Open flood and inland inundation chain generation disaster intelligent early warning directional release method and system
By connecting cities to monitor the Internet of Things, building flooding association identification and prediction models, determining the target population and conducting targeted releases, the problem of inaccurate information release of traditional disaster warning systems has been solved, intelligent early warning has been achieved, and information transmission efficiency and accuracy have been improved. reduces disaster losses.
Patent Information
- Application Number
- CN202411018878.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-29
- Publication Date
- 2024-11-26
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional disaster warning systems have problems with insufficient accuracy in information release, resulting in low efficiency in information transmission and cannot be customized for different regions and populations. The timeliness and accuracy of information are difficult to guarantee, affecting the effectiveness of disaster response.
By connecting cities to monitor the Internet of Things, obtain real-time data, conduct flooding association identification and prediction model construction, generate risk assessment reports, determine target groups and issue warning information in a targeted manner, and use advanced Internet of Things, data analysis and communication technologies to achieve intelligent early warning .
It improves the efficiency and accuracy of information transmission, ensures that early warning information can quickly and accurately reach places where it is needed, reduces disaster losses, and improves the city's ability to respond to disasters.
Smart Images

Figure CN119026904A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of flood disaster warning, and specifically to a method and system for issuing intelligent warnings for external flood and internal waterlogging chain disasters. Background Art
[0002] With the acceleration of urbanization, urban waterlogging has become increasingly prominent, especially under extreme weather conditions, the risk of urban waterlogging chain disasters has increased significantly. In traditional disaster warning systems, the release of warning information generally adopts a wide-area coverage broadcast information dissemination method, that is, sending warning information to the general public in a unified manner. Although this method can cover a wide range of areas and populations, it has certain limitations. First, since the information is unified, it may not be customized according to the characteristics of different regions and populations, resulting in a decrease in the relevance and practicality of the information. Secondly, the traditional warning release method may not be able to achieve accurate information push, which means that in some cases, residents who are really in dangerous areas may not receive timely and effective warnings, while residents in other relatively safe areas may receive unnecessary panic information. In addition, traditional warning information release methods often lack flexibility. Once the disaster situation changes, it is difficult for the system to quickly adjust and update the warning information, resulting in a significant reduction in the timeliness and accuracy of the information. These shortcomings have greatly weakened the effectiveness of the warning system, making it impossible for people to make timely and reasonable responses in emergencies due to insufficient information or information overload. Summary of the invention
[0003] The present application provides a method and system for the targeted release of intelligent early warnings for external flood and internal waterlogging chain disasters, which solves the technical problem that traditional early warning release methods are not accurate enough, resulting in low efficiency in information transmission, and achieves the technical effect of intelligently and targetedly releasing early warning information and improving the efficiency and accuracy of information transmission.
[0004] In view of the above problems, on the one hand, the present application provides a method for targeted release of intelligent early warnings for external flood and internal waterlogging chain disasters, the method comprising: connecting to the city monitoring Internet of Things to obtain a city monitoring data set of the target city; performing internal waterlogging correlation identification based on the city monitoring data set to obtain monitoring correlation identification results; constructing a prediction model for external flood and internal waterlogging chain disasters; based on the monitoring correlation identification results and according to the external flood and internal waterlogging chain disaster prediction model, obtaining a city internal waterlogging risk assessment report; based on the city internal waterlogging risk assessment report, generating a first warning message; based on the target city, determining a warning target population; and targetedly releasing the first warning message to the warning target population.
[0005] On the other hand, the present application also provides a system for issuing intelligent early warnings for chain disasters caused by external floods and internal waterlogging, the system comprising: a monitoring data acquisition module, the monitoring data acquisition module is used to connect to the city monitoring Internet of Things to obtain a city monitoring data set of a target city; an internal waterlogging association identification module, the internal waterlogging association identification module is used to perform internal waterlogging association identification based on the city monitoring data set to obtain a monitoring association identification result; a disaster prediction model construction module, the disaster prediction model construction module is used to construct a prediction model for chain disasters caused by external floods and internal waterlogging; an internal waterlogging risk assessment module, the internal waterlogging risk assessment module is used to obtain a city internal waterlogging risk assessment report based on the external flood and internal waterlogging chain disaster prediction model based on the monitoring association identification result; an early warning information generation module, the early warning information generation module is used to generate a first early warning information based on the city internal waterlogging risk assessment report; a target population determination module, the target population determination module is used to determine the early warning target population based on the target city; an early warning information release module, the early warning information release module is used to release the first early warning information to the early warning target population in a targeted manner.
