Disaster early warning method and device based on low earth orbit satellite and storage medium

Abstract

The invention discloses a disaster early warning method and device based on a low earth orbit satellite and a storage medium, and the method comprises the steps: determining a first wave position coverage map corresponding to a first ground region, and determining a first wave position of the first ground region; determining a first geographic traffic map and a first grid map corresponding to the first wave position, and generating a first grid connection relation map corresponding to the first wave position based on the first geographic traffic map and the first grid map; based on the first grid connection relation graph, constructing a graph structure corresponding to the first wave position; inputting the graph structure into a pre-trained graph neural network model, and outputting a first influence coefficient corresponding to each first node; and comparing the first influence coefficient of each first node with a preset influence coefficient threshold, and carrying out disaster early warning on users in a second ground area corresponding to the second grid. The technical effects that the possibly affected user can be accurately notified without consuming more resources, and then the safety of the user can be guaranteed are achieved.

Description

Technical Field

[0001] This application relates to the technical field of disaster warning, and particularly to a disaster warning method, device and storage medium based on low-earth orbit satellites. Background Technique

[0002] With the continuous development of technologies related to low-earth orbit satellites, low-earth orbit satellites have shown great advantages in aspects such as high transmission rate and high signal quality. Further, due to the fact that low-earth orbit satellites are relatively close to the ground and have high signal quality, high-resolution remote sensing images of specific regions are often taken using low-earth orbit satellites. For disaster warning, high-resolution remote sensing images can be taken using low-earth orbit satellites, and the surface deformation conditions, building collapse conditions, large congestion conditions, etc. in the areas surrounding the disaster can be captured. Thus, in the case where the low-earth orbit satellite captures the changes in the areas surrounding the disaster, warning information can be further sent to the mobile terminals of users by using the low-earth orbit satellite, ensuring the safety of users' lives and normal activities.

[0003] However, if warning information is sent to all users in the areas surrounding the disaster by using a low-earth orbit satellite, then since the low-earth orbit satellite needs to communicate with a large number of mobile terminals, the low-earth orbit satellite will consume a lot of resources; further, since some users may not live or work in the areas surrounding the disaster, it is not very necessary for users who have no intersection with the areas surrounding the disaster. Thus, the method of using a low-earth orbit satellite to send warning information in the prior art requires the low-earth orbit satellite to consume a lot of resources and is not very necessary for some users who have no intersection with the areas surrounding the disaster.

[0004] The publication number is CN118470939A, and the name is a disaster warning information generation method and device based on satellite remote sensing data. It includes: obtaining the electronic map, multi-source satellite remote sensing data, and geological disaster distribution map of the observation area; mapping multiple transportation hub stations to the geological disaster distribution map, obtaining multiple mapped transportation hub stations and then dividing them to obtain a risk-mapped transportation hub station subset and a non-risk-mapped transportation hub station subset; for the risk-mapped transportation hub stations, determining the geological disaster risk probability and geological disaster level according to optical remote sensing data and radar remote sensing data; for the non-risk-mapped transportation hub stations, determining the optical remote sensing data or radar remote sensing data to generate the corresponding geological disaster risk probability; generating the geological disaster risk warning information of the observation area.

[0005] The publication number is CN118114992A, and the name is a remote sensing satellite geological disaster warning method. It includes the following steps: based on the remote sensing satellite information, analyzing the terrain data and soil type in the area, and combining with the rainfall and vegetation coverage rate to evaluate the changes in hydrological conditions and geological conditions, and generating a geological risk data set.

[0006] Regarding the method of sending early warning information to users in the above-mentioned existing technologies, there is a technical problem that low-orbit satellites consume a large amount of resources and it is not very necessary for some users who do not intersect with the areas around the disaster. Currently, no effective solution has been proposed. Summary of the Invention

[0007] Embodiments of the present disclosure provide a disaster warning method, device, and storage medium based on low-orbit satellites, so as to at least solve the technical problem in the existing technology that the method of sending early warning information to users requires low-orbit satellites to consume a large amount of resources and is not very necessary for some users who do not intersect with the areas around the disaster.

[0008] According to one aspect of the embodiments of the present disclosure, a disaster warning method based on low-orbit satellites is provided, including: determining a first wave position coverage map corresponding to a first ground area, and determining a first wave position where the first ground area is located; determining a first geographical traffic map and a first grid map corresponding to the first wave position, and generating a first grid connectivity relationship map corresponding to the first wave position based on the first geographical traffic map and the first grid map, where the first geographical traffic map includes road connection relationships within the first wave position, and the first grid map includes a plurality of first grids corresponding to the first wave position; constructing a graph structure corresponding to the first wave position based on the first grid connectivity relationship map, where the first nodes of the graph structure correspond to each first grid, and the edges of the graph structure correspond to the connectivity relationships of each first grid; inputting the graph structure into a pre-trained graph neural network model, and outputting a first influence coefficient corresponding to each first node; and comparing the first influence coefficient of each first node with a pre-set influence coefficient threshold, and when the first influence coefficient is greater than the influence coefficient threshold, determining the corresponding first node and the second grid corresponding to the first node, and giving a disaster warning to users in the second ground area corresponding to the second grid.

[0009] According to another aspect of the embodiments of the present disclosure, a storage medium is further provided. The storage medium includes a stored program, where, when the program runs, the method described in any one of the above is executed by a processor.

