Geological disaster risk warning processing method, system and electronic equipment

Abstract

This application provides a geological disaster risk early warning processing method, system, and electronic device. By dividing a target area into multiple sub-areas and identifying corresponding similar areas, when precipitation occurs, the system determines surface runoff forecast data for each sub-area within a non-raining area based on the runoff volume of similar areas within the raining area. This system then determines the probability of a geohazard occurring when rain clouds move into the non-raining area. This system can achieve ultra-short-term, precise early warnings, improving the accuracy and immediacy of geological disaster early warnings.

Description

Technical Field

[0001] The present application relates to the field of geological disaster risk warning processing, and specifically, to a geological disaster risk warning processing method, system and electronic equipment. Background Art

[0002] Geological disasters have always been the focus of natural disaster monitoring. There are many types of geological disasters, such as landslides, mudslides, collapses, ground collapses, etc. Traditional detection methods mainly obtain information on geological changes through manual inspections or through information feedback from sensors and monitoring equipment, thereby inferring the possibility of geological disasters.

[0003] However, due to the complex changes in the objects of geological disasters, especially landslides, mudslides, mountain torrents and other disasters, the formation of geological disasters is affected by vegetation coverage, soil softness, water content, slope, etc., and is also greatly affected by climatic conditions such as short-term heavy rainfall. The information on single geological changes obtained from the target monitoring site is difficult to accurately provide a sufficiently long warning time, and it is impossible to achieve ultra-short-term accurate warning. Summary of the Invention

[0004] In order to overcome the above-mentioned deficiencies in the prior art, the present application aims to provide a geological disaster risk early warning processing method, the method comprising:

[0005] Divide the target area into multiple sub-areas;

[0006] For each of the sub-regions, determining a similar region having similar terrain features to the sub-region based on the terrain feature data of the sub-region;

[0007] Obtaining surface runoff data of each sub-area collected by a plurality of intelligent detection devices in the rainy area, and determining the direction of movement of rain clouds;

[0008] Taking each sub-region in the non-raining area in the direction of the rain cloud movement as a target sub-region, searching whether there is a target similar region corresponding to the target sub-region in the raining area;

[0009] For a first target sub-region in the target sub-region where the target similar region exists, the runoff volume of the target similar region corresponding thereto is used as the surface runoff prediction data of the first target sub-region;

[0010] For a second target sub-region in the target sub-region where the target similar region does not exist, calculating surface runoff prediction data for the second target sub-region based on historical surface runoff data of the second target sub-region;

[0011] The probability of an address disaster occurring when rain clouds move to the non-raining area is determined based on the surface runoff prediction data of each target sub-area, and a corresponding alarm notification is output based on the probability of an address disaster occurring.

[0012] In a possible implementation, the step of dividing the target area into multiple sub-areas includes:

[0013] Obtain surface trend data of the target area;

[0014] The target area is subjected to a surface triangular mesh division process according to the surface trend data to obtain a triangular mesh model of the target area, wherein the triangular mesh model includes sub-areas composed of a plurality of triangular facets.

[0015] In a possible implementation, the step of performing surface triangulation processing on the target area according to the surface trend data includes:

[0016] converting the terrain of the target area into a curved surface according to the surface trend data;

[0017] Determining convex peaks and concave valleys in the curved surface;

[0018] Each of the peak points is connected to its adjacent valley point, and each of the valley points is connected to other adjacent valley points to form a plurality of triangular facets.

[0019] In a possible implementation, the step of determining, for each sub-region, a similar region having similar terrain features to the sub-region based on the terrain feature data of the sub-region includes:

[0020] Determining a terrain vector of each sub-region based on the terrain feature data of each sub-region; the terrain vector includes data items representing the area of ​​the sub-region, the slope direction of the sub-region, the slope inclination of the sub-region, the vegetation coverage rate of the sub-region, and the soil looseness of the sub-region;

[0021] For each of the sub-regions, calculating the similarity between the terrain vectors of the sub-region and other sub-regions beyond a preset distance from the sub-region;

[0022] Other sub-regions whose similarity to the terrain vector of the sub-region is greater than a preset threshold are determined as the similar regions of the sub-region.

