Landslide lake burst risk assessment method and system

Abstract

The present invention is applicable to the field of risk assessment and provides a method and system for assessing the risk of a landslide-dammed lake burst. The system includes: a data retention module, a risk judgment module, a multi-channel data acquisition module, and a warning dissemination module. This solution not only enhances the monitoring system's reliance on and processing capabilities of traditional data, but more importantly, when conventional monitoring is limited, it can rely on more informal data, such as social media intelligence, to obtain necessary information. In addition, the solution can amplify tiny signals through discerning data processing methods, helping decision makers make detailed judgments, ensuring that disaster response strategies are as detailed and accurate as possible, and effectively improving the timeliness and appropriateness of disaster management and emergency response.

Description

Technical Field

[0001] The present invention belongs to the field of risk assessment, and in particular relates to a method and system for assessing the risk of a dammed lake burst. Background Art

[0002] Barrier lake outburst risk assessment is the process of predicting and quantifying the potential impact of the failure of natural dams (i.e., barrier lakes) formed in rivers due to landslides, debris flows, earthquakes, or other geological events. This multidisciplinary process involves geology, hydrology, hydraulics, engineering, and environmental science, aiming to reduce the threat posed by potential disasters to human life and property.

[0003] The risk assessment process for barrier lake outbursts relies on cross-disciplinary collaboration, continuously developing advanced technologies and innovative methods to enhance the responsiveness of assessment and early warning systems. These approaches identify and mitigate the serious threats posed by barrier lake outbursts, providing a solid foundation for protecting people's lives and property.

[0004] Disaster monitoring relies on data sources such as sensor networks and satellite imagery. Data such as lake level and flow velocity provided by digital flow mapping or field measurements become a barrier when communications are disrupted. This limits real-time monitoring and understanding of the dynamic changes in the barrier lake. In the event of an incident, timely information exchange is crucial for disaster assessment and response. However, when infrastructure is damaged, traditional communication methods or data transmission mechanisms are unable to convey crucial information to decision-makers, including the scale of the disaster, the safety status of the affected area, and the deployment of rescue forces. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for assessing the risk of a barrier lake burst, aiming to solve the technical problems existing in the prior art identified in the background technology.

[0006] The present invention is achieved by providing a method for assessing the risk of a barrier lake burst, the method comprising:

[0007] Monitor various data of the barrier lake in real time and establish a data repository to store the monitored data;

[0008] Establish a risk analysis model and combine the real-time data of various barrier lakes to determine whether the current barrier lake has the risk of bursting;

[0009] When a collapse risk is identified, information about the area where a collapse may occur or has already occurred is obtained, and real-time disaster information about the area is obtained. If real-time disaster information cannot be obtained, all social media information about the current area is collected and features are extracted from the social media information based on the disaster situation. This information is then used to obtain the current disaster situation in the area and, combined with available real-time data, a level assessment of the current disaster risk is performed.

[0010] Based on the assessed level of disaster risk, warning notices are prepared and sent to affected areas.

[0011] As a further solution of the present invention, the real-time monitoring of various data of the barrier lake and the establishment of a data repository to store the monitored data in the data repository specifically include:

[0012] Build a data transmission channel, and obtain various data of real-time monitoring of the barrier lake through sensors through the data transmission channel, and pre-process all the collected data;

[0013] A data repository is established to store the preprocessed data in the data repository, and a time tag of when the data was collected is added to the data during storage.

[0014] As a further solution of the present invention, the risk analysis model is established, and combined with the real-time data of various barrier lakes obtained, to determine whether the current barrier lake has a risk of bursting, specifically including:

[0015] Set indicators related to the outburst of barrier lakes and use these indicators as input to establish a risk analysis model;

[0016] Extract data with the same time tag and matching relevant indicators from the data repository, substitute it into the risk analysis model, and calculate the risk level of the current time tag;

[0017] Set a burst risk threshold and compare the risk level with the burst risk threshold.

[0018] As a further solution of the present invention, the feature extraction of social media information based on the disaster situation is performed to obtain the current disaster situation information in the area, and the current disaster risk level is assessed in combination with the available real-time data, specifically including:

[0019] When the risk level exceeds the collapse risk threshold, the area where collapse may occur or has occurred is determined, and all data of the area and the smoothness of data transmission in the area are extracted from the data repository;

[0020] When the transmission smoothness of the area is low, so that the data in the area cannot be transmitted to the data storage, all social platform information in the area is intercepted, including text, pictures and videos;

[0021] Taking disaster-related content as the main feature, we extract disaster features from all intercepted social platform information, including collecting geographic location and time information through text mining and natural language processing; and obtaining disaster information through image recognition;

[0022] Based on the acquired disaster characteristics and the latest data extracted from the area, determine the level of collapse that the current area may face or is facing.