[0010] According to another aspect of the embodiments of the present disclosure, there is also provided a disaster warning device based on a low-earth orbit satellite, including: a wave position coverage map determination module, configured to determine a first wave position coverage map corresponding to a first ground area and determine a first wave position where the first ground area is located; a grid connectivity relationship map generation module, configured to determine a first geographic traffic map and a first grid map corresponding to the first wave position, and generate a first grid connectivity relationship map corresponding to the first wave position based on the first geographic traffic map and the first grid map, where the first geographic traffic map includes road connection relationships within the first wave position, and the first grid map includes a plurality of first grids corresponding to the first wave position; a graph structure construction module, configured to construct a graph structure corresponding to the first wave position based on the first grid connectivity relationship map, where the first nodes of the graph structure correspond to the respective first grids, and the edges of the graph structure correspond to the connectivity relationships of the respective first grids; an influence coefficient output module, configured to input the graph structure into a pre-trained graph neural network model and output a first influence coefficient corresponding to each first node; and a disaster warning module, configured to compare the first influence coefficients of the respective first nodes with a pre-set influence coefficient threshold, and in the case where the first influence coefficient is greater than the influence coefficient threshold, determine the corresponding first node and a second grid corresponding to the first node, and issue a disaster warning to users in a second ground area corresponding to the second grid.

[0011] According to another aspect of the embodiments of the present disclosure, there is also provided a disaster warning device based on a low-earth orbit satellite, including: a processor; and a memory, connected to the processor, for providing instructions for the processor to perform the following processing steps: determining a first wave position coverage map corresponding to a first ground area and determining a first wave position where the first ground area is located; determining a first geographic traffic map and a first grid map corresponding to the first wave position, and generating a first grid connectivity relationship map corresponding to the first wave position based on the first geographic traffic map and the first grid map, where the first geographic traffic map includes road connection relationships within the first wave position, and the first grid map includes a plurality of first grids corresponding to the first wave position; constructing a graph structure corresponding to the first wave position based on the first grid connectivity relationship map, where the first nodes of the graph structure correspond to the respective first grids, and the edges of the graph structure correspond to the connectivity relationships of the respective first grids; inputting the graph structure into a pre-trained graph neural network model and outputting a first influence coefficient corresponding to each first node; and comparing the first influence coefficients of the respective first nodes with a pre-set influence coefficient threshold, and in the case where the first influence coefficient is greater than the influence coefficient threshold, determining the corresponding first node and a second grid corresponding to the first node, and issuing a disaster warning to users in a second ground area corresponding to the second grid.

[0012] The present application discloses a disaster warning method based on low-earth orbit satellites. First, the processor determines a first wave position coverage map corresponding to a first ground area and determines the first wave position where the first ground area is located. Then, the processor determines a first geographic traffic map and a first grid map corresponding to the first wave position, and generates a first grid connectivity relationship map corresponding to the first wave position based on the first geographic traffic map and the first grid map. Further, the processor constructs a graph structure corresponding to the first wave position based on the first grid connectivity relationship map. After that, the processor inputs the graph structure into a pre-trained graph neural network model and outputs a first influence coefficient corresponding to each first node. Finally, the processor compares the first influence coefficient of each first node with a preset influence coefficient threshold, and when the first influence coefficient is greater than the influence coefficient threshold, determines the corresponding first node and the second grid corresponding to the first node, and issues a disaster warning to the users in the first ground area corresponding to the second grid.

[0013] As can be seen from the above description, before using the low-earth orbit satellite to issue a disaster warning to users, the present application further divides the first wave position corresponding to the first ground area. Therefore, compared with the first wave position corresponding to the first ground area, the first grid corresponding to the first ground area can more accurately define the surrounding area corresponding to the first ground area.

[0014] Further, since the present application uses each first grid as the first node of the graph structure and the connectivity relationship between each first grid as the edge to construct the graph structure, and determines the first influence coefficient corresponding to each first node based on the graph structure and the pre-trained graph neural network model, the low-earth orbit satellite can determine which users in the second ground area corresponding to the second grid need to send warning information based on the first influence coefficient corresponding to each first node.

[0015] Therefore, different from the prior art where the low-earth orbit satellite needs to send warning information to all users in the wave position area corresponding to the target area, when the present application determines that a disaster occurs in the target area, it only needs to issue a disaster warning to the ground area that is greatly affected. Thus, the low-earth orbit satellite does not need to consume a lot of resources to accurately notify the users who may be affected, and further achieves the technical effect of ensuring the safety of users.

[0016] Furthermore, it solves the technical problem in the prior art that the method of sending warning information to users requires the low-earth orbit satellite to consume a lot of resources and is not very necessary for some users who have no intersection with the area around the disaster. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings described herein are used to provide a further understanding of the present disclosure, and constitute a part of this application. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation of the present disclosure. In the drawings: Figure 1 is a schematic diagram of a disaster warning system based on low-earth orbit satellites according to Embodiment 1 of the present application; Figure 2A is a schematic diagram of the hardware architecture of a low-earth orbit satellite according to Embodiment 1 of the present application; Figure 2B is a schematic diagram of the hardware architecture of a user's mobile terminal according to Embodiment 1 of the present application; Figure 3 is a schematic flowchart of a disaster warning method based on low-earth orbit satellites according to Embodiment 1 of the present application; Figure 4 is a first wave position coverage map corresponding to a target area according to Embodiment 1 of the present application; Figure 5 is a first geographical traffic map corresponding to the first wave position according to Embodiment 1 of the present application; Figure 6 is a first grid map corresponding to the first wave position according to Embodiment 1 of the present application; Figure 7 is a first grid connectivity relationship map according to Embodiment 1 of the present application; and Figure 8 is a schematic diagram of a disaster warning device based on low-earth orbit satellites according to Embodiment 2 of the present application; and Figure 9 is a schematic diagram of a disaster warning device based on low-earth orbit satellites according to Embodiment 3 of the present application. Detailed implementation manners

[0018] In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present disclosure.

