Unmanned aerial vehicle radar monitoring method applied to geological disaster emergency

Abstract

The application discloses an unmanned aerial vehicle radar monitoring method applied to geological disaster emergency, relates to the technical field of geological disasters, and has the following steps: dividing a geological disaster monitoring region set by risk levels to obtain a risk condition monitoring region set, and extracting a target associated risk condition region set from the risk condition monitoring region set; comparing historical disaster data of various different geological disaster types in the risk condition monitoring region set and historical actual monitoring data of unmanned aerial vehicle radars in the corresponding region to obtain a comparison result set; wherein the comparison result set comprises a first comparison result and a second comparison result; extracting a target risk region set meeting the first comparison result from the risk condition monitoring region set; and the effect is that monitoring resources can be dynamically allocated according to the disaster threat degree of different regions.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of geological disasters, more particularly, it relates to a method for unmanned aerial vehicle radar monitoring applied to geological disaster emergency. BACKGROUND

[0002] With the intensification of global climate change and the increase of human engineering activities, geological disasters such as landslides, debris flows and collapses occur frequently, which pose a serious threat to people's life and property safety and infrastructure. The existing geological disaster emergency monitoring system often lacks integration and in-depth analysis of multi-source data, and the allocation of monitoring resources relies on experience, which cannot be scientifically scheduled according to the dynamic changes of disaster risks. For example, in landslides caused by heavy rain, there is often a phenomenon that the monitoring resources in high-risk areas are insufficient, while the resources in low-risk areas are redundant, resulting in low monitoring efficiency. SUMMARY

[0003] In view of the deficiencies in the prior art, the purpose of the present application is to provide a method for unmanned aerial vehicle radar monitoring applied to geological disaster emergency.

[0004] To achieve the above-mentioned purpose, the present application provides the following technical scheme:

[0005] The method for unmanned aerial vehicle radar monitoring applied to geological disaster emergency comprises the following steps:

[0006] After the risk level division of the geological disaster monitoring region set, a risk condition monitoring region set is obtained, and a target associated risk condition region set is extracted from the risk condition monitoring region set;

[0007] The historical disaster data of multiple different geological disaster types in the risk condition monitoring region set and the historical actual monitoring data of the unmanned aerial vehicle radar in the corresponding region are compared to obtain a comparison result set; wherein the comparison result set includes a first comparison result and a second comparison result;

[0008] A target risk region set meeting the first comparison result is extracted from the risk condition monitoring region set;

[0009] According to the target risk region set and the second comparison result, an associated monitoring risk region set adjacent to the target risk region set is screened from the risk condition monitoring region set;

[0010] After processing and analyzing the comparison result set, the associated monitoring risk region set, the target risk region set and the target associated risk condition region set, a monitoring condition set is obtained;

[0011] The current influence monitoring feature information set of the target risk region set and the associated monitoring risk region set in the current geological disaster emergency period is collected;

[0012] According to the current influence monitoring feature information set, the pre-processing monitoring condition is matched from the monitoring condition set, and the unmanned aerial vehicle radar monitoring resource of the target risk region set and the associated monitoring risk region set in the current geological disaster emergency period is re-scheduled and allocated according to the pre-processing monitoring condition.

[0013] Preferably, the comparison result set, the associated monitoring risk region set, the target risk region set and the target associated risk condition region set are processed and analyzed to obtain the monitoring condition set, which specifically includes the following steps:

[0014] The first comparison result and the second comparison result are analyzed to obtain the associated difference data set one, and the target associated risk region set conforming to the associated difference data set one is extracted from the associated monitoring risk region set;

[0015] The monitoring condition one is extracted from the target associated risk region set and the target risk region set in the first historical period, and the monitoring condition set two is extracted from the target associated risk condition region set and the target risk region set in the second historical period; wherein, the monitoring condition one and the monitoring condition set two are combined to obtain the monitoring condition set, and the second historical period is earlier than the first historical period.

[0016] Preferably, the risk condition monitoring region set is obtained by dividing the geological disaster monitoring region set into risk levels, which specifically includes the following steps:

[0017] The distribution of various geological disaster types in the geological disaster monitoring region set is counted to obtain the disaster distribution statistical result;

[0018] According to the disaster distribution statistical result, the geological disaster monitoring region set is divided into geological disaster risk levels to obtain the risk condition monitoring region set.

[0019] Preferably, the comparison result set is obtained by comparing the historical disaster data of various different geological disaster types in the risk condition monitoring region set and the historical actual monitoring data of the unmanned aerial vehicle radar in the corresponding region; wherein, the comparison result set includes the first comparison result and the second comparison result, and specifically includes the following steps:

[0020] The distribution of the unmanned aerial vehicle radar in the risk condition monitoring region set is counted to obtain the radar distribution statistical result set;

[0021] The historical actual monitoring data set of the unmanned aerial vehicle radar in the radar distribution statistical result set is obtained;

[0022] The historical disaster data set in the risk condition monitoring region set is collected;

[0023] The comparison result set is obtained by comparing the historical disaster data set with the historical actual monitoring data set;

[0024] The first comparison result refers to a value of the historical disaster data set being greater than or equal to the historical actual monitoring data set, and the first comparison result refers to a value of the historical disaster data set being less than the historical actual monitoring data set.

