Geological disaster prevention and control early warning intelligent decision-making method and system and storage medium

Abstract

The invention discloses a geological disaster prevention and control early-warning intelligent decision-making method and system and a storage medium, relates to the technical field of geological disaster prevention and control, and aims to solve the problems that in the prior art, a traditional geological disaster prediction method often depends on limited data and experience judgment, complex changes of a geological environment are difficult to accurately capture, and the geological disaster prediction accuracy is high. The method specifically comprises the following steps: dynamically monitoring regional environment and geological data, accurately identifying hidden danger points, constructing a disaster prediction path, detecting a path triggering state by a system in real time, capturing a disaster trajectory and an extension trend, generating targeted prevention and control deployment, and introducing a prevention and control efficiency dynamic evaluation mechanism to determine a disaster prediction result. Through quantitative analysis of disaster expansion speed and prevention and control effect, adaptive optimization of a deployment strategy is realized, accuracy of hidden danger identification and early warning timeliness are significantly improved, conversion from passive response to active accurate prevention and control is realized, and effective technical guarantee is provided for regional safety.

Description

Technical Field

[0001] This invention relates to the field of geological disaster prevention and control technology, specifically to an intelligent decision-making method, system, and storage medium for geological disaster prevention and early warning. Background Technology

[0002] Geological disasters, as a highly destructive phenomenon in nature, constantly threaten human life and property safety and the stability of the ecological environment. Common geological disasters such as landslides, mudslides, and ground subsidence are often sudden and have great destructive power. Faced with such a severe geological disaster situation, traditional geological disaster prevention and control methods have gradually revealed their limitations and are no longer able to meet the current needs for efficient and precise disaster prevention and mitigation.

[0003] However, in existing technologies, traditional geological disaster prediction methods often rely on limited data and experience-based judgments, making it difficult to accurately capture the complex changes in the geological environment, resulting in large errors in the prediction results. Furthermore, geological disaster prevention and control measures often lack specificity and cannot meet the needs of different disaster scenarios. Therefore, a solution is proposed. Summary of the Invention

[0004] The purpose of this invention is to solve the problems mentioned above by proposing an intelligent decision-making method, system and storage medium for geological disaster prevention and early warning.

[0005] The objective of this invention can be achieved through the following technical solution: an intelligent decision-making method for geological disaster prevention and early warning, the specific steps of which are as follows: Step S1: Monitoring and analysis of the distribution of protected areas; S11: Hazard point analysis, dividing the protection area into points, and conducting geological monitoring based on the points. By monitoring, the fluctuation of environmental data at the points in the protection area is inferred to identify hazard points. S12: Predicted path determination: Based on real-time risk parameters and the fluctuation of corresponding impact data under the current environment, determine the risk parameters of the same type, and determine the disaster path of the protected area in combination with the corresponding hidden danger points; Step S2: Path trigger detection; Based on the monitoring of real-time risk parameters and geological parameters of the area where the potential hazard is located, path trigger detection is carried out to predict disasters, and targeted deployments are made based on the prediction results. Step S3: Assessment of prevention and control efficiency; S31: Prevention and control deployment: Based on the comparison between the predicted disaster path and the actual disaster trajectory, determine the real-time disaster route and carry out targeted deployment; S32: Conduct an assessment of the effectiveness of prevention and control measures based on the deployment of prevention and control measures.

[0006] Furthermore, the analysis process for potential hazards in S11 is as follows: The protected area is divided into points based on the coverage of the equipped sensors, and the boundaries of the points are connected. Real-time environmental data is monitored at the points, where real-time environmental data is represented by rainfall and wind speed. The monitoring period is determined, and historical protection stages are extracted based on the duration of the monitoring period to obtain the historical protection stages. The time periods in the current protection stage where the environmental data of the points continuously shows an adverse trend are obtained, and the duration percentage is collected based on the progress time of the current protection stage and marked as the adverse impact ratio. The current protection stage is divided according to the adverse impact ratio, that is, the percentage of time other than the adverse impact ratio is marked as the normal impact ratio. The frequency of peak value changes in the adverse trend of the environmental data within the corresponding time period of the adverse impact ratio is obtained.

[0007] Furthermore, if the weighting of the adverse impact ratio and the normal impact ratio increases, and the frequency of peak changes in the adverse trend of environmental data within the corresponding period exceeds the set threshold for the frequency of changes, then the corresponding points in the current protection phase will be marked as potential hazards. If the weighting of the adverse impact ratio and the normal impact ratio does not increase, or if the frequency of peak changes in the adverse trend of environmental data within the corresponding period of the adverse impact ratio does not exceed the set threshold for the frequency of changes, then the corresponding points in the current protection phase will be marked as non-hazard points.