[0019] It should be noted that the terms "first", "second", etc. in the description, claims and the above-mentioned drawings of the present disclosure are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order different from those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0020] Embodiment 1 According to this embodiment, a method embodiment for disaster warning based on low-earth orbit satellites is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that here.

[0021] Figure 1 is a schematic diagram of a disaster warning system based on low-earth orbit satellites according to Embodiment 1 of the present application. Refer to Figure 1 As shown, the low-earth orbit satellite 10 interacts with the mobile terminal 20 within the first communication coverage 110. And it is worth noting that the low-earth orbit satellite 10 generates multiple beams, and each beam has its own second communication coverage. For example, beam Q 1 corresponds to the second communication coverage 120, and the low-earth orbit satellite 10 can interact with the mobile terminal 20 within the second communication coverage 120 through beam Q 1 Thus, when the low-earth orbit satellite 10 generates multiple beams and the second communication coverages of each beam do not overlap, the first communication coverage 110 as shown in Figure 1 can be formed.

[0022] Furthermore, each second communication coverage of the beams emitted by the low-earth orbit satellite 10 has a corresponding cluster, and each cluster includes multiple wave positions. Thus, each beam can communicate with the mobile terminals within each wave position in sequence according to the hopping beam pattern.

[0023] Figure 2A Further shows Figure 1 a schematic diagram of the hardware architecture of the low-earth orbit satellite 10 in Figure 2AAs shown, the low-earth orbit satellite 10 includes an integrated electronic system, which includes: a processor, a memory, a bus management module, and a communication interface. The memory is connected to the processor, so that the processor can access the memory, read the program instructions stored in the memory, read data from the memory, or write data to the memory. The bus management module is connected to the processor and is also connected to a bus such as a CAN bus. Thus, the processor can communicate with the on-board peripherals connected to the bus through the bus managed by the bus management module. In addition, the processor is also communicatively connected to devices such as a camera, a star sensor, a TT&C transponder, and a data transmission device. Those of ordinary skill in the art can understand that Figure 2A The structure shown is only illustrative and does not limit the structure of the above-mentioned electronic device. For example, the satellite system may also include more or fewer components than those shown in Figure 2A or have a different configuration from that shown in Figure 2A .

[0024] Figure 2B Further shown is Figure 1 a schematic diagram of the hardware architecture of the mobile terminal 20 in Figure 2B . As shown in Figure 2B , the mobile terminal 20 may include one or more processors (the processor may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory for storing data, a transmission device for communication functions, and an input / output interface. The memory, the transmission device, and the input / output interface are connected to the processor through a bus. In addition, it may further include: a display, a keyboard, and a cursor control device connected to the input / output interface. Those of ordinary skill in the art can understand that Figure 2B The structure shown is only illustrative and does not limit the structure of the above-mentioned electronic device. For example, the ground system may also include more or fewer components than those shown in Figure 2B or have a different configuration from that shown in Figure 2B .

[0025] It should be noted that Figure 2A and Figure 2B One or more processors and / or other data processing circuits shown in are generally referred to as "data processing circuits" herein. The data processing circuit may be embodied in whole or in part as software, hardware, firmware, or any combination thereof. In addition, the data processing circuit may be a single independent processing module, or be incorporated in whole or in part into any one of other elements in the computing device. As involved in the embodiments of the present disclosure, the data processing circuit is a processor control (such as the selection of a variable resistance terminal path connected to an interface).

[0026] Figure 2A and Figure 2BThe memory shown can be used to store software programs and modules of application software, such as the program instruction / data storage device corresponding to the disaster warning method based on low-earth orbit satellites in the embodiments of the present disclosure. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, implements the disaster warning method based on low-earth orbit satellites of the above application program. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memories.

[0027] It should be noted here that in some alternative embodiments, the above Figure 2A and Figure 2B The devices shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware elements and software elements. It should be noted that Figure 2A and Figure 2B is only an example of a specific specific instance and is intended to show the types of components that may exist in the above devices.

[0028] Under the above operating environment, according to the first aspect of this embodiment, a disaster warning method based on low-earth orbit satellites is provided, and this method is implemented by the Figure 2A low-earth orbit satellite 10 shown in Figure 3 shows a schematic flow diagram of this method. Referring to Figure 3 shown, this method includes: S302: Determine a first wave position coverage map corresponding to a first ground area, and determine the first wave position where the first ground area is located; S304: Determine a first geographical traffic map and a first grid map corresponding to the first wave position, and generate a first grid connectivity relationship map corresponding to the first wave position based on the first geographical traffic map and the first grid map, where the first geographical traffic map includes road connection relationships within the first wave position, and the first grid map includes a plurality of first grids corresponding to the first wave position; S306: Based on the first grid connectivity relationship map, construct a graph structure corresponding to the first wave position, where the first nodes of the graph structure correspond to each first grid, and the edges of the graph structure correspond to the connectivity relationships of each first grid; S308: Input the graph structure into a pre-trained graph neural network model, and output a first influence coefficient corresponding to each first node; and S310: Compare the first influence coefficients of each first node with a preset influence coefficient threshold, and in the case where the first influence coefficient is greater than the influence coefficient threshold, determine the corresponding first node and the second grid corresponding to the first node, and give a disaster warning to users within the second ground area corresponding to the second grid.