[0025] Preferably, the associated monitoring risk region set adjacent to the target risk region set is screened from the risk condition monitoring region set according to the target risk region set and the second comparison result, and specifically includes the following steps:

[0026] The associated risk region set is obtained after screening the risk region set adjacent to the target risk region set from the risk condition monitoring region set;

[0027] The associated monitoring risk region set meeting the second comparison result is extracted from the associated risk region set.

[0028] Preferably, the associated difference data set one is obtained by difference analysis of the first comparison result and the second comparison result, and specifically includes the following steps:

[0029] The first disaster difference set is obtained by difference calculation of the historical disaster data set and the historical actual monitoring data set in the first comparison result;

[0030] The second disaster difference set is obtained by difference calculation of the historical disaster data set and the historical actual monitoring data set in the second comparison result;

[0031] The difference data set is obtained by corresponding difference value statistics of the first disaster difference set and the second disaster difference set;

[0032] The associated difference data set one is screened from the difference data set in a disaster difference associated interval value.

[0033] Preferably, the monitoring condition one is extracted from the monitoring conditions of the target associated risk region set and the target risk region set in the first historical period, and the monitoring condition set two is extracted from the monitoring conditions of the target associated risk condition region set and the target risk region set in the second historical period; wherein the monitoring condition one and the monitoring condition set two are combined into the monitoring condition set, and specifically includes the following steps:

[0034] The first influence monitoring feature information set is output after respectively collecting the respective influence monitoring feature information of the target risk region set and the target associated risk region set in the first historical period;

[0035] The monitoring condition one is combined from the first influence monitoring feature information set and the associated difference data set one;

[0036] The second influence monitoring feature information set is output after respectively collecting the respective influence monitoring feature information of the target risk region set and the target associated risk condition region set in the second historical period;

[0037] Combining the second influence monitoring characteristic information set and the associated difference data set into a second monitoring condition set;

[0038] The first influence monitoring characteristic information and the second influence monitoring characteristic information are combined into an influence monitoring characteristic reference information set; and the first monitoring condition and the second monitoring condition set are combined into a monitoring condition set.

[0039] Preferably, the pre-processing monitoring condition is matched from the monitoring condition set according to the current influence monitoring characteristic information set, and the matching specifically includes the following steps:

[0040] The pre-processing influence monitoring characteristic information set that is most matched with the current influence monitoring characteristic information set is screened from the influence monitoring characteristic reference information set;

[0041] The corresponding pre-processing monitoring condition is screened from the monitoring condition set according to the pre-processing influence monitoring characteristic information set.

[0042] Preferably, the unmanned aerial vehicle radar monitoring resource of the target risk region set and the associated monitoring risk region set in the current geological disaster emergency period is rescheduled and allocated according to the pre-processing monitoring condition, and the rescheduling and allocation specifically includes the following steps:

[0043] The current disaster prediction value data set is obtained after the disaster prediction value of the target risk region set and the disaster prediction value of the associated monitoring risk region set in the current geological disaster emergency period are predicted according to the current influence monitoring characteristic information set;

[0044] The total amount of radar monitoring resources is obtained after the unmanned aerial vehicle radar monitoring resource of the target risk region set and the associated monitoring risk region set in the current geological disaster emergency period is collected;

[0045] The total amount of radar monitoring resources, the current disaster prediction value data set and the pre-processing monitoring condition are input into the geological disaster emergency monitoring resource model to reschedule and allocate the unmanned aerial vehicle radar monitoring resource.

[0046] An electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the unmanned aerial vehicle radar monitoring method applied to geological disaster emergency when executing the program.

[0047] Compared with the prior art, the present application has the following beneficial effects:

[0048] This invention, through the scientific classification of geological disaster monitoring areas and in-depth comparison of historical disaster data with UAV radar monitoring data, can accurately pinpoint high-risk areas. By inputting disaster prediction values, total resource availability, and pre-processed monitoring conditions into the model, monitoring resources can be dynamically allocated according to the degree of disaster threat in different areas. For example, high-resolution, long-endurance UAVs are prioritized for high-frequency monitoring in high-risk landslide areas, while lower-frequency collaborative monitoring is used in related areas to avoid resource waste. Attached Figure Description

[0049] Fig. 1 This is a schematic diagram illustrating the steps of the UAV radar monitoring method for geological disaster emergency response proposed in this invention;

[0050] Fig. 2 This is a schematic diagram illustrating the steps involved in calculating the associated differential dataset 1 in the UAV radar monitoring method for geological disaster emergency response proposed in this invention.

[0051] Fig. 3 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention.

[0052] 610. Processor; 620. Communication interface; 630. Memory; 640. Communication bus. Detailed Implementation

[0053] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0054] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0055] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0056] Reference Figs. 1-3 As shown.

[0057] The embodiments further illustrate the UAV radar monitoring method for geological disaster emergency response proposed in this invention.

