Urban surface ponding point location prediction method based on large model technology

Abstract

The invention provides an urban surface ponding point location prediction method based on a large model technology, and the method comprises the steps: collecting facility data corresponding to each drainage facility in a to-be-detected city, building an urban drainage model of the to-be-detected city in combination with the landform data of the to-be-detected city, and carrying out the rainfall training of the urban drainage model, obtaining corresponding urban water discharge information and urban water accumulation information of the to-be-measured city under different rainfall intensity data, analyzing regional water accumulation corresponding to each urban region of the to-be-measured city according to the urban water discharge information and the urban water accumulation information, and determining water accumulation distribution information of the to-be-measured city, determining a plurality of ponding points corresponding to the to-be-detected city under different rainfall intensities, and generating a rainfall-ponding point distribution diagram of the to-be-detected city, the method can accurately predict the whole process of urban surface ponding, and helps emergency personnel to take preventive measures in advance, thereby effectively reducing loss caused by urban rainfall ponding.

Description

Technical Field

[0001] The invention relates to the technical field of urban drainage, and in particular to a method for predicting urban ground waterlogging points based on a large model technology. Background Art

[0002] With the development of cities, the impervious area in urban areas has increased, and flooding caused by rainfall is more common. When there is heavy rainfall, the pressure on the drainage network is too high, and the rainwater cannot be discharged in time, forming water accumulation in low-lying areas in the urban area, seriously affecting urban traffic and residents' lives. At the same time, the pipelines that have been in operation for many years have fallen into disrepair. Therefore, it is necessary and urgent to use numerical simulation methods to understand the current operation status of urban rainwater pipe networks and to rationally optimize and expand the drainage network. At present, mathematical models have begun to be used to simulate the response process of urban surface runoff to rainfall events for urban flood control planning and pipe network optimization. However, existing models generally have problems such as large amount of calculation, long calculation time, and high requirements for computing power.

[0003] Therefore, the present invention provides a method for predicting urban ground waterlogging points based on large model technology. Summary of the invention

[0004] The invention discloses a method for predicting urban ground waterlogging points based on large model technology, which can accurately predict the entire process of urban ground waterlogging and help emergency personnel take preventive measures in advance, thereby effectively reducing the losses caused by urban rainfall and waterlogging.

[0005] The present invention provides a method for predicting urban ground waterlogging points based on a large model technology, comprising:

[0006] Step 1: Collect facility data corresponding to each drainage facility in the city to be tested, and establish an urban drainage model of the city to be tested in combination with the topographic data of the city to be tested;

[0007] Step 2: using each preset precipitation intensity data to perform precipitation training on the urban drainage model, and obtaining the urban drainage volume information and urban water accumulation volume information corresponding to the tested city under different precipitation intensity data;

[0008] Step 3: Analyze the regional waterlogging volume corresponding to each urban area of ​​the city to be tested according to the urban drainage volume information and the urban waterlogging volume information, and determine the waterlogging distribution information of the city to be tested according to the regional waterlogging volume;

[0009] Step 4: Determine a number of waterlogging points corresponding to different precipitation intensities in the city to be tested according to the waterlogging distribution information, and generate a precipitation-waterlogging point distribution map of the city to be tested.

[0010] In one practicable manner,

[0011] When precipitation occurs in the city to be tested, a real-time precipitation distribution map of the city to be tested is established according to the real-time precipitation intensity corresponding to each of the urban areas;

[0012] Searching the precipitation-waterlogging distribution map for high-frequency waterlogging points in each of the urban areas under the corresponding real-time precipitation intensity;

[0013] Using the real-time precipitation distribution map, real-time waterlogging monitoring is performed on each of the high-frequency waterlogging points to obtain a first real-time waterlogging volume corresponding to each of the high-frequency waterlogging points in the city to be tested;

[0014] Sampling waterlogging points in each of the urban areas, and using the real-time precipitation distribution map to perform real-time waterlogging monitoring on each sampled waterlogging point, to obtain a second real-time waterlogging volume corresponding to each sampled waterlogging point in the city to be tested;

[0015] The real-time waterlogging information of the city to be tested is determined and displayed according to the first real-time waterlogging volume corresponding to each of the first high-frequency waterlogging points and the second real-time waterlogging volume corresponding to each of the sampling waterlogging points.