[0023] As a further solution of the present invention, the method of formulating a warning notice based on the disaster risk assessment level and sending the warning notice to the affected area specifically includes:

[0024] Develop corresponding warning information and emergency plans for each level of failure;

[0025] Obtain the final collapse level and disseminate the corresponding warning information and emergency plan for the collapse level.

[0026] Another object of the present invention is to provide a barrier lake burst risk assessment system, the system comprising:

[0027] The data retention module is used to monitor various data of the barrier lake in real time and establish a data repository to store the monitored data in the data repository;

[0028] The risk assessment module is used to establish a risk analysis model and, based on the acquired real-time data of various barrier lakes, determine whether the current barrier lake has a risk of collapse.

[0029] A multi-channel data collection module is used to obtain information about areas where a collapse may occur or has already occurred, and to obtain real-time disaster information about the area when a collapse risk is identified. If real-time disaster information cannot be obtained, the module collects all social media information about the current area and extracts features from the social media information based on the disaster situation. This module then obtains the current disaster information about the area and, combined with available real-time data, assesses the current disaster risk level.

[0030] The warning dissemination module is used to formulate warning notices based on the assessment level of disaster risk and send warning notices to the affected areas.

[0031] As a further solution of the present invention, the data retention module includes:

[0032] An information collection unit is used to establish a data transmission channel, and obtain various data of the barrier lake monitored in real time by sensors through the data transmission channel, and pre-process all the collected data;

[0033] The data storage unit is used to set up a data storage library, store the pre-processed data in the data storage library, and add a time tag when the data is collected to the data during data storage.

[0034] As a further solution of the present invention, the risk judgment module includes:

[0035] The model building unit is used to set indicators related to the outburst of the barrier lake and establish a risk analysis model using the relevant indicators as input sources;

[0036] The level determination unit is used to extract data with the same time tag and matching relevant indicators from the data repository, and substitute it into the risk analysis model to calculate the risk level of the current time tag;

[0037] The risk comparison unit is used to set a burst risk threshold and compare the risk level with the burst risk threshold.

[0038] As a further solution of the present invention, the multi-channel data acquisition module includes:

[0039] The signal smoothness determination unit is used to determine the area where a collapse may occur or has occurred when the risk level exceeds the collapse risk threshold, and extract all the data of the area and the smoothness of the data transmission in the area from the data storage;

[0040] The multi-channel collection unit is used to intercept all social platform information in the area, including text, pictures and videos, when the transmission fluency of the area is low and the data in the area cannot be transmitted to the data storage;

[0041] A multi-channel information recognition unit is used to extract disaster characteristics from all intercepted social platform information, using disaster-related content as the main feature. This includes collecting geographic location and time information through text mining and natural language processing; and obtaining disaster information through image recognition.

[0042] The collapse risk assessment unit is used to determine the collapse level that the current area may face or is facing based on the acquired disaster characteristics and the latest data extracted from the area.

[0043] As a further solution of the present invention, the warning dissemination module includes:

[0044] The scenario planning unit is used to develop corresponding warning information and emergency plans for each failure level;

[0045] The information dissemination unit is used to obtain the final collapse level and disseminate the corresponding warning information and emergency plan for the collapse level.

[0046] The beneficial effects of the present invention are:

[0047] This solution not only enhances the monitoring system's reliance on and processing capabilities for traditional data, but more importantly, it can rely on less formal data, such as social media intelligence, to obtain necessary information when conventional monitoring is limited. Furthermore, through discerning data processing, this solution can amplify subtle signals, helping decision-makers make detailed judgments and ensuring that disaster response strategies are as detailed and precise as possible, effectively improving the timeliness and appropriateness of disaster management and emergency response. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A flow chart of a method for assessing the risk of a barrier lake burst provided by an embodiment of the present invention;

[0049] Figure 2 A flowchart of an embodiment of the present invention for real-time monitoring of various data of a landslide lake, establishing a data repository, and storing the monitored data in the data repository;

[0050] Figure 3 A flow chart for establishing a risk analysis model provided by an embodiment of the present invention, combining various acquired real-time data on the barrier lake, and determining whether the current barrier lake has a risk of breaching;

[0051] Figure 4 A flowchart for evaluating the current disaster risk level provided by an embodiment of the present invention;