[0058] A drone radar monitoring method for geological disaster emergency response, comprising the following steps:

[0059] obtaining a risk condition monitoring region set after the risk level division of the geological disaster monitoring region set, and extracting a target associated risk condition region set from the risk condition monitoring region set;

[0060] comparing historical disaster data of multiple different geological disaster types in the risk condition monitoring region set and historical actual monitoring data of the unmanned aerial vehicle radar in the corresponding region to obtain a comparison result set; wherein the comparison result set includes a first comparison result and a second comparison result;

[0061] extracting a target risk region set meeting the first comparison result from the risk condition monitoring region set;

[0062] screening an associated monitoring risk region set adjacent to the target risk region set from the risk condition monitoring region set according to the target risk region set and the second comparison result;

[0063] obtaining a monitoring condition set after processing and analyzing the comparison result set, the associated monitoring risk region set, the target risk region set and the target associated risk condition region set;

[0064] collecting a current influence monitoring feature information set of the target risk region set and the associated monitoring risk region set in the current geological disaster emergency period;

[0065] matching a pretreatment monitoring condition from the monitoring condition set according to the current influence monitoring feature information set, and re-scheduling and distributing the unmanned aerial vehicle radar monitoring resources of the target risk region set and the associated monitoring risk region set in the current geological disaster emergency period according to the pretreatment monitoring condition.

[0066] The application first divides the geological disaster monitoring region set by risk level, and classifies different regions into corresponding risk levels to form a risk condition monitoring region set according to geological conditions (such as rock-soil type, mountain slope), historical disaster frequency and other factors.

[0067] extracting a target associated risk condition region set from the risk condition monitoring region set according to the spatial position, the disaster-causing factor and the disaster chain core.

[0068] The region association relationship closely related to the development and influence of geological disasters is mined. In the geological disaster emergency scene, different regions are not isolated, but are connected through geological structure, disaster-causing factor transmission and disaster chain conduction. For example, the loose soil region around the landslide body may have secondary sliding due to the traction of the main landslide; the change of the source area upstream of the debris flow valley will affect the disaster scale of the downstream valley. Therefore, the extraction work needs to first sort out the association characteristics of geological disasters, determine the dimensions of spatial position, disaster-causing factor and disaster chain core, and use them as screening basis.

[0069] Then, the correlation characteristics of the divided risk monitoring area set are combed and labeled. With the help of GIS and other tools, combined with regional geological exploration data and historical disaster records, the correlation attributes of each risk area are marked. From the perspective of spatial correlation, the distance and direction of the area from known high-risk areas (such as large landslides and debris flow main gullies) are measured and recorded to determine whether the area is in the potential impact path (such as the extension zone of landslide sliding direction and the downstream of debris flow flow-through area); for disaster-causing factors, the degree of overlap of factors affected by the same rainfall system, seismic fault zone, and human engineering activities (such as mining areas) is analyzed; from the perspective of disaster chain, it is identified whether the area belongs to the key link of secondary disaster triggering, such as residential areas easily buried under landslide bodies and river backwater areas that may be blocked by debris flow.

[0070] An association degree evaluation model is constructed to quantitatively screen the areas. A reasonable weight is set for each dimension (adjusted according to the disaster type, such as higher spatial correlation weight in landslide disasters and higher correlation weight of disaster-causing factors such as debris flow disasters), and then the specific factors under each dimension are valued (such as closer distance to high-risk areas and higher degree of overlap of disaster-causing factors, the higher the value). The correlation degree of each risk area is calculated by formula, and the correlation degree value is used as the screening basis to screen out the target correlation risk area set that meets the correlation degree threshold (verified by historical disaster cases to ensure that it covers the real correlation area and avoids excessive redundancy).

[0071] The historical disaster data (disaster occurrence time, scale, damage degree, etc.) of different geological disaster types (landslides, debris flows, etc.) in the risk monitoring area set and the corresponding regional unmanned aerial radar historical monitoring data (monitoring coverage, data accuracy, frequency, etc.) are compared. The first comparison result (such as the disaster threat reflected in the historical disaster data exceeding the monitoring capability of the unmanned aerial radar, meaning that the monitoring is insufficient) and the second comparison result (the threat corresponding to the historical disaster data is within the monitoring coverage of the unmanned aerial radar and the monitoring is relatively sufficient) are distinguished to understand the matching situation between past monitoring and disasters.

[0072] The target risk area set that meets the first comparison result is extracted from the risk monitoring area set, and the adjacent correlation monitoring risk area set is screened out based on the target risk area set and the second comparison result, because geological disasters are easily linked and affected, the state change of adjacent areas will be associated with the target area and need to be monitored cooperatively.

[0073] The comparison result set, correlation monitoring risk area set, target risk area set, and target correlation risk area set are integrated and processed. The matching differences between different areas and disasters, the correlation characteristics between areas, etc. are analyzed to extract the monitoring rules, parameters, etc. suitable for the current monitoring to form a monitoring condition set, which guides the subsequent emergency monitoring period.

[0074] In the current geological disaster emergency period, the target risk area set and the current influence monitoring feature information set of the associated monitoring risk area set are collected, which covers real-time topographic changes, weather conditions (rainfall, wind speed), ground displacement, etc. Compare these real-time features with the monitoring condition set to find the appropriate pre-processing monitoring conditions and determine how to use the unmanned aerial vehicle radar to monitor at the moment.