[0016] In one practicable manner,

[0017] Also includes:

[0018] According to the real-time waterlogging information, searching for a number of actual waterlogging points in the city to be tested where the real-time waterlogging volume is higher than the standard waterlogging volume;

[0019] Establishing a waterlogging distribution matrix of the city to be tested according to the distribution of the actual waterlogging points;

[0020] Inputting the water accumulation difference between the real-time water accumulation volume corresponding to each of the actual water accumulation points and the standard water accumulation volume into the water accumulation distribution matrix to obtain the water accumulation information matrix of the city to be tested;

[0021] Performing singular value decomposition on the water accumulation information matrix to obtain dimension reduction data corresponding to each water accumulation difference;

[0022] According to capturing the data trend of the dimension reduction data by using a preset linear regression model, the water accumulation trend corresponding to each actual water accumulation point is obtained;

[0023] According to the water accumulation trend, a corresponding number of security execution personnel are allocated to each actual water accumulation point.

[0024] In one practicable manner,

[0025] The step 1 comprises:

[0026] Step 11: Counting a number of drainage facilities included in the city to be tested, respectively obtaining facility specification data corresponding to each drainage facility, respectively obtaining setting location data of each drainage facility in the city to be tested, and constructing facility data corresponding to each drainage facility based on the facility specification data and the setting location data;

[0027] Step 12: Acquire the geomorphic data of the city to be tested, establish the surface undulation information of the city to be tested according to the geomorphic data, determine several water flow directions of the city to be tested according to the undulation information, and establish the drainage range and drainage direction corresponding to each drainage facility according to the facility data;

[0028] Step 13: construct a virtual drainage sub-model corresponding to each drainage facility according to the drainage range and drainage direction corresponding to the same drainage facility, establish a virtual direction sub-model of the city to be tested according to each water flow direction, use the virtual drainage sub-model to analyze the water basin length and self-consumption of accumulated water corresponding to each virtual drainage direction in the virtual direction sub-model, and establish a virtual domain length sub-model of the city to be tested according to the water basin length;

[0029] Step 14: Establish a three-dimensional city image of the city to be tested based on the topographic data, map the virtual drainage sub-model, the virtual direction sub-model and the virtual domain length sub-model into the three-dimensional city image respectively, adjust the mapping result using the self-consumption of accumulated water, and generate an urban drainage model of the city to be tested.

[0030] In one practicable manner,

[0031] The step 2 comprises:

[0032] Step 21: retrieve historical precipitation information of the geographical location of the city to be tested, determine a number of first preset precipitation intensity data according to the historical precipitation information, search for a number of rainstorm disaster precipitation information in big data, determine a number of second preset precipitation intensity data according to the rainstorm disaster precipitation information, and establish a precipitation training database for the city to be tested according to the first precipitation intensity data and the second preset precipitation intensity data;

[0033] Step 22: Use each training data in the precipitation training database to perform time-length iterative cycle precipitation training on the urban drainage model, obtain a number of training results corresponding to each training data, and establish the time-domain drainage information and time-domain waterlogging information corresponding to each training data of the urban drainage model based on the training results;

[0034] Step 23: Determine the training precipitation intensity corresponding to each iteration cycle according to the number of iteration cycles corresponding to each training data to construct a precipitation information axis, and use the precipitation information axis corresponding to the same training data to dynamically analyze the time-domain drainage information and the time-domain waterlogging information to obtain the first drainage volume and the first waterlogging volume corresponding to the city under test at different time-length precipitation intensities;

[0035] Step 24: Establish a number of dynamic precipitation intensity data based on the precipitation training database, use the dynamic precipitation intensity data to perform dynamic precipitation training on the urban drainage model, obtain the second drainage volume and the second water accumulation volume corresponding to the urban drainage model under different dynamic precipitation intensities, establish the urban drainage information of the city to be tested based on the number of the first drainage volumes and the second drainage volumes, and establish the urban water accumulation information of the city to be tested based on the number of the first water accumulation volumes and the second water accumulation volumes.

[0036] In one practicable manner,

[0037] Also includes:

[0038] Determine, according to the urban waterlogging information, a number of information points in the city to be tested where the amount of urban waterlogging is greater than the standard amount of waterlogging;

[0039] Determine a training precipitation pattern corresponding to each of the information points based on the urban waterlogging information, and establish a warning trigger tag for the information point based on the training precipitation pattern;

[0040] When the current precipitation pattern of the city to be tested is the same as the training precipitation pattern, the warning trigger tag is activated, and a warning message is generated and displayed.