[0052] Figure 5 A flowchart of an embodiment of the present invention for formulating a warning notice based on a disaster risk assessment level and sending the warning notice to the affected area;

[0053] Figure 6 A structural block diagram of a barrier lake burst risk assessment system provided by an embodiment of the present invention;

[0054] Figure 7 A structural block diagram of a data retention module provided in an embodiment of the present invention;

[0055] Figure 8 A structural block diagram of a risk assessment module provided by an embodiment of the present invention;

[0056] Figure 9 A structural block diagram of a multi-channel data acquisition module provided by an embodiment of the present invention;

[0057] Figure 10 This is a structural block diagram of the warning dissemination module provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0059] It is understood that the terms "first," "second," etc., used herein may be used to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script without departing from the scope of this application.

[0060] Figure 1 A flow chart of a method for assessing the risk of a barrier lake burst provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, a method for assessing the risk of a barrier lake outburst is provided, the method comprising:

[0061] S100, real-time monitoring of various data of the barrier lake, and establishing a data repository to store the monitored data in the data repository;

[0062] This step will build an automated monitoring network specifically for the barrier lake. This network will consist of various sensors that regularly collect data on key parameters such as water level, flow rate, and osmotic pressure. This data will be transmitted in real time via a series of predefined data transmission channels.

[0063] The data is then screened and preprocessed for the first time, aiming to smooth the data, reduce noise interference, and provide signal integration and recognition enhancement operations. Ensuring the reliability of information transmitted in a timely manner is the cornerstone of decision-making in subsequent steps. After the data is submitted to the core processing unit, it is stored and indexed in a carefully designed data repository. In addition to being assigned an accurate time label to indicate the specific time sequence, each data point is also used to depict the continuous scenario of changes in the time dimension, so that the decision support system can understand the time correlation. The database system itself must support fast reading and writing, as well as disaster recovery and online migration capabilities to further ensure the long-term security, stability and accessibility of the data.

[0064] S200, establishing a risk analysis model, combining the acquired real-time data of various barrier lakes, and determining whether the barrier lake currently has a risk of bursting;

[0065] This step defines a series of indicators closely related to the risk of a landslide lake breach, such as water level, volumetric flow rate, crack size, and soil moisture. These indicators were selected not only based on historical case studies and theoretical research but also considered state-of-the-art geological data analysis to ensure they comprehensively and accurately represent the current state of the landslide lake. Leveraging artificial intelligence, machine learning, and multidimensional statistical models, the risk analysis model is built on robust algorithms that can extract valuable risk indicators from complex and multivariate data.

[0066] From a pre-defined data repository, we precisely locate records that are time-synchronized with the required risk indicators. These data streams are then processed and analyzed. The matching data is then fed into the model to comprehensively assess the risk level at that moment. Through an iterative learning process, the model is continuously optimized to improve predictive accuracy.

[0067] Finally, by setting multiple risk thresholds in detail, regional risks can be subdivided into multiple levels, such as normal, caution, warning, and emergency. When the risk level predicted by the model exceeds a certain threshold, the early warning system will automatically activate, creating a favorable window for preparing for possible disasters.

[0068] S300: When a disaster risk is identified, information about the area where a disaster may occur or has already occurred is obtained, and disaster information about the area is obtained in real time. If real-time disaster information cannot be obtained, all social media information about the current area is collected and features are extracted from the social media information based on the disaster situation. This information is then used to obtain disaster information about the current area and, combined with available real-time data, a level assessment of the current disaster risk is performed.

[0069] When the calculated risk level exceeds the preset breach risk threshold, an emergency state is entered. The system quickly locates and identifies the area of ​​the barrier lake with potential breach. It also retrieves all relevant real-time data for the area, such as meteorological, hydrological, and geological information, and assesses the accessibility (unobstructedness) of this information. This assessment of unobstructedness is crucial because it determines whether accurate information can be successfully collected and disseminated.

[0070] To address data disruptions caused by communication barriers and other factors, this approach initiates an alternative approach by extensively collecting information from social media platforms in the region as a data source. This data source may include text, images, and videos uploaded by citizens. Social media becomes a key supplementary source of information, especially when formal monitoring methods are blocked.

[0071] Advanced text mining techniques and natural language processing algorithms are used to process textual information from social media, extracting appropriate time and location data. Image recognition technology is also used to analyze uploaded images and videos to obtain real-time, geographically relevant disaster data. This integrated approach to information retrieval and processing can significantly enhance our understanding of the true nature of the incident.