[0075] According to the matched pre-processing monitoring conditions, the unmanned aerial vehicle radar monitoring resources (number of unmanned aerial vehicles, flight route, monitoring time, radar parameter setting, etc.) of the target risk area set and the associated monitoring risk area set are rescheduled and allocated. Let the unmanned aerial vehicle radar monitor the key areas in the emergency and the associated areas in the emergency, improve the efficiency and effectiveness of geological disaster emergency monitoring, and help to discover disaster signs and assess development trends in a timely manner.

[0076] After processing and analyzing the comparison result set, the associated monitoring risk area set, the target risk area set and the target associated risk status area set, the monitoring condition set is obtained, which includes the following steps:

[0077] The difference between the first comparison result and the second comparison result is analyzed to obtain the associated difference data set one, and the target associated risk area set that meets the associated difference data set one is extracted from the associated monitoring risk area set;

[0078] Extract the monitoring conditions of the target associated risk area set and the target risk area set in the first historical period to obtain the monitoring condition one; extract the monitoring conditions of the target associated risk status area set and the target risk area set in the second historical period to obtain the monitoring condition set two; wherein, the monitoring condition one and the monitoring condition set two constitute the monitoring condition set, and the second historical period is earlier than the first historical period.

[0079] The application carries out difference analysis on the first comparison result (the case where the historical disaster data and the radar monitoring data present a certain relationship) and the second comparison result (another data relationship performance), obtains a correlation difference data set one through operations such as calculating the difference between the two on the historical disaster data and the unmanned aerial vehicle radar monitoring data, thereby quantifying the characteristic differences between different comparison results; then, according to the data set, the part that fits the difference characteristics is selected from the correlation monitoring risk area set to determine the target correlation risk area set. Secondly, the monitoring conditions are extracted in the historical period, considering the evolution law of geological disasters and monitoring data over time, a second historical period earlier and a first historical period relatively closer are divided. The monitoring conditions of the target correlation risk area set and the target risk area set in the first historical period form monitoring condition one, capturing the monitoring needs of the correlation area and the core risk area in the relatively new period; the monitoring conditions of the target correlation risk situation area set and the target risk area set in the second historical period obtain monitoring condition set two. Finally, the monitoring conditions are integrated. Since the monitoring conditions of different historical periods carry the long-term geological evolution law (the second historical period) and the recent disaster mutation characteristics (the first historical period) respectively, monitoring condition one and monitoring condition set two are combined to form a complete monitoring condition set covering the space-time dimension and adapting to the current geological disaster emergency scene, providing accurate and comprehensive rule basis for subsequent unmanned aerial vehicle radar monitoring resource scheduling, allowing resource allocation to refer to both long-term rules and recent changes, and improving the scientificity and effectiveness of geological disaster emergency monitoring.

[0080] After dividing the geological disaster monitoring area set into risk levels, the risk situation monitoring area set is obtained, which includes the following steps:

[0081] The distribution of various geological disaster types in the geological disaster monitoring area set is counted to obtain the disaster distribution statistical result.

[0082] According to the disaster distribution statistical result, the geological disaster monitoring area set is divided into geological disaster risk levels to obtain the risk situation monitoring area set.

[0083] The application is used for dividing the risk levels of geological disaster monitoring areas. First, the geological disaster monitoring area set is comprehensively combed. For various geological disaster types such as landslides, debris flows and collapses contained in the area, the distribution density, coverage range and occurrence frequency of various disasters in different sub-areas are clearly mastered through statistical means, so as to form disaster distribution statistical results. Then, according to the obtained disaster distribution statistical results, the geological disaster monitoring area set is classified according to the preset risk level division rules (such as according to the disaster occurrence frequency, possible damage degree and other standards), the areas with dense disaster distribution, high occurrence possibility and large potential harm are classified as high risk level, the areas with relatively sparse distribution and small threat are classified as low risk level, and finally the risk condition monitoring area set is obtained, so as to accurately carry out geological disaster emergency monitoring and other work for different risk level areas, and realize the orderly management and prevention and control of geological disaster risk.

[0084] The historical disaster data of various geological disaster types in the risk condition monitoring area set and the historical actual monitoring data of the unmanned aerial radar in the corresponding area are compared to obtain a comparison result set; wherein the comparison result set includes a first comparison result and a second comparison result, and specifically includes the following steps:

[0085] The distribution of the unmanned aerial radar in the risk condition monitoring area set is counted to obtain a radar distribution statistical result set;

[0086] The historical actual monitoring data set of the unmanned aerial radar in the radar distribution statistical result set is obtained;

[0087] The historical disaster data set in the risk condition monitoring area set is collected;

[0088] The historical disaster data set and the historical actual monitoring data set are compared to obtain a comparison result set;

[0089] The first comparison result is that the historical disaster data set is greater than or equal to the numerical value of the historical actual monitoring data set, and the first comparison result is that the historical disaster data set is less than the numerical value of the historical actual monitoring data set.

