Urban rainfall emergency processing method and system

Abstract

The invention provides an urban rainfall emergency processing method and system, and relates to the technical field of rainfall disaster emergency processing, and the method comprises the steps: obtaining historical urban rainfall data and drainage information, and generating an urban rainfall simulation model through the three-dimensional modeling and rainfall simulation technology; furthermore, a disaster tree model is constructed in combination with a machine learning algorithm and a fault tree analysis method, and association and influence relationships of historical rainfall disasters are identified. And based on the disaster template data and a preset historical emergency processing scheme, systematically analyzing and optimizing a disaster prediction model, and realizing real-time prediction of disaster information and generation of the emergency processing scheme. An emergency processing scheme is optimized by adopting a simulated annealing algorithm, and optimal response under different disaster levels is ensured. Through multi-level data analysis and algorithm optimization, the accuracy and efficiency of emergency response are improved, and the occurrence probability and loss of disasters such as urban waterlogging are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of emergency treatment of rainfall disasters, and in particular to an emergency treatment method and system for urban rainfall. Background Art

[0002] At present, emergency treatment of urban rainfall is an important task in urban management. With the acceleration of urbanization, urban waterlogging is becoming increasingly serious. Traditional urban drainage systems are often unable to respond in time when faced with sudden heavy rainfall, and problems such as insufficient drainage capacity and pipe network blockage frequently occur. Existing technologies mainly rely on historical experience and simple mathematical models for emergency treatment. These methods usually lack scientificity and foresight, and it is difficult to provide effective solutions. For example, some existing methods only rely on historical rainfall data and drainage data for analysis, and fail to fully consider the complex relationship between rainfall characteristics and urban structure, resulting in limited effectiveness of emergency treatment plans and inability to cope with complex and changeable rainfall conditions.

[0003] There is an urgent need for a method and system that can effectively improve the scientificity and predictability of urban rainfall emergency response and solve the problems of untimely emergency response and poor results in traditional methods. Summary of the invention

[0004] The purpose of the present invention is to provide an emergency treatment method and system for urban rainfall to improve the above problems. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0005] In a first aspect, the present application provides an emergency treatment method for urban rainfall, comprising:

[0006] Acquire first information and second information, wherein the first information includes historical urban rainfall data information and historical urban drainage information, and the second information includes processing solution information corresponding to the historical urban rainfall data information;

[0007] Performing three-dimensional modeling and rainfall simulation on the first information to obtain an urban rainfall simulation model, wherein the urban rainfall simulation model is a three-dimensional model that simulates urban rainfall data and urban drainage data;

[0008] Based on the evolutionary algorithm, the influence relationship between all the data in the urban rainfall simulation model and the preset historical rainfall disaster information is identified, and the reliability engineering method is applied to perform statistical analysis on the preset historical rainfall disaster information, and a disaster tree model is established based on the statistical analysis results and the influence relationship to obtain disaster template data;

[0009] Learning the disaster template data and the first information based on a machine learning algorithm to construct a disaster prediction model;

[0010] Predicting disaster information based on real-time urban rainfall data information and urban drainage information acquired by the disaster prediction model, and constructing an emergency response plan based on the predicted disaster information to obtain at least two emergency response plans;

[0011] Adaptive analysis and processing are performed based on all emergency response plans and preset historical emergency response data information, and disaster response is carried out based on the optimal emergency response plan information obtained according to the analysis.

[0012] In a second aspect, the present application also provides an emergency treatment system for urban rainfall, comprising:

[0013] An acquisition unit, configured to acquire first information and second information, wherein the first information includes historical urban rainfall data information and historical urban drainage information, and the second information includes processing solution information corresponding to the historical urban rainfall data information;

[0014] A modeling unit, configured to perform three-dimensional modeling and rainfall simulation on the first information to obtain an urban rainfall simulation model, wherein the urban rainfall simulation model is a three-dimensional model that simulates urban rainfall data and urban drainage data;

[0015] An analysis unit, used for identifying the influence relationship between all data in the urban rainfall simulation model and preset historical rainfall disaster information based on an evolutionary algorithm, and applying a reliability engineering method to perform statistical analysis on the preset historical rainfall disaster information, and establishing a disaster tree model based on the statistical analysis results and the influence relationship to obtain disaster template data;

[0016] A learning unit, used to learn the disaster template data and the first information based on a machine learning algorithm to construct a disaster prediction model;

[0017] A prediction unit, configured to predict disaster information based on the real-time urban rainfall data information and urban drainage information acquired by the disaster prediction model, and to construct an emergency response plan based on the predicted disaster information to obtain at least two emergency response plans;

[0018] The processing unit is used to perform adaptive analysis and processing according to all emergency response plans and preset historical emergency response data information, and to handle disasters based on the optimal emergency response plan information obtained according to the analysis.