[0008] Furthermore, the prediction path determination process in S12 is as follows: Geological parameters of both hazardous and non-hazardous points are monitored, with geological parameters represented as surface displacement, deep displacement, and crack opening / closing degree. The unfavorable trend stage of environmental parameters corresponding to the hazardous point is determined, and the fluctuation range of geological parameters within the corresponding stage is obtained. At the same time, based on the current protection stage, the fluctuation range of geological parameters of non-hazardous points within the non-unfavorable trend stage is obtained, and these are respectively marked as the current disturbed fluctuation data and the current undisturbed fluctuation data. Based on the historical protection phases, the range of geological parameter fluctuations for the points within the unfavorable trend phase and the range of geological parameter fluctuations for the points within the corresponding non-unfavorable trend phase are obtained. The disaster occurrence results for the corresponding phase are obtained based on the historical protection results. If a disaster occurs, it is marked as the unfavorable trend disaster range and the non-unfavorable trend disaster range, respectively. If no disaster occurs, it is marked as the unfavorable trend safe range and the non-unfavorable trend safe range, respectively.

[0009] Furthermore, based on data comparison, if the current disturbance fluctuation data is within the unfavorable trend disaster range, the current potential hazard point is marked as a predicted disaster point; if the current disturbance fluctuation data is within the unfavorable trend safe range, the current potential hazard point is marked as a low-risk disaster point; if the current non-disturbing fluctuation data is within the non-unfavorable trend disaster range, the current non-potential hazard point is marked as a predicted extension point; if the current non-disturbing fluctuation data is within the non-unfavorable trend safe range, the current non-potential hazard point is marked as a monitoring-normal point. A predicted disaster path is constructed by connecting the predicted disaster points, and a predicted extension path is constructed by connecting the predicted extension points with the predicted disaster path. At the same time, adjacent monitoring points that are not different from the predicted disaster path and the predicted extension path are marked. Points that are in the path or adjacent to the path need to be marked.

[0010] Furthermore, the path trigger detection process in S2 is as follows: Trigger monitoring is performed on predicted disaster paths and predicted extension paths. The growth rate of the floating span of geological data corresponding to the predicted disaster points in the predicted disaster path is collected, and the time when the floating span of geological data increases is collected simultaneously. If the growth rate of the floating span exceeds a set growth rate threshold, or if the number of times the floating span of geological data increases exceeds a set number of times, the path is inferred to be triggered, and the corresponding predicted disaster path is intercepted. The road segment that triggers the disaster is marked as a disaster trajectory. Based on the geographical location of the predicted disaster path, the high-altitude road segments that generate disaster trajectories are marked as road segments to be triggered. Simultaneously, the geological parameter fluctuation process of adjacent points corresponding to the predicted extension path and the predicted disaster path is acquired. If the interval between the floating parameters of the predicted extension path and the floating parameters of the predicted disaster path continuously shortens, the corresponding predicted extension path is marked as a real-time extension path; otherwise, if the interval between the floating parameters of the predicted extension path and the floating parameters of the predicted disaster path does not shorten, the corresponding predicted extension path is marked as a path that has not yet been extended. Here, the floating parameter represents the floating speed or floating span of the geological parameter. At the same time, points with no abnormalities are monitored in real time, and when the geological parameters are abnormal, the corresponding points are merged into the disaster trajectory; otherwise, monitoring continues.

[0011] Furthermore, the prevention and control deployment process in S31 is as follows: The generated disaster trajectory and real-time extension path are determined. The generated disaster trajectory and real-time extension path are compared with the predicted disaster path and predicted extension path, respectively. If the number of overlapping points continues to increase, or the number of points in the predicted path that do not generate disasters continues to decrease, then protection deployment is carried out based on the trajectory of the predicted path while implementing real-time disaster protection. The predicted path is a general term for the predicted disaster path and the predicted extension path. If the number of overlapping points does not continue to rise, and the number of points in the predicted path that do not generate disasters does not continue to decrease, then disaster blocking deployment will be carried out to protect the real-time disaster trajectory while preventing the disaster trajectory from moving into the predicted path.

