jointly solving multiple constraints to obtain optimal grid partitioning parameters includes: According to the scene semantic type, selecting the optimization goal and constraint condition associated therewith from a predefined optimization goal set and constraint condition set; Based on the selected optimization objectives and constraints, a multi-objective collaborative optimization function is constructed with the grid partitioning parameters as decision variables; The function is solved by using a multi-constraint optimization algorithm, and the optimal grid partitioning parameters that meet all the constraints are output.

[0008] In some preferred embodiments, dividing the target area into a plurality of target grids according to the optimal grid division parameters, and constructing a spatiotemporal relationship graph of the plurality of target grids in combination with map information of the target area includes: Decomposing the target area into a plurality of non-overlapping target grid sets according to the dynamic grid division strategy; Obtain historical trajectory data of airborne equipment and count the access frequency of each target grid in different time periods; A spatial adjacency matrix between grid cells is established, and periodic traffic pattern data are integrated to generate a spatiotemporal relationship graph structure with spatiotemporal weights.

[0009] In some preferred embodiments, the method of using a pre-trained spatiotemporal graph neural network model to predict the access probability and access intensity of each target grid within a preset future time period includes: Based on the constructed spatiotemporal relationship graph, the historical access sequence features of the target grid corresponding to each node in the graph and the spatial correlation features between nodes are extracted; Inputting the historical access sequence features and spatial association features into the multi-level memory pool, the multi-level memory pool includes at least a short-term memory unit and a long-term memory unit, which are respectively used to cache real-time track data and integrate historical airspace events and typical traffic pattern features; Based on the inference engine, combined with the scene semantic type of the current target area, model parameters suitable for the current scene are generated, and under the control of the inference engine, the output features of the multi-level memory pool are integrated to perform forward reasoning calculations; The preliminary results obtained by the forward reasoning calculation are matched and verified with the preset aviation rules, and the outputs that do not meet the safety constraints are corrected; Output the access probability and access intensity of each target grid in a future preset time period that is corrected to meet the aviation rule safety constraints.

[0010] In some preferred embodiments, sequentially loading map information of each target grid into the onboard device according to the access probability and the access intensity includes: Based on the preset weighted fusion function, the access probability and access intensity of the same target grid are linearly weighted to determine the priority score corresponding to each target grid; Determining airspace control requirements for the target area, and adjusting priority scores of target grids within airspace control areas within the target area; Arrange the target grids according to their corresponding priority scores to obtain a map loading sequence; According to the map loading sequence, the map information of each target grid is loaded.

[0011] In some preferred embodiments, loading the map information of each target grid according to the map loading sequence includes: parsing the map loading sequence, dividing the plurality of target grids into a plurality of loading batches, each loading batch including at least one target grid; According to the hardware performance of the onboard device, the loading rate and rendering strategy are assigned to the target meshes of different loading batches one by one; Map information of each target grid is presented on a display interface of the onboard device according to the loading rate and rendering strategy.

[0012] In some preferred embodiments, the training process of the spatiotemporal graph neural network model includes: Collecting historical aviation data of multiple regions, wherein the historical aviation data includes grid access records of airspaces of different scales; Performing a normalization process on the historical aviation data to eliminate regional scale and grid density differences to obtain a training sample set, wherein the normalization process includes: converting the physical dimensions of grids in different airspaces into dimensionless values ​​in a uniform scale coordinate system, and performing hierarchical normalization on grid access frequencies according to airspace type; Based on the training sample set, the model is iteratively trained using a small batch gradient descent algorithm. The loss function value on the validation set is calculated during each round of training, and the learning rate of the model is dynamically adjusted according to the loss function value until the preset training termination condition is met.