[0029] Specifically, first, when a disaster occurs in a certain ground area, the processor (i.e., the processor of the low-earth orbit satellite 10, the same hereinafter) takes this ground area as the first ground area, and determines the first wave position coverage map corresponding to the first ground area, and the first wave position where the first ground area is located (S302). Figure 4 It is the first wave position coverage map corresponding to the first ground area according to the present application. Refer to Figure 4 As shown, when the processor determines the first ground area 30, based on the geographical location where the first ground area 30 is located, it generates the first wave position coverage map corresponding to the first ground area 30. And when generating the first wave position coverage map corresponding to the first ground area 30, it can determine the first wave position 40 where the first ground area 30 is located.

[0030] After that, the processor collects the first geographical traffic map corresponding to the first wave position 40. Figure 5 It is the first geographical traffic map corresponding to the first wave position according to the embodiments of the present application. Refer to Figure 5 As shown, when the processor determines the first wave position 40 where the first ground area 30 is located, the processor further collects the first geographical traffic map corresponding to the first wave position 40. Among them, the first geographical traffic map is used to display the road connection relationship of the ground area corresponding to the first wave position 40. At the same time, the processor determines the first grid map corresponding to the first wave position 40. Figure 6 It is the first grid map corresponding to the first wave position according to the embodiments of the present application. Refer to Figure 6 As shown, when the processor determines the first wave position 40, it divides the first wave position coverage map corresponding to the first wave position 40, and divides the first wave position coverage map into multiple grids of the same size, so as to generate the first grid map corresponding to the first wave position 40.

[0031] Furthermore, Figure 7 It is the first grid connection relationship map according to the embodiments of the present application. Refer to Figure 7 As shown, when the processor determines the first geographical traffic map and the first grid map, it superimposes the first geographical traffic map and the first grid map, so as to generate Figure 7 the first grid connection relationship map corresponding to the first wave position as shown (S304). Among them, the first grid connection relationship map shows the road connection status in the multiple first grids corresponding to the first wave position.

[0032] After that, the processor constructs a graph structure corresponding to the first wave position based on the determined first grid connection relationship map (S306). Refer to Figure 7As shown, in this embodiment, the processor uses each first grid in the first grid connectivity relationship diagram as a first node, and uses the connectivity relationship between each first grid as an edge to construct a graph structure. For example, the graph structure G includes multiple first nodes and multiple edges . Among them, i = 1~n, j = 1~m. In this embodiment, when the processor constructs a graph structure corresponding to the first wave position, the influence coefficient of the first node corresponding to the first ground area is 1, and the influence coefficients of other first nodes in the graph structure are 0.

[0033] Furthermore, the processor inputs the graph structure into a pre-trained graph neural network model and outputs a first influence coefficient corresponding to each first node (S308). For example, when the processor inputs the graph structure into a pre-trained graph neural network model, the graph neural network model outputs a first influence coefficient corresponding to the first node , a first influence coefficient corresponding to the first node ,..., a first influence coefficient corresponding to the first node . Among them, the first influence coefficient is used to indicate the degree of influence of each first grid after a disaster occurs. , a first influence coefficient corresponding to the first node , a first influence coefficient corresponding to the first node . Among them, the first influence coefficient is used to indicate the degree of influence of each first grid after a disaster occurs.

[0034] Finally, the processor compares the first influence coefficients of each first node with a preset influence coefficient threshold. When the first influence coefficient of each first node is greater than the influence coefficient threshold, it determines the corresponding first node and the second grid corresponding to the first node, and issues a disaster warning to the users in the second ground area corresponding to the second grid (S310). For example, the processor determines the first influence coefficient corresponding to each first node . Then the processor compares the sizes of each first influence coefficient and the influence coefficient threshold . If the processor determines that the first influence coefficients corresponding to the first nodes , and are greater than the influence coefficient threshold , and , then in the case of a disaster occurring at the first node corresponding to the first ground area, the degrees of influence on the first grids corresponding to the first nodes , and are relatively large. Thus, the processor determines the first nodes corresponding to the first grids , and ​​, and use the first grid corresponding to the above first node , and as the second grid, and issue disaster warnings to users within the second ground area corresponding to the second grid. That is, the processor of the low-earth orbit satellite sends disaster warning information to the mobile terminals of users within the second ground area corresponding to the second grid.

[0035] As described in the background art, if a low-earth orbit satellite is used to send warning information to all users in the area around the disaster, since the low-earth orbit satellite needs to communicate with a large number of mobile terminals, the low-earth orbit satellite needs to consume a lot of resources; furthermore, since some users may not live or work in the area around the disaster, it is not very necessary for users who have no intersection with the area around the disaster. Therefore, the method of using a low-earth orbit satellite to send warning information to users in the prior art requires the low-earth orbit satellite to consume a lot of resources and is not very necessary for some users who have no intersection with the area around the disaster.