[0019] The beneficial effects of the present invention are:

[0020] The present invention acquires and processes historical urban rainfall data information and urban drainage information, uses three-dimensional modeling technology to simulate rainfall, and constructs an urban rainfall simulation model. The model can accurately simulate urban rainfall and drainage conditions, and combines evolutionary algorithms and reliability engineering methods to identify the influence relationship between rainfall data and historical rainfall disaster information, thereby improving the accuracy of predicting future rainfall disasters.

[0021] The present invention builds a disaster prediction model based on machine learning algorithms, which can predict urban rainfall data and drainage information obtained in real time and quickly generate disaster information. Based on this disaster information, at least two emergency response plans are constructed, and adaptability analysis is performed to select the optimal plan for emergency response, which greatly improves the efficiency and effectiveness of emergency response.

[0022] The present invention combines a variety of algorithms and technical means, and comprehensively considers historical data, real-time data and predicted data. The method of the present invention has high adaptability and flexibility, can cope with various complex and changeable rainfall conditions, and provide diversified emergency response solutions, thereby significantly reducing the probability and losses of disasters such as urban waterlogging.

[0023] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 It is a schematic flow chart of the emergency treatment method for urban rainfall described in an embodiment of the present invention;

[0026] Figure 2 It is a schematic diagram of the topological structure of the emergency treatment system for urban rainfall described in an embodiment of the present invention.

[0027] In the figure: 701, acquisition unit; 702, modeling unit; 703, analysis unit; 704, learning unit; 705, prediction unit; 706, processing unit. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0029] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0030] Embodiment 1:

[0031] This embodiment provides an emergency treatment method for urban rainfall.

[0032] See also Figure 1 , the figure shows that the method includes step S1, step S2, step S3, step S4, step S5 and step S6.

[0033] Step S1, obtaining first information and second information, wherein the first information includes historical urban rainfall data information and historical urban drainage information, and the second information includes processing solution information corresponding to the historical urban rainfall data information;

[0034] It can be understood that in this step, the historical urban rainfall data obtained from the Meteorological Bureau includes rainfall amount information, rainfall duration information, rainfall range and other information, and the historical urban drainage information obtained from the urban planning department includes urban drainage efficiency information, urban drainage pipe layout information and urban drainage method and other information. Through the systematic collection and organization of the first information and the second information, it can provide key support for the subsequent steps of the urban rainfall emergency treatment method, ensuring the scientificity and effectiveness of the entire emergency treatment process.

[0035] Step S2, performing three-dimensional modeling and rainfall simulation on the first information to obtain an urban rainfall simulation model, wherein the urban rainfall simulation model is a three-dimensional model that simulates urban rainfall data and urban drainage data;

[0036] It can be understood that this step can accurately simulate the urban terrain and drainage system through three-dimensional modeling, reflect the actual drainage conditions and geographical features in the city, improve the accuracy of rainfall simulation, and the model can truly reproduce the flow and accumulation of rainwater during historical rainfall, providing an intuitive reference for subsequent analysis. In this step, step S2 includes step S21, step S22, step S23 and step S24.

[0037] Step S21, converting the drainage pipe structure in the historical urban drainage information into a format, performing XOY plane selection processing on the drainage pipe structure in the converted historical urban drainage information to obtain a drainage pipe structure diagram after the selection;

[0038] It can be understood that this step ensures the compatibility of drainage pipe data between different modeling software through format conversion, making the data processing and modeling process smoother. The plane frame selection process simplifies the data preparation process and lays the foundation for the rapid construction of high-precision three-dimensional models.

[0039] Step S22, sending the discrete elevation data of the urban structure in the historical urban drainage information and the selected drainage pipe structure diagram to the three-dimensional modeling software for processing to obtain a three-dimensional model of the urban structure and the drainage pipe;

[0040] It can be understood that the terrain model generated by the discrete elevation data in this step can truly reflect the ups and downs of the urban terrain, improving the accuracy and authenticity of the simulation. The accurate three-dimensional model makes the rainfall simulation and analysis process more efficient and reduces repeated processing and errors caused by inaccurate or incomplete data.

[0041] Step S23, discretizing the three-dimensional model of the urban structure and the drainage pipe to obtain at least one three-dimensional geological columnar unit, and performing linear interpolation processing on each of the three-dimensional geological columnar units based on a linear interpolation method to obtain a columnar three-dimensional model of the urban structure and the drainage pipe;

[0042] It can be understood that this step refines the complex three-dimensional model into multiple small units through discretization processing, making the model more refined and easier to analyze and calculate. Among them, the linear interpolation method can estimate the accurate intermediate value between known data points, improving the accuracy and reliability of the model.