[0013] The embodiment of the present invention further provides a map-based location information display system, comprising: a data response module configured to respond to a position display request from an onboard device, determine a target area to be displayed, and a scene semantic type corresponding to the target area; a strategy calculation module configured to construct a multi-objective collaborative optimization function based on the scene semantic type, and obtain optimal grid partitioning parameters by solving the optimization function, wherein the constraint objectives of the optimization function include a complexity minimization objective and a redundancy minimization objective, wherein the complexity minimization objective is used to ensure that the computational load of the onboard equipment is below a preset threshold; and the redundancy minimization objective is used to minimize duplicate caching of map information between adjacent grids; a strategy execution module configured to divide the target area into a plurality of target grids according to the optimal grid division parameters, and construct a spatiotemporal relationship graph of the plurality of target grids in combination with map information of the target area; A model prediction module is configured to predict the access probability and access intensity of each target grid within a preset future time period based on the spatiotemporal relationship graph using a pre-trained spatiotemporal graph neural network model. The spatiotemporal graph neural network model is a memory-enhanced spatiotemporal metagraph network with a built-in inference engine and a multi-level memory pool. The inference engine is used to dynamically generate model parameters based on the scene semantic type of the target area. The multi-level memory pool is used to integrate real-time flight tracks and historical event features, and to impose constraints based on preset aviation rules to output prediction results that meet the constraints. A data loading module is configured to sequentially load map information of each target grid into the onboard device according to the access probability and the access intensity.

[0014] Beneficial effects of the present invention: Traditional methods use fixed grid divisions and static loading strategies, making them difficult to adapt to complex and changing flight environments. This invention responds to location requests by first identifying the scene semantic type of the target area and dynamically generating optimal grid division parameters based on this information. This allows the grid division to be adaptively adjusted based on the complexity of the actual scene, achieving intelligent and adaptive loading of onboard map information and significantly improving system performance and efficiency.

[0015] Based on the present invention, by constructing a multi-objective optimization function with complexity minimization and redundancy minimization as the core, the optimal grid parameters are solved, thereby ensuring that the divided grid can strictly control the computing load of the airborne equipment below the preset threshold, avoiding freezes or delays due to excessive rendering pressure, and can minimize the redundant data cache between adjacent grids, saving valuable memory and storage space, thereby achieving the optimal balance of performance under resource constraints.

[0016] This invention constructs a spatiotemporal relationship graph of grids and utilizes an innovative memory-enhanced spatiotemporal metagraph network model for prediction. This model not only captures the spatiotemporal dependencies between grids through a spatiotemporal graph neural network, but also enhances generalization capabilities by dynamically adjusting model parameters based on scene semantics through its built-in inference engine. Its multi-level memory pool integrates real-time flight paths with historical event features and performs constraint corrections based on preset aviation rules, resulting in more accurate predictions. Based on these predictions, map information is preloaded sequentially, ensuring that the data required by the user is ready before switching perspectives. This completely eliminates the lag caused by real-time loading in traditional methods and provides a smoother visual experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Other features, objects and advantages of the present application will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 11 is a flowchart of a method for displaying location information based on a map according to an embodiment of the present invention; Figure 2 It is a structural diagram of a computer system proposed in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The present application will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are intended only to illustrate the relevant invention and are not intended to limit the invention. It should also be noted that, for ease of description, only portions relevant to the relevant invention are shown in the accompanying drawings.

[0019] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0020] Reference Figure 1 ,like Figure 1 As shown, the present invention provides a method for displaying location information based on a map, comprising: Step S10, responding to a position display request from an onboard device, determining a target area to be displayed and a scene semantic type corresponding to the target area; Specifically, the location display request in this embodiment includes but is not limited to the following core input parameters: Current status of onboard equipment: Real-time geographic location: longitude, latitude, altitude (provided by GPS / INS); attitude and heading: pitch, roll, true heading / magnetic heading; motion status: airspeed, ground speed, vertical rate; display request parameters: Display mode: for example, map mode (MAP), planning mode (PLN), vertical situation display (VSD), airport map (APT), etc. The mode determines the processing logic; range / zoom level: the requested display range, such as 5 nautical miles, 10 nautical miles, full range, etc.

[0021] In this embodiment, the target area refers to the geographical range ultimately displayed on the screen, and its determination is based on the following criteria: Location-based centered region: With the current latitude and longitude of the onboard device as the geometric center, a rectangular latitude and longitude range (North-East-South-West) or a circular region is calculated based on the requested zoom level (for example, a 20-nautical-mile radius).

[0022] Heading-based look-ahead area: Based on the current ground speed and heading, the position is predicted for a period of time in the future, so that the heading always points to the top of the screen (heading-up mode).

[0023] Focus-based offset area: If the driver selects a specific target (such as ZOOM FPV or directly clicking an airport), the coordinates of the target will be used as the display center.

[0024] In this embodiment, after determining the target geographical area, by understanding the scene semantics of the area, it is determined how to optimally render and display information to highlight the key elements of the target area and deemphasize secondary information.