[0036] In view of this, before using the low-earth orbit satellite to issue disaster warnings to users, the present application further divides the first wave position corresponding to the first ground area. Thus, compared with the first wave position corresponding to the first ground area, the first grid corresponding to the first ground area can more accurately define the surrounding range corresponding to the first ground area.

[0037] Furthermore, since the present application takes each first grid as the first node of the graph structure, takes the connection relationship between each first grid as the edge, constructs a graph structure, and determines the first influence coefficient corresponding to each first node based on the graph structure and the pre-trained graph neural network model, the low-earth orbit satellite can determine which users in the ground area corresponding to the first grid need to send warning information based on the first influence coefficient corresponding to each first node.

[0038] Thus, different from the prior art in which the low-earth orbit satellite needs to send warning information to all users in the wave position area corresponding to the first ground area, when the present application determines that a disaster occurs in the first ground area, it only needs to determine the ground area that is greatly affected and issue disaster warnings to the users in the ground area. Thus, the low-earth orbit satellite does not need to consume a lot of resources to accurately notify the users who may be affected, and thus achieves the technical effect of ensuring the safety of the users.

[0039] Furthermore, it solves the technical problem in the prior art that the method of sending warning information to users requires the low-earth orbit satellite to consume a lot of resources and is not very necessary for some users who have no intersection with the area around the disaster.

[0040] Optionally, the operation of generating the first grid connection relationship graph corresponding to the first wave position based on the first geographic traffic map and the first grid map includes: dividing the first wave positions corresponding to the first ground area in the first wave position coverage map into multiple first grids, and generating the first grid map corresponding to the first wave position, where the sizes of the respective first grids are the same; and overlaying the first grid map with the first geographic traffic map to determine the first grid connection relationship graph corresponding to the first wave position.

[0041] Specifically, referring to Figure 6 As shown, when the processor determines the first wave position 40, it divides the first wave position coverage map corresponding to the first wave position 40 and divides the first wave position coverage map into multiple grids of the same size, thereby generating the first grid map corresponding to the first wave position 40.

[0042] Furthermore, Figure 7 is the first grid connection relationship graph according to the embodiment of the present application. Referring to Figure 7 As shown, when the processor determines the first geographic traffic map and the first grid map, it overlays the first geographic traffic map with the first grid map to generate, as shown in Figure 7 the first grid connection relationship graph corresponding to the first wave position. Among them, the first grid connection relationship graph shows the road connection status in the multiple first grids corresponding to the first wave position.

[0043] Optionally, it further includes: pre-building a graph neural network model and training the graph neural network model. Further optionally, the operation of pre-building a graph neural network model and training the graph neural network model includes: determining the second wave position coverage maps corresponding to the respective third ground areas and determining the second wave positions where the respective third ground areas are located; determining the second geographic traffic maps and second grid maps corresponding to the respective second wave positions, and generating the second grid connection relationship graphs corresponding to the respective second wave positions based on the second geographic traffic maps and the second grid maps; respectively constructing multiple first graph structure samples corresponding to the second wave positions based on the multiple second grid connection relationship graphs; annotating the multiple first graph structure samples and generating multiple second graph structure samples; and using the multiple first graph structure samples as input samples and the multiple second graph structure samples as output samples to train the graph neural network model.

[0044] Specifically, when the processor uses the pre-trained graph neural network model to determine the first influence coefficients corresponding to the respective first nodes in the graph structure, it is also necessary to pre-build a graph neural network model and train the graph neural network model.

[0045] First, the processor determines the areas where disasters occurred during the historical period and uses this area as the third ground area . Then, the processor determines second wave position coverage maps corresponding to respective third ground regions and determines the second wave positions wherein the respective third ground regions are located, as specifically shown in FIG. 4. For example, the processor determines a third ground region corresponding to a historical period and determines the second wave position wherein the third ground region is located ; the processor determines a third ground region corresponding to a historical period and determines the second wave position wherein the third ground region is located ;...; the processor determines a third ground region corresponding to a historical period and determines the second wave position wherein the third ground region is located .

[0046] Furthermore, the processor determines a second geographical traffic map and a second grid map corresponding to respective second wave positions and generates a second grid connection relationship map corresponding to respective second wave positions based on the second geographical traffic map and the second grid map, as specifically shown in Figure 7 .

[0047] After that, the processor respectively constructs multiple first graph structure samples corresponding to the second wave positions based on the multiple second grid connection relationship maps. Among them, the second grids in each second grid connection relationship map are used as nodes, and the connection relationships between the respective second grids are used as edges to construct multiple first graph structure samples corresponding to respective second wave positions. And in each first graph structure sample , the second grid corresponding to the third sample region is used as the target node, and the initial influence coefficient corresponding to the target node is 1, and the initial influence coefficients corresponding to the remaining second nodes are 0. For example, in the first graph structure sample , the second grid corresponding to the third sample region is used as the target node , so that the initial influence coefficient corresponding to the target node is 1, and the initial influence coefficients corresponding to the other second nodes in the first graph structure sample are 0. For another example, in the first graph structure sample , the second grid corresponding to the third sample region ​As the target node , so as to be associated with the target node , the corresponding initial influence coefficient is 1, and for other second nodes in the first graph structure sample , , the corresponding initial influence coefficient is 0.