[0043] Step S24: Send the historical urban rainfall data to the three-dimensional modeling software for data labeling and rainwater flow simulation to obtain an urban rainfall simulation model.

[0044] It can be understood that the simulation process in this step can truly reproduce the water accumulation and flow conditions of historical rainfall events, providing a reference for emergency response. The rainfall simulation model provides detailed rainfall and drainage data, providing a scientific basis for decision makers and supporting the formulation and implementation of emergency decisions.

[0045] Step S3, identifying the influence relationship between all data in the urban rainfall simulation model and preset historical rainfall disaster information based on the evolutionary algorithm, and applying the reliability engineering method to perform statistical analysis on the preset historical rainfall disaster information, and establishing a disaster tree model based on the statistical analysis results and the influence relationship to obtain disaster template data;

[0046] It can be understood that this step combines the evolutionary algorithm with the reliability engineering method to generate an accurate model of the impact relationship between the urban rainfall simulation model data and the historical rainfall disaster information. By establishing a comprehensive disaster tree model, it is possible to effectively identify the possible main disaster paths under urban rainfall conditions and improve the prediction accuracy. In this step, step S3 includes step S31, step S32, step S33 and step S34.

[0047] Step S31, performing topological data analysis on the simulated urban rainfall data and urban drainage data in the urban rainfall simulation model, wherein a dynamic change graph of the simulated urban rainfall data and urban drainage data is obtained by extracting features from the simulated urban rainfall data and urban drainage data and performing network construction processing based on the extracted feature data;

[0048] It can be understood that this step extracts simulated rainfall data from the urban rainfall simulation model, which may include information such as rainfall, rainfall distribution, and spatiotemporal changes. At the same time, the data of the urban drainage system is extracted from the model, including key parameters such as the structure, capacity, and flow rate of the drainage pipe. Then, through mathematical and statistical methods, key features are extracted from the simulated urban rainfall data and urban drainage data, such as the time variation of rainfall intensity and the flow distribution of the drainage pipe. Finally, the features extracted from the simulated data and drainage data are used as nodes, and a network structure is constructed by analyzing the correlation and influence between them. This step is based on evolutionary algorithms and network construction processing to achieve accurate extraction of important features in simulated urban rainfall data and urban drainage data. The constructed feature network can accurately reflect the complex correlation between different features and reveal the complexity of the dynamic changes of urban rainfall data and drainage data.

[0049] Step S32, performing data conversion processing according to the dynamic change graph to obtain a spatiotemporal feature matrix;

[0050] It can be understood that this step effectively structures and organizes the dynamic characteristics of urban rainfall data and drainage data by converting the complex dynamic change graph into a spatiotemporal feature matrix. The data conversion aims to convert the complex relationships in the dynamic change graph into a form that can be processed by mathematical models, so as to facilitate further time series analysis and the establishment of prediction models.

[0051] Step S33, performing time series analysis on the spatiotemporal feature matrix according to a preset vector autoregression model, by analyzing the dynamic change data of urban rainfall feature data and urban drainage feature data over time;

[0052] It can be understood that the vector autoregression model in this step is a multivariate time series analysis method used to describe the interdependence between multiple variables and the dynamic characteristics that change over time. In urban management, the vector autoregression model can be used to analyze the temporal variation of urban rainfall data and urban drainage data to help predict future trends. By performing vector autoregression analysis on the spatiotemporal feature matrix, the ability to predict future urban rainfall and drainage system behavior is improved, providing a scientific basis for disaster prediction and the formulation of emergency response plans.

[0053] Step S34, performing correlation analysis based on the dynamically changing data and the preset historical rainfall disasters, and obtaining the influence relationship between all the data in the urban rainfall simulation model and the preset historical rainfall disasters by mining the correlation between the urban rainfall characteristic data and the urban drainage characteristic data at different times and the preset historical rainfall disasters.

[0054] It is understandable that this step, through correlation analysis, deeply understands the response mechanism of the urban internal drainage system under different rainfall conditions, and provides a scientific basis for disaster management. Among them, the established impact relationship model can help accurately predict the type and degree of disasters that may be caused by specific rainfall events, and improve the efficiency of early warning and response. Then, based on the analysis results, the emergency response plan is optimized to make it more adaptable to the response needs under different disaster scenarios, and improve the city's disaster resistance and emergency response efficiency.

[0055] In this step, step S3 also includes step S35, step S36, step S37, step S38 and step S39.