[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0007] Connect the city monitoring Internet of Things to obtain the city monitoring data set of the target city, ensure the real-time collection of key data, and provide the necessary information basis for subsequent analysis. Perform waterlogging association identification based on the city monitoring data set to obtain monitoring association identification results, find out the key factors leading to waterlogging through data analysis, and provide a basis for the prediction model. Construct an external flood and waterlogging chain disaster prediction model, based on the monitoring association identification results, obtain an urban waterlogging risk assessment report according to the external flood and waterlogging chain disaster prediction model, accurately predict the probability of disaster occurrence and impact range, and provide quantitative risk assessment, and provide an accurate reference basis for the subsequent generation of early warning information. Generate the first early warning information based on the urban waterlogging risk assessment report, generate specific early warning information based on the risk assessment, and provide guidance for taking action. Based on the target city, determine the early warning target population to ensure that the early warning information can target the correct audience. The first early warning information is directed to the early warning target population, and the early warning information is quickly and accurately disseminated, ensuring the early warning effect and reducing disaster losses.
[0008] To sum up, this application realizes the intelligent early warning and targeted release of external flood and internal waterlogging disasters by integrating advanced Internet of Things technology, data analysis technology and communication technology, ensuring that information can quickly reach where it is most needed, improving the efficiency and accuracy of information transmission, and ensuring the timeliness, accuracy and pertinence of urban waterlogging disaster warnings, significantly improving the city's ability to respond to disasters and reducing the losses caused by disasters.
[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] Figure 1 A flow chart of a method for issuing intelligent warnings for external flood and internal waterlogging chain disasters provided in an embodiment of the present application;
[0011] Figure 2 A schematic diagram of a process for constructing a prediction model for external flood and internal waterlogging chain disasters in the method for issuing intelligent early warnings for external flood and internal waterlogging chain disasters provided in an embodiment of the present application;
[0012] Figure 3 A schematic diagram of a process for optimizing waterlogging risk warning in a method for issuing intelligent warnings for external flood and waterlogging chain disasters provided in an embodiment of the present application;
[0013] Figure 4 A schematic diagram of the structure of the intelligent early warning and targeted release system for external flood and internal waterlogging disasters provided in an embodiment of the present application.
[0014] Explanation of the reference numerals: monitoring data acquisition module 10 , waterlogging association identification module 20 , disaster prediction model construction module 30 , waterlogging risk assessment module 40 , warning information generation module 50 , target population determination module 60 , warning information release module 70 . DETAILED DESCRIPTION
[0015] The embodiments of the present application provide a method and system for the targeted issuance of intelligent early warnings for external flood and internal waterlogging disasters, thereby solving the technical problem that traditional early warning issuance methods are not accurate enough, resulting in low efficiency in information transmission, and achieving the technical effect of intelligent targeted issuance of early warning information and improving the efficiency and accuracy of information transmission.
[0016] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a method for issuing intelligent warnings for external flood and internal waterlogging chain disasters, the method comprising:
[0017] Step S1: Connect to the city monitoring Internet of Things to obtain the city monitoring data set of the target city.
[0018] Specifically, the Urban Monitoring Internet of Things is a network composed of various sensors and monitoring devices, which is used to collect various data in the urban environment, such as rainfall, water level, traffic conditions, etc. The target city refers to any city that needs to be warned and monitored for disasters. The urban monitoring data set refers to a series of data about the target city collected from the Urban Monitoring Internet of Things. These data are updated in real time and are used to analyze and predict urban waterlogging and other disasters.
[0019] Establish a connection with the target city's monitoring Internet of Things to ensure that the sensors and devices in the Internet of Things can operate normally and collect data in real time. Through the city monitoring Internet of Things, various monitoring data of the city are collected in real time, including rainfall, river water level, soil moisture, traffic conditions and other data related to floods and waterlogging. Aggregate these monitoring data to form a comprehensive data set, namely the city monitoring data set. This data set is the basis for subsequent analysis and early warning, and it can help predict and assess the risks of disasters such as urban waterlogging.
[0020] Step S2: Perform waterlogging association identification based on the urban monitoring data set to obtain a monitoring association identification result.
[0021] Furthermore, step S2 of the embodiment of the present application includes:
[0022] Preprocessing is performed on the urban monitoring data set to generate a standard monitoring data set; and waterlogging association identification is performed on the standard monitoring data set to generate the monitoring association identification result.
[0023] Specifically, waterlogging correlation identification refers to finding the correlation between various factors that may cause waterlogging by analyzing various data in the urban monitoring data set. For example, factors such as rainfall, drainage system capacity, and terrain height may affect the risk of waterlogging. By identifying the correlation between these factors, the occurrence of waterlogging can be better predicted and corresponding preventive measures can be formulated.