[0072] Finally, an activation function based on multiple weights and input data is used to assess and predict the risk of collapse, ensuring that the disaster response strategy is as detailed and accurate as possible, effectively improving the timeliness and appropriateness of disaster management and emergency response.

[0073] S400: Based on the disaster risk assessment level, a warning notice is formulated and sent to the affected area.

[0074] Figure 2 The flow chart of the embodiment of the present invention for real-time monitoring of various data of the barrier lake, establishing a data repository, and storing the monitored data in the data repository is as follows: Figure 2 As shown, the real-time monitoring of various data of the barrier lake and the establishment of a data repository to store the monitored data in the data repository specifically include:

[0075] S110, establishing a data transmission channel, obtaining various data of the barrier lake monitored in real time by sensors through the data transmission channel, and preprocessing all the collected data;

[0076] S120, establishing a data repository, storing the pre-processed data in the data repository, and adding a time tag of when the data was collected to the data during storage;

[0077] In the step of preprocessing all collected data, the corresponding process has the following relationship:

[0078] ;

[0079] in, Indicates time After preprocessing, Indicates sensor time The original data, Indicates sensor In time The mean of the collected data on Indicates sensor The standard deviation of the collected data, Indicates the total number of sensors, Represents a constant that prevents the denominator from wrapping around to zero.

[0080] Specifically, by combining the cosine function and high-order exponential function, the nonlinear changes and outliers in the data can be better captured; by using a complex combination of sine function and power, the impact of noise on data processing is reduced to ensure the smoothness and stability of the data.

[0081] Figure 3 The flow chart of establishing a risk analysis model provided by the embodiment of the present invention and combining the obtained real-time data of various barrier lakes to determine whether the current barrier lake has a risk of bursting is as follows: Figure 3 As shown, the risk analysis model is established, and combined with the real-time data of various barrier lakes obtained, it is determined whether the current barrier lake has a risk of bursting, specifically including:

[0082] S210, set indicators related to the outburst of the barrier lake and establish a risk analysis model using the relevant indicators as input sources;

[0083] S220, extracting data with the same time tag and matching the relevant indicators from the data repository, and substituting the data into the risk analysis model to calculate the risk level of the current time tag;

[0084] S230, setting a collapse risk threshold, and comparing the risk level with the collapse risk threshold;

[0085] In the step of extracting data with the same time tag and matching relevant indicators from the data repository and substituting it into the risk analysis model to calculate the risk level of the current time tag, the risk level is further judged by calculating and obtaining a comprehensive risk score. The specific steps for calculating and obtaining the comprehensive risk score are as follows:

[0086] The standardized risk factor is calculated using the maximum and minimum values ​​of the indicator. The corresponding relationship is:

[0087] ;

[0088] in, represents the standardized risk factor, Indicator In time The measured value on Indicator The minimum value of Indicator The maximum value of

[0089] The standardized risk factor is nonlinearly scaled to obtain the nonlinearly scaled risk factor. The corresponding process relationship is:

[0090] ;

[0091] in, represents the exponent used to adjust the nonlinear effect, represents the risk factor after nonlinear scaling;

[0092] Based on the maximum and minimum values ​​of the indicator, the inverse tangent conversion operation is performed to obtain the factor after the inverse tangent conversion. The relationship between the corresponding process is:

[0093] ;

[0094] in, Indicates a constant used to prevent operation errors. Indicates the factor after arc tangent transformation;

[0095] Based on the risk factors after nonlinear scaling and the factors after arctangent transformation, the comprehensive risk score is obtained by weighted summation. The relationship between the corresponding process is:

[0096] ;

[0097] in, Indicates time The comprehensive risk score of Indicator The weight of Indicates the total number of indicators.

[0098] Specifically, the inverse tangent function and nonlinear scaling are introduced to handle extreme changes in data, making the risk score more sensitive to abnormal situations.