[0023] In a possible implementation, the step of calculating, for a second target subregion in the target subregion where the target similar region does not exist, surface runoff prediction data for the second target subregion based on historical surface runoff data of the second target subregion includes:

[0024] Acquiring historical surface runoff data according to the first target sub-area and the second target sub-area;

[0025] determining a runoff data correlation ratio between the first target sub-area and the second target sub-area based on historical surface runoff data of the first target sub-area and the second target sub-area;

[0026] Acquiring surface runoff prediction data for each of the first target sub-areas;

[0027] The surface runoff prediction data of the second target sub-area is calculated according to the runoff data correlation ratio and the surface runoff prediction data of the first target sub-area.

[0028] In a possible implementation, the step of determining the probability of an address disaster occurring when rain clouds move to the non-raining area based on the surface runoff prediction data of each target sub-area includes:

[0029] Determining the total runoff prediction data of the non-raining area based on the surface runoff prediction data of each target sub-area;

[0030] Acquiring GNSS surface displacement monitoring data of the non-raining area;

[0031] The probability of an address disaster occurring when rain clouds move to the non-raining area is determined based on the total runoff prediction data of the non-raining area and the GNSS surface displacement monitoring data.

[0032] In one possible implementation, the step of determining the probability of an address disaster occurring when rain clouds move to the non-raining area based on the total runoff prediction data and the GNSS surface displacement monitoring data includes:

[0033] Acquiring multi-model detection data collected by each of the intelligent detection devices in the target area, wherein the intelligent detection devices include a motion sensor, a thermometer, and a meteorological sensor;

[0034] The probability of generating an address disaster when rain clouds move to the non-raining area is determined based on the multi-model detection data, the total runoff prediction data and the GNSS surface displacement monitoring data of the non-raining area.

[0035] Another object of the present application is to provide a geological disaster risk early warning processing system, the system comprising:

[0036] A region division module is used to divide the target region into multiple sub-regions;

[0037] A similarity calculation module is used to determine, for each of the sub-regions, a similar region with similar terrain features to the sub-region based on the terrain feature data of the sub-region;

[0038] a data acquisition module, configured to acquire surface runoff data of each sub-area collected by a plurality of intelligent detection devices in the rainy area, and determine the direction of movement of rain clouds;

[0039] A region query module is used to take each sub-region in the non-raining region in the direction of rain cloud movement as a target sub-region, and to search whether there is a target similar region corresponding to the target sub-region in the raining region;

[0040] a first prediction module, configured to use, for a first target sub-region where the target similar region exists in the target sub-region, the runoff volume of the target similar region corresponding thereto as surface runoff prediction data of the first target sub-region;

[0041] a second prediction module, configured to calculate, for a second target sub-region in which the target similar region does not exist, surface runoff prediction data of the second target sub-region based on historical surface runoff data of the second target sub-region;

[0042] The alarm notification module is used to determine the probability of address disaster generation when rain clouds move to the non-raining area based on the surface runoff prediction data of each target sub-area, and output a corresponding alarm notification based on the address disaster generation probability.

[0043] Another object of the present application is to provide an electronic device, including a processor and a machine-readable storage medium, wherein the machine-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are executed by the processor, the geological disaster risk warning processing method provided in the present application is implemented.

[0044] Another object of the present application is to provide a machine-readable storage medium, characterized in that the machine-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are executed by one or more processors, they implement the geological disaster risk warning processing method provided by the present application.

[0045] Compared with the prior art, this application has the following beneficial effects:

[0046] The geological disaster risk early warning processing method, system, and electronic device provided in the embodiments of the present application divide the target area into multiple sub-areas and identify corresponding similar areas. When precipitation occurs, the system determines surface runoff forecast data for each sub-area within the non-raining area based on the runoff volume of similar areas within the raining area. This further determines the probability of a geohazard occurring when rain clouds move into the non-raining area. This enables ultra-short-term, precise early warning, improving the accuracy and immediacy of geological disaster early warnings. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 A schematic diagram of a geological disaster risk early warning processing method provided in an embodiment of the present application;

[0049] Figure 2 A schematic diagram of the sub-region division provided in an embodiment of the present application;

[0050] Figure 3 One of the schematic diagrams of the principle of determining similar regions provided in the embodiment of the present application;

[0051] Figure 4 The second schematic diagram of the principle of determining similar regions provided in the embodiment of the present application;

[0052] Figure 5 A schematic diagram of an electronic device provided in an embodiment of the present application;

[0053] Figure 6 Schematic diagram of the functional modules of the geological disaster risk warning and processing system provided in the embodiment of the present application. DETAILED DESCRIPTION

[0054] To make the objectives, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Generally, the components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0055] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for protection, but merely represents selected embodiments of the present application. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments in the present application without creative work are within the scope of protection of the present application.