[0025] As a feasible implementation method, the elements contained in the target area can be determined by querying the onboard comprehensive database (such as the navigation database, terrain database, and airport database provided by Jeppesen and LIDO, etc.), and then the scene semantic type can be determined.

[0026] Step S20: constructing a multi-objective collaborative optimization function based on the scene semantic type, and obtaining optimal grid partitioning parameters by solving the optimization function. The constraints of the optimization function include a complexity minimization objective and a redundancy minimization objective. The complexity minimization objective is used to ensure that the computational load of the onboard equipment is below a preset threshold; the redundancy minimization objective is used to minimize duplicate caching of map information between adjacent grids. The grid partitioning parameter in this embodiment refers to a multi-dimensional parameter used to define the grid partitioning process, which at least includes: G_size: used to indicate the physical size of the base grid; LOD_levels: Used to indicate the number of levels of detail contained in each mesh. Different LODs correspond to different map data resolutions.

[0027] In this embodiment, at least two constraint objectives are quantified and combined into a solvable optimization function.

[0028] It is easy to understand that the computational load of the onboard equipment is strongly correlated with factors such as the number of mesh vertices that need to be processed and rendered and the LOD complexity. Therefore, based on its computational load, the number of vertices and LOD complexity of the mesh division can be effectively determined.

[0029] It should be noted that the redundancy referred to in this embodiment mainly comes from: Data overlap across mesh boundaries: For seamless rendering, adjacent meshes typically retain a certain amount of overlap at their boundaries. The larger the overlap, the higher the redundancy. Multi-LOD caching: The same geographic area typically caches data at multiple levels of detail (LOD) for quick switching. Obviously, the more LOD levels cached, the higher the redundancy.

[0030] Since two or more constraint objectives (reducing complexity, reducing redundancy) may conflict (for example, a finer grid may reduce redundancy but increase complexity), this embodiment requires multi-objective collaborative optimization.

[0031] For example, the two objective functions can be combined into an overall objective function through the weighted summation method, and the weight coefficient can be used to reflect the emphasis of the two objectives. The weight coefficient can be dynamically set according to the scene semantic type, so that the grid division is fully adapted to the limitations of the scene semantics.

[0032] The optimization function in this embodiment is a typical constrained nonlinear optimization problem, which can be solved by using a genetic algorithm (GA) or a particle swarm optimization (PSO), and this embodiment does not impose too many restrictions on this.

[0033] Step S30, dividing the target area into a plurality of target grids according to the optimal grid division parameters, and constructing a spatiotemporal relationship graph of the plurality of target grids in combination with map information of the target area; Specifically, the process of constructing the spatiotemporal relationship graph in this step includes: According to the dynamic grid division strategy, the target area is decomposed into multiple non-overlapping target grid sets; the historical trajectory data of the airborne equipment is obtained, and the access frequency of each target grid in different time periods is counted; a spatial adjacency matrix between grid cells is established, and the periodic traffic pattern data is integrated to generate a spatiotemporal relationship graph structure with spatiotemporal weights.

[0034] Step S40: Based on the spatiotemporal relationship graph, a pre-trained spatiotemporal graph neural network model is used to predict the access probability and access intensity of each target grid within a preset future time period. The spatiotemporal graph neural network model is a memory-enhanced spatiotemporal metagraph network. The memory-enhanced spatiotemporal metagraph network has a built-in inference engine and a multi-level memory pool. The inference engine is used to dynamically generate model parameters based on the scene semantic type of the target area. The multi-level memory pool is used to integrate real-time flight tracks and historical event features, and to impose constraints based on preset aviation rules, and output prediction results that meet the constraints. Step S50 : loading map information of each target grid in sequence into the onboard device according to the access probability and access intensity.

[0035] Specifically, in step S40, the access probability and access intensity of each target grid in a future preset time period are predicted using a pre-trained spatiotemporal graph neural network model, including: Based on the constructed spatiotemporal relationship graph, the historical access sequence features of the target grids corresponding to each node in the graph and the spatial correlation features between the nodes are extracted; the historical access sequence features and the spatial correlation features are input into the multi-level memory pool, which includes at least short-term memory units and long-term memory units, which are respectively used to cache real-time track data and integrate historical airspace events and typical traffic pattern features; based on the inference engine, combined with the scene semantic type of the current target area, model parameters suitable for the current scene are generated, and under the control of the inference engine, the output features of the multi-level memory pool are integrated to perform forward reasoning calculations; the preliminary results obtained by the forward reasoning calculations are matched and verified with the preset aviation rules, and the outputs that do not meet the safety constraints are corrected; the access probability and access intensity of each target grid in the future preset time period that meet the safety constraints of the aviation rules after correction are output.