[0041] In one practicable manner,

[0042] The step 3 comprises:

[0043] Step 31: establishing a plurality of drainage flow paths of the city to be tested according to the urban drainage information corresponding to each of the precipitation intensity data, and establishing a plurality of water accumulation flow paths of the city to be tested under the corresponding precipitation intensity data according to the urban water accumulation information;

[0044] Step 32: Divide the city to be tested into a plurality of urban areas according to the urban planning of the city to be tested, respectively obtain first coincidence information between each of the urban areas and different drainage flow paths, and respectively obtain second coincidence information between each of the urban areas and different ponding flow paths;

[0045] Step 33: establishing the regional water accumulation corresponding to the urban area under the corresponding precipitation intensity data according to the first overlap information and the second overlap information, and determining the water flow accumulation characteristics of the corresponding urban area according to the first overlap information and the second overlap information;

[0046] Step 34: Record the urban areas where the regional waterlogging volume is higher than the preset standard waterlogging volume as waterlogged urban areas, and use the water flow accumulation characteristics and the regional waterlogging volume to determine the corresponding waterlogging distribution information of each waterlogged urban area under the corresponding precipitation intensity data and display it.

[0047] In one practicable manner,

[0048] The step 4 comprises:

[0049] Step 41: using the waterlogging distribution information to establish a number of waterlogging points corresponding to different precipitation intensities in the city to be tested, and counting waterlogging flow information corresponding to each of the waterlogging points;

[0050] Step 42: Draw the dynamic water flow corresponding to each of the urban areas according to the water accumulation points corresponding to each of the precipitation intensities and the water accumulation flow information;

[0051] Step 43: Determine the collective position of water flows in each corresponding urban area according to the dynamic water flow, and generate a precipitation-waterlogging point distribution map of the city to be tested.

[0052] In one practicable manner,

[0053] Also includes:

[0054] The urban drainage model of the city to be tested is updated according to the real-time facility construction information of the city to be tested.

[0055] In one practicable manner,

[0056] Also includes:

[0057] A protection deployment plan corresponding to each precipitation intensity is established and displayed based on the precipitation-waterlogging point distribution map.

[0058] The achievable beneficial effects of the above technical solution are: in order to achieve early prevention and avoid unnecessary troubles caused by waterlogging to the city, first, an urban drainage model of the city to be tested is established based on the facility data and landform data of the city to be tested, and then precipitation data of different intensities are used to train the urban drainage model for precipitation, so as to determine the urban drainage volume and urban waterlogging volume presented by the city under the influence of precipitation of different intensities, thereby analyzing the regional waterlogging volume corresponding to each urban area in the city to be tested and determining the waterlogging distribution information of the city to be tested, thereby analyzing the waterlogging points corresponding to the city to be tested at different precipitation intensities, thereby generating a precipitation-waterlogging point distribution map of the city, so that when it rains in the city to be tested, the waterlogging points of the city to be tested can be found according to the precipitation intensity, which is convenient for relevant personnel to deal with the waterlogging points in time to ensure the normal operation of the city.

[0059] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing 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 and the accompanying drawings.

[0060] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0062] Figure 1 A schematic diagram of the workflow of a method for predicting urban ground waterlogging points based on a large model technology in an embodiment of the present invention;

[0063] Figure 2 This is a schematic diagram of the workflow of step 1 of a method for predicting urban ground waterlogging points based on large model technology in an embodiment of the present invention. DETAILED DESCRIPTION

[0064] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0065] Example 1

[0066] This embodiment provides a method for predicting urban ground waterlogging points based on large model technology. Figure 1 As shown, including:

[0067] Step 1: Collect facility data corresponding to each drainage facility in the city to be tested, and establish an urban drainage model of the city to be tested in combination with the topographic data of the city to be tested;

[0068] Step 2: using each preset precipitation intensity data to perform precipitation training on the urban drainage model, and obtaining the urban drainage volume information and urban water accumulation volume information corresponding to the tested city under different precipitation intensity data;

[0069] Step 3: Analyze the regional waterlogging volume corresponding to each urban area of ​​the city to be tested according to the urban drainage volume information and the urban waterlogging volume information, and determine the waterlogging distribution information of the city to be tested according to the regional waterlogging volume;

[0070] Step 4: Determine a number of waterlogging points corresponding to different precipitation intensities in the city to be tested according to the waterlogging distribution information, and generate a precipitation-waterlogging point distribution map of the city to be tested.

[0071] In this example, drainage facilities include: tube wells, drainage rivers and rainwater collection stations;

[0072] In this example, the topographic data represents the terrain elevation data of the city to be tested;

[0073] In this example, the preset precipitation intensity data refers to data set in advance and used to express precipitation of different intensities;

[0074] In this example, precipitation training refers to the process of simulating the impact of precipitation of different intensities on the city to be tested;

[0075] In this example, the waterlogging distribution information indicates the distribution of waterlogging in the city to be tested;

[0076] In this example, the precipitation-waterlogging point distribution represents the distribution of waterlogging points in the tested city under the action of precipitation of different intensities.