[0056] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0057] In the description of this application, it should be noted that the terms "first", "second", "third", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0058] It should also be noted that, in the description of this application, unless otherwise expressly specified or limited, the terms "disposed," "installed," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0059] Please refer to Figure 1 , Figure 1 A flowchart of a geological disaster risk early warning processing method provided in this embodiment will be described in detail below including each step of the method.

[0060] Step S110: Divide the target area into multiple sub-areas.

[0061] In one possible implementation, surface trend data of the target area can be obtained in step S110, and then the surface triangulated mesh of the target area is processed according to the surface trend data to obtain a triangular mesh model of the target area, wherein the triangular mesh model includes sub-areas composed of multiple triangular facets.

[0062] For example, see Figure 2, the terrain of the target area is converted into a curved surface based on the surface trend data. The peaks and valleys of the surface are identified. Each peak is connected to its adjacent valley, and each valley is connected to its adjacent valleys to form multiple triangular facets. Optionally, to reduce computational complexity, some smaller protrusions can be ignored, and only protrusions greater than a preset value can be analyzed. This method allows for the use of computer programming to implement slope segmentation of a terrain map, significantly reducing the time and cost of manual segmentation.

[0063] In this embodiment, the target area may be an area for early warning management, or an area set in other ways, which is not specifically limited here. Preferably, in this embodiment, the coverage area of ​​the target area may be greater than tens of kilometers.

[0064] Step S120 : for each of the sub-regions, determine a similar region having similar terrain features to the sub-region according to the terrain feature data of the sub-region.

[0065] In one possible implementation, in step S120, the terrain vector of the sub-area can be determined based on the terrain feature data of each sub-area, wherein the terrain vector includes data items representing the area of ​​the sub-area, the slope orientation of the sub-area, the inclination of the slope of the sub-area, the vegetation coverage rate of the sub-area, and the looseness of the soil in the sub-area.

[0066] To facilitate subsequent calculations, terrain vectors can be normalized. To facilitate similarity calculations, terrain vectors can be normalized, with the slope orientation set to due east at 0 degrees, due north at 90 degrees, due west at 180 degrees, and due south at 270 degrees. The slope angle is normalized to a scale of 0-1; the slope inclination is normalized to a scale of 0-1 from 0-90 degrees; and the vegetation coverage and soil looseness are normalized to a scale of 0-1 based on the range of the target area.

[0067] Then, for each sub-region, similarities between the terrain vector of the sub-region and other sub-regions beyond the preset distance of the sub-region are calculated, and other sub-regions whose similarities with the terrain vector of the sub-region are greater than a preset threshold are determined as similar regions of the sub-region.

[0068] Since it takes a certain amount of time for cumulonimbus clouds to reach the predicted area, if the predicted area is too close to the raining area, the prediction time is too short and the prediction is not very meaningful. Therefore, it is necessary to predict areas that are more than a certain distance away. Based on the above principle, for each sub-area, the similarity between all other sub-areas outside the preset distance and the sub-area center is calculated. For example, please refer to Figure 3 , Figure 3The center of the circle is the sub-region, and the radius is the preset record. In this embodiment, only the similarity between the sub-regions outside the circle and the sub-region at the center of the circle is calculated. Figure 4 As shown, it is raining in area A and the wind is blowing towards area B. The prediction is meaningful only when the distance between area A and area B reaches a certain value.

[0069] In this embodiment, the similarity can be calculated using any vector similarity calculation method, and is not limited here. Subregion pairs with similarities greater than the preset threshold are saved. For example, if the similarity between subregion 345 and subregion 872 is greater than 0.8, (345, 872, 0.8) is saved to the database. A similar similarity calculation is performed on each subregion in the target region to obtain all subregion pairs with similarities greater than the preset threshold.

[0070] Step S130: obtaining surface runoff data of each sub-area collected by a plurality of intelligent detection devices in the rainy area, and determining the movement direction of the rain cloud.

[0071] In this embodiment, the surface runoff data of each sub-area in the rainy area can be obtained by multiple intelligent detection devices set in the target area. In addition, meteorological data can be obtained by the intelligent detection devices or from other devices to determine the movement direction of the rain cloud.

[0072] Step S140 , taking each sub-region in the non-raining region in the moving direction of the rain cloud as a target sub-region, and searching whether there is a target similar region corresponding to the target sub-region in the raining region.