[0090] The application is used for comparing geological disaster historical data with unmanned aerial vehicle radar monitoring data. First, focus on the risk condition monitoring area set, count the distribution of unmanned aerial vehicle radars in the area, and determine the deployment position and quantity of radars in each sub-area to form a radar distribution statistical result set. On this basis, the historical actual monitoring data set of the corresponding unmanned aerial vehicle radar is obtained, covering various types of past monitoring data. At the same time, the historical disaster data set of various geological disaster types (such as landslides, debris flows, etc.) in the area set is collected, including the time, scale, and influence range of the disaster. The historical disaster data set and the historical actual monitoring data set are compared in terms of numerical value, and the matching degree of the two is analyzed from the data level. If the historical disaster data set value is greater than or equal to the historical actual monitoring data set value, it is classified as the first comparison result, reflecting the lack of coverage or capture of monitoring data on disasters. If the historical disaster data set value is less than the historical actual monitoring data set value, it is the second comparison result, indicating that the monitoring data in the corresponding area is relatively sufficient, and finally forming a comparison result set, providing data comparison basis for subsequent geological disaster emergency monitoring analysis and decision-making, and helping to judge the effectiveness and improvement direction of unmanned aerial vehicle radar monitoring.

[0091] According to the target risk area set and the second comparison result, an associated monitoring risk area set adjacent to the target risk area set is selected from the risk condition monitoring area set, which includes the following steps:

[0092] After selecting the risk area set adjacent to the target risk area set from the risk condition monitoring area set, an associated risk area set is obtained;

[0093] The associated monitoring risk area set meeting the second comparison result is extracted from the associated risk area set.

[0094] The application selects all risk areas adjacent to the target risk area set from the divided risk condition monitoring area set through spatial position relationship discrimination. These areas may have mutual influence in the development process of geological disasters due to geographical proximity, thus forming an associated risk area set. This step is based on the characteristics of geological disasters that are often linked and transmitted, and includes spatially related areas in the analysis scope. Then, combined with the second comparison result obtained in the previous step (i.e. the historical disaster data set is less than the historical actual monitoring data set, meaning that the unmanned aerial vehicle radar monitoring in the corresponding area is relatively sufficient and the data is more referable), the associated monitoring risk area set meeting the result is further extracted from the associated risk area set. The purpose is to select areas adjacent to the target risk area and with high quality past monitoring data to provide effective support for current emergency monitoring, so as to more accurately carry out subsequent geological disaster cooperative monitoring and focus monitoring resources on areas that are associated and have reliable data basis, improving the scientificity and pertinence of geological disaster emergency monitoring.

[0095] The difference analysis on the first comparison result and the second comparison result obtains a correlation difference data set one, specifically including the following steps:

[0096] The difference value calculation on the historical disaster data set and the historical actual monitoring data set in the first comparison result obtains a first disaster difference set;

[0097] The difference value calculation on the historical disaster data set and the historical actual monitoring data set in the second comparison result obtains a second disaster difference set;

[0098] The corresponding difference value statistics on the first disaster difference set and the second disaster difference set obtains a difference data set;

[0099] A disaster difference correlation interval value is preset, and a correlation difference data set one located in the disaster difference correlation interval value is filtered out from the difference data set.

[0100] The application is used for mining the difference characteristics of two types of comparison results. Firstly, the difference value calculation is performed on the respective historical disaster data set and the historical actual monitoring data set for the first comparison result (historical disaster data set >= historical actual monitoring data set) and the second comparison result (historical disaster data set < historical actual monitoring data set), to obtain a first disaster difference set and a second disaster difference set. This step quantifies the difference degree of the disaster data and the monitoring data in the two types of results. The corresponding difference value statistics on the two difference sets generates a difference data set, so as to further highlight the difference between the two types of comparison results in the difference value. Then, a disaster difference correlation interval value is preset. The interval is determined based on the experience or data analysis requirement of the geological disaster emergency monitoring. The data falling in this interval is filtered out from the difference data set, and finally a correlation difference data set one is formed. The purpose is to accurately extract the data set of the difference characteristics between the two types of comparison results that meet a specific range, to provide differentiated data basis for subsequent operations such as filtering target regions from the correlation monitoring risk region set, to help more detailed analysis of the difference relationship between the geological disaster monitoring data, and to serve the accurate decision of the geological disaster emergency monitoring.

[0101] The monitoring conditions of the target correlation risk region set and the target risk region set in the first historical period are extracted to obtain a monitoring condition one, and the monitoring conditions of the target correlation risk condition region set and the target risk region set in the second historical period are extracted to obtain a monitoring condition set two. The monitoring condition one and the monitoring condition set two are combined into a monitoring condition set, specifically including the following steps:

[0102] The respective influence monitoring feature information of the target risk region set and the target correlation risk region set in the first historical period is collected to output a first influence monitoring feature information set;

[0103] The first influence monitoring feature information set and the correlation difference data set one are combined into the monitoring condition one;

[0104] respectively, output a second influence monitoring feature information set;

[0105] combine the second influence monitoring feature information set and the associated difference data set two into a monitoring condition set two;

[0106] The first influence monitoring feature information and the second influence monitoring feature information form an influence monitoring feature reference information set; the monitoring condition one and the monitoring condition set two form a monitoring condition set.