[0077] The working principle and beneficial effects of the above technical solution: In order to achieve early prevention and avoid unnecessary troubles caused by waterlogging to the city, first, an urban drainage model of the city to be tested is established based on the facility data and landform data of the city to be tested, and then the urban drainage model is trained with precipitation data of different intensities, so as to determine the urban drainage volume and urban waterlogging volume of the city under the influence of precipitation of different intensities, thereby analyzing the regional waterlogging volume corresponding to each urban area in the city to be tested and determining the waterlogging distribution information of the city to be tested, thereby analyzing the waterlogging points corresponding to the city to be tested at different precipitation intensities, thereby generating a precipitation-waterlogging point distribution map of the city, so that when it rains in the city to be tested, the waterlogging points of the city to be tested can be found according to the precipitation intensity, which is convenient for relevant personnel to deal with the waterlogging points in time to ensure the normal operation of the city.

[0078] Example 2

[0079] On the basis of Example 1, the method for predicting urban ground waterlogging points based on large model technology further includes:

[0080] When precipitation occurs in the city to be tested, a real-time precipitation distribution map of the city to be tested is established according to the real-time precipitation intensity corresponding to each of the urban areas;

[0081] Searching the precipitation-waterlogging distribution map for high-frequency waterlogging points in each of the urban areas under the corresponding real-time precipitation intensity;

[0082] Using the real-time precipitation distribution map, real-time waterlogging monitoring is performed on each of the high-frequency waterlogging points to obtain a first real-time waterlogging volume corresponding to each of the high-frequency waterlogging points in the city to be tested;

[0083] Sampling waterlogging points in each of the urban areas, and using the real-time precipitation distribution map to perform real-time waterlogging monitoring on each sampled waterlogging point, to obtain a second real-time waterlogging volume corresponding to each sampled waterlogging point in the city to be tested;

[0084] The real-time waterlogging information of the city to be tested is determined and displayed according to the first real-time waterlogging volume corresponding to each of the first high-frequency waterlogging points and the second real-time waterlogging volume corresponding to each of the sampling waterlogging points.

[0085] In this example, the high-frequency waterlogging points refer to the waterlogging points in the tested city under real-time precipitation intensity determined by training the urban drainage model, that is, the waterlogging points that can be queried in the precipitation-waterlogging distribution map;

[0086] In this example, the first real-time water accumulation volume represents the water accumulation volume corresponding to the high-frequency water accumulation point, and the second real-time water accumulation volume represents the water accumulation volume corresponding to the sampling water accumulation point;

[0087] In this example, the number of the sampling water accumulation points is twice the number of the high-frequency water accumulation points, and the sampling water accumulation points do not overlap with the high-frequency water accumulation points.

[0088] The working principle and beneficial effects of the above technical solution are as follows: when precipitation occurs in the city to be tested, several high-frequency waterlogging points in the city are determined according to the precipitation-waterlogging distribution map, and then real-time waterlogging monitoring is carried out on the high-frequency waterlogging points. In order to avoid contingency and improve the monitoring credibility, waterlogging points are sampled in the city to be tested, and then corresponding real-time waterlogging monitoring is also carried out on the sampled waterlogging points. In this way, real-time waterlogging information of the city to be tested can be established based on the real-time waterlogging monitoring results, and not only the high-frequency waterlogging points are analyzed, but also the overall waterlogging situation of the city is analyzed.

[0089] Example 3

[0090] On the basis of Example 2, the method for predicting urban ground waterlogging points based on large model technology further includes:

[0091] According to the real-time waterlogging information, searching for a number of actual waterlogging points in the city to be tested where the real-time waterlogging volume is higher than the standard waterlogging volume;

[0092] Establishing a waterlogging distribution matrix of the city to be tested according to the distribution of the actual waterlogging points;

[0093] Inputting the water accumulation difference between the corresponding real-time water accumulation volume of each actual water accumulation point and the standard water accumulation volume into the water accumulation distribution matrix to obtain the water accumulation information matrix of the city to be tested;

[0094] Performing singular value decomposition on the water accumulation information matrix to obtain dimension reduction data corresponding to each water accumulation difference;

[0095] According to capturing the data trend of the dimension reduction data by using a preset linear regression model, the water accumulation trend corresponding to each actual water accumulation point is obtained;

[0096] According to the water accumulation trend, a corresponding number of security execution personnel are allocated to each actual water accumulation point.