[0099] Figure 4 The flow chart for evaluating the current disaster risk level provided by the embodiment of the present invention is as follows: Figure 4 As shown, the feature extraction of social media information based on the disaster situation is performed to obtain the current disaster situation information of the area, and the current disaster risk level is assessed in combination with the available real-time data, specifically including:

[0100] S310, when the risk level exceeds the flood risk threshold, determining the area where flooding may occur or has occurred, and extracting all data of the area and the transmission smoothness of all data of the area from the data repository;

[0101] S320: When the transmission smoothness of the area is low, so that the data of the area cannot be transmitted to the data storage, all social platform information of the area is intercepted, including text, pictures and videos;

[0102] S330, using disaster-related content as the primary feature, extracts disaster features from all intercepted social platform information, including collecting geographic location and time information through text mining and natural language processing; and obtaining disaster information through image recognition;

[0103] S340: Based on the acquired disaster characteristics and the latest data extracted for the area, determine the level of collapse that the current area may face or is facing;

[0104] In the step of determining the level of collapse that the current area may face or is facing based on the acquired disaster characteristics and the latest data extracted for the area, the overall disaster severity score is obtained through information data from social platforms. The specific steps for obtaining the overall disaster severity score are as follows:

[0105] Extract and obtain text features and image features based on social platform information data;

[0106] The text features are used to calculate the scores related to the text features. The corresponding relationship is:

[0107] ;

[0108] in, represents the score related to text features, Indicates the The weight of the text features, represents the total frequency of all text features, Indicates time Previous The frequency of occurrence of a text feature, represents the total number of text features, represents the index used to adjust the influence of text features;

[0109] The image features are used to calculate the scores related to the image features. The corresponding relationship is:

[0110] ;

[0111] in, represents the score related to the image features, represents the total number of image features, represents the weight of the image feature, Indicates time The feature values ​​extracted from the image are Indicates time Previous The frequency of occurrence of image features, Represents the parameters used to adjust the impact of image features, represents a constant to prevent the denominator from returning to zero;

[0112] The scores related to text features and image features are added together to obtain the total disaster severity score. The corresponding relationship is:

[0113] ;

[0114] in, Indicates time The overall disaster severity score.

[0115] In the step of judging the level of collapse that the current region may face or is facing based on the acquired disaster characteristics and the latest data extracted for the region, the corresponding process has the following relationship:

[0116] ;

[0117] in, Indicates the level of collapse, represents a positive number used to stabilize calculations, Indicates time The smoothness of data transmission;

[0118] Specifically, the complex interactions between features can be captured through the sinusoidal function and nonlinear features. At the same time, by combining text and image features, the formula provides a multi-dimensional disaster information extraction method.

[0119] In the step of judging the level of collapse that the current region may face or is facing based on the acquired disaster characteristics and the latest data extracted for the region, the corresponding process has the following relationship:

[0120] ;

[0121] in, Indicates the level of collapse, represents a positive number used to stabilize calculations, Indicates time The smoothness of data transmission.

[0122] Specifically, by combining the comprehensive risk score and the total disaster severity score, a comprehensive assessment of the collapse level can be made; at the same time, by using the hyperbolic cosine function and the cubic root to capture the complex relationship between the scores, it can better reflect the actual situation.

[0123] Figure 5 The embodiment of the present invention provides a flowchart for formulating a warning notice based on the disaster risk assessment level and sending the warning notice to the affected area, such as Figure 5As shown, according to the assessment level of disaster risk, a warning notice is formulated and sent to the affected area, specifically including:

[0124] S410, develop corresponding warning information and emergency plans for each failure level;

[0125] S420, obtaining the final collapse level, and disseminating the corresponding warning information and emergency plan of the collapse level.

[0126] Figure 6 The structural block diagram of the barrier lake burst risk assessment system provided by the embodiment of the present invention is as follows: Figure 6 As shown, a barrier lake burst risk assessment system includes:

[0127] The data storage module 100 is used to monitor various data of the barrier lake in real time, establish a data repository, and store the monitored data in the data repository;

[0128] This module will build an automated monitoring network related to the landslide lake topic. It will be composed of various types of sensors that can regularly collect data on important parameters such as water level, flow, osmotic pressure, etc. This data will be transmitted in real time through a series of pre-defined data transmission channels.

[0129] The data is then screened and preprocessed for the first time, aiming to smooth the data, reduce noise interference, and provide signal integration and recognition enhancement operations. Ensuring the reliability of information transmitted in a timely manner is the cornerstone of decision-making in subsequent steps. After the data is submitted to the core processing unit, it is stored and indexed in a carefully designed data repository. In addition to being assigned an accurate time label to indicate the specific time sequence, each data point is also used to depict the continuous scenario of changes in the time dimension, so that the decision support system can understand the time correlation. The database system itself must support fast reading and writing, as well as disaster recovery and online migration capabilities to further ensure the long-term security, stability and accessibility of the data.

[0130] The risk judgment module 200 is used to establish a risk analysis model and determine whether the current barrier lake has a risk of collapse by combining the acquired real-time data of the barrier lake.