[0024] First, the raw data in the urban monitoring dataset is preprocessed, including data cleaning, format conversion and standardization, to ensure the quality and consistency of the data. A standard monitoring dataset is generated by removing outliers, filling missing data and normalizing the data range. Among them, the standard monitoring dataset refers to a preprocessed, uniformly formatted and high-quality monitoring dataset, which is used for subsequent waterlogging association identification analysis. Exemplarily, the urban monitoring dataset contains different types of sensor data, such as water level, rainfall, soil moisture, etc. In the preprocessing stage, those obviously wrong readings, such as negative water level readings, are cleaned; the data collected by different sensors are converted into a unified unit, such as converting all length data into meters; and the data is normalized for easy comparison and analysis.
[0025] Then, statistical analysis, machine learning or other data mining techniques are used to analyze the processed data and find the correlation between variables. First, feature selection algorithms such as principal component analysis (PCA) or correlation analysis are used to select the most useful features for waterlogging prediction from the preprocessed data set. Then, a suitable machine learning algorithm is selected to build a prediction model to generate monitoring association identification results. Machine learning algorithms such as decision trees, random forests, support vector machines and other tools can be used to build prediction models. Among them, monitoring association identification results refer to the conclusions about the relationship and influence between various monitoring parameters after in-depth analysis of urban monitoring data sets. These results reveal how different environmental factors interact with each other and their correlation with waterlogging phenomena, providing data support for subsequent disaster prediction.
[0026] For example, a random forest algorithm is used for waterlogging association identification. First, daily rainfall, river water level, and waterlogging event records for the past few years are collected. The integrity and consistency of the data are ensured through preprocessing steps. Next, rainfall and river water level are selected as feature inputs using a feature selection algorithm. The preprocessed data is used for model training. During the training process, the random forest constructs multiple decision trees, each of which learns how to predict the occurrence of waterlogging events based on the input features. The performance of the model is evaluated using the test set data. Evaluation indicators may include accuracy, recall, F1 score, etc. If the performance of the model does not meet the requirements, you can try to adjust the model parameters or select other features for training. Each decision tree is trained on a random subset, which helps improve the generalization ability of the model. The trained random forest model is used to predict new data. The model outputs the probability of waterlogging events based on the input features, such as rainfall, soil moisture, wind speed, etc. Based on the prediction results of the model, monitoring association identification results can be generated, such as which factors are most related to waterlogging events and their degree of correlation. These monitoring association identification results will be used for subsequent disaster warnings.
[0027] Step S3: Construct a disaster prediction model for external flood and internal waterlogging.
[0028] Furthermore, if Figure 2 As shown, step S3 of the embodiment of the present application includes:
[0029] Loading the target city's external flood and internal waterlogging chain disaster record database; performing standardization processing on the external flood and internal waterlogging chain disaster record database to generate an external flood and internal waterlogging chain disaster database; dividing the external flood and internal waterlogging chain disaster database to obtain a disaster prediction training set and a disaster prediction test set; training and testing the disaster prediction training set and the disaster prediction test set based on a neural network to generate the external flood and internal waterlogging chain disaster prediction model.
[0030] Specifically, the external flood and internal waterlogging chain disaster prediction model refers to a model specifically used to predict urban waterlogging and its chain reactions caused by external floods. This model considers how floods affect urban infrastructure and the secondary disasters that may be caused, such as traffic disruptions and power supply problems. Its goal is to predict the likelihood and severity of these disasters so that preventive measures can be taken.
[0031] The construction of the external flood and internal waterlogging chain disaster prediction model specifically includes the following steps: first, load the external flood and internal waterlogging chain disaster record library of the target city, and then standardize these data to generate an external flood and internal waterlogging chain disaster database. Among them, the external flood and internal waterlogging chain disaster record library is a database containing the external flood and internal waterlogging chain disaster events in the history of the target city, recording the time, location, impact range, severity and other information of the disaster. The external flood and internal waterlogging chain disaster database is a disaster record library after standardization, with a unified data format, which is convenient for analysis and modeling. The quality and consistency of the data are ensured by cleaning the data and reverse data in the flood and internal waterlogging chain disaster record library, data conversion and data normalization. For example, suppose there is a record library containing flood and internal waterlogging disaster events in the past ten years. In the standardization stage, those records with incomplete data will be cleaned, all time data will be converted into a unified format, such as Unix timestamp, and data such as disaster severity will be normalized.