[0056] Step S35, performing normalization processing according to preset historical rainfall disaster information, and calculating the occurrence frequency and distribution of the historical rainfall disaster information, to obtain statistical characteristic data of the historical rainfall disaster information;

[0057] It can be understood that this step identifies the distribution patterns of different types of rainfall disasters in time and space through statistical feature data, providing a scientific basis for urban disaster management and prevention. Based on the normalization and frequency analysis of historical disaster data, the city's emergency response strategy is optimized to improve the efficiency and response capabilities of various disaster events. The calculation formula for calculating the frequency and distribution of historical rainfall disaster information includes:

[0058]

[0059] P i =1-exp(-λ i ·t c ·P e );

[0060] Where i represents the index of rainfall disaster; j represents the index of historical rainfall data; N represents the total number of historical rainfalls; λ i represents the occurrence frequency of the i-th type of rainfall disaster; N i represents the number of occurrences of the i-th type of rainfall disaster; T j represents the time of the jth historical rainfall; P e Indicates the preset drainage efficiency parameter; P i represents the frequency distribution of the i-th type of rainfall disaster; t c Indicates the duration of historical rainfall data.

[0061] Step S36, clustering processing is performed according to the statistical characteristic data of the historical rainfall disaster information, and the main disaster types of the historical rainfall disaster information are identified by combining the influence relationship between all the data in the urban rainfall simulation model and the preset historical rainfall disaster information to obtain historical rainfall disaster classification data;

[0062] It can be understood that this step accurately identifies the main types of historical rainfall disasters through cluster analysis, which helps to distinguish the characteristics and occurrence patterns of different types of disasters. It then provides accurate historical disaster classification data to support urban management departments in formulating more effective emergency response strategies and plans, thereby improving the efficiency and effectiveness of disaster response. Furthermore, by combining model data and statistical characteristics, the prediction model of urban rainfall disasters is optimized, the accuracy and practicality of the prediction are improved, and the losses and impacts caused by disasters are reduced.

[0063] Step S37, performing association analysis according to the historical rainfall disaster classification data, and combining the association relationships between the historical rainfall disaster data obtained through analysis based on a preset dynamic threshold mechanism to obtain association data of historical rainfall disasters;

[0064] It can be understood that this step uses association analysis and dynamic threshold mechanisms to deeply understand the relationship between different historical rainfall disaster types, including their spatiotemporal linkage and co-occurrence patterns. It provides accurate historical rainfall disaster association data for urban management departments to help them more accurately predict and respond to complex rainfall disaster events and improve the timeliness and accuracy of emergency response. Association analysis can use statistical methods such as correlation analysis and covariance analysis, and can also apply machine learning methods such as association rule mining to reveal the potential connections between different types of disasters.

[0065] Step S38, constructing a model for the associated data of the historical rainfall disasters according to a fault tree analysis algorithm, wherein a disaster tree model is constructed by determining the logical relationship between each basic event and the top event of the historical rainfall disasters;

[0066] It can be understood that the fault tree analysis in this step is a quantitative risk assessment method used to analyze the possibility and impact of events in a system or process. It represents events and their results as a tree structure, starting from the top event (the event that is ultimately undesirable), and gradually decomposes it into basic events (original events that cannot be decomposed any further) through logical relationships. This step identifies and confirms each basic event through the associated data of historical rainfall disasters. These basic events can be specific rainfall disaster types, such as floods, geological landslides, etc. Each type of disaster is usually used as a basic event in the fault tree. Further, the final top event is determined, that is, the most serious rainfall disaster event generated in the city. The top event is usually the most important and riskiest event in the overall system, which will be caused by a combination of one or more basic events. Then, according to the association relationship between different types of rainfall disaster events in the historical data, a logical relationship is established. For example, it is determined how various basic events interact or jointly cause the occurrence of the top event. These relationships can be determined by expert knowledge, statistical analysis or the probabilistic relationship of historical data. This step is based on the disaster tree model, which can quantitatively analyze the probability and impact of different rainfall disaster events, which helps to predict the top events that may occur in the future and carry out risk management and preparation in advance.

[0067] Step S39: Decompose the disaster tree model to generate disaster template data by extracting the probability of occurrence and impact relationship of key events.

[0068] It can be understood that this step determines the key events that affect the occurrence of top events based on the disaster tree model. These key events may be specific weather conditions, specific states of the urban drainage system, or other factors related to the occurrence of rainfall disasters. Then, for each key event, the probability of its occurrence is estimated through historical data or expert judgment. These probabilities reflect the possibility of the event leading to a top event under specific conditions. Then analyze the degree of influence of each key event on the occurrence of the top event. This is done through quantitative methods (such as probability distribution, influence coefficient) or qualitative methods (such as expert evaluation) to help understand the role of each event in the disaster chain, and then the extracted probability of occurrence and impact relationship can be integrated into disaster template data, providing a scientific basis for urban planners and managers to help them formulate long-term and short-term disaster management strategies. These data are usually presented in a table or structured format, including key information such as the name of each key event, probability of occurrence, and influence coefficient.