[0012] Furthermore, the process for evaluating the prevention and control efficiency in S32 is as follows: The system obtains the rate of increase in the number of disaster-related points corresponding to the disaster trajectory after the current protection deployment. Simultaneously, after the current protection deployment, it obtains the rate of increase in the number of disaster-related points in the road segment to be affected. The sum of the increase rates is obtained by superimposing the rates and marked as the prevention and control rate feature information. The constant value of the number of disaster-free points in the predicted path after the current protection deployment is obtained, along with the remaining number of points in the predicted path. The point number ratio is then calculated based on this ratio. If the speed characteristic information of prevention and control exceeds the set speed threshold, or the number of points does not exceed the set number ratio threshold, it is inferred that the efficiency of prevention and control deployment cannot adapt to the current disaster, and redeployment is carried out in combination with the disaster trajectory generated in real time; if the speed characteristic information of prevention and control does not exceed the set speed threshold, and the number of points exceeds the set number ratio threshold, it is inferred that the efficiency of prevention and control deployment adapts to the current disaster, and disaster protection is carried out according to the current prevention and control deployment.

[0013] A geological disaster prevention and early warning intelligent decision-making system includes an intelligent decision-making platform, wherein the intelligent decision-making platform is communicatively connected to a hidden danger point analysis unit, a prediction path determination unit, a path trigger detection unit, a prevention and control deployment unit, and an efficiency evaluation unit; The hazard point analysis unit divides the protection area into points and conducts geological monitoring based on the points. By monitoring, it infers the fluctuations in environmental data of the points in the protection area to identify hazard points. The prediction path determination unit determines the same type of risk parameters based on real-time risk parameters and the fluctuation of corresponding impact data under the current environment, and determines the disaster path of the protection area based on the corresponding hidden danger points. The path trigger detection unit performs path trigger detection based on real-time risk parameter monitoring and geological parameter monitoring of the area where the potential hazard point is located, thereby making disaster predictions and making targeted deployments based on the prediction results; The prevention and control deployment unit compares the predicted disaster path with the actual disaster trajectory to determine the real-time disaster route and make targeted deployments. The efficiency assessment unit evaluates the effectiveness of prevention and control measures based on the deployment.

[0014] A computer storage medium storing a computer program, which, when executed by a processor, implements the aforementioned intelligent decision-making method for geological disaster prevention and early warning.

[0015] Compared with the prior art, the beneficial effects of the present invention are: 1. By analyzing the hidden danger points in step S1 and combining the adverse trends and peak frequency of environmental data (such as rainfall and wind speed), hidden danger points and non-hidden danger points are dynamically marked. This data-driven analysis can effectively distinguish high-risk areas and avoid the problems of missed or false alarms caused by slow changes in environmental parameters in traditional methods. At the same time, the hidden danger point type is updated in real time as the protection stage progresses and pushed to the administrator terminal to ensure the timeliness of monitoring information and provide a reliable basis for early warning.

[0016] 2. In the prediction path determination S12, not only are the fluctuations in geological parameters of potential hazard points considered, but data from non-potential hazard points are also integrated to construct predicted disaster paths and predicted extension paths. By comparing historical data with real-time parameters, the types of points are accurately classified (such as predicted disaster points, low-risk disaster points, etc.), forming a multi-dimensional disaster propagation network. This dynamic path prediction can adapt to changes in complex geological environments, improve the predictability of disaster development trends, and provide a scientific basis for the pre-positioning of prevention and control resources.

[0017] 3. Step S2 monitors the floating span and growth rate of geological parameters (such as surface displacement and crack opening and closing degree) in real time, promptly determines the path triggering conditions, sets growth rate thresholds and time number thresholds, ensures that the disaster can be identified in the bud stage, and extracts the path as the disaster trajectory. At the same time, by analyzing the parameter interval changes between the predicted extension path and the disaster path, the real-time extension path and the path that has not yet extended are distinguished, so as to realize the real-time assessment of the disaster spread risk and reduce the response delay.

[0018] 4. In the prevention and control deployment, the deployment strategy is dynamically adjusted according to the overlap between the actual disaster trajectory and the predicted path. If the number of overlapping points increases, the protection of the predicted path is strengthened; otherwise, disaster blocking deployment is carried out to prevent the disaster from spreading to the predicted area. This flexibility ensures that the prevention and control measures are highly matched with the actual development of the disaster, avoids waste of resources, and reduces the risk of secondary disasters caused by chain reactions.