[0032] Next, the external flood and internal waterlogging chain disaster database is divided into a disaster prediction training set and a disaster prediction test set. The disaster prediction training set and the disaster prediction test set are two parts of data divided from the disaster database. The training set is used to train the prediction model, and the test set is used to evaluate the performance of the model. It is usually achieved by random division or time division. For example, the data of the first seven years can be used as the training set, and the data of the last three years can be used as the test set; or 70% of the data can be used as the training set and 30% of the data can be used as the test set.
[0033] Finally, use TensorFlow or PyTorch to build a neural network model, determine the architecture of the neural network, including the number and size of input layers, hidden layers, and output layers, and use the disaster prediction training set and disaster prediction test set for training and testing to generate a disaster prediction model for external floods and waterlogging. During the training process, the neural network calculates the predicted value through forward propagation, and then updates the weights and biases through backpropagation to reduce the difference between the predicted value and the true value. Use optimization algorithms such as gradient descent and Adam to optimize the weights and biases of the neural network. Use the test data set to evaluate the trained model. Evaluation indicators may include accuracy, recall, F1 score, etc. Based on the results of the model evaluation, optimize the model, including increasing or decreasing the number of hidden layers, adjusting the activation function or loss function, using regularization methods, etc. For example, a neural network with multiple hidden layers can be used to learn the mapping relationship between input features such as rainfall, water level, soil moisture and the occurrence of waterlogging events.
[0034] A trained neural network can predict future disaster events by learning the complex relationship between input and output, predict the probability and impact range of future disasters based on current monitoring data, and provide a data source for the generation of subsequent warning information.
[0035] Step S4: Based on the monitoring association identification results and the external flood and internal waterlogging chain disaster prediction model, an urban waterlogging risk assessment report is obtained.
[0036] Furthermore, step S4 of the embodiment of the present application includes:
[0037] Based on the monitoring association identification results, according to the external flood and internal waterlogging chain disaster prediction model, the urban waterlogging risk prediction results are obtained; the waterlogging risk assessment report template is activated; based on the waterlogging risk assessment report template, the urban waterlogging risk prediction results are sorted out to generate the urban waterlogging risk assessment report.
[0038] Specifically, the monitoring association identification results obtained in step S2 are input into the trained external flood and internal waterlogging chain disaster prediction model, and the model will analyze the input data, calculate the possibility of risk occurrence and potential losses, and output the urban waterlogging risk prediction results. Among them, the urban waterlogging risk prediction results are the probability and possible severity of urban waterlogging predicted by the model based on the current monitoring data.
[0039] Activate the Waterlogging Risk Assessment Report Template. The Waterlogging Risk Assessment Report Template is a pre-designed report format for organizing and presenting waterlogging risk forecast results. It can be a Word document, PDF file, or web page template that contains a fixed format and content structure for the report. For example, the template may include sections such as title, summary, risk assessment results, and recommended preventive measures.
[0040] Use text editing tools, such as Microsoft Word, Google Docs, etc., or report generation software, such as Tableau, PowerBI, etc., to organize and display urban waterlogging risk prediction results and generate a clear and intuitive urban waterlogging risk assessment report. The above process predicts urban waterlogging risks through the external flood and internal waterlogging chain disaster prediction model and automatically generates a waterlogging risk assessment report, which facilitates the subsequent generation of accurate and targeted early warning information.
[0041] Step S5: Generate first warning information based on the urban waterlogging risk assessment report.
[0042] Furthermore, step S5 of the embodiment of the present application includes:
[0043] Perform a warning level analysis based on the urban waterlogging risk assessment report to generate a waterlogging risk warning level; organize the urban waterlogging risk assessment report and the waterlogging risk warning level to generate warning content feature information; perform feature integration on the warning content feature information based on a disaster warning template to obtain the first warning information.
[0044] Specifically, the first warning information refers to an early warning generated based on the urban waterlogging risk assessment report, with the purpose of notifying relevant personnel and the public of the impending waterlogging situation so that they can take necessary preventive measures. The warning level is a quantitative assessment of waterlogging risk, usually divided into different levels, such as red warning, orange warning, yellow warning and blue warning, to indicate the urgency of the risk.
[0045] First, according to the urban waterlogging risk assessment report, the warning level analysis is carried out, the risk point area and the water depth are analyzed, and the thresholds corresponding to each risk level are pre-set. When the predicted risk exceeds these thresholds, the corresponding warning level will be triggered. For example, red warning: the risk point area: multiple cities and states; water depth: greater than or equal to 60 cm. Orange warning: the risk point area: multiple cities and states; water depth: greater than or equal to 40 cm and less than 60 cm. Yellow warning: the risk point area: multiple cities and states; water depth: greater than or equal to 27 cm and less than 40 cm. Blue warning: the risk point area: a certain city or local area; water depth: less than 27 cm.