[0048] Furthermore, the processor labels multiple first graph structure samples and generates multiple second graph structure samples . The above content will be described in detail later, so it will not be elaborated here.

[0049] Finally, the processor uses multiple first graph structure samples as the input samples of the graph neural network model, uses multiple second graph structure samples as the output samples of the graph neural network model, and trains the graph neural network model.

[0050] Further optionally, the operation of labeling multiple first graph structure samples and generating multiple second graph structure samples includes: respectively using the second nodes corresponding to the third ground area in each first graph structure sample as the target nodes; determining the trajectory information of each user in the third ground area corresponding to the target nodes, and determining the proportional relationship of each user in the third ground area moving to the fourth ground area based on the trajectory information, where the fourth ground area corresponds to other second nodes except the target nodes; and determining the proportional relationship corresponding to each second node as the influence coefficient corresponding to each second node, and labeling each second node, so as to generate multiple second graph structure samples.

[0051] Specifically, first, the processor respectively uses the second nodes corresponding to the third ground area in each first graph structure sample as the target nodes. For example, the processor uses the second node corresponding to the third ground area in the first graph structure sample as the target node, and the processor uses the second node corresponding to the third ground area in the first graph structure sample as the target node,..., the processor uses the second node corresponding to the third ground area in the first graph structure sample as the target nodes respectively.

[0052] Then, the processor determines the trajectory information of each user within the third ground area corresponding to the target node. For example, the processor of the LEO satellite may call the trajectory information of each user in the third ground area corresponding to the target node from a database, and this trajectory information may be collected by the processor of the LEO satellite in advance based on remote sensing images.

[0053] Further, the processor determines the proportional relationship of each user in the third ground area moving to the fourth ground area based on the trajectory information. The fourth ground area corresponds to other second nodes except the target node. For example, when the processor determines the target node corresponding to the first graph structure sample corresponding target node , it further determines the proportional relationship of each user in the third ground area moving to the fourth ground area . For another example, when the processor determines the target node corresponding to the first graph structure sample corresponding target node , it further determines the proportional relationship of each user in the third ground area moving to the fourth ground area , .

[0054] Finally, the processor determines the proportional relationship corresponding to each second node as the influence coefficient corresponding to each second node, and labels each second node, thereby generating multiple second graph structure samples.

[0055] Thus, according to the first aspect of this embodiment, the technical effect of being able to accurately notify users who may be affected without consuming too many resources is achieved, and further the technical effect of being able to ensure the safety of users is achieved.

[0056] In addition, as shown in Figure 1 , according to the second aspect of this embodiment, a storage medium is provided. The storage medium includes a stored program, wherein, when the program runs, the method described in any one of the above is executed by a processor.

[0057] Thus, according to this embodiment, the technical effect of being able to accurately notify users who may be affected without consuming too many resources is achieved, and further the technical effect of being able to ensure the safety of users is achieved.

[0058] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0059] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0060] Embodiment 2 Figure 8 Fig. 800 shows a disaster warning device based on a low-earth orbit satellite according to the present embodiment. The device 800 corresponds to the method according to Embodiment 1. Refer to Figure 8 As shown, the device 800 includes: a wave position coverage map determination module 810, configured to determine a first wave position coverage map corresponding to a first ground area, and determine a first wave position where the first ground area is located; a grid connectivity relationship map generation module 820, configured to determine a first geographical traffic map and a first grid map corresponding to the first wave position, and generate a first grid connectivity relationship map corresponding to the first wave position based on the first geographical traffic map and the first grid map, where the first geographical traffic map includes road connection relationships within the first wave position, and the first grid map includes a plurality of first grids corresponding to the first wave position; a graph structure construction module 830, configured to construct a graph structure corresponding to the first wave position based on the first grid connectivity relationship map, where the first nodes of the graph structure correspond to each first grid, and the edges of the graph structure correspond to the connectivity relationships of each first grid; an influence coefficient output module 840, configured to input the graph structure into a pre-trained graph neural network model, and output a first influence coefficient corresponding to each first node; and a disaster warning module 850, configured to compare the first influence coefficient of each first node with a pre-set influence coefficient threshold, and in the case where the first influence coefficient is greater than the influence coefficient threshold, determine the corresponding first node and a second grid corresponding to the first node, and issue a disaster warning to users within the second ground area corresponding to the second grid.

[0061] Optionally, the grid connectivity relationship map generation module 820 includes: a grid map generation module, configured to divide the first wave position corresponding to the first ground area in the first wave position coverage map into a plurality of first grids, and generate a first grid map corresponding to the first wave position, where the size of each first grid is the same; and a superposition module, configured to superpose the first grid map and the first geographical traffic map to determine a first grid connectivity relationship map corresponding to the first wave position.

[0062] Optionally, the apparatus 800 further includes: a training module, configured to pre-construct a graph neural network model and train the graph neural network model.

[0063] Optionally, the training module includes: a second wave position determination module, configured to determine second wave position coverage maps corresponding to respective third ground regions and determine second wave positions where the respective third ground regions are located; a geographical traffic map determination module, configured to determine second geographical traffic maps and second grid maps corresponding to respective second wave positions, and generate second grid connectivity relation maps corresponding to respective second wave positions based on the second geographical traffic maps and the second grid maps; a graph structure sample construction module, configured to respectively construct a plurality of first graph structure samples corresponding to the second wave positions based on the plurality of second grid connectivity relation maps; a graph structure sample generation module, configured to label the plurality of first graph structure samples and generate a plurality of second graph structure samples; and an input sample determination module, configured to use the plurality of first graph structure samples as input samples and the plurality of second graph structure samples as output samples to train the graph neural network model.