[0019] 5. Through prevention and control efficiency assessment, based on the characteristics of prevention and control speed and the ratio of the number of points, the deployment effect is quantitatively evaluated. If the efficiency is insufficient, the system will automatically prompt redeployment or adjustment of facility specifications to form a closed-loop control. This continuous optimization mechanism ensures that the prevention and control strategy always adapts to the current disaster situation and improves the resilience and reliability of the overall disaster prevention system. Attached Figure Description

[0020] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0021] Figure 1 This is a flowchart of the method of the present invention; Figure 2 This is a system principle block diagram of the present invention. Detailed Implementation

[0022] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0024] Please see Figure 1 As shown, a smart decision-making method for geological disaster prevention and early warning includes the following steps: Step S1: Monitoring and analysis of the distribution of protected areas; S11: Hazard point analysis, dividing the protection area into points, and conducting geological monitoring based on the points. By monitoring, the fluctuation of environmental data at the points in the protection area is inferred to identify hazard points. S12: Predicted path determination: Based on real-time risk parameters and the fluctuation of corresponding impact data under the current environment, determine the risk parameters of the same type, and determine the disaster path of the protected area in combination with the corresponding hidden danger points; Step S2: Path trigger detection; Based on the monitoring of real-time risk parameters and geological parameters of the area where the potential hazard is located, path trigger detection is carried out to predict disasters, and targeted deployments are made based on the prediction results. Step S3: Assessment of prevention and control efficiency; S31: Prevention and control deployment: Based on the comparison between the predicted disaster path and the actual disaster trajectory, determine the real-time disaster route and carry out targeted deployment; S32: Conduct an assessment of the effectiveness of prevention and control measures based on the deployment of prevention and control measures.

[0025] The analysis process for potential hazards in S11 is as follows: The protected area is divided into points according to the coverage of the equipped sensors, and the boundaries of the points are connected. Real-time environmental data is monitored at the points, and the real-time environmental data is represented by rainfall, wind speed, etc. The monitoring period is determined, and historical protection stages are extracted based on the duration of the monitoring period to obtain the historical protection stages. The time periods in which the environmental data of the divided points within the current protection stage show a continuous adverse trend are obtained. The duration percentage is collected based on the progress time of the current protection stage and marked as the adverse impact ratio. The adverse trend represents the geological impact corresponding to each type of environmental data. If the increase of environmental parameters leads to the occurrence of mountain disasters, such as the continuous increase in rainfall increasing the probability of disasters, then the increase is an adverse trend. Conversely, if the decrease of environmental parameters leads to the occurrence of mountain disasters, such as the continuous decrease in temperature increasing soil freezing and cracking, then the decrease is an adverse trend. Therefore, the adverse trends correspond to different types of environmental parameters. To adapt to various environmental data scenarios, unfavorable trends are uniformly described. For example, in the case of mountain disasters, a continuous increase in rainfall will saturate the soil moisture content, increasing the probability of landslides and debris flows. In this case, the increase in rainfall is an unfavorable trend. In cold regions, a continuous drop in temperature may cause soil freezing and cracking, which in turn may lead to geological disasters such as ground subsidence. In this case, the drop in temperature is also an unfavorable trend. Through in-depth analysis of the geological impact of various types of environmental data, unfavorable trends in environmental data can be accurately identified.

[0026] The current protection phase is divided according to the adverse impact ratio. The proportion of time excluding the adverse impact ratio is marked as the normal impact ratio. For example, in a one-month protection phase, if the period when the environmental data at a certain location shows an adverse trend is 10 days, then the adverse impact ratio is 10 / 30≈0.33, and the normal impact ratio is 1-0.33=0.67. These two ratios are like a "balance" to measure the risk of geological disasters. By observing their changes, we can intuitively understand the stability of the geological environment in the current protection phase. Obtain the frequency of peak changes and increases in the adverse impact compared to the corresponding adverse trend in environmental data within the same time period; If the weighting of the adverse impact ratio and the normal impact ratio increases, and the frequency of peak changes in the adverse trend of environmental data within the corresponding period exceeds the set threshold for the frequency of changes, then the corresponding points in the current protection phase will be marked as potential hazards. If the weighting ratio of the adverse impact ratio to the normal impact ratio does not show an increasing trend, or if the frequency of peak change in the adverse trend of environmental data within the corresponding period of the adverse impact ratio does not exceed the set threshold for the frequency of change, then the corresponding points in the current protection phase will be marked as non-hazard points. It should be explained that the environmental data corresponding to different mountain locations in the protection area are inconsistent. If the environmental data of adjacent areas do not have a large span difference, the environmental data analysis results of any area shall prevail. In addition, during the process of marking hidden danger points, as the environmental data changes and the progress of the protection stage increases, the hidden danger points and the corresponding non-hidden danger points will change alternately, and the latest point type will be continuously sent to the administrator's communication terminal. Taking rainfall as an example, in geological disaster monitoring in a mountainous area, if the threshold is set to once every 3 hours, when the frequency of the peak rainfall in the area reaches or exceeds once every 3 hours within the corresponding period of the adverse impact ratio, it indicates that the rainfall changes are abnormally drastic, the stability of the geological environment is seriously threatened, and the risk of geological disasters in the area has increased significantly. At this time, combined with the changing trend of the weight ratio of the adverse impact ratio and the normal impact ratio, if the weight ratio also shows an increasing trend, then the corresponding division point in the area is very likely to be marked as a potential hazard point. The setting of this threshold can help us to capture abnormal changes in environmental data in a timely manner, identify potential geological disaster hazards in advance, and provide an important basis for subsequent prevention and control measures.