[0073] In this embodiment, the target sub-region in the non-raining area may have multiple similar regions whose terrain vector similarity is greater than a preset threshold. In step S140, the raining area can be searched to see whether there is a target similar region corresponding to the target sub-region.

[0074] Step S150 : for a first target sub-region in which the target similar region exists, the runoff volume of the target similar region corresponding to the first target sub-region is used as surface runoff prediction data of the first target sub-region.

[0075] Since the target similarity area and the target sub-area have a high degree of similarity in geographical features, when a rain cloud passes through, the surface runoff of the target sub-area and the target similarity area should also have a high degree of similarity. Therefore, the measured runoff volume of the corresponding target similar area can be used as the surface runoff prediction data of the first target sub-area when a rain cloud passes through the first target sub-area.

[0076] For example, Figure 4As shown, Region A (i.e., the rainy area) is experiencing heavy rain, and cumulonimbus clouds are moving toward Region B (i.e., the non-rainy area). For each subregion in Region B, a similar region is searched for in Region A. If a subregion in Region B contains an area similar to Region A, this indicates that if cumulonimbus clouds move to Region B, similar areas in Regions A and B will produce similar water accumulation effects. Therefore, the measured real-time runoff in Region A can be assigned to the similar area in Region B for subsequent prediction.

[0077] Step S160 : for a second target sub-region in which the target similar region does not exist, calculating surface runoff prediction data of the second target sub-region based on historical surface runoff data of the second target sub-region.

[0078] In a possible implementation, in step S160, historical surface runoff data of the first target sub-area and the second target sub-area can be obtained, and the runoff data correlation ratio of the first target sub-area and the second target sub-area can be determined based on the historical surface runoff data of the first target sub-area and the second target sub-area.

[0079] Then, the surface runoff prediction data of each of the first target sub-areas is obtained, and the surface runoff prediction data of the second target sub-area is calculated based on the runoff data correlation ratio and the surface runoff prediction data of the first target sub-area.

[0080] For example, if no similar rainy area is found in Region B, runoff calculation can be performed using data from subregions of the rainy area and historical data. For example, Region 1 has a corresponding similar rainy subregion, and the runoff for Region 1 is determined to be m based on the rainy subregion. Region 2 has no corresponding similar rainy subregion, but historical data indicates that the runoff for Region 2 is 0.8 times that of Region 1. In this case, the runoff for Region 2 is set to 0.8 m.

[0081] Step S170 , determining the probability of an address disaster occurring when rain clouds move to the non-raining area based on the surface runoff prediction data of each target sub-area, and outputting a corresponding alarm notification based on the probability of an address disaster occurring.

[0082] Surface runoff values ​​are assigned to all sub-areas in area B. The runoff generated by each slope will converge at the lowest point of the triangle. Then, the runoff in all minimum values ​​(i.e., each small valley) is calculated based on the surface runoff in each sub-area. The runoff in each small valley converges into the valley with lower coordinates, and the surface runoff generated by all large and small slopes in the entire predicted area can be obtained. Flash floods and mudslides are mainly caused by excessive short-term runoff. The larger the runoff, the greater the probability of flash floods and mudslides. Therefore, the surface runoff size when cumulonimbus clouds move to the non-raining area can be determined based on the runoff calculation results, thereby predicting the probability of flash floods, mudslides and other disasters after rain in the non-raining area. When the probability is very high, an ultra-short-term warning is issued. The specific probability can be determined based on historical runoff data and disaster data.

[0083] Based on the above design, since cumulonimbus clouds move at a certain speed, usually 30 to 60 kilometers per hour, when it rains in one area, it may take more than ten or even dozens of minutes for it to rain in another area. By utilizing this time difference, real-time data from the rainy area can be used to predict the area where it will rain, thereby improving accuracy.

[0084] Furthermore, in this embodiment, once the monitoring data reaches the warning conditions, a warning will be issued. The warning process is as follows: monitoring warning - triggering system warning - SMS, WeChat public account warning - warning and disposal linkage - starting the plan - dispatch and command. After the system obtains the warning results through model analysis, it triggers the system warning process, and pushes the warning information to different responsible persons according to the warning registration. A variety of warning notification methods are used to ensure that the warning information can be notified to relevant personnel; warning and disposal linkage: automatically locate the warning location, display the surrounding geographical location information and the affected villages, personnel, and road information, link the surrounding smart devices and display real-time monitoring information and the corresponding historical change trends, video surveillance, etc., and link the disposal plan, etc.