[0131] This module defines a series of indicators closely related to the risk of landslide lake failure, such as water level, volumetric flow rate, crack size, and soil moisture. These indicators were selected not only based on historical case studies and theoretical research, but also considered state-of-the-art geological data analysis to ensure that the selected indicators comprehensively and accurately represent the current state of the landslide lake. Leveraging artificial intelligence, machine learning, and multidimensional statistical models, the risk analysis model is built on a robust algorithm that can extract valuable risk indicators from complex and multivariate data.

[0132] From a pre-defined data repository, we precisely locate records that are time-synchronized with the required risk indicators. These data streams are then processed and analyzed. The matching data is then fed into the model to comprehensively assess the risk level at that moment. Through an iterative learning process, the model is continuously optimized to improve predictive accuracy.

[0133] Finally, by setting multiple risk thresholds in detail, regional risks can be subdivided into multiple levels, such as normal, caution, warning, and emergency. When the risk level predicted by the model exceeds a certain threshold, the early warning system will automatically activate, creating a favorable window for preparing for possible disasters.

[0134] The multi-channel data collection module 300 is used to obtain information about areas where a disaster may occur or has already occurred, and obtain real-time disaster information about the area when a disaster risk is identified. If real-time disaster information cannot be obtained, the module collects all social media information about the current area and extracts features from the social media information based on the disaster situation. This module then obtains current disaster information about the area and, combined with available real-time data, assesses the current disaster risk level.

[0135] If the module determines the risk level exceeds a preset breach risk threshold, it enters an emergency state. The system quickly locates and identifies the area of ​​the barrier lake at risk of breach. It also retrieves all relevant real-time data for the area, including meteorological, hydrological, and geological information, and assesses its accessibility. This assessment of accessibility is crucial because it determines whether accurate information can be successfully collected and disseminated.

[0136] When data transmission is interrupted due to communication barriers and other factors, the module will initiate a fallback plan by collecting information from social media platforms in the region as a data source. This information may include text, pictures, and videos uploaded by the public. Social media has become a key supplementary source of information, especially when formal monitoring methods are blocked.

[0137] Advanced text mining techniques and natural language processing algorithms are used to process textual information from social media, extracting appropriate time and location data. Image recognition technology is also used to analyze uploaded images and videos to obtain real-time, geographically relevant disaster data. This integrated approach to information retrieval and processing can significantly enhance our understanding of the true nature of the incident.

[0138] Finally, an activation function based on multiple weights and input data is used to assess and predict the risk of collapse, ensuring that the disaster response strategy is as detailed and accurate as possible, effectively improving the timeliness and appropriateness of disaster management and emergency response.

[0139] The warning dissemination module 400 is used to formulate warning notices according to the assessment level of disaster risk and send the warning notices to the affected areas.

[0140] Figure 7 The structural block diagram of the data retention module provided by the embodiment of the present invention is as follows: Figure 7 As shown, the data retention module includes:

[0141] The information collection unit 110 is used to establish a data transmission channel, and obtain various data of the barrier lake monitored in real time by sensors through the data transmission channel, and pre-process all the collected data;

[0142] The data storage unit 120 is used to establish a data storage library, store the pre-processed data in the data storage library, and add a time tag when the data is collected to the data during storage.

[0143] Figure 8 The structural block diagram of the risk judgment module provided by the embodiment of the present invention is as follows: Figure 8 As shown, the risk judgment module includes:

[0144] The model building unit 210 is used to set indicators related to the outburst of the barrier lake and establish a risk analysis model using the relevant indicators as input sources;

[0145] The level determination unit 220 is used to extract data with the same time tag and matching the relevant indicators from the data repository, and substitute it into the risk analysis model to calculate the risk level of the current time tag;

[0146] The risk comparison unit 230 is used to set a collapse risk threshold and compare the risk level with the collapse risk threshold.

[0147] Figure 9 The structural block diagram of the multi-channel data acquisition module provided by the embodiment of the present invention is as follows: Figure 9 As shown, the multi-channel data acquisition module includes:

[0148] The signal smoothness determination unit 310 is used to determine the area where a collapse may occur or has occurred when the risk level exceeds the collapse risk threshold, and extract all data of the area and the smoothness of the data transmission in the area from the data storage;

[0149] The multi-channel collection unit 320 is used to intercept all social platform information in the area, including text, pictures and videos, when the transmission smoothness of the area is low and the data in the area cannot be transmitted to the data storage;

[0150] The multi-channel information recognition unit 330 is used to extract disaster characteristics from all intercepted social platform information, using disaster-related content as the main feature. This includes collecting geographic location and time information through text mining and natural language processing; and obtaining disaster information through image recognition.