[0069] Step S4: learning the disaster template data and the first information based on a machine learning algorithm to construct a disaster prediction model;

[0070] It can be understood that this step learns historical data and disaster templates through machine learning algorithms, and the model can accurately predict the types of disasters and the extent of impact that may be caused by future urban rainfall events. Among them, the establishment of the prediction model enables city managers to formulate response strategies and emergency plans in advance to reduce disaster losses and improve emergency response efficiency. In this step, step S4 includes step S41, step S42, step S43 and step S44.

[0071] Step S41, filtering the statistical characteristic data of historical rainfall disaster information based on the LASSO regression method to obtain the characteristic data set that has the greatest impact on disaster prediction;

[0072] It can be understood that in this step, LASSO regression is a compression estimation method that can perform variable selection and parameter estimation at the same time. Its characteristic is that it can make some coefficients become zero, thereby achieving the purpose of feature selection. This step selects feature variables with non-zero coefficients based on the results of LASSO regression. These variables are considered to be the most influential feature data sets for disaster prediction.

[0073] Step S42, dividing the feature data set and the first information that have the greatest impact on disaster prediction into a training set and a test set according to a preset ratio;

[0074] It can be understood that this step provides the necessary data foundation for the subsequent machine learning algorithm model training by preparing training sets and test sets.

[0075] Step S43, performing model training and optimization on the training set, wherein prediction training is performed by constructing a BP neural network model, and the model parameters are optimized using a grid search method, and a preliminary disaster prediction model is obtained through training;

[0076] It can be understood that this step selects BP neural network as a model for disaster prediction training, which can predict possible disasters in the future based on the input historical rainfall disaster information feature data. Among them, BP neural network is a commonly used type of artificial neural network, which is suitable for processing complex nonlinear relationships and has certain applicability to disaster prediction problems.

[0077] Step S44: perform model verification and evaluation based on the disaster prediction model, and obtain a final disaster prediction model by verifying and optimizing the model using a test set.

[0078] It can be understood that this step verifies and optimizes the model by using the test set, which can ensure that the disaster prediction model has high accuracy and reliability, can effectively respond to possible urban rainfall disasters in the future, and provide strong support for emergency management and urban planning.

[0079] Step S5: predicting disaster information based on the real-time urban rainfall data information and urban drainage information acquired by the disaster prediction model, and constructing an emergency response plan based on the predicted disaster information to obtain at least two emergency response plans;

[0080] It is understandable that this step, by generating at least two emergency response plans, can select the most appropriate response measures according to different prediction results and disaster scenarios, thereby improving the flexibility and effectiveness of disaster response. In this step, step S5 includes step S51, step S52 and step S53.

[0081] Step S51, classifying the predicted disaster information to obtain level information corresponding to the disaster information;

[0082] It can be understood that this step is to classify each type of disaster information into grades. The grades can be determined based on factors such as the severity of the disaster, the scope of impact, and the expected losses. Symbols such as numbers or letters are usually used to represent different grades, such as grade 1, grade 2, grade 3, etc. This effectively classifies and grades the predicted disaster information, which helps to accurately assess and respond to various potential urban rainfall disasters.

[0083] Step S52: weighting the level information corresponding to the disaster information based on a preset deep deterministic policy gradient mathematical model to obtain the weight ratio of the level information corresponding to all the disaster information;

[0084] It can be understood that this step applies a weight allocation strategy to each disaster information level by using a preset deep deterministic policy gradient model. During the allocation process, the model parameters are adjusted according to historical data, empirical knowledge or expert advice to correctly allocate the weight of each level of information. This step can effectively determine the weight ratio of each disaster level information, which helps to optimize the emergency response and resource allocation strategy when facing urban rainfall disasters of different levels.

[0085] Step S53: readjust the allocated weight ratio based on the minimum discrimination principle, and allocate the number of emergency personnel based on the adjusted weight ratio, wherein personnel are allocated according to the weight ratio corresponding to each level of information, and the allocated number of emergency personnel is matched with the preset historical emergency response plan to obtain at least two emergency response plans.