[0036] More specifically, in the above embodiment, responding to the position display request of the airborne device and determining the target area to be displayed and the scene semantic type corresponding to the target area include: Receive a display request sent by an airborne device, parse the latitude and longitude range, altitude parameters, and display scale contained in the request; determine a three-dimensional space boundary based on the latitude and longitude range and altitude parameters, the three-dimensional space boundary including a horizontal range boundary and a vertical height boundary; and determine the target area based on the three-dimensional space boundary and the display scale.

[0037] More specifically, in the above embodiment, the method for obtaining the scene semantic type includes: Call a preset geographic information database to extract the distribution characteristics of land objects and airspace attributes in the target area; based on the land object distribution characteristics and airspace attributes, determine the scene semantic type corresponding to the target area, and the scene semantic type includes urban airspace type, route corridor type and special control area type.

[0038] More specifically, constructing a multi-objective collaborative optimization function according to the scene semantic type, and solving the multi-objective collaborative optimization function by jointly solving multiple constraints to obtain the optimal grid partitioning parameters includes: According to the semantic type of the scene, the associated optimization objectives and constraints are selected from a predefined set of optimization objectives and constraint conditions; based on the selected optimization objectives and constraints, a multi-objective collaborative optimization function with grid partitioning parameters as decision variables is constructed; a multi-constraint optimization solution algorithm is used to solve the function, and the optimal grid partitioning parameters that meet all constraints are output.

[0039] More specifically, in the above embodiment, dividing the target area into a plurality of target grids according to the optimal grid division parameters, and constructing a spatiotemporal relationship graph of the plurality of target grids in combination with map information of the target area includes: According to the dynamic grid division strategy, the target area is decomposed into multiple non-overlapping target grid sets; the historical trajectory data of the airborne equipment is obtained, and the access frequency of each target grid in different time periods is counted; a spatial adjacency matrix between grid cells is established, and the periodic traffic pattern data is integrated to generate a spatiotemporal relationship graph structure with spatiotemporal weights.

[0040] More specifically, in the above embodiment, sequentially loading the map information of each target grid in the onboard device according to the access probability and access intensity includes: Based on the preset weighted fusion function, the access probability and access intensity of the same target grid are linearly weighted to determine the priority score corresponding to each target grid; Determining airspace control requirements for the target area, and adjusting priority scores of target grids within airspace control areas within the target area; Arrange the target grids according to their corresponding priority scores to obtain a map loading sequence; According to the map loading sequence, the map information of each target grid is loaded.

[0041] More specifically, loading the map information of each target grid according to the map loading sequence includes: parsing the map loading sequence, dividing the plurality of target grids into a plurality of loading batches, each loading batch including at least one target grid; According to the hardware performance of the onboard device, the loading rate and rendering strategy are assigned to the target meshes of different loading batches one by one; Map information of each target grid is presented on a display interface of the onboard device according to the loading rate and rendering strategy.

[0042] More specifically, in the above embodiment, the training process of the spatiotemporal graph neural network model includes: Collecting historical aviation data of multiple regions, wherein the historical aviation data includes grid access records of airspaces of different scales; Performing a normalization process on the historical aviation data to eliminate regional scale and grid density differences to obtain a training sample set, wherein the normalization process includes: converting the physical dimensions of grids in different airspaces into dimensionless values ​​in a uniform scale coordinate system, and performing hierarchical normalization on grid access frequencies according to airspace type; Based on the training sample set, the model is iteratively trained using a small batch gradient descent algorithm. The loss function value on the validation set is calculated during each round of training, and the learning rate of the model is dynamically adjusted according to the loss function value until the preset training termination condition is met.