[0027] The prediction path determination process in S12 is as follows: Geological parameters of both hazardous and non-hazardous points are monitored, including parameters such as surface displacement, deep displacement, and crack opening degree. Determine the unfavorable trend stage of environmental parameters corresponding to the hazard points, obtain the fluctuation range of geological parameters within the corresponding stage, and at the same time, based on the current protection stage, obtain the fluctuation range of geological parameters of non-hazard points within the non-unfavorable trend stage, and mark them as the current disturbed fluctuation data and the current undisturbed fluctuation data, respectively. Based on the historical protection stages, the range of geological parameter fluctuations for the points in the unfavorable trend stage and the range of geological parameter fluctuations for the points in the corresponding non-unfavorable trend stage are obtained. Based on the historical protection results, the disaster occurrence results for the corresponding stage are obtained. If a disaster occurs, it is marked as the unfavorable trend disaster range and the non-unfavorable trend disaster range, respectively. If no disaster occurs, it is marked as the unfavorable trend safe range and the non-unfavorable trend safe range, respectively. Based on data comparison, if the current disturbance fluctuation data is within the unfavorable trend disaster range, the current potential hazard point will be marked as a predicted disaster point; if the current disturbance fluctuation data is within the unfavorable trend safe range, the current potential hazard point will be marked as a low-risk disaster point; if the current non-disturbing fluctuation data is within the non-unfavorable trend disaster range, the current non-potential hazard point will be marked as a predicted extension point; if the current non-disturbing fluctuation data is within the non-unfavorable trend safe range, the current non-potential hazard point will be marked as a monitoring-normal point. Based on the connection of predicted disaster points, a predicted disaster path is constructed. Then, based on the connection between the predicted disaster extension points and the predicted disaster path, a predicted extension path is constructed. At the same time, adjacent monitoring points that are not different from the predicted disaster path and the predicted extension path are marked. Points that are in the path or adjacent to the path need to be marked. Targeted prediction and protection are carried out according to different point types.

[0028] The path trigger detection process in S2 is as follows: Trigger monitoring is performed on predicted disaster paths and predicted extension paths. The growth rate of the floating span of geological data corresponding to the predicted disaster points in the predicted disaster path is collected, and the time when the floating span of geological data increases is collected simultaneously. If the growth rate of the floating span exceeds the set growth rate threshold, or the number of times the floating span of geological data increases exceeds the set number of times, the path is inferred to be triggered, and the corresponding predicted disaster path is intercepted. The road segment that triggers the disaster is marked as a disaster trajectory. Based on the geographical location of the predicted disaster path, the high-altitude road segments that generate disaster trajectories are marked as road segments to be generated. Regarding the threshold setting, a specific scenario could be setting the threshold for the rate of increase in surface displacement to 5 millimeters per hour. When the rate of increase in surface displacement at a predicted disaster location is detected to reach 8 millimeters per hour, or when the geological data fluctuation span is detected to increase multiple times within a short period of time, exceeding the set number of times (e.g., more than 3 times per hour), the system will determine that a path has been triggered. Once a path is triggered, the system will quickly capture the corresponding predicted disaster path and mark the section of the path that triggered the disaster as a disaster trajectory. This disaster trajectory acts like a "roadmap" for the disaster, clearly indicating the possible direction of its development. It should be explained that the set number of time intervals is also an important parameter in path trigger detection. It refers to the limit of the number of times when the fluctuation span of geological data increases during the monitoring process. Taking the landslide disaster monitoring mentioned above as an example, the set number of time intervals is 5 times per hour. If, within a certain hour, the geological data (such as surface displacement, crack opening and closing degree, etc.) at the predicted disaster point is found to have increased in fluctuation span 5 times or more, even if the growth rate of each time does not exceed the threshold of the geological data fluctuation span growth rate, the system will infer that the path has been triggered. This is because frequent increases in geological data indicate that the state of the geological body is extremely unstable and may trigger geological disasters at any time. By monitoring the set number of time intervals, signs of geological disasters can be captured from another perspective, further improving the accuracy and reliability of path trigger detection. Simultaneously, the geological parameter fluctuation process of adjacent points corresponding to the predicted extension path and the predicted disaster path is acquired. If the interval between the floating parameters of the predicted extension path and the floating parameters of the predicted disaster path continues to shorten, the corresponding predicted extension path is marked as a real-time extension path. Conversely, if the interval between the floating parameters of the predicted extension path and the floating parameters of the predicted disaster path does not shorten, the corresponding predicted extension path is marked as a path that has not yet been extended. Among them, the floating parameters represent parameters such as the floating speed and floating span of geological parameters. Any one of the parameters is used as a comparison standard. At the same time, points with no abnormalities are monitored in real time, and when the geological parameters are abnormal, the corresponding points are merged into the disaster trajectory. Otherwise, monitoring continues.