[0046] Use data analysis software such as Excel, R or Python to organize urban waterlogging risk assessment reports and warning levels, extract key information, and generate warning content feature information. Among them, warning content feature information is the core content of warning information, including warning level, possible impact range, estimated time, possible impact and recommended preventive measures. Use the disaster warning template to integrate the warning content feature information to form the final first warning information. The disaster warning template is a pre-designed format for quickly generating and communicating warning information. This template ensures that the information is presented in a clear and consistent manner for quick understanding and action.
[0047] Through the above process, a clear and accurate first warning information can be generated to provide timely warning and guidance to government departments and the public. For example, the warning information may suggest taking evacuation measures in advance in predicted high-risk areas and strengthening the maintenance and cleaning of drainage systems to reduce the occurrence and impact of waterlogging events.
[0048] Step S6: Based on the target city, determine the target population for early warning.
[0049] Specifically, the target population for early warning refers to the population in the target city that may be affected by the disaster or need to take preventive measures, including government departments, rescue teams, directly affected residents, and other stakeholders that may be affected. First, it is necessary to analyze the geographical, population, infrastructure and other characteristics of the target city to determine the population that may be affected by disasters such as waterlogging and other stakeholders that may be affected. For example, residents in low-lying areas in the city, residents along the river, the elderly and children, and these commercial facilities, schools and hospitals. Next, use geographic information system (GIS) tools to help determine the distribution of the target population for early warning. GIS can provide population distribution maps, topographic maps, infrastructure distribution maps, etc. of the city to help more accurately determine which areas and populations need to receive early warning information. For example, suppose there is GIS data for a city, including population distribution, terrain height, drainage system, etc. Use GIS software, such as ArcGIS, QGIS, etc., to analyze these data to find out which areas have high population density, low-lying terrain, weak drainage system, etc. People in these areas may be more susceptible to waterlogging and should therefore be included in the target population for early warning.
[0050] After determining the target population for early warning, it is also necessary to determine the specific method of conveying early warning information to the target population. When sending early warning information, you can use a variety of communication channels, such as text messages, application push, social media, broadcasting, etc., to ensure that the information can be conveyed to the people who need early warning in a timely and accurate manner. Through big data, the characteristics and preferences of different groups of people are obtained, and different communication channels are matched for them to establish a communication channel database. This communication channel database contains different early warning target populations and their corresponding communication channels. According to the determined early warning target population, this communication channel database is traversed to determine the corresponding target communication channel. For example, government departments can use SMS warnings and map warnings for early warning; rescue teams can use broadcast warnings and SMS warnings for early warnings; the elderly can use telephone or TV broadcast warnings; young people can use social media or mobile application warnings.
[0051] Through the above process, the warning target population and the corresponding communication channels are determined, which can ensure that the warning information can be accurately and timely conveyed to each warning target, thereby improving the ability and effectiveness of responding to flood disasters.
[0052] Step S7: Directly publish the first warning information to the warning target group.
[0053] Specifically, the warning information is released to the warning target population through the communication channels corresponding to the warning target population determined in step S6, using automated communication systems such as the Emergency Alert System (EAS), SMS services, social media platforms, and broadcast networks, so as to quickly and accurately convey the warning information and ensure that the warning effect is achieved.
[0054] Furthermore, if Figure 3 As shown, step S7 of the embodiment of the present application also includes:
[0055] Obtain a warning feedback data set for the warning target population; evaluate the waterlogging risk warning effect based on the warning feedback data set to obtain a warning effect evaluation index; determine whether the warning effect evaluation index is less than a predetermined warning effect evaluation index; if the warning effect evaluation index is less than the predetermined warning effect evaluation index, optimize the waterlogging risk warning based on the warning feedback data set.
[0056] Specifically, the warning feedback data set is collected through questionnaires, automated feedback systems or behavior tracking technology. The warning feedback data set refers to the data collected from the warning target population about their response to the warning information, which may include whether they received the information, whether they understood the content of the information, and what actions they took. The warning effect is evaluated, and the warning feedback data set is analyzed to obtain the warning effect evaluation index to determine whether the warning information is effectively conveyed to the target population and prompt them to take the right actions. Among them, the warning effect evaluation index is a quantitative evaluation of the effect of the warning system, which is used to measure whether the warning information has achieved the expected effect. Data analysis tools such as Excel, R, and Python can be used to analyze the collected warning feedback data and calculate the warning effect evaluation index. For example, indicators such as the reception rate of warning information, the response speed of the public, and the proportion of preventive measures taken can be calculated.