[0064] Optionally, the graph structure sample generation module includes: a target node determination module, configured to respectively use second nodes corresponding to third ground regions in respective first graph structure samples as target nodes; a proportional relationship determination module, configured to determine trajectory information of respective users within the third ground region corresponding to the target node and determine a proportional relationship of respective users within the third ground region moving to a fourth ground region based on the trajectory information, where the fourth ground region corresponds to other second nodes except the target node; and a labeling module, configured to determine the proportional relationship corresponding to respective second nodes as influence coefficients corresponding to respective second nodes and label respective second nodes, thereby generating a plurality of second graph structure samples.

[0065] Thus, according to this embodiment, the technical effect of being able to accurately notify users who may be affected without consuming too many resources is achieved, and further the technical effect of being able to ensure the safety of users is achieved.

[0066] Embodiment 3 Figure 9 Shows a disaster warning apparatus 900 based on a low-earth orbit satellite according to this embodiment, and the apparatus 900 corresponds to the method according to Embodiment 1. Refer to Figure 9As shown, the device 900 includes: a processor 910; and a memory 920, connected to the processor 910, for providing instructions for the processor 910 to process the following processing steps: determining a first wave position coverage map corresponding to a first ground area and determining a first wave position where the first ground area is located; determining a first geographical traffic map and a first grid map corresponding to the first wave position, and generating a first grid connectivity relationship map corresponding to the first wave position based on the first geographical traffic map and the first grid map, where the first geographical traffic map includes road connection relationships within the first wave position, and the first grid map includes a plurality of first grids corresponding to the first wave position; constructing a graph structure corresponding to the first wave position based on the first grid connectivity relationship map, where the first nodes of the graph structure correspond to the respective first grids, and the edges of the graph structure correspond to the connectivity relationships of the respective first grids; inputting the graph structure into a pre-trained graph neural network model and outputting first influence coefficients corresponding to the respective first nodes; and comparing the first influence coefficients of the respective first nodes with a preset influence coefficient threshold, and when the first influence coefficient is greater than the influence coefficient threshold, determining the corresponding first node and the second grid corresponding to the first node, and issuing a disaster warning to users within the second ground area corresponding to the second grid.

[0067] Optionally, the operation of generating a first grid connectivity relationship map corresponding to the first wave position based on the first geographical traffic map and the first grid map includes: dividing the first wave position corresponding to the first ground area in the first wave position coverage map into a plurality of first grids and generating a first grid map corresponding to the first wave position, where the sizes of the respective first grids are the same; and superimposing the first grid map and the first geographical traffic map to determine the first grid connectivity relationship map corresponding to the first wave position.

[0068] Optionally, it further includes: pre-constructing a graph neural network model and training the graph neural network model.

[0069] Optionally, the operation of pre-constructing a graph neural network model and training the graph neural network model includes: determining second wave position coverage maps corresponding to respective third ground areas and determining second wave positions where the respective third ground areas are located; determining second geographical traffic maps and second grid maps corresponding to the respective second wave positions, and generating second grid connectivity relationship maps corresponding to the respective second wave positions based on the second geographical traffic maps and the second grid maps; respectively constructing a plurality of first graph structure samples corresponding to the second wave positions based on the plurality of second grid connectivity relationship maps; annotating the plurality of first graph structure samples and generating a plurality of second graph structure samples; and using the plurality of first graph structure samples as input samples and the plurality of second graph structure samples as output samples to train the graph neural network model.

[0070] Optionally, the operation of annotating multiple first graph structure samples and generating multiple second graph structure samples includes: respectively taking the second nodes corresponding to the third ground area in each first graph structure sample as target nodes; determining the trajectory information of each user in the third ground area corresponding to the target nodes, and determining the proportional relationship of each user in the third ground area moving to the fourth ground area based on the trajectory information, where the fourth ground area corresponds to other second nodes except the target nodes; and determining the proportional relationship corresponding to each second node as the influence coefficient corresponding to each second node, and annotating each second node, so as to generate multiple second graph structure samples.

[0071] Thus, according to this embodiment, the technical effect of being able to accurately notify the users who may be affected without consuming too many resources is achieved, and further the technical effect of being able to ensure the safety of users is achieved.

[0072] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0073] In the above embodiments of the present invention, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0074] In several embodiments provided in the present application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces, and the indirect coupling or communication connection of units or modules can be in an electrical or other form.

[0075] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0076] In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0077] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0078] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A disaster warning method based on low-orbit satellite, characterized in that: include: Determine a first wave position coverage map corresponding to a first ground area, and determine a first wave position at which the first ground area is located; Determine a first geographic traffic map and a first grid map corresponding to the first wave position, and generate a first grid connectivity relationship map corresponding to the first wave position based on the first geographic traffic map and the first grid map, wherein the first geographic traffic map includes a road connection relationship within the first wave position, and the first grid map includes a plurality of first grids corresponding to the first wave position; Based on the first grid connectivity relationship graph, construct a graph structure corresponding to the first wave position, wherein the first nodes of the graph structure correspond to the first grids, and the edges of the graph structure correspond to the connectivity relationships of the first grids; Inputting the graph structure into a pre-trained graph neural network model, and outputting a first influence coefficient corresponding to each first node; as well as The first influence coefficient of each first node is compared with a preset influence coefficient threshold, and when the first influence coefficient is greater than the influence coefficient threshold, the corresponding first node and the second grid corresponding to the first node are determined, and disaster warnings are issued to users in the second ground area corresponding to the second grid.