[0029] The prevention and control deployment process in S31 is as follows: The generated disaster trajectory and real-time extension path are determined. The generated disaster trajectory and real-time extension path are compared with the predicted disaster path and predicted extension path, respectively. If the number of overlapping points continues to increase, or the number of points in the predicted path that do not generate disasters continues to decrease, then while carrying out real-time disaster protection, protection deployment is carried out based on the trajectory of the predicted path to improve the targeting of disaster protection deployment. It should be explained that the predicted path is a general term for the predicted disaster path and the predicted extension path. If the number of overlapping points does not continue to rise, and the number of points in the predicted path that do not generate disasters does not continue to decrease, then disaster blocking deployment will be carried out. This will protect the real-time disaster trajectory while preventing the disaster trajectory from moving to the predicted path, thereby reducing the unnecessary disaster impact caused by the chain reaction of points.

[0030] The process for evaluating the prevention and control efficiency in S32 is as follows: After the current protection deployment, obtain the rate of increase of the number of disaster-related points corresponding to the disaster trajectory. At the same time, after the current protection deployment, obtain the rate of increase of the number of disaster-related points in the road segment to be generated. The sum of the increase rates is obtained by superimposing the rates and marked as the prevention and control speed feature information. The constant value of the number of disaster-free points in the predicted path after the current protection deployment is obtained, along with the remaining number of points in the predicted path. The point number ratio is then calculated based on this ratio. If the speed characteristic information of prevention and control exceeds the set speed threshold, or the number of points does not exceed the set number ratio threshold, it is inferred that the efficiency of prevention and control deployment cannot adapt to the current disaster. In combination with the real-time disaster trajectory, redeployment is carried out, and the facility specifications are changed with reference to the current deployment. When guiding the trajectory, parameters such as the area of ​​the pre-set area are added. If the speed characteristic information of prevention and control does not exceed the set speed threshold, and the number of points exceeds the set number ratio threshold, it is inferred that the efficiency of prevention and control deployment is adapted to the current disaster, and disaster protection is carried out according to the current prevention and control deployment. It should be explained that setting a speed threshold is a key indicator in the assessment of prevention and control efficiency, used to measure the boundary of prevention and control speed characteristics. For example, in the prevention and control of debris flow disasters in a certain area, the speed threshold is set to 8 points per hour. If the actual calculated prevention and control speed characteristics exceed 8 points per hour, it indicates that under the current prevention and control deployment, the disaster is spreading too fast, and the current prevention and control measures have failed to effectively curb the development of the disaster, requiring readjustment and optimization of the prevention and control deployment. The setting of this threshold can intuitively reflect the control effect of the current prevention and control measures on the disaster, providing a clear basis for adjusting the prevention and control strategy. Setting a threshold for the number ratio is also an important reference in assessing the effectiveness of disaster prevention and control, used to measure the limits of the number ratio of locations. For example, in the prevention and control of geological disasters in a mountainous area, a threshold of 0.6 is set. If the actual calculated number ratio of locations does not exceed 0.6, it means that the proportion of unaffected locations on the predicted path is low, the potential disaster risk is high, and the current prevention and control deployment has not sufficiently reduced the disaster risk. It is necessary to re-examine and adjust the prevention and control strategy. Conversely, if the number ratio of locations exceeds 0.6, it indicates that the current prevention and control deployment has achieved certain results in reducing disaster risk, and disaster protection can continue according to the current prevention and control deployment. Setting this threshold can help us accurately assess the control capability of the prevention and control deployment on the potential disaster risk on the predicted path, adjust the prevention and control strategy in a timely manner, and ensure the effectiveness of the prevention and control work.