[0057] A predetermined early warning effect evaluation index is set in advance. This predetermined early warning effect evaluation index is a pre-set standard used to evaluate whether the performance of the early warning system meets expectations. The early warning effect evaluation index is compared with the predetermined indicator to determine whether the early warning effect meets the standard. If the early warning effect evaluation index is lower than the predetermined standard, the early warning feedback data set is used to identify the problem and optimize the early warning system, including adjusting the early warning threshold, improving the content and format of the early warning information, and optimizing the transmission channel of the early warning information.
[0058] Through the above process, the early warning process can be continuously evaluated and optimized to make it more adaptable to public needs and environmental changes, ensuring that in real crisis situations, early warning information can be effectively conveyed to the target population, thereby improving the efficiency and accuracy of information transmission.
[0059] Furthermore, step S7 of the embodiment of the present application also includes:
[0060] Connect to the city monitoring Internet of Things to obtain an updated monitoring data set of the target city; based on the updated monitoring data set and according to the external flood and internal waterlogging chain disaster prediction model, obtain an updated internal waterlogging risk assessment report; based on the updated internal waterlogging risk assessment report, generate a second warning information.
[0061] Specifically, the updated monitoring data set is based on the original monitoring data set, and the latest data set is obtained by connecting to the urban monitoring Internet of Things. The updated waterlogging risk assessment report is generated based on the latest monitoring data and prediction models, reflecting the current status of waterlogging risk. The second warning information is generated based on the updated risk assessment report, which is used to inform the target population of the current waterlogging risk.
[0062] Connect to the city monitoring Internet of Things, obtain the real-time updated target city monitoring data set, that is, the updated monitoring data set, repeat steps S2 to S5 based on the updated monitoring data set, perform waterlogging association identification on the updated monitoring data set, and obtain the corresponding monitoring association identification result. Input this monitoring association identification result into the external flood and waterlogging chain disaster prediction model to obtain an updated waterlogging risk assessment report. Based on the updated waterlogging risk assessment report, generate updated warning information, that is, the second warning information. And send the second warning information to the target warning population.
[0063] The above process continuously monitors and updates the risks of internal flooding through real-time monitoring data and external flood and internal waterlogging chain disaster prediction models, ensuring that the early warning information always reflects the latest situation, ensuring the reliability and timeliness of the early warning information, and significantly improving the early warning effect.
[0064] In summary, the method for issuing intelligent warnings for external flood and internal waterlogging chain disasters provided by the embodiments of the present application has the following technical effects:
[0065] Connect the city monitoring Internet of Things to obtain the city monitoring data set of the target city, ensure the real-time collection of key data, and provide the necessary information basis for subsequent analysis. Perform waterlogging association identification based on the city monitoring data set to obtain monitoring association identification results, find out the key factors leading to waterlogging through data analysis, and provide a basis for the prediction model. Construct an external flood and waterlogging chain disaster prediction model, based on the monitoring association identification results, obtain an urban waterlogging risk assessment report according to the external flood and waterlogging chain disaster prediction model, accurately predict the probability of disaster occurrence and impact range, and provide quantitative risk assessment, and provide an accurate reference basis for the subsequent early warning information generation. Generate the first early warning information based on the urban waterlogging risk assessment report, generate specific early warning information based on the risk assessment, and provide guidance for taking action. Based on the target city, determine the early warning target population to ensure that the early warning information can target the correct audience. The first early warning information is directed to the early warning target population, and the early warning information is quickly and accurately disseminated, ensuring the early warning effect and reducing disaster losses. In addition, the waterlogging risk early warning effect is evaluated based on the early warning feedback data set, and the waterlogging risk early warning is optimized based on the evaluation results and the early warning feedback data set, and the early warning strategy and release mechanism are further improved. Obtain an updated monitoring data set for the target city; based on the updated monitoring data set and in accordance with the external flood and internal waterlogging chain disaster prediction model, obtain an updated waterlogging risk assessment report; based on the updated waterlogging risk assessment report, generate a second warning information, respond to changes in the city's monitoring information in a timely manner, and ensure the timeliness and reliability of the warning information.
[0066] Overall, the embodiments of the present application realize intelligent early warning and targeted release of external flood and waterlogging disasters by integrating advanced Internet of Things technology, data analysis technology and communication technology, ensuring that information can quickly reach where it is most needed, and can optimize early warnings based on early warning effects, and update early warning information in real time in response to changes in urban monitoring data, thereby improving the efficiency and accuracy of information transmission, ensuring the timeliness, accuracy and pertinence of urban waterlogging disaster early warnings, significantly improving the city's ability to respond to disasters, and reducing the losses caused by disasters.