[0151] The collapse risk assessment unit 340 is used to determine the collapse level that the current area may face or is facing based on the acquired disaster characteristics and the latest data extracted for the area.

[0152] Figure 10 The structural block diagram of the warning dissemination module provided by the embodiment of the present invention is as follows: Figure 10 As shown, the warning dissemination module includes:

[0153] A program planning unit 410 is used to formulate matching warning information and emergency plans for each failure level;

[0154] The information dissemination unit 420 is used to obtain the final collapse level and disseminate warning information and emergency plans corresponding to the collapse level.

[0155] It should be understood that, although the various steps in the flow chart of each embodiment of the present invention are shown in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in order, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0156] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When executed, the program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0157] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0158] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0159] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for assessing the risk of a barrier lake burst, characterized in that: The method comprises the following steps: Monitor various data of the barrier lake in real time and establish a data repository to store the monitored data; Establish a risk analysis model and combine the real-time data of various barrier lakes to determine whether the current barrier lake has the risk of bursting; When a collapse risk is identified, information about the area where a collapse may occur or has already occurred is obtained, and real-time disaster information about the area is obtained. If real-time disaster information cannot be obtained, all social media information about the current area is collected and features are extracted from the social media information based on the disaster situation. This information is then used to obtain the current disaster situation in the area and, combined with available real-time data, a level assessment of the current disaster risk is performed. Prepare warning notices based on the assessed level of disaster risk and send them to affected areas; The real-time monitoring of various data of the barrier lake and the establishment of a data repository to store the monitored data in the data repository specifically include: Build a data transmission channel, and obtain various data of real-time monitoring of the barrier lake through sensors through the data transmission channel, and pre-process all the collected data; Establishing a data repository, storing the pre-processed data in the data repository, and adding a time tag when the data is collected to the data during storage; The risk analysis model is established to determine whether there is a risk of the current landslide lake bursting, in combination with the real-time data of the landslide lake obtained, including: Set indicators related to the outburst of barrier lakes and use these indicators as input to establish a risk analysis model; Extract data with the same time tag and matching relevant indicators from the data repository, substitute it into the risk analysis model, and calculate the risk level of the current time tag; Set a burst risk threshold and compare the risk level with the burst risk threshold; In the step of extracting data with the same time tag and matching relevant indicators from the data repository and substituting it into the risk analysis model to calculate the risk level of the current time tag, the risk level is further evaluated by calculating and obtaining a comprehensive risk score. The specific steps for calculating and obtaining the comprehensive risk score are as follows: The standardized risk factor is calculated using the maximum and minimum values ​​of the indicator. The corresponding relationship is: ； in, represents the standardized risk factor, Indicator In time The measured value on Indicator The minimum value of Indicator The maximum value of The standardized risk factor is nonlinearly scaled to obtain the nonlinearly scaled risk factor. The corresponding process relationship is: ； in, represents the exponent used to adjust the nonlinear effect, represents the risk factor after nonlinear scaling; Based on the maximum and minimum values ​​of the indicator, the inverse tangent conversion operation is performed to obtain the factor after the inverse tangent conversion. The relationship between the corresponding process is: ； in, Indicates a constant used to prevent operation errors. Indicates the factor after arc tangent transformation; Based on the risk factors after nonlinear scaling and the factors after arctangent transformation, the comprehensive risk score is obtained by weighted summation. The relationship between the corresponding process is: ； in, Indicates time The comprehensive risk score of Indicator The weight of Indicates the total number of indicators; The feature extraction of social media information based on the disaster situation is performed to obtain the current disaster situation information in the area, and the current disaster risk level is assessed in combination with the available real-time data. Specifically, the process includes the following sub-steps: When the risk level exceeds the collapse risk threshold, the area where collapse may occur or has occurred is determined, and all data of the area and the transmission smoothness of all data of the area are extracted from the data repository; When the transmission smoothness of the area is low, so that the data in the area cannot be transmitted to the data storage, all social platform information in the area is intercepted, including text, pictures and videos; Taking disaster-related content as the main feature, all intercepted social platform information is subjected to disaster feature extraction, including collecting geographic location and time information through text mining and natural language processing; and obtaining disaster information through image recognition; Based on the acquired disaster characteristics and the latest data extracted for the area, determine the level of collapse that the current area may face or is facing; In the step of determining the level of collapse that the current area may face or is facing based on the acquired disaster characteristics and the latest data extracted for the area, the overall disaster severity score is obtained through information data from social platforms. The specific steps for obtaining the overall disaster severity score are as follows: Extract and obtain text features and image features based on social platform information data; The text features are used to calculate the scores related to the text features. The corresponding relationship is: ； in, represents the score related to text features, Indicates the The weight of the text features, represents the total frequency of all text features, Indicates time Previous The frequency of occurrence of a text feature, represents the total number of text features, represents the index used to adjust the influence of text features; The image features are used to calculate the scores related to the image features. The corresponding relationship is: ； in, represents the score related to the image features, represents the total number of image features, represents the weight of the image feature, Indicates time The feature values ​​extracted from the image are Indicates time Previous The frequency of occurrence of image features, Represents the parameters used to adjust the impact of image features, represents a constant to prevent the denominator from returning to zero; The scores related to text features and image features are added together to obtain the total disaster severity score. The corresponding relationship is: ； in, Indicates time The overall disaster severity score; In the step of judging the level of collapse that the current region may face or is facing based on the acquired disaster characteristics and the latest data extracted for the region, the corresponding process has the following relationship: ； in, Indicates the level of collapse, represents a positive number used to stabilize calculations, Indicates time The smoothness of data transmission; In the step of preprocessing all collected data, the corresponding process has the following relationship: ； in, Indicates time After preprocessing, Indicates sensor In time The original data on Indicates sensor In time The mean of the collected data on Indicates sensor The standard deviation of the collected data, Indicates the total number of sensors, Represents a constant that prevents the denominator from wrapping around to zero.