[0097] In this example, the standard water accumulation is less than or equal to 15 mm;

[0098] In this example, the water accumulation distribution matrix represents a matrix established according to the position distribution relationship of actual water accumulation points and used to represent the water accumulation position;

[0099] In this example, the water accumulation trend indicates the trend of changes in the amount of water accumulation at an actual water accumulation point;

[0100] In this example, the dimension-reduced data refers to the data obtained after mapping the water accumulation difference into a low-dimensional space;

[0101] In this example, singular value decomposition represents the process of decomposing the waterlogged information matrix into the product of three matrices;

[0102] In this example, the preset linear regression model represents a mathematical model used to analyze the linear relationship between dimensionality reduction data.

[0103] The working principle and beneficial effects of the above technical solution are as follows: Real-time waterlogging information is used to determine several actual waterlogging points in the city to be tested, and then a matrix is ​​used to analyze the waterlogging trend corresponding to each actual waterlogging point in the city to be tested, so as to assign corresponding security enforcement personnel to the waterlogging points and implement effective dredging and security.

[0104] Example 4

[0105] On the basis of Example 1, the urban ground water point prediction method based on large model technology is as follows: Figure 2 The step 1 shown includes:

[0106] Step 11: Counting a number of drainage facilities included in the city to be tested, respectively obtaining facility specification data corresponding to each drainage facility, respectively obtaining setting location data of each drainage facility in the city to be tested, and constructing facility data corresponding to each drainage facility based on the facility specification data and the setting location data;

[0107] Step 12: Acquire the geomorphic data of the city to be tested, establish the surface undulation information of the city to be tested according to the geomorphic data, determine several water flow directions of the city to be tested according to the undulation information, and establish the drainage range and drainage direction corresponding to each drainage facility according to the facility data;

[0108] Step 13: construct a virtual drainage sub-model corresponding to each drainage facility according to the drainage range and drainage direction corresponding to the same drainage facility, establish a virtual direction sub-model of the city to be tested according to each water flow direction, use the virtual drainage sub-model to analyze the water basin length and self-consumption of accumulated water corresponding to each virtual drainage direction in the virtual direction sub-model, and establish a virtual domain length sub-model of the city to be tested according to the water basin length;

[0109] Step 14: Establish a three-dimensional city image of the city to be tested based on the topographic data, map the virtual drainage sub-model, the virtual direction sub-model and the virtual domain length sub-model into the three-dimensional city image respectively, adjust the mapping result using the self-consumption of accumulated water, and generate an urban drainage model of the city to be tested.

[0110] In this example, the water flow direction represents a number of water flow directions formed due to the influence of the surface undulation on the water flow;

[0111] In this example, the drainage range refers to the working range of the drainage facility, and the drainage direction refers to the direction in which the drainage facility guides water;

[0112] In this example, the water flow length indicates the length of the water flow corresponding to a virtual drainage direction;

[0113] In this example, the self-consumption of accumulated water refers to the consumption of accumulated water under the influence of the external environment.

[0114] The working principle and beneficial effects of the above technical solution are as follows: in order to establish a drainage model that is the same as the actual situation of the city to be tested, firstly, the facility data of the drainage facility is constructed according to the facility specification data corresponding to each drainage facility in the city to be tested and its corresponding setting position, and then the surface undulation information of the city is determined according to the geomorphic data of the city to be tested, thereby determining several water flow directions in the city to be tested, and further combining the facility data to determine the drainage range and drainage direction corresponding to each drainage facility, thereby establishing a virtual drainage sub-model corresponding to the drainage facility, and further establishing a virtual direction sub-model of the city to be tested according to the water flow direction, and adjusting the water basin length and water accumulation self-consumption corresponding to each virtual drainage direction in the virtual direction sub-model through model adjustment training, thereby establishing a virtual domain length sub-model of the city to be tested, in order to beautify the model, a three-dimensional city image of the city to be tested is established according to the geomorphic data, and then the obtained virtual drainage sub-model, virtual direction sub-model and virtual domain length sub-model are all mapped to the three-dimensional city image, and the water accumulation self-consumption measurement mapping result is used to make corresponding adjustments, thereby generating an urban drainage model with the same function as the city to be tested, which serves as a basis for subsequent precipitation training.