[0031] Please see Figure 2 As shown, the present invention also proposes an intelligent decision-making system for geological disaster prevention and early warning, including an intelligent decision-making platform, wherein the intelligent decision-making platform is communicatively connected to a hidden danger point analysis unit, a prediction path determination unit, a path trigger detection unit, a prevention and control deployment unit, and an efficiency evaluation unit; The hazard point analysis unit divides the protection area into points and conducts geological monitoring based on the points. By monitoring, it infers the fluctuations in environmental data of the points in the protection area to identify hazard points. The prediction path determination unit determines the same type of risk parameters based on real-time risk parameters and the fluctuation of corresponding impact data under the current environment, and determines the disaster path of the protection area based on the corresponding hidden danger points. The path trigger detection unit performs path trigger detection based on real-time risk parameter monitoring and geological parameter monitoring of the area where the potential hazard point is located, thereby making disaster predictions and making targeted deployments based on the prediction results; The prevention and control deployment unit compares the predicted disaster path with the actual disaster trajectory to determine the real-time disaster route and make targeted deployments. The efficiency assessment unit evaluates the effectiveness of prevention and control measures based on the deployment.

[0032] A computer storage medium storing a computer program, which, when executed by a processor, implements the above-described intelligent decision-making method for geological disaster prevention and early warning. Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to the computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0033] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A smart decision-making method for geological disaster prevention and early warning, characterized in that, The specific steps are as follows: Step S1: Monitoring and analysis of the distribution of protected areas; S11: Hazard point analysis, dividing the protection area into points, and conducting geological monitoring based on the points. By monitoring, the fluctuation of environmental data at the points in the protection area is inferred to identify hazard points. S12: Predicted path determination: Based on real-time risk parameters and the fluctuation of corresponding impact data under the current environment, determine the risk parameters of the same type, and determine the disaster path of the protected area in combination with the corresponding hidden danger points; Step S2: Path trigger detection; Based on the monitoring of real-time risk parameters and geological parameters of the area where the potential hazard is located, path trigger detection is carried out to predict disasters, and targeted deployments are made based on the prediction results. Step S3: Assessment of prevention and control efficiency; S31: Prevention and control deployment: Based on the comparison between the predicted disaster path and the actual disaster trajectory, determine the real-time disaster route and carry out targeted deployment; S32: Conduct an assessment of the effectiveness of prevention and control measures based on the deployment of prevention and control measures.

2. The intelligent decision-making method for geological disaster prevention and early warning according to claim 1, characterized in that, The process of analyzing potential hazards in S11 is as follows: The protected area is divided into points based on the coverage of the equipped sensors, and the boundaries of the points are connected. Real-time environmental data is monitored at the points, where real-time environmental data is represented by rainfall and wind speed. The monitoring period is determined, and historical protection stages are extracted based on the duration of the monitoring period to obtain the historical protection stages. The time periods in the current protection stage where the environmental data of the points continuously shows an adverse trend are obtained, and the duration percentage is collected based on the progress time of the current protection stage and marked as the adverse impact ratio. The current protection stage is divided according to the adverse impact ratio, that is, the percentage of time other than the adverse impact ratio is marked as the normal impact ratio. The frequency of peak value changes in the adverse trend of the environmental data within the corresponding time period of the adverse impact ratio is obtained.

3. The intelligent decision-making method for geological disaster prevention and early warning according to claim 2, characterized in that, If the weighting of the adverse impact ratio and the normal impact ratio increases, and the frequency of peak changes in the adverse trend of environmental data within the corresponding period exceeds the set threshold for the frequency of changes, then the corresponding points in the current protection phase will be marked as potential hazards. If the weighting of the adverse impact ratio and the normal impact ratio does not increase, or if the frequency of peak changes in the adverse trend of environmental data within the corresponding period of the adverse impact ratio does not exceed the set threshold for the frequency of changes, then the corresponding points in the current protection phase will be marked as non-hazard points.

4. The intelligent decision-making method for geological disaster prevention and early warning according to claim 1, characterized in that, The prediction path determination process in S12 is as follows: Geological parameters of both hazardous and non-hazardous points are monitored, with geological parameters represented as surface displacement, deep displacement, and crack opening / closing degree. The unfavorable trend stage of environmental parameters corresponding to the hazardous point is determined, and the fluctuation range of geological parameters within the corresponding stage is obtained. At the same time, based on the current protection stage, the fluctuation range of geological parameters of non-hazardous points within the non-unfavorable trend stage is obtained, and these are respectively marked as the current disturbed fluctuation data and the current undisturbed fluctuation data. Based on the historical protection stages, the range of geological parameter fluctuations for the points within the unfavorable trend stage and the range of geological parameter fluctuations for the points within the corresponding non-unfavorable trend stage are obtained. The disaster occurrence results for the corresponding stage are obtained based on the historical protection results. If a disaster occurs, it is marked as the unfavorable trend disaster range and the non-unfavorable trend disaster range, respectively. If no disaster occurs, they are marked as the safe range of adverse trends and the safe range of non-adverse trends, respectively.