[0085] Furthermore, after the early warning is triggered, it can be processed according to the pre-set emergency plan. For example, the plan is first structured: by decomposing and digitizing the original text plan, an intelligent plan is formed. The plan is structured according to the basic information of the plan, the command relationship diagram, the emergency resource allocation, etc. The basic information of the plan includes: the name of the plan, the plan level (Level I (Extremely serious), Level II (Serious), Level III (Large) and Level IV (General)), the type (natural disaster, accident disaster), the event scenario and other information; the command relationship diagram: match the position name and contact information of the personnel associated with the plan in advance to facilitate timely dispatch when the plan is activated; emergency resource allocation: according to the plan, relevant information such as emergency resources, expert resources, rescue teams, shelters, medical and health, and communication agencies are linked in advance. Secondly, the plan process design: the plan process design is carried out according to the process of early warning occurrence, early warning positioning, plan identification, and plan execution. The plan execution process logic is as follows: First, the intelligent plan content is linked by warning type, warning level, and warning location, extracting key plan processes and displaying a brief overview of the intelligent plan. Second, industrial television video is focused, using the warning GPS location to focus on and match surrounding surveillance video, and transmit on-site footage in real time. Third, key plan content is matched, including the main plan process, the current process, plan-related equipment, plan-related emergency resources, and plan-related emergency expert teams. Fourth, emergency response is carried out based on the plan and on-site content. This includes tracking the emergency response stage, displaying emergency response content, matching emergency supplies, emergency expert teams, and video conferencing. Finally, the plan is summarized by extracting the steps and processing procedures in the early warning and disposal process, such as the automatic focus time of industrial TV after the emergency occurs, the focus point on the industrial TV video matching analysis of manual operation click viewing; resource flow tracking after emergency resource scheduling; personnel scheduling tracking; audio and video recording during video conferences, etc., to extract the key content of each stage in the intelligent plan, analyze the matching degree with the plan, and generate a summary report to support the optimization of the intelligent plan based on the summary report.

[0086] In a possible implementation, in step S170, the total runoff prediction data of the non-raining area may be determined based on the surface runoff prediction data of each target sub-area.

[0087] At the same time, the GNSS surface displacement monitoring data of the non-raining area can also be obtained, and the probability of address disasters occurring when rain clouds move to the non-raining area can be determined based on the total runoff prediction data of the non-raining area and the GNSS surface displacement monitoring data.

[0088] Among them, the single-device data analysis model (GNSS) is based on the historical and real-time monitoring data of a single device. First, the displacement and deformation of the GNSS are analyzed, and the displacement is calculated from the X, Y, and Z directions. The displacement level is clarified, such as 30mm / d for attention, 50mm / d for warning level, and 80mm / d for alert level. The displacement is calculated by subtracting the current GNSS coordinates from yesterday's coordinates. Secondly, the deformation rate is analyzed, and the deformation change rate in the X, Y, and Z directions is calculated. Finally, the deformation direction angle is analyzed, and the deformation angle is calculated through the changes in the X, Y, and Z directions. Based on the displacement, deformation rate, and deformation angle required for geological disasters such as landslides and collapses, it is determined whether the disaster warning level can be reached.

[0089] Furthermore, multi-model detection data collected by each of the intelligent detection devices in the target area can also be obtained, and the intelligent detection devices include displacement sensors, thermometers, and meteorological sensors; based on the multi-model detection data of the non-raining area, the total runoff prediction data and the GNSS surface displacement monitoring data, the probability of an address disaster occurring when rain clouds move to the non-raining area is determined.

[0090] After receiving the binary data sent back by each smart device, the data is parsed to obtain the meaning of various fields in the data and classified according to different data types. The classified data is then verified to remove data with obvious errors.

[0091] Specifically, the smart devices described in this embodiment include but are not limited to commonly used monitoring equipment in current geological disaster detection, such as displacement sensors, thermometers, meteorological sensors (for measuring wind speed, temperature, rainfall, etc.), flow meters, etc. The smart devices are installed at the target detection locations, which are usually distributed at locations such as mountain peaks, valley bottoms, and sensitive slopes. The smart devices can obtain various geological, geographical, and meteorological data at the installation location, and after obtaining the data, transmit the data to the background server in real time via a wired or wireless network for subsequent analysis and processing. At the same time, the background server will record all historical data and call and analyze it when necessary.