[0115] Example 5

[0116] On the basis of Example 1, the method for predicting urban ground waterlogging points based on large model technology, step 2 comprises:

[0117] Step 21: retrieve historical precipitation information of the geographical location of the city to be tested, determine a number of first preset precipitation intensity data according to the historical precipitation information, search for a number of rainstorm disaster precipitation information in big data, determine a number of second preset precipitation intensity data according to the rainstorm disaster precipitation information, and establish a precipitation training database for the city to be tested according to the first precipitation intensity data and the second preset precipitation intensity data;

[0118] Step 22: Use each training data in the precipitation training database to perform time-length iterative cycle precipitation training on the urban drainage model, obtain a number of training results corresponding to each training data, and establish the time-domain drainage information and time-domain waterlogging information corresponding to each training data of the urban drainage model based on the training results;

[0119] Step 23: Determine the training precipitation intensity corresponding to each iteration cycle according to the number of iteration cycles corresponding to each training data to construct a precipitation information axis, and use the precipitation information axis corresponding to the same training data to dynamically analyze the time-domain drainage information and the time-domain waterlogging information to obtain the first drainage volume and the first waterlogging volume corresponding to the city under test at different time-length precipitation intensities;

[0120] Step 24: Establish a number of dynamic precipitation intensity data based on the precipitation training database, use the dynamic precipitation intensity data to perform dynamic precipitation training on the urban drainage model, obtain the second drainage volume and the second water accumulation volume corresponding to the urban drainage model under different dynamic precipitation intensities, establish the urban drainage information of the city to be tested based on the number of the first drainage volumes and the second drainage volumes, and establish the urban water accumulation information of the city to be tested based on the number of the first water accumulation volumes and the second water accumulation volumes.

[0121] In this example, the first preset precipitation intensity data represents data consistent with historical precipitation intensity;

[0122] In this example, the second preset precipitation intensity data represents data consistent with the intensity of a rainstorm disaster when a rainstorm disaster occurs;

[0123] In this example, the duration iteration loop indicates the process of iteratively executing the same training data in a 5-minute unit.

[0124] In this example, the time-domain drainage information represents the drainage volume and drainage efficiency of the city under test when continuous precipitation lasts for different periods of time under the same precipitation intensity;

[0125] In this example, the time-domain water accumulation information represents the water accumulation amount and water accumulation efficiency of the city to be tested when continuous precipitation lasts for different periods of time under the same precipitation intensity;

[0126] In this example, the precipitation information axis represents a time axis about precipitation changes established according to the duration of the iteration cycle;

[0127] In this example, the first displacement represents the displacement of the city to be tested under different continuous precipitation conditions, and each iterative cycle training result corresponds to a first displacement;

[0128] In this example, the first water accumulation volume represents the water accumulation volume corresponding to the city to be tested under different continuous precipitation effects, and each iterative cycle training result corresponds to a first water accumulation volume;

[0129] In this example, dynamic precipitation data refers to precipitation data with dynamic change characteristics established by extracting two or more training data from the precipitation training database;

[0130] In this example, the second drainage volume represents the drainage volume corresponding to different dynamic precipitation intensities of the city to be tested;

[0131] In this example, the second water accumulation volume represents the corresponding water accumulation volume of the tested city under different dynamic precipitation intensities.

[0132] The working principle and beneficial effects of the above technical solution are as follows: in order to analyze various precipitation conditions in advance and to conduct specific analysis based on the actual precipitation in the city to be tested, the precipitation information of the city to be tested is first retrieved, thereby determining a number of first preset precipitation intensity data for the city to be tested. At the same time, in order to take certain precautions against rainstorm disasters, a number of second precipitation intensity data are established based on the rainstorm disaster precipitation information, thereby obtaining a precipitation training database for model training. The training data in the precipitation training database is then used in combination with a time-length iterative cycle to train the urban drainage model, thereby obtaining the time-domain drainage information and time-domain water accumulation information presented by the urban drainage model under different training data. The number of iterative cycles is then used to establish precipitation information axes with the same axis length. The precipitation information axis is used to dynamically analyze the time-domain drainage information and time-domain waterlogging information, and the first drainage volume and the first waterlogging volume corresponding to the city to be tested under the influence of precipitation intensities of different durations are determined. Since the rain intensity may fluctuate when it rains, dynamic precipitation intensity data is established based on the training data in the precipitation training database, so as to conduct dynamic precipitation training on the urban drainage model, thereby obtaining the second drainage volume and the second waterlogging volume of the urban drainage model under different dynamic precipitation intensities. The urban waterlogging information of the city to be tested is established by the above means. The established urban waterlogging information contains the drainage volume and waterlogging volume corresponding to a variety of precipitation conditions, realizing dynamic analysis and long-term analysis, reducing randomness, and enabling the analysis results to be better applied to daily precipitation analysis.