5. The intelligent decision-making method for geological disaster prevention and early warning according to claim 4, characterized in that, Based on data comparison, if the current disturbance fluctuation data is within the unfavorable trend disaster range, then the current potential hazard location will be marked as a predicted disaster location; if the current disturbance fluctuation data is within the unfavorable trend safe range, then the current potential hazard location will be marked as a low-risk disaster location. If the current undisturbed floating data is within the non-adverse trend disaster range, then mark the current non-hazard point as the predicted extension point; If the current undisturbed floating data is within the safe range of a non-adverse trend, then mark the current non-hazardous point as a monitoring point with no abnormalities. A predicted disaster path is constructed by connecting the predicted disaster points, and a predicted extension path is constructed by connecting the predicted extension points with the predicted disaster path. At the same time, adjacent monitoring points that are not different from the predicted disaster path and the predicted extension path are marked. Points that are in the path or adjacent to the path need to be marked.

6. The intelligent decision-making method for geological disaster prevention and early warning according to claim 1, characterized in that, The path trigger detection process in S2 is as follows: Trigger monitoring is performed on predicted disaster paths and predicted extension paths. The growth rate of the floating span of geological data corresponding to the predicted disaster points in the predicted disaster path is collected, and the time when the floating span of geological data increases is collected simultaneously. If the growth rate of the floating span exceeds a set growth rate threshold, or if the number of times the floating span of geological data increases exceeds a set number of times, the path is inferred to be triggered, and the corresponding predicted disaster path is intercepted. The road segment that triggers the disaster is marked as a disaster trajectory. Based on the geographical location of the predicted disaster path, the high-altitude road segments that generate disaster trajectories are marked as road segments to be triggered. Simultaneously, the geological parameter fluctuation process of adjacent points corresponding to the predicted extension path and the predicted disaster path is acquired. If the interval between the floating parameters of the predicted extension path and the floating parameters of the predicted disaster path continuously shortens, the corresponding predicted extension path is marked as a real-time extension path; otherwise, if the interval between the floating parameters of the predicted extension path and the floating parameters of the predicted disaster path does not shorten, the corresponding predicted extension path is marked as a path that has not yet been extended. Here, the floating parameter represents the floating speed or floating span of the geological parameter. At the same time, points with no abnormalities are monitored in real time, and when the geological parameters are abnormal, the corresponding points are merged into the disaster trajectory; otherwise, monitoring continues.

7. The intelligent decision-making method for geological disaster prevention and early warning according to claim 1, characterized in that, The prevention and control deployment process in S31 is as follows: The generated disaster trajectory and real-time extension path are determined. The generated disaster trajectory and real-time extension path are compared with the predicted disaster path and predicted extension path, respectively. If the number of overlapping points continues to increase, or the number of points in the predicted path that do not generate disasters continues to decrease, then protection deployment is carried out based on the trajectory of the predicted path while implementing real-time disaster protection. The predicted path is a general term for the predicted disaster path and the predicted extension path. If the number of overlapping points does not continue to rise, and the number of points in the predicted path that do not generate disasters does not continue to decrease, then disaster blocking deployment will be carried out to protect the real-time disaster trajectory while preventing the disaster trajectory from moving into the predicted path.

8. The intelligent decision-making method for geological disaster prevention and early warning according to claim 7, characterized in that, The process for evaluating the effectiveness of prevention and control measures in S32 is as follows: The system obtains the rate of increase in the number of disaster-related points corresponding to the disaster trajectory after the current protection deployment. Simultaneously, after the current protection deployment, it obtains the rate of increase in the number of disaster-related points in the road segment to be affected. The sum of the increase rates is obtained by superimposing the rates and marked as the prevention and control rate feature information. The constant value of the number of disaster-free points in the predicted path after the current protection deployment is obtained, along with the remaining number of points in the predicted path. The point number ratio is then calculated based on this ratio. If the speed characteristic information of prevention and control exceeds the set speed threshold, or the number of points does not exceed the set number ratio threshold, it is inferred that the efficiency of prevention and control deployment cannot adapt to the current disaster, and redeployment is carried out in combination with the disaster trajectory generated in real time; if the speed characteristic information of prevention and control does not exceed the set speed threshold, and the number of points exceeds the set number ratio threshold, it is inferred that the efficiency of prevention and control deployment adapts to the current disaster, and disaster protection is carried out according to the current prevention and control deployment.

9. A geological disaster prevention and early warning intelligent decision-making system, characterized in that, It is applied to the intelligent decision-making method for geological disaster prevention and early warning as described in any one of claims 1-8.

10. A computer storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements a smart decision-making method for geological disaster prevention and early warning as described in any one of claims 1-8.

Images