[0086] It can be understood that the minimum discriminant principle in this step is a mathematical principle, which is usually used for weight adjustment and resource allocation in optimization problems. Here, it is used to re-evaluate and adjust the weight ratio assigned according to the disaster information level to minimize the difference in preset goals (such as resource utilization efficiency or response efficiency). Re-adjusting the weight based on the minimum discriminant principle can ensure that when a disaster occurs, emergency personnel resources can be effectively allocated according to the actual situation and the adjusted weight ratio, and corresponding emergency response plans can be formulated to improve the efficiency and effectiveness of disaster response.

[0087] Step S6: Adaptive analysis is performed according to all emergency response plans and preset historical emergency response data information, and disaster response is performed based on the optimal emergency response plan information obtained according to the analysis.

[0088] It can be understood that this step can ensure that when a disaster occurs, the most appropriate and effective emergency response plan can be selected based on detailed analysis and evaluation through adaptive analysis processing, thereby improving the efficiency and effectiveness of disaster response. In this step, step S6 includes step S61 and step S62.

[0089] Step S61: construct an objective function based on all emergency response plans and preset historical emergency response data information;

[0090] It can be understood that this step constructs an objective function to minimize the impact and losses caused by disasters, wherein the formula of the objective function is as follows:

[0091]

[0092] Among them, F(x) represents the objective function, v represents the progress of disaster handling, d represents the total amount of disasters to be handled, A represents the emergency response plan, t0 represents the start time of disaster handling, t1 represents the end time of disaster handling, v(t) represents the progress of disaster handling at time t, P(v(t)) represents the material consumption rate under the disaster handling progress v(t), and t represents time.

[0093] Step S62: Perform a random search in the solution space using a simulated annealing algorithm and accept inferior solutions with a preset probability to obtain an optimized emergency response plan corresponding to each disaster level information.

[0094] It can be understood that the simulated annealing algorithm in this step is a global optimization algorithm, which is usually used to find a local optimal solution or a solution close to the global optimal solution in the solution space. The process of the simulated annealing algorithm in this step starts from the preset initial solution. These solutions are the emergency treatment solutions obtained before. Then, based on the simulated annealing algorithm, a random search is performed in the solution space, and each time a neighboring solution is selected and its objective function value is calculated. During the search process, the simulated annealing algorithm accepts inferior solutions according to a certain probability, which helps to avoid falling into the local optimal solution and promotes global search. Finally, the optimized emergency treatment solution is obtained.

[0095] Embodiment 2:

[0096] like Figure 2 As shown, this embodiment provides an emergency treatment system for urban rainfall, see Figure 2 The system includes an acquisition unit 701 , a modeling unit 702 , an analysis unit 703 , a learning unit 704 , a prediction unit 705 and a processing unit 706 .

[0097] An acquisition unit 701 is used to acquire first information and second information, wherein the first information includes historical urban rainfall data information and historical urban drainage information, and the second information includes processing solution information corresponding to the historical urban rainfall data information;

[0098] A modeling unit 702 is used to perform three-dimensional modeling and rainfall simulation on the first information to obtain an urban rainfall simulation model, wherein the urban rainfall simulation model is a three-dimensional model that simulates urban rainfall data and urban drainage data;

[0099] The analysis unit 703 is used to identify the influence relationship between all the data in the urban rainfall simulation model and the preset historical rainfall disaster information based on the evolutionary algorithm, and to perform statistical analysis on the preset historical rainfall disaster information using the reliability engineering method, and to establish a disaster tree model based on the statistical analysis results and the influence relationship to obtain disaster template data;

[0100] A learning unit 704, configured to learn the disaster template data and the first information based on a machine learning algorithm to construct a disaster prediction model;

[0101] The prediction unit 705 is used to predict the disaster information based on the real-time urban rainfall data information and urban drainage information obtained by the disaster prediction model, and to construct an emergency treatment plan based on the predicted disaster information to obtain at least two emergency treatment plans;

[0102] The processing unit 706 is used to perform adaptive analysis and processing according to all emergency response plans and preset historical emergency response data information, and to perform disaster processing based on the optimal emergency response plan information obtained according to the analysis.

[0103] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0104] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0105] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An emergency treatment method for urban rainfall, characterized in that: include: Acquire first information and second information, wherein the first information includes historical urban rainfall data information and historical urban drainage information, and the second information includes processing solution information corresponding to the historical urban rainfall data information; Performing three-dimensional modeling and rainfall simulation on the first information to obtain an urban rainfall simulation model, wherein the urban rainfall simulation model is a three-dimensional model that simulates urban rainfall data and urban drainage data; Based on the evolutionary algorithm, the influence relationship between all the data in the urban rainfall simulation model and the preset historical rainfall disaster information is identified, and the reliability engineering method is applied to perform statistical analysis on the preset historical rainfall disaster information, and a disaster tree model is established based on the statistical analysis results and the influence relationship to obtain disaster template data; Learning the disaster template data and the first information based on a machine learning algorithm to construct a disaster prediction model; Predicting disaster information based on real-time urban rainfall data information and urban drainage information acquired by the disaster prediction model, and constructing an emergency response plan based on the predicted disaster information to obtain at least two emergency response plans; Adaptive analysis and processing are performed based on all emergency response plans and preset historical emergency response data information, and disaster response is carried out based on the optimal emergency response plan information obtained according to the analysis.