[0092] Due to the large amount of detection data, and in order to reduce the amount of data transmission, smart devices usually return binary data. In order to facilitate subsequent analysis, after receiving the binary data, it is necessary to parse the data, obtain the meaning of various fields in the data, and classify it according to different data types. In order to facilitate the call of each type of data, it is stored in a data table or a database.

[0093] Due to reasons such as aging of sensor equipment, differences in installation locations, and local weather conditions, the data reported by smart devices is not completely reliable. Therefore, after parsing the data, further analysis of the data is required to determine whether the data problems are caused by equipment errors.

[0094] Specifically, since the single-device data analysis model can only perform analysis from a local location, if geological changes occur in a very small range, such as rock fractures, there is a high probability of false alarms. Furthermore, this embodiment also provides a device area comprehensive analysis model. Based on the design data analysis results of multiple smart devices (such as GNSS) in some geological disaster areas, the daily change rate, displacement and other data of multiple devices, deformation angles and trends, etc. are analyzed to analyze the changes in an area. Based on whether the overall area has reached the displacement, deformation rate, and deformation angle required for landslides, collapses, etc., it is determined whether the disaster warning level can be reached.

[0095] Furthermore, factors such as weather and vegetation can also affect the formation of geological disasters. To account for these factors, this implementation further provides a multi-type equipment analysis model. By acquiring data from different types of equipment and analyzing the monitored displacement, weather history comparisons and weather change processes, displacement change speed, displacement direction, and other changes, a more comprehensive trend forecast for geological disasters can be made, reducing false alarm rates.

[0096] Furthermore, the single-device data analysis model, the equipment area comprehensive analysis model, and the multi-type equipment analysis model are all suitable for long-term monitoring, while geological disasters are more sudden; mountain torrents, mudslides, etc. can save a lot of lives and property as long as early warning can be given more than ten minutes in advance. In order to be able to carry out ultra-short-term warning, this embodiment further provides a regional joint model.

[0097] An important factor causing flash floods, mudslides and other outbreaks is short-term heavy rainfall. Although rainfall, wind direction, etc. can be predicted through weather forecasts, on the one hand, weather forecasts themselves have certain errors and are forecast for a large area, making them difficult to use for short-term accurate predictions in special areas; on the other hand, due to the differences in terrain, landforms, vegetation, etc. in the monitoring area, the surface runoff formed under the same rainfall is not exactly the same, and the probability of forming flash floods and mudslides is also not exactly the same. Therefore, it is difficult to use the same parameters to carry out detailed modeling of different differences, making accurate predictions difficult.

[0098] This embodiment also provides an electronic device, which may be, but is not limited to, a server, a personal computer (PC), etc. Figure 5 , which is a block diagram of the electronic device 100. The electronic device 100 includes a geological disaster risk warning processing system 110, a machine-readable storage medium 120, and a processor 130.

[0099] The machine-readable storage medium 120, the processor 130, and the communication unit 140 are electrically connected to each other directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses or signal lines. The geological disaster risk warning processing system 110 includes at least one software function module that can be stored in the machine-readable storage medium 120 in the form of software or firmware or solidified in the operating system (OS) of the electronic device 100. The processor 130 is used to execute the executable modules stored in the machine-readable storage medium 120, such as the software function modules and computer programs included in the geological disaster risk warning processing system 110.

[0100] The machine-readable storage medium 120 may be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. The machine-readable storage medium 120 is used to store a program, and the processor 130 executes the program after receiving an execution instruction to implement the geological disaster risk early warning processing method provided in this embodiment.

[0101] The processor 130 may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0102] Please refer to Figure 6This embodiment further provides a geological hazard risk early warning processing system 110, which includes at least one functional module that can be stored in a machine-readable storage medium 120 in software form. Functionally, the geological hazard risk early warning processing system 110 can include a region division module 111, a similarity calculation module 112, a data acquisition module 113, a region query module 114, a first prediction module 115, a second prediction module 116, and an alarm notification module 117.

[0103] The region division module 111 is configured to divide the target region into multiple sub-regions.

[0104] In this embodiment, the region division module 111 can be used to perform Figure 1 As shown in step S110 , for a detailed description of the area division module 111 , please refer to the description of step S110 .

[0105] The similarity calculation module 112 is configured to determine, for each of the sub-regions, a similar region having similar terrain features to the sub-region based on the terrain feature data of the sub-region.