[0133] Example 6

[0134] On the basis of Example 5, the method for predicting urban ground waterlogging points based on large model technology further includes:

[0135] Determine, according to the urban waterlogging information, a number of information points in the city to be tested where the amount of urban waterlogging is greater than the standard amount of waterlogging;

[0136] Determine a training precipitation pattern corresponding to each of the information points based on the urban waterlogging information, and establish a warning trigger tag for the information point based on the training precipitation pattern;

[0137] When the current precipitation pattern of the city to be tested is the same as the training precipitation pattern, the warning trigger tag is activated, and a warning message is generated and displayed.

[0138] The working principle and beneficial effects of the above technical solution are as follows: warning trigger tags are added to several information points in the city to be tested where the amount of water accumulation is greater than the standard amount of water accumulation, so that when the current precipitation pattern of the city to be tested is the same as the training precipitation pattern of the information point, corresponding warning information is generated to remind relevant personnel to respond in time.

[0139] Example 7

[0140] On the basis of Example 1, the method for predicting urban ground waterlogging points based on large model technology, step 3 comprises:

[0141] Step 31: establishing a plurality of drainage flow paths of the city to be tested according to the urban drainage information corresponding to each of the precipitation intensity data, and establishing a plurality of water accumulation flow paths of the city to be tested under the corresponding precipitation intensity data according to the urban water accumulation information;

[0142] Step 32: Divide the city to be tested into a plurality of urban areas according to the urban planning of the city to be tested, respectively obtain first coincidence information between each of the urban areas and different drainage flow paths, and respectively obtain second coincidence information between each of the urban areas and different ponding flow paths;

[0143] Step 33: establishing the regional water accumulation corresponding to the urban area under the corresponding precipitation intensity data according to the first overlap information and the second overlap information, and determining the water flow accumulation characteristics of the corresponding urban area according to the first overlap information and the second overlap information;

[0144] Step 34: Record the urban areas where the regional waterlogging volume is higher than the preset standard waterlogging volume as waterlogged urban areas, and use the water flow accumulation characteristics and the regional waterlogging volume to determine the corresponding waterlogging distribution information of each waterlogged urban area under the corresponding precipitation intensity data and display it.

[0145] The working principle and beneficial effects of the above technical solution: in order to further believe and analyze the waterlogging points and waterlogging amounts in the city to be tested, the drainage flow path of the city is established according to the urban drainage belief corresponding to each precipitation intensity data, thereby determining the waterlogging flow path of the city to be tested under different precipitation intensities, and then constructing the water flow accumulation characteristics of the city area based on the overlapping information between each urban area and the drainage flow path and the waterlogging flow path, further searching for waterlogged urban areas with high waterlogging amounts, and then using the water flow accumulation characteristics and regional waterlogging amounts to determine the waterlogging distribution information corresponding to each of the waterlogged urban areas under the corresponding precipitation intensity data, thereby determining a number of waterlogging points in the city to be tested, and at the same time determining the waterlogging amount corresponding to each waterlogging point, thereby achieving the purpose of early prediction.

[0146] Example 8

[0147] On the basis of Example 1, the method for predicting urban ground waterlogging points based on large model technology, step 4 comprises:

[0148] Step 41: using the waterlogging distribution information to establish a number of waterlogging points corresponding to different precipitation intensities in the city to be tested, and counting waterlogging flow information corresponding to each of the waterlogging points;

[0149] Step 42: Draw the dynamic water flow corresponding to each of the urban areas according to the water accumulation points corresponding to each of the precipitation intensities and the water accumulation flow information;

[0150] Step 43: Determine the collective position of water flows in each corresponding urban area according to the dynamic water flow, and generate a precipitation-waterlogging point distribution map of the city to be tested.

[0151] The working principle and beneficial effects of the above technical solution are as follows: by counting the water accumulation points and water flow information of the city to be tested under different precipitation intensities, the water flow aggregation position of the city to be tested is determined, thereby establishing a water accumulation point distribution map corresponding to the city to be tested under different precipitation intensities.

[0152] Example 9

[0153] On the basis of Example 1, the method for predicting urban ground waterlogging points based on large model technology further includes:

[0154] The urban drainage model of the city to be tested is updated according to the real-time facility construction information of the city to be tested.

[0155] The working principle and beneficial effects of the above technical solution are as follows: when the city to be tested is under construction, the urban drainage model is updated according to the real-time construction information, which reduces the lag of the model analysis results and improves the intelligence of the model.

[0156] Example 10

[0157] On the basis of Example 1, the method for predicting urban ground waterlogging points based on large model technology further includes:

[0158] A protection deployment plan corresponding to each precipitation intensity is established and displayed based on the precipitation-waterlogging point distribution map.