2. The emergency treatment method for urban rainfall according to claim 1 is characterized in that , performing three-dimensional modeling and rainfall simulation on the first information to obtain an urban rainfall simulation model, including: The drainage pipe structure in the historical urban drainage information is formatted, and the drainage pipe structure in the converted historical urban drainage information is subjected to XOY plane frame selection processing to obtain a drainage pipe structure diagram after frame selection; Sending the discrete elevation data of the urban structure in the historical urban drainage information and the selected drainage pipe structure diagram to the three-dimensional modeling software for processing to obtain a three-dimensional model of the urban structure and the drainage pipe; Discretizing the three-dimensional model of the urban structure and the drainage pipe to obtain at least one three-dimensional geological columnar unit, and performing linear interpolation processing on each of the three-dimensional geological columnar units based on a linear interpolation method to obtain a columnar three-dimensional model of the urban structure and the drainage pipe; The historical urban rainfall data is sent to the 3D modeling software for data labeling and rainwater flow simulation to obtain an urban rainfall simulation model.

3. The emergency treatment method for urban rainfall according to claim 1 is characterized in that The method of identifying the influence relationship between all data in the urban rainfall simulation model and preset historical rainfall disaster information based on the evolutionary algorithm includes: Performing topological data analysis on simulated urban rainfall data and urban drainage data in the urban rainfall simulation model, wherein, by extracting features from the simulated urban rainfall data and urban drainage data, and performing network construction processing based on the extracted feature data, a dynamic change graph of the simulated urban rainfall data and urban drainage data is obtained; Performing data conversion processing according to the dynamic change graph to obtain a spatiotemporal feature matrix; Performing time series analysis on the spatiotemporal feature matrix according to a preset vector autoregression model, by analyzing the dynamic change data of urban rainfall feature data and urban drainage feature data over time; A correlation analysis is performed based on the dynamically changing data and the preset historical rainfall disasters, and the influence relationship between all the data in the urban rainfall simulation model and the preset historical rainfall disasters is obtained by mining the correlation between the urban rainfall characteristic data and the urban drainage characteristic data at different times and the preset historical rainfall disasters.

4. The emergency treatment method for urban rainfall according to claim 1 is characterized in that , and applying the reliability engineering method to statistically analyze the preset historical rainfall disaster information, establish a disaster tree model based on the statistical analysis results and the impact relationship, and obtain disaster template data, including: Perform normalization processing according to preset historical rainfall disaster information, calculate the occurrence frequency and distribution of historical rainfall disaster information, and obtain statistical characteristic data of historical rainfall disaster information; Clustering is performed based on the statistical characteristic data of the historical rainfall disaster information, and the main disaster types of the historical rainfall disaster information are identified by combining the influence relationship between all the data in the urban rainfall simulation model and the preset historical rainfall disaster information to obtain historical rainfall disaster classification data; Performing correlation analysis based on the historical rainfall disaster classification data, and combining the correlation relationships between the historical rainfall disaster data obtained through analysis based on a preset dynamic threshold mechanism to obtain correlation data of historical rainfall disasters; A model is constructed for the associated data of the historical rainfall disasters according to a fault tree analysis algorithm, wherein a disaster tree model is constructed by determining the logical relationship between each basic event and the top event of the historical rainfall disasters; Decomposition processing is performed according to the disaster tree model, and disaster template data is generated by extracting the occurrence probability and impact relationship of key events.

5. The emergency treatment method for urban rainfall according to claim 4 is characterized in that The disaster prediction model is constructed by learning the disaster template data, real-time urban rainfall data information and urban drainage information based on the machine learning algorithm, including: Based on the LASSO regression method, the statistical characteristic data of historical rainfall disaster information is screened to obtain the characteristic data set that has the greatest impact on disaster prediction; The feature data set and the first information that have the greatest impact on disaster prediction are divided into a training set and a test set according to a preset ratio; The training set is subjected to model training and optimization, wherein prediction training is performed by constructing a BP neural network model, and model parameters are optimized using a grid search method, so as to obtain a preliminary disaster prediction model through training; Model verification and evaluation are performed based on the disaster prediction model, and the model is verified and optimized by using a test set to obtain a final disaster prediction model.