[0106] In this embodiment, the similarity calculation module 112 can be used to perform Figure 1 As shown in step S120 , for a detailed description of the similarity calculation module 112 , please refer to the description of step S120 .

[0107] The data acquisition module 113 is used to acquire the surface runoff data of each sub-area collected by multiple intelligent detection devices in the rainy area, and determine the movement direction of the rain cloud.

[0108] In this embodiment, the data acquisition module 113 can be used to perform Figure 1 As shown in step S130 , for a detailed description of the data acquisition module 113 , please refer to the description of step S130 .

[0109] The region query module 114 is configured to take each subregion in the non-raining region in the direction of movement of the rain cloud as a target subregion, and search the raining region for a target similar region corresponding to the target subregion.

[0110] In this embodiment, the area query module 114 can be used to perform Figure 1 As shown in step S140 , for a detailed description of the area query module 114 , please refer to the description of step S140 .

[0111] The first prediction module 115 is configured to use, for a first target sub-region where the target similar region exists in the target sub-region, the runoff volume of the target similar region corresponding thereto as surface runoff prediction data for the first target sub-region.

[0112] In this embodiment, the first prediction module 115 can be used to perform Figure 1 As shown in step S150 , for a detailed description of the first prediction module 115 , please refer to the description of step S150 .

[0113] The second prediction module 116 is configured to calculate surface runoff prediction data of a second target sub-region in the target sub-region where the target similar region does not exist, based on historical surface runoff data of the second target sub-region.

[0114] In this embodiment, the second prediction module 116 can be used to perform Figure 1 As shown in step S160 , for a detailed description of the second prediction module 116 , please refer to the description of step S160 .

[0115] The alarm notification module 117 is used to determine the probability of an address disaster occurring when rain clouds move to the non-raining area based on the surface runoff prediction data of each target sub-area, and output a corresponding alarm notification based on the address disaster probability.

[0116] In this embodiment, the alarm notification module 117 can be used to perform Figure 1 As shown in step S170, for a detailed description of the alarm notification module 117, please refer to the description of step S170.

[0117] In summary, the geological disaster risk warning processing method, system, and electronic device provided in the embodiments of the present application divide the target area into multiple sub-areas and identify corresponding similar areas. When precipitation occurs, the system determines the surface runoff forecast data for each sub-area in the non-raining area based on the runoff volume of similar areas in the raining area, thereby determining the probability of an address disaster occurring when rain clouds move into the non-raining area. This allows for ultra-short-term, precise warnings, improving the accuracy and immediacy of geological disaster warnings.

[0118] In the embodiments provided in this application, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the systems, methods, and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment, or a portion of code, and the module, program segment, or a portion of code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes 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 flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0119] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0120] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the 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 enabling 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 method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0121] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0122] The above descriptions are merely examples of various embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any modifications or substitutions that can be readily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included within the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A geological disaster risk early warning processing method, characterized in that: The method comprises: Divide the target area into multiple sub-areas; For each of the sub-regions, determining a similar region having similar terrain features to the sub-region based on the terrain feature data of the sub-region; Obtaining surface runoff data of each sub-area collected by a plurality of intelligent detection devices in the rainy area, and determining the direction of movement of rain clouds; Taking each sub-region in the non-raining area in the direction of the rain cloud movement as a target sub-region, searching whether there is a target similar region corresponding to the target sub-region in the raining area; For a first target sub-region in the target sub-region where the target similar region exists, the runoff volume of the target similar region corresponding thereto is used as the surface runoff prediction data of the first target sub-region; For a second target sub-region in the target sub-region where the target similar region does not exist, calculating surface runoff prediction data for the second target sub-region based on historical surface runoff data of the second target sub-region; determining, based on the surface runoff prediction data of each target sub-area, a probability of an address disaster occurring when rain clouds move to the non-raining area, and outputting a corresponding alarm notification based on the probability of the address disaster occurring; The step of calculating the surface runoff prediction data of a second target sub-region in the target sub-region where the target similar region does not exist, based on the historical surface runoff data of the second target sub-region, comprises: Acquiring historical surface runoff data according to the first target sub-area and the second target sub-area; determining a runoff data correlation ratio between the first target sub-area and the second target sub-area based on historical surface runoff data of the first target sub-area and the second target sub-area; Acquiring surface runoff prediction data for each of the first target sub-areas; The surface runoff prediction data of the second target sub-area is calculated according to the runoff data correlation ratio and the surface runoff prediction data of the first target sub-area.