[0107] The present application collects the influence monitoring feature information (such as terrain, weather, displacement, etc.) of the target risk area set (monitoring insufficient core area) and the target associated risk area set (differential screening associated area) in the first historical period to form the first influence monitoring feature information set, and then combines it with the associated difference data set one (reflecting the monitoring supply-demand difference) to obtain the monitoring condition one, capturing the monitoring demand of the associated area and the core area in the near future. At the same time, the influence monitoring feature information of the target risk area set and the target associated risk situation area set in the second historical period is collected to generate the second influence monitoring feature information set, combined with the associated difference data set two (early monitoring supply-demand difference) to form the monitoring condition set two. Finally, the first and second influence monitoring feature information sets are integrated into the influence monitoring feature reference information set, which gathers the features of different periods; the monitoring condition one and the monitoring condition set two are combined into the monitoring condition set, which covers both the recent disaster mutation characteristics and the long-term geological regularity, providing a complete basis for the current emergency monitoring resource scheduling in time and space dimensions, and realizing the comprehensive coverage and precise adaptation of geological disaster monitoring demand.

[0108] According to the present influence monitoring feature information set, the pre-processing monitoring condition is matched from the monitoring condition set, which includes the following steps:

[0109] From the influence monitoring feature reference information set, the pre-processing influence monitoring feature information set that is most matched with the present influence monitoring feature information set is selected;

[0110] According to the pre-processing influence monitoring feature information set, the corresponding pre-processing monitoring condition is selected from the monitoring condition set.

[0111] The application is used for condition matching of geological disaster emergency monitoring. First, from the influence monitoring feature reference information set integrating influence features of different historical periods (first and second historical periods), according to the current influence monitoring feature information set collected in the current geological disaster emergency period, the pretreatment influence monitoring feature information set most close to the actual situation is screened out through feature similarity matching (such as the matching degree of topographic change, weather condition, ground displacement and the like), then based on the screened pretreatment influence monitoring feature information set, the corresponding pretreatment monitoring condition is matched from the monitoring condition set (containing monitoring rules integrated in different historical periods) constructed in advance, so as to provide accurate adaptation basis for unmanned aerial vehicle radar monitoring resource scheduling and the like in the current geological disaster emergency period, realize the use of historical monitoring logic to guide the actual monitoring work, and improve the pertinence and effectiveness of emergency monitoring.

[0112] According to the pretreatment monitoring condition, the unmanned aerial vehicle radar monitoring resources of the target risk region set and the associated monitoring risk region set in the current geological disaster emergency period are rescheduled and allocated, specifically including the following steps:

[0113] According to the current influence monitoring feature information set, the disaster prediction values of the target risk region set and the associated monitoring risk region set in the current geological disaster emergency period are predicted to obtain the current disaster prediction value data set;

[0114] After collecting the unmanned aerial vehicle radar monitoring resources of the target risk region set and the associated monitoring risk region set in the current geological disaster emergency period, the total amount of radar monitoring resources is obtained;

[0115] The total amount of radar monitoring resources, the current disaster prediction value data set and the pretreatment monitoring condition are input into the geological disaster emergency monitoring resource model to reschedule and allocate the unmanned aerial vehicle radar monitoring resources.

[0116] The application is used for intelligent scheduling of unmanned aerial vehicle radar monitoring resources in geological disaster emergency. Based on the current influence monitoring feature information set (such as topographic change, weather data, ground displacement and the like) collected in the current geological disaster emergency period, the disaster development trend of the target risk region set (core area with insufficient monitoring) and the associated monitoring risk region set (cooperative monitoring area) is pre-judged to obtain respective disaster prediction values to form the current disaster prediction value data set.

[0117] The present application, through deep mining and model application of real-time features, accurately predicts the development trend of disasters. First, focus on the current impact monitoring feature information set collected during the current emergency period. These information covers the multi-feature of target risk area set (monitoring short board core area) and associated monitoring risk area set (coordinated correlation area), such as surface displacement rate, rainfall intensity, soil humidity, terrain slope, etc. Then, based on rich historical disaster cases and geological research, a prediction model system suitable for different regions and different disaster types (landslide, debris flow, etc.) is constructed. For the target risk area set, which is a relatively weak monitoring high-risk area, it is focused on combining its geological background (such as rock and soil characteristics, fault zone distribution) and real-time features, using statistical regression (fitting the historical correlation between features and disaster size), machine learning (such as LSTM to capture the nonlinear law of displacement time sequence change) or physical mechanism model (calculate landslide stability according to Mohr-Coulomb criterion) to simulate the evolution path of disaster from "potential deformation" to "actual occurrence". The associated monitoring risk area set is based on the spatial correlation with the target area and the disaster factor conduction (such as mudslide source supply in the same rainfall basin), and analyzes the disaster possibility of the target area disaster linkage influence or independent development of itself through model logic. In the prediction execution, the feature information of the current emergency period is input into the corresponding model. For the target risk area, the disaster size or occurrence probability is accurately calculated, such as landslide volume, debris flow flow; for the associated monitoring risk area, the prediction value of the disaster caused by the target area disaster chain reaction (such as secondary debris flow triggered by landslide) or its own geological condition change is evaluated. Finally, these prediction results belonging to different regions and different disaster types are integrated into a structured current disaster prediction value data set according to the region category, disaster attribute and other dimensions, and the disaster threat degree of each region in the current emergency period is clearly presented, providing intuitive and quantitative basis for subsequent scientific scheduling of unmanned aerial vehicle radar monitoring resources and accurate formulation of disaster emergency decision-making, so that the geological disaster emergency response is more in line with the actual risk situation.