6. The emergency treatment method for urban rainfall according to claim 1 is characterized in that , and constructing an emergency response plan based on the predicted disaster information to obtain at least two emergency response plans, including: Classify the predicted disaster information to obtain level information corresponding to the disaster information; Based on a preset deep deterministic policy gradient mathematical model, weights are assigned to the level information corresponding to the disaster information to obtain the weight ratios of the level information corresponding to all the disaster information; The allocated weight ratio is readjusted based on the minimum discrimination principle, and the number of emergency personnel is allocated based on the adjusted weight ratio, wherein personnel are allocated according to the weight ratio corresponding to each level of information, and the allocated number of emergency personnel is matched with the preset historical emergency response plans to obtain at least two emergency response plans.

7. The emergency treatment method for urban rainfall according to claim 1 is characterized in that , the adaptive analysis and processing according to all emergency response plans and preset historical emergency response data information includes: Construct an objective function based on all emergency response plans and preset historical emergency response data information; Based on random search in the solution space through simulated annealing algorithm, the inferior solution is accepted with a preset probability to obtain the optimized emergency response plan corresponding to each disaster level information.

8. An emergency treatment system for urban rainfall, characterized in that: include: An acquisition unit, configured to acquire first information and second information, wherein the first information includes historical urban rainfall data information and historical urban drainage information, and the second information includes processing solution information corresponding to the historical urban rainfall data information; A modeling unit, configured to perform three-dimensional modeling and rainfall simulation on the first information to obtain an urban rainfall simulation model, wherein the urban rainfall simulation model is a three-dimensional model that simulates urban rainfall data and urban drainage data; An analysis unit, used for identifying the influence relationship between all data in the urban rainfall simulation model and preset historical rainfall disaster information based on an evolutionary algorithm, and applying a reliability engineering method to perform statistical analysis on the preset historical rainfall disaster information, and establishing a disaster tree model based on the statistical analysis results and the influence relationship to obtain disaster template data; A learning unit, used to learn the disaster template data and the first information based on a machine learning algorithm to construct a disaster prediction model; A prediction unit, configured to predict disaster information based on the real-time urban rainfall data information and urban drainage information acquired by the disaster prediction model, and to construct an emergency response plan based on the predicted disaster information to obtain at least two emergency response plans; The processing unit is used to perform adaptive analysis and processing according to all emergency response plans and preset historical emergency response data information, and to handle disasters based on the optimal emergency response plan information obtained according to the analysis.

9. The emergency treatment system for urban rainfall according to claim 8, characterized in that: The modeling unit comprises: The first modeling subunit is used to convert the drainage pipe structure in the historical urban drainage information into a format, and perform XOY plane frame selection processing on the drainage pipe structure in the converted historical urban drainage information to obtain a drainage pipe structure diagram after the frame selection; The second modeling subunit is used to send the discrete elevation data of the urban structure in the historical urban drainage information and the drainage pipe structure diagram after the box selection to the three-dimensional modeling software for processing to obtain a three-dimensional model of the urban structure and the drainage pipe; The third modeling subunit is used to discretize the three-dimensional model of the urban structure and the drainage pipe to obtain at least one three-dimensional geological columnar unit, and perform linear interpolation processing on each of the three-dimensional geological columnar units based on a linear interpolation method to obtain a columnar three-dimensional model of the urban structure and the drainage pipe; The fourth modeling subunit is used to send the historical urban rainfall data to the three-dimensional modeling software for data labeling and rainwater flow simulation to obtain an urban rainfall simulation model.

10. The emergency treatment system for urban rainfall according to claim 8, characterized in that: The analysis unit comprises: The first analysis subunit is used to perform topological data analysis on the simulated urban rainfall data and urban drainage data in the urban rainfall simulation model, wherein a dynamic change graph of the simulated urban rainfall data and urban drainage data is obtained by extracting features from the simulated urban rainfall data and urban drainage data and performing network construction processing based on the extracted feature data; A second analysis subunit is used to perform data conversion processing according to the dynamic change graph to obtain a spatiotemporal feature matrix; The third analysis subunit is used to perform time series analysis on the spatiotemporal feature matrix according to a preset vector autoregression model, by analyzing the dynamic change data of urban rainfall feature data and urban drainage feature data over time; The fourth analysis subunit is used to perform correlation analysis based on the dynamically changing data and the preset historical rainfall disasters, and obtain the influence relationship between all the data in the urban rainfall simulation model and the preset historical rainfall disasters by mining the correlation between the urban rainfall characteristic data and the urban drainage characteristic data at different times and the preset historical rainfall disasters.

Images