2. The method for assessing the risk of a barrier lake burst according to claim 1, wherein: According to the disaster risk assessment level, a warning notice is formulated and sent to the affected areas, specifically including: Develop corresponding warning information and emergency plans for each level of failure; Obtain the final collapse level and disseminate the corresponding warning information and emergency plan for the collapse level.

3. A barrier lake burst risk assessment system, characterized in that: The method for assessing the risk of a barrier lake burst according to any one of claims 1 to 2 is applied, wherein the system comprises: The data retention module is used to monitor various data of the barrier lake in real time and establish a data repository to store the monitored data in the data repository; The risk assessment module is used to establish a risk analysis model and, based on the acquired real-time data of various barrier lakes, determine whether the current barrier lake has a risk of collapse. A multi-channel data collection module is used to obtain information about areas where a collapse may occur or has already occurred, and to obtain real-time disaster information about the area when a collapse risk is identified. If real-time disaster information cannot be obtained, the module collects all social media information about the current area and extracts features from the social media information based on the disaster situation. This module then obtains the current disaster information about the area and, combined with available real-time data, assesses the current disaster risk level. The warning dissemination module is used to formulate warning notices based on the assessment level of disaster risk and send warning notices to the affected areas.

4. The barrier lake burst risk assessment system according to claim 3, characterized in that: The data retention module includes: An information collection unit is used to establish a data transmission channel, and obtain various data of the barrier lake monitored in real time by sensors through the data transmission channel, and pre-process all the collected data; A data storage unit is used to set up a data storage library, store the pre-processed data in the data storage library, and add a time tag when the data is collected to the data during storage; The risk judgment module includes: The model building unit is used to set indicators related to the outburst of the barrier lake and establish a risk analysis model using the relevant indicators as input sources; The level determination unit is used to extract data with the same time tag and matching relevant indicators from the data repository, and substitute it into the risk analysis model to calculate the risk level of the current time tag; The risk comparison unit is used to set the collapse risk threshold and compare the risk level with the collapse risk threshold; The multi-channel data acquisition module includes: The signal smoothness determination unit is used to determine the area where a collapse may occur or has occurred when the risk level exceeds the collapse risk threshold, and extract all the data of the area and the smoothness of the data transmission in the area from the data storage; The multi-channel collection unit is used to intercept all social platform information in the area, including text, pictures and videos, when the transmission fluency of the area is low and the data in the area cannot be transmitted to the data storage; A multi-channel information recognition unit is used to extract disaster characteristics from all intercepted social platform information, using disaster-related content as the main feature. This includes collecting geographic location and time information through text mining and natural language processing; and obtaining disaster information through image recognition. The collapse risk assessment unit is used to determine the collapse level that the current area may face or is facing based on the acquired disaster characteristics and the latest data extracted from the area; The warning dissemination module includes: The scenario planning unit is used to develop corresponding warning information and emergency plans for each failure level; The information dissemination unit is used to obtain the final collapse level and disseminate the corresponding warning information and emergency plan for the collapse level.

Images