[0067] Embodiment 2, as Figure 4 As shown, the embodiment of the present application provides an intelligent early warning and directional release system for external flood and internal waterlogging chain disasters, and the system includes:
[0068] The monitoring data acquisition module 10 is used to connect to the city monitoring Internet of Things to obtain the city monitoring data set of the target city.
[0069] The waterlogging association recognition module 20 is used to perform waterlogging association recognition based on the urban monitoring data set to obtain a monitoring association recognition result.
[0070] The disaster prediction model construction module 30 is used to construct a disaster prediction model for external flood and internal waterlogging chain disasters.
[0071] The waterlogging risk assessment module 40 is used to obtain an urban waterlogging risk assessment report based on the monitoring association identification result and the external flood and waterlogging chain disaster prediction model.
[0072] The warning information generation module 50 is used to generate first warning information based on the urban waterlogging risk assessment report.
[0073] The target population determination module 60 is used to determine the warning target population based on the target city.
[0074] The warning information publishing module 70 is used to publish the first warning information to the warning target group.
[0075] Furthermore, the waterlogging association identification module 20 described in the embodiment of the present application is also used to perform the following steps:
[0076] Preprocessing is performed on the urban monitoring data set to generate a standard monitoring data set; and waterlogging association identification is performed on the standard monitoring data set to generate the monitoring association identification result.
[0077] Furthermore, the disaster prediction model building module 30 described in the embodiment of the present application is also used to perform the following steps:
[0078] Loading the target city's external flood and internal waterlogging chain disaster record database; performing standardization processing on the external flood and internal waterlogging chain disaster record database to generate an external flood and internal waterlogging chain disaster database; dividing the external flood and internal waterlogging chain disaster database to obtain a disaster prediction training set and a disaster prediction test set; training and testing the disaster prediction training set and the disaster prediction test set based on a neural network to generate the external flood and internal waterlogging chain disaster prediction model.
[0079] Furthermore, the waterlogging risk assessment module 40 described in the embodiment of the present application is also used to perform the following steps:
[0080] Based on the monitoring association identification results, according to the external flood and internal waterlogging chain disaster prediction model, the urban waterlogging risk prediction results are obtained; the waterlogging risk assessment report template is activated; based on the waterlogging risk assessment report template, the urban waterlogging risk prediction results are sorted out to generate the urban waterlogging risk assessment report.
[0081] Furthermore, the warning information generating module 50 described in the embodiment of the present application is also used to perform the following steps:
[0082] Perform a warning level analysis based on the urban waterlogging risk assessment report to generate a waterlogging risk warning level; organize the urban waterlogging risk assessment report and the waterlogging risk warning level to generate warning content feature information; perform feature integration on the warning content feature information based on a disaster warning template to obtain the first warning information.
[0083] Furthermore, the warning information publishing module 70 described in the embodiment of the present application is also used to perform the following steps:
[0084] Obtain a warning feedback data set for the warning target population; evaluate the waterlogging risk warning effect based on the warning feedback data set to obtain a warning effect evaluation index; determine whether the warning effect evaluation index is less than a predetermined warning effect evaluation index; if the warning effect evaluation index is less than the predetermined warning effect evaluation index, optimize the waterlogging risk warning based on the warning feedback data set.
[0085] Furthermore, the warning information publishing module 70 described in the embodiment of the present application is also used to perform the following steps:
[0086] Connect to the city monitoring Internet of Things to obtain an updated monitoring data set of the target city; based on the updated monitoring data set and according to the external flood and internal waterlogging chain disaster prediction model, obtain an updated internal waterlogging risk assessment report; based on the updated internal waterlogging risk assessment report, generate a second warning information.
[0087] Through the aforementioned detailed description of the method for targeted issuance of intelligent early warnings for disasters caused by external floods and internal waterlogging, those skilled in the art can clearly understand that the system for targeted issuance of intelligent early warnings for disasters caused by external floods and internal waterlogging in this embodiment is a system for targeted issuance of intelligent early warnings for disasters caused by internal floods and internal waterlogging. As for the system disclosed in Embodiment 2, since it corresponds to the method disclosed in Embodiment 1 and has corresponding functional modules and beneficial effects, the relevant parts may be referred to the description of the method part.
[0088] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. Targeted release method of intelligent early warning for external flood and internal waterlogging disasters, It is characterized in that The method comprises: Connect to the city monitoring Internet of Things to obtain the city monitoring data set of the target city; Performing waterlogging association identification based on the urban monitoring data set to obtain a monitoring association identification result; Construct a disaster prediction model for external flood and internal waterlogging chain; Based on the monitoring association identification results, and according to the external flood and internal waterlogging chain disaster prediction model, an urban waterlogging risk assessment report is obtained; Based on the urban waterlogging risk assessment report, generating first warning information; Based on the target cities, determine the target population for early warning; The first warning information is directed to the warning target group.