[0118] The potential threat degree of different regions is clear. At the same time, the total amount of radar monitoring resources is obtained by statistically counting the unmanned aerial vehicle radar monitoring resources available in the target risk area set and the associated monitoring risk area set during the current emergency period, including the number of unmanned aerial vehicles, endurance, radar parameters, etc. The total amount of radar monitoring resources, the current disaster prediction value data set and the pre-matched pre-processing monitoring conditions (monitoring rules suitable for the current scene) are input into the geological disaster emergency monitoring resource model.

[0119] The construction of geological disaster emergency monitoring resource model needs to be designed systematically from multiple dimensions to realize the scientific scheduling and efficient configuration of monitoring resources in disaster emergency scenarios. First of all, the modeling goal needs to be clear, that is, to construct an intelligent decision-making model that can comprehensively consider the disaster threat level, resource availability, and monitoring rules, in order to ensure that high-risk areas have sufficient monitoring resources, maximize the overall monitoring efficiency under the condition of limited total resources, and adapt to the changes in the disaster evolution process.

[0120] Secondly, the input system of the model needs to integrate three types of core data. The first is disaster risk data, which predicts the disaster prediction value of the target risk area and the associated area based on the influence monitoring characteristic information set (such as topography, rock and soil parameters, rainfall data, etc.), and clearly defines the occurrence probability and impact scale of disasters such as landslides and collapses in each region. The second is resource endowment data, which includes the number of unmanned aerial vehicles, endurance time, load capacity, resolution, scanning range, data transmission rate, and other physical attributes of radar, as well as real-time location, maintenance status, and other dynamic information of resources. The third is monitoring rule data, which sets monitoring standards for different disaster types, such as the spatial resolution required for landslide monitoring, the monitoring frequency requirement for aftershock areas after an earthquake, and the priority rules for resource scheduling (such as life rescue areas taking priority over general monitoring areas).

[0121] A combination of multi-objective optimization and rule engine is adopted. The mathematical model is constructed with disaster threat degree (risk area disaster prediction value weighted), resource utilization efficiency (device endurance and coverage matching degree), and monitoring compliance (whether meeting the accuracy and frequency requirements) as optimization objectives. Heuristic algorithms such as genetic algorithm and particle swarm algorithm are used to generate initial scheduling schemes. Parameters such as unmanned aerial vehicle task path and radar working mode need to be encoded in the algorithm to evaluate the pros and cons of the scheme and iteratively optimize it. At the same time, the rule engine is embedded to convert rigid monitoring standards (such as high-risk areas must be scanned every hour) into constraints, and the output scheme is checked. If there is a resource conflict (such as multiple regions applying for the same unmanned aerial vehicle), the conflict is resolved through priority rules.

[0122] In the model training and verification stage, historical disaster case data (such as the actual effect of resource scheduling in a landslide event) and simulated emergency scenario data are used to combine offline training with online optimization. In the offline stage, the algorithm weight parameters are adjusted based on historical data to enable the model to learn scheduling experience such as "high-risk areas should be prioritized for high-precision radar allocation"; in the online stage, model parameters are dynamically corrected based on real-time monitoring feedback (such as the deviation between actual monitoring data and predicted values), for example, when a large prediction error is found for a certain type of disaster, the weight of that disaster type in the objective function is increased. By comparing the model output scheme with the resource use efficiency in actual emergency response (such as monitoring coverage and data completeness), the model accuracy is evaluated and continuously iterated.

[0123] When deploying the model, integration with the emergency monitoring platform is considered, and the trained algorithm module is embedded into the command system to realize real-time data access (such as obtaining UAV status through the Internet of Things), automatic generation of schemes (outputting scheduling plans within 10 minutes after receiving disaster warning), and dynamic adjustment (triggering a rescheduling mechanism when the disaster area expands). At the same time, a model updating mechanism is established, and new disaster data and resource performance data (such as endurance test data of new UAVs) are imported into the model for retraining after each round of emergency response. When monitoring technology upgrades (such as improved radar resolution) or disaster types evolve (such as the addition of freeze-thaw disaster monitoring needs), the monitoring standards in the rule engine are updated simultaneously to ensure that the model continues to adapt to emergency monitoring needs. Throughout the construction process, strategies for dealing with difficult problems such as dynamic disaster evolution (such as risk area expansion due to increasing rainfall), multi-region resource competition (such as resource coordination during cross-region emergency support), and heterogeneous resource collaboration (data fusion monitoring of UAVs and ground-based radars) are considered, and ultimately an intelligent resource scheduling model that is both scientific and practical is formed, providing decision support for geological disaster emergency response.