[0043] Reference below Figure 2 , which shows a structural diagram of a computer system of a server suitable for implementing the method and system embodiments of the present application. Figure 2 The server shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0044] like Figure 2 As shown, the computer system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303. Various programs and data required for system operation are also stored in the RAM 303. The CPU 301, ROM 302 and RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0045] The following components are connected to the input / output interface 305: an input section 306 including a keyboard, a mouse, and the like; an output section 307 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 303 including a hard disk and the like; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the input / output interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 310 as needed so that a computer program read therefrom can be installed into the storage section 308 as needed.

[0046] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 309, and / or installed from the removable medium 311. When the computer program is executed by the central processing unit 301, the above-mentioned functions defined in the method of the present application are executed. It should be noted that the computer-readable medium mentioned above in the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above.

[0047] More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code embodied on a computer-readable medium may be transmitted using any suitable medium, including, but not limited to, wireless, wire, optical cable, RF, etc., or any suitable combination thereof.

[0048] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0049] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0050] The terms "first", "second", etc. are used to distinguish similar objects, rather than to describe or indicate a particular order or sequence.

[0051] The term "comprise" or any other similar term is intended to cover non-exclusive inclusion such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0052] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings.

[0053] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for displaying location information based on a map, characterized in that: The method comprises: In response to a position display request from an airborne device, determining a target area to be displayed and a scene semantic type corresponding to the target area; Constructing a multi-objective collaborative optimization function based on the scene semantic type, and obtaining optimal grid partitioning parameters by solving the optimization function, wherein the constraint objectives of the optimization function include a complexity minimization objective and a redundancy minimization objective. The complexity minimization objective is used to ensure that the computational load of the onboard equipment is lower than a preset threshold; the redundancy minimization objective is used to minimize duplicate caching of map information between adjacent grids; Dividing the target area into a plurality of target grids according to the optimal grid division parameters, and constructing a spatiotemporal relationship graph of the plurality of target grids in combination with map information of the target area; Based on the spatiotemporal relationship graph, a pre-trained spatiotemporal graph neural network model is used to predict the access probability and access intensity of each target grid within a preset future time period. The spatiotemporal graph neural network model is a memory-enhanced spatiotemporal metagraph network with a built-in inference engine and a multi-level memory pool. The inference engine is used to dynamically generate model parameters based on the scene semantic type of the target area. The multi-level memory pool is used to integrate real-time flight tracks and historical event features, and to impose constraints based on preset aviation rules to output prediction results that meet the constraints. According to the access probability and access intensity, map information of each target grid is sequentially loaded into the onboard device.

2. The method for displaying location information based on a map according to claim 1, wherein: The responding to the position display request of the airborne device and determining the target area to be displayed and the scene semantic type corresponding to the target area include: Receive the display request sent by the airborne equipment, and parse the latitude and longitude range, altitude parameters and display scale contained in the request; Determine a three-dimensional space boundary according to the latitude and longitude range and the altitude layer parameter, wherein the three-dimensional space boundary includes a horizontal range boundary and a vertical height boundary; The target area is determined according to the three-dimensional space boundary and the display scale.

3. The map-based location information display method according to claim 2, characterized in that: The method for obtaining the scene semantic type includes: Call the preset geographic information database to extract the distribution characteristics of land objects and airspace attributes in the target area; According to the feature distribution characteristics and airspace attributes, the scene semantic type corresponding to the target area is determined, and the scene semantic type includes an urban airspace type, an airway corridor type, and a special control area type.

4. The method for displaying location information based on a map according to claim 1, wherein: The constructing of a multi-objective collaborative optimization function according to the scene semantic type, and solving the multi-objective collaborative optimization function by jointly solving multiple constraints to obtain optimal grid partitioning parameters includes: According to the scene semantic type, selecting the optimization goal and constraint condition associated therewith from a predefined optimization goal set and constraint condition set; Based on the selected optimization objectives and constraints, a multi-objective collaborative optimization function is constructed with the grid partitioning parameters as decision variables; The function is solved by using a multi-constraint optimization algorithm, and the optimal grid partitioning parameters that meet all the constraints are output.

5. The method for displaying location information based on a map according to claim 1, wherein: The step of dividing the target area into a plurality of target grids according to the optimal grid division parameters and constructing a spatiotemporal relationship graph of the plurality of target grids in combination with map information of the target area includes: Decomposing the target area into a plurality of non-overlapping target grid sets according to the optimal grid division parameters; Obtain historical trajectory data of airborne equipment and count the access frequency of each target grid in different time periods; A spatial adjacency matrix between grid cells is established, and periodic traffic pattern data are integrated to generate a spatiotemporal relationship graph structure with spatiotemporal weights.