2. The method according to claim 1, It is characterized in that Based on the urban monitoring data set, waterlogging association identification is performed to obtain monitoring association identification results, including: Preprocessing the urban monitoring data set to generate a standard monitoring data set; Waterlogging association identification is performed according to the standard monitoring data set to generate the monitoring association identification result.
3. The method according to claim 1, It is characterized in that Construct a disaster prediction model for external floods and internal waterlogging, including: Loading the external flood and internal waterlogging chain disaster record database of the target city; Performing standardization processing on the external flood and internal waterlogging chain disaster record database to generate an external flood and internal waterlogging chain disaster database; Dividing the external flood and internal waterlogging chain disaster database to obtain a disaster prediction training set and a disaster prediction test set; The disaster prediction training set and the disaster prediction test set are trained and tested based on a neural network to generate the external flood and internal waterlogging chain disaster prediction model.
4. The method according to claim 1, It is characterized in that Based on the monitoring association identification results and the external flood and internal waterlogging chain disaster prediction model, an urban waterlogging risk assessment report is obtained, including: Based on the monitoring association identification results, and according to the external flood and internal waterlogging chain disaster prediction model, a city waterlogging risk prediction result is obtained; Activate waterlogging risk assessment report template; Based on the waterlogging risk assessment report template, the urban waterlogging risk prediction results are sorted out to generate the urban waterlogging risk assessment report.
5. The method according to claim 1, It is characterized in that Based on the urban waterlogging risk assessment report, a first warning information is generated, including: Performing warning level analysis based on the urban waterlogging risk assessment report to generate a waterlogging risk warning level; Organizing the urban waterlogging risk assessment report and the waterlogging risk warning level, and generating warning content feature information; The warning content feature information is integrated according to the disaster warning template to obtain the first warning information.
6. The method according to claim 1, It is characterized in that Directly publishing the first warning information to the warning target group also includes: Obtaining a warning feedback data set of the warning target population; Performing waterlogging risk warning effect evaluation based on the warning feedback data set to obtain a warning effect evaluation index; Determining whether the early warning effect evaluation index is less than a predetermined early warning effect evaluation index; If the early warning effect evaluation index is less than the predetermined early warning effect evaluation index, the waterlogging risk early warning is optimized according to the early warning feedback data set.
7. The method according to claim 1, It is characterized in that Directly publishing the first warning information to the warning target group also includes: Connecting to the city monitoring Internet of Things to obtain updated monitoring data sets for the target city; Based on the updated monitoring data set and according to the external flood and internal waterlogging chain disaster prediction model, an updated internal waterlogging risk assessment report is obtained; Based on the updated waterlogging risk assessment report, a second warning information is generated.
8. Intelligent early warning and targeted release system for external flood and internal waterlogging disasters. It is characterized in that The system comprises: A monitoring data acquisition module, which is used to connect to the city monitoring Internet of Things to obtain a city monitoring data set of a target city; A waterlogging association recognition module, the waterlogging association recognition module is used to perform waterlogging association recognition based on the urban monitoring data set to obtain a monitoring association recognition result; A disaster prediction model construction module, wherein the disaster prediction model construction module is used to construct a disaster prediction model for external floods and internal waterlogging; A waterlogging risk assessment module, the waterlogging risk assessment module is used to obtain an urban waterlogging risk assessment report based on the monitoring association identification result and the external flood and internal waterlogging chain disaster prediction model; A warning information generation module, the warning information generation module is used to generate first warning information based on the urban waterlogging risk assessment report; A target population determination module, the target population determination module is used to determine the warning target population based on the target city; The warning information release module is used to release the first warning information to the warning target group in a targeted manner.
Citation Information
Patent Citations
Method and system for testing power grid meteorological risk early warning model
CN113159411A
High-temperature heat wave early warning information pushing method, device, equipment, medium and product
CN114611894A
Early warning information pushing method and device based on big data, equipment and storage medium
CN114723498A
Urban inland inundation monitoring and early warning system and method thereof
CN116758706A
Urban flood disaster monitoring and early warning method and device
CN117218801A
Cited By
Urban inland inundation risk management method and system based on multi-model coupling
CN120450214A
A city waterlogging risk management method and system based on multi-model coupling
CN120450214B
Meteorological early warning service quality-based effect evaluation model construction method
CN120875658A
Urban inland inundation prevention and control method based on water conservancy dispatching and pipe network cooperation
CN121235391A