[0124] The model intelligently calculates and optimally allocates based on factors such as disaster threat level, resource capacity, and monitoring condition requirements. For example, more high-performance, long-endurance UAVs are allocated to target risk areas with high disaster prediction values to prioritize key area monitoring; for associated monitoring risk areas, resources are allocated reasonably based on collaborative monitoring needs, ultimately achieving scientific and precise rescheduling of UAV radar monitoring resources in the current emergency period, improving the efficiency and effectiveness of geological disaster emergency monitoring, and assisting in timely capturing disaster development dynamics.

[0125] An electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements a UAV radar monitoring method for geological disaster emergencies when executing the program.

[0126] As Fig. 3As shown, the electronic device can include a processor 610, a communications interface 620, a memory 630, and a communications bus 640, wherein the processor 610, the communications interface 620, and the memory 630 complete mutual communication through the communications bus 640. The processor 610 can invoke a logical instruction in the memory 630 to execute the unmanned aerial vehicle radar monitoring method applied to geological disaster emergency.

[0127] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment scheme according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0128] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software and the necessary general hardware platform, and of course, can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0129] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for unmanned aerial vehicle radar monitoring applied to geological disaster emergency, characterized in that, The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: 2.The unmanned aerial vehicle radar monitoring method for geological disaster emergency according to claim 1, characterized in that, The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: 3.The unmanned aerial vehicle radar monitoring method for geological disaster emergency of claim 2, wherein, The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the The disaster distribution statistical result is obtained by counting the distribution of various geological disaster types in the geological disaster monitoring region set; The risk condition monitoring region set is obtained by dividing the geological disaster monitoring region set according to the disaster distribution statistical result. 4.The unmanned aerial vehicle radar monitoring method for geological disaster emergency of claim 3, wherein, The difference analysis is performed on the first comparison result and the second comparison result to obtain the correlation difference data set one, and the difference analysis specifically includes the following steps: The difference value calculation is performed on the historical disaster data set and the historical actual monitoring data set in the first comparison result to obtain the first disaster difference set; The difference value calculation is performed on the historical disaster data set and the historical actual monitoring data set in the second comparison result to obtain the second disaster difference set; The corresponding difference value statistics are performed on the first disaster difference set and the second disaster difference set to obtain the difference data set; The disaster difference correlation interval value is preset, and the correlation difference data set one located in the disaster difference correlation interval value is filtered out from the difference data set. 5.The unmanned aerial vehicle radar monitoring method for geological disaster emergency of claim 4, wherein, The monitoring condition one is obtained by extracting the monitoring conditions of the target correlation risk region set and the target risk region set in the first historical period, and the monitoring condition set two is obtained by extracting the monitoring conditions of the target correlation risk condition region set and the target risk region set in the second historical period; wherein, the monitoring condition one and the monitoring condition set two are combined into the monitoring condition set, and the combination specifically includes the following steps: The first influence monitoring characteristic information set is output by respectively collecting the influence monitoring characteristic information of the target risk region set and the target correlation risk region set in the first historical period; The first influence monitoring characteristic information set and the correlation difference data set one are combined into the monitoring condition one; The second influence monitoring characteristic information set is output by respectively collecting the influence monitoring characteristic information of the target risk region set and the target correlation risk condition region set in the second historical period; The second influence monitoring characteristic information set and the correlation difference data set two are combined into the monitoring condition set two; The first influence monitoring characteristic information and the second influence monitoring characteristic information are combined into the influence monitoring characteristic reference information set; and the monitoring condition one and the monitoring condition set two are combined into the monitoring condition set. 6.The unmanned aerial vehicle radar monitoring method for geological disaster emergency of claim 5, wherein, The preprocessing monitoring condition is matched from the monitoring condition set according to the current influence monitoring characteristic information set, and the matching specifically includes the following steps: The preprocessing influence monitoring characteristic information set most matched with the current influence monitoring characteristic information set is filtered out from the influence monitoring characteristic reference information set; The corresponding preprocessing monitoring condition is filtered out from the monitoring condition set according to the preprocessing influence monitoring characteristic information set. 7.The unmanned aerial vehicle radar monitoring method for geological disaster emergency of claim 6, wherein, The unmanned aerial vehicle radar monitoring resource of the target risk region set and the correlation monitoring risk region set in the current geological disaster emergency period is re-scheduled and allocated according to the preprocessing monitoring condition, and the re-scheduling and allocation specifically includes the following steps: The current disaster prediction value data set is obtained by predicting the disaster prediction value of the target risk region set and the disaster prediction value of the correlation monitoring risk region set in the current geological disaster emergency period according to the current influence monitoring characteristic information set; The total amount of the radar monitoring resource is obtained by collecting the unmanned aerial vehicle radar monitoring resource of the target risk region set and the correlation monitoring risk region set in the current geological disaster emergency period; The total amount of radar monitoring resources, the current disaster prediction value data set and the preprocessed monitoring conditions are input into the geological disaster emergency monitoring resource model to re-schedule and allocate the unmanned aerial vehicle radar monitoring resources.

8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the program to realize the unmanned aerial vehicle radar monitoring method applied to geological disaster emergency in any one of claims 1 to 7.

Images