6. The method for displaying location information based on a map according to claim 1, wherein: The method of using the pre-trained spatiotemporal graph neural network model to predict the access probability and access intensity of each target grid in a future preset time period includes: Based on the constructed spatiotemporal relationship graph, the historical access sequence features of the target grid corresponding to each node in the graph and the spatial correlation features between nodes are extracted; Inputting the historical access sequence features and spatial association features into the multi-level memory pool, the multi-level memory pool includes at least a short-term memory unit and a long-term memory unit, which are respectively used to cache real-time track data and integrate historical airspace events and typical traffic pattern features; Based on the inference engine, combined with the scene semantic type of the current target area, model parameters suitable for the current scene are generated, and under the control of the inference engine, the output features of the multi-level memory pool are integrated to perform forward reasoning calculations; Matching and verifying the preliminary results obtained by the forward reasoning calculation with the preset aviation rules, and correcting the outputs that do not conform to the preset aviation rules; Output the visit probability and visit intensity of each target grid in a future preset time period that are corrected and conform to the preset aviation rules.

7. The method for displaying location information based on a map according to claim 1, wherein: The step of sequentially loading map information of each target grid into the onboard device according to the access probability and the access intensity includes: Based on the preset weighted fusion function, the access probability and access intensity of the same target grid are linearly weighted to determine the priority score corresponding to each target grid; Determining airspace control requirements for the target area, and adjusting priority scores of target grids within airspace control areas within the target area; Arrange the target grids according to their corresponding priority scores to obtain a map loading sequence; According to the map loading sequence, the map information of each target grid is loaded.

8. The map-based location information display method according to claim 7, characterized in that: The step of loading the map information of each target grid according to the map loading sequence includes: parsing the map loading sequence, dividing the plurality of target grids into a plurality of loading batches, each loading batch including at least one target grid; According to the hardware performance of the onboard device, the loading rate and rendering strategy are assigned to the target meshes of different loading batches one by one; Map information of each target grid is presented on a display interface of the onboard device according to the loading rate and rendering strategy.

9. The method for displaying location information based on a map according to claim 1, wherein: The training process of the spatiotemporal graph neural network model includes: Collecting historical aviation data of multiple regions, wherein the historical aviation data includes grid access records of airspaces of different scales; Performing a normalization process on the historical aviation data to eliminate regional scale and grid density differences to obtain a training sample set, wherein the normalization process includes: converting the physical dimensions of grids in different airspaces into dimensionless values ​​in a uniform scale coordinate system, and performing hierarchical normalization on grid access frequencies according to airspace type; Based on the training sample set, the model is iteratively trained using a small batch gradient descent algorithm. The loss function value on the validation set is calculated during each round of training, and the learning rate of the model is dynamically adjusted according to the loss function value until the preset training termination condition is met.

10. A map-based location information display system, characterized in that: The system comprises: a data response module configured to respond to a position display request from an onboard device, determine a target area to be displayed, and a scene semantic type corresponding to the target area; a strategy calculation module configured to construct a multi-objective collaborative optimization function based on the scene semantic type, and obtain optimal grid partitioning parameters by solving the optimization function, wherein the constraint objectives of the optimization function include a complexity minimization objective and a redundancy minimization objective, wherein the complexity minimization objective is used to ensure that the computational load of the onboard equipment is below a preset threshold; and the redundancy minimization objective is used to minimize duplicate caching of map information between adjacent grids; a strategy execution module configured to divide the target area into a plurality of target grids according to the optimal grid division parameters, and construct a spatiotemporal relationship graph of the plurality of target grids in combination with map information of the target area; A model prediction module is configured to predict the access probability and access intensity of each target grid within a preset future time period based on the spatiotemporal relationship graph using a pre-trained spatiotemporal graph neural network model. The spatiotemporal graph neural network model is a memory-enhanced spatiotemporal metagraph network with a built-in inference engine and a multi-level memory pool. The inference engine is used to dynamically generate model parameters based on the scene semantic type of the target area. The multi-level memory pool is used to integrate real-time flight tracks and historical event features, and to impose constraints based on preset aviation rules to output prediction results that meet the constraints. A data loading module is configured to sequentially load map information of each target grid into the onboard device according to the access probability and access intensity.

Images