2. The method according to claim 1, characterized in that The operation of generating a first grid connectivity relationship graph corresponding to the first wave position based on the first geographic traffic map and the first grid map includes: Dividing the first wave position corresponding to the first ground area in the first wave position coverage map into a plurality of first grids, and generating a first grid map corresponding to the first wave position, wherein the sizes of the first grids are the same; and The first grid map is superimposed on the first geographic traffic map to determine a first grid connectivity relationship map corresponding to the first wave position.

3. The method according to claim 1, characterized in that Also includes: A graph neural network model is pre-built and trained.

4. The method according to claim 3, characterized in that The operations of pre-building a graph neural network model and training the graph neural network model include: Determine second wave position coverage maps corresponding to respective third ground areas, and determine the second wave position at which each third ground area is located; Determine a second geographic traffic map and a second grid map corresponding to each second wave position, and generate a second grid connectivity relationship map corresponding to each second wave position based on the second geographic traffic map and the second grid map; Based on the plurality of second grid connectivity relationship graphs, constructing a plurality of first graph structure samples corresponding to the second wave positions respectively; Annotating the plurality of first graph structure samples and generating a plurality of second graph structure samples; and The graph neural network model is trained by using the multiple first graph structure samples as input samples and the multiple second graph structure samples as output samples.

5. The method according to claim 4, characterized in that The operation of labeling the plurality of first graph structure samples and generating a plurality of second graph structure samples includes: taking the second nodes corresponding to the third ground area in each of the first graph structure samples as target nodes respectively; Determine trajectory information of each user in a third ground area corresponding to the target node, and determine a proportion of each user in the third ground area moving to a fourth ground area based on the trajectory information, wherein the fourth ground area corresponds to other second nodes except the target node; and The proportional relationship corresponding to each second node is determined as the influence coefficient corresponding to each second node, and each second node is labeled, thereby generating a plurality of second graph structure samples.

6. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is run, the processor executes the method according to any one of claims 1 to 5.

7. A disaster warning device based on a low-orbit satellite, characterized in that: include: A wave position coverage map determining module, used to determine a first wave position coverage map corresponding to a first ground area, and determine a first wave position at which the first ground area is located; a grid connectivity relationship graph generation module, configured to determine a first geographic traffic map and a first grid map corresponding to the first wave position, and generate a first grid connectivity relationship graph corresponding to the first wave position based on the first geographic traffic map and the first grid map, wherein the first geographic traffic map includes a road connection relationship within the first wave position, and the first grid map includes a plurality of first grids corresponding to the first wave position; A graph structure construction module, configured to construct a graph structure corresponding to the first wave position based on the first grid connectivity relationship graph, wherein the first nodes of the graph structure correspond to the first grids, and the edges of the graph structure correspond to the connectivity relationships of the first grids; An influence coefficient output module, used to input the graph structure into a pre-trained graph neural network model and output a first influence coefficient corresponding to each first node; as well as The disaster warning module is used to compare the first influence coefficient of each first node with a preset influence coefficient threshold, and when the first influence coefficient is greater than the influence coefficient threshold, determine the corresponding first node and the second grid corresponding to the first node, and issue a disaster warning to users in the second ground area corresponding to the second grid.

8. The device according to claim 7, characterized in that The grid connectivity relationship graph generation module comprises: a grid map generating module, configured to divide the first wave position corresponding to the first ground area in the first wave position coverage map into a plurality of first grids, and generate a first grid map corresponding to the first wave position, wherein the sizes of the first grids are the same; and The superposition module is used to superimpose the first grid map with the first geographic traffic map, so as to determine a first grid connectivity relationship map corresponding to the first wave position.

9. The device according to claim 7, characterized in that The device also includes: a training module, which is used to pre-build a graph neural network model and train the graph neural network model.

10. A disaster warning device based on a low-orbit satellite, characterized in that: include: processor; as well as A memory, connected to the processor, configured to provide the processor with instructions for processing the following processing steps: Determine a first wave position coverage map corresponding to a first ground area, and determine a first wave position at which the first ground area is located; Determine a first geographic traffic map and a first grid map corresponding to the first wave position, and generate a first grid connectivity relationship map corresponding to the first wave position based on the first geographic traffic map and the first grid map, wherein the first geographic traffic map includes a road connection relationship within the first wave position, and the first grid map includes a plurality of first grids corresponding to the first wave position; Based on the first grid connectivity relationship graph, construct a graph structure corresponding to the first wave position, wherein the first nodes of the graph structure correspond to the first grids, and the edges of the graph structure correspond to the connectivity relationships of the first grids; Inputting the graph structure into a pre-trained graph neural network model, and outputting a first influence coefficient corresponding to each first node; as well as The first influence coefficient of each first node is compared with a preset influence coefficient threshold, and when the first influence coefficient is greater than the influence coefficient threshold, the corresponding first node and the second grid corresponding to the first node are determined, and disaster warnings are issued to users in the second ground area corresponding to the second grid.

Images