2. The method according to claim 1, characterized in that The step of dividing the target area into a plurality of sub-areas includes: Obtain surface trend data of the target area; The target area is subjected to a surface triangular mesh division process according to the surface trend data to obtain a triangular mesh model of the target area, wherein the triangular mesh model includes sub-areas composed of a plurality of triangular facets.

3. The method according to claim 2, characterized in that The step of performing surface triangulation processing on the target area according to the surface trend data comprises: converting the terrain of the target area into a curved surface according to the surface trend data; Determining convex peaks and concave valleys in the curved surface; Each of the peak points is connected to its adjacent valley point, and each of the valley points is connected to other adjacent valley points to form a plurality of triangular facets.

4. The method according to claim 1, wherein The step of determining, for each of the sub-regions, a similar region having similar terrain features to the sub-region based on the terrain feature data of the sub-region, comprises: Determining a terrain vector of each sub-region based on the terrain feature data of each sub-region; the terrain vector includes data items representing the area of ​​the sub-region, the slope direction of the sub-region, the slope inclination of the sub-region, the vegetation coverage rate of the sub-region, and the soil looseness of the sub-region; For each of the sub-regions, calculating the similarity between the terrain vectors of the sub-region and other sub-regions beyond a preset distance from the sub-region; Other sub-regions whose similarity to the terrain vector of the sub-region is greater than a preset threshold are determined as the similar regions of the sub-region.

5. The method according to claim 1, wherein The step of determining the probability of an address disaster occurring when rain clouds move to the non-raining area based on the surface runoff prediction data of each target sub-area comprises: Determining the total runoff prediction data of the non-raining area based on the surface runoff prediction data of each target sub-area; Acquiring GNSS surface displacement monitoring data of the non-raining area; The probability of an address disaster occurring when rain clouds move to the non-raining area is determined based on the total runoff prediction data of the non-raining area and the GNSS surface displacement monitoring data.

6. The method according to claim 5, characterized in that The step of determining the probability of an address disaster occurring when rain clouds move to the non-raining area based on the total runoff prediction data and the GNSS surface displacement monitoring data of the non-raining area comprises: Acquire multi-model detection data collected by each of the intelligent detection devices in the target area, wherein the intelligent detection devices include a motion sensor, a thermometer, and a meteorological sensor; The probability of generating an address disaster when rain clouds move to the non-raining area is determined based on the multi-model detection data, the total runoff prediction data and the GNSS surface displacement monitoring data of the non-raining area.

7. A geological disaster risk early warning processing system, characterized in that: The system comprises: A region division module is used to divide the target region into multiple sub-regions; A similarity calculation module is used to determine, for each of the sub-regions, a similar region with similar terrain features to the sub-region based on the terrain feature data of the sub-region; a data acquisition module, configured to acquire surface runoff data of each sub-area collected by a plurality of intelligent detection devices in the rainy area, and determine the direction of movement of rain clouds; A region query module is used to take each sub-region in the non-raining region in the direction of rain cloud movement as a target sub-region, and to search whether there is a target similar region corresponding to the target sub-region in the raining region; a first prediction module, configured to use, for a first target sub-region where the target similar region exists in the target sub-region, the runoff volume of the target similar region corresponding thereto as surface runoff prediction data of the first target sub-region; a second prediction module, configured to calculate, for a second target sub-region in which the target similar region does not exist, surface runoff prediction data of the second target sub-region based on historical surface runoff data of the second target sub-region; an alarm notification module, configured to determine, based on the surface runoff prediction data of each target sub-area, the probability of an address disaster occurring when rain clouds move to the non-raining area, and output a corresponding alarm notification based on the address disaster probability; The second prediction module is specifically configured to: Acquiring historical surface runoff data according to the first target sub-area and the second target sub-area; determining a runoff data correlation ratio between the first target sub-area and the second target sub-area based on historical surface runoff data of the first target sub-area and the second target sub-area; Acquiring surface runoff prediction data for each of the first target sub-areas; The surface runoff prediction data of the second target sub-area is calculated according to the runoff data correlation ratio and the surface runoff prediction data of the first target sub-area.

8. An electronic device, characterized in that: The method comprises a processor and a machine-readable storage medium, wherein the machine-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are executed by the processor, the method according to any one of claims 1 to 6 is implemented.

9. A machine-readable storage medium, characterized in that The machine-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are executed by one or more processors, the method according to any one of claims 1 to 6 is implemented.

Images