[0159] The working principle and beneficial effects of the above technical solution: by identifying high-risk areas in advance and formulating preventive measures, the property losses caused by waterlogging can be effectively reduced.

[0160] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for predicting urban ground waterlogging points based on large model technology, characterized in that: include: Step 1: Collect facility data corresponding to each drainage facility in the city to be tested, and establish an urban drainage model of the city to be tested in combination with the topographic data of the city to be tested; Step 2: using each preset precipitation intensity data to perform precipitation training on the urban drainage model, and obtaining the urban drainage volume information and urban water accumulation volume information corresponding to the tested city under different precipitation intensity data; Step 3: Analyze the regional waterlogging volume corresponding to each urban area of ​​the city to be tested according to the urban drainage volume information and the urban waterlogging volume information, and determine the waterlogging distribution information of the city to be tested; Step 4: Determine a number of waterlogging points corresponding to different precipitation intensities in the city to be tested according to the waterlogging distribution information, and generate a precipitation-waterlogging point distribution map of the city to be tested.

2. A method for predicting urban ground waterlogging points based on large model technology as claimed in claim 1, characterized in that: Also includes: When precipitation occurs in the city to be tested, a real-time precipitation distribution map of the city to be tested is established according to the real-time precipitation intensity corresponding to each of the urban areas; Searching the precipitation-waterlogging distribution map for high-frequency waterlogging points in each of the urban areas under the corresponding real-time precipitation intensity; Using the real-time precipitation distribution map, real-time waterlogging monitoring is performed on each of the high-frequency waterlogging points to obtain a first real-time waterlogging volume corresponding to each of the high-frequency waterlogging points in the city to be tested; Sampling waterlogging points in each of the urban areas, and using the real-time precipitation distribution map to perform real-time waterlogging monitoring on each sampled waterlogging point, to obtain a second real-time waterlogging volume corresponding to each sampled waterlogging point in the city to be tested; The real-time waterlogging information of the city to be tested is determined and displayed according to the first real-time waterlogging volume corresponding to each of the first high-frequency waterlogging points and the second real-time waterlogging volume corresponding to each of the sampling waterlogging points.

3. A method for predicting urban ground waterlogging points based on large model technology as claimed in claim 2, characterized in that: Also includes: According to the real-time waterlogging information, searching for a number of actual waterlogging points in the city to be tested where the real-time waterlogging volume is higher than the standard waterlogging volume; Establishing a waterlogging distribution matrix of the city to be tested according to the distribution of the actual waterlogging points; Inputting the water accumulation difference between the real-time water accumulation volume corresponding to each of the actual water accumulation points and the standard water accumulation volume into the water accumulation distribution matrix to obtain the water accumulation information matrix of the city to be tested; Performing singular value decomposition on the water accumulation information matrix to obtain dimension reduction data corresponding to each water accumulation difference; According to capturing the data trend of the dimension reduction data by using a preset linear regression model, the water accumulation trend corresponding to each actual water accumulation point is obtained; According to the water accumulation trend, a corresponding number of security execution personnel are allocated to each actual water accumulation point.

4. The method for predicting urban ground waterlogging points based on large model technology according to claim 1, characterized in that: The step 1 comprises: Step 11: Counting a number of drainage facilities included in the city to be tested, respectively obtaining facility specification data corresponding to each drainage facility, respectively obtaining setting location data of each drainage facility in the city to be tested, and constructing facility data corresponding to each drainage facility based on the facility specification data and the setting location data; Step 12: Acquire the geomorphic data of the city to be tested, establish the surface undulation information of the city to be tested according to the geomorphic data, determine several water flow directions of the city to be tested according to the undulation information, and establish the drainage range and drainage direction corresponding to each drainage facility according to the facility data; Step 13: construct a virtual drainage sub-model corresponding to each drainage facility according to the drainage range and drainage direction corresponding to the same drainage facility, establish a virtual direction sub-model of the city to be tested according to each water flow direction, use the virtual drainage sub-model to analyze the water basin length and self-consumption of accumulated water corresponding to each virtual drainage direction in the virtual direction sub-model, and establish a virtual domain length sub-model of the city to be tested according to the water basin length; Step 14: Establish a three-dimensional city image of the city to be tested based on the topographic data, map the virtual drainage sub-model, the virtual direction sub-model and the virtual domain length sub-model into the three-dimensional city image respectively, adjust the mapping result using the self-consumption of accumulated water, and generate an urban drainage model of the city to be tested.

5. The method for predicting urban ground waterlogging points based on large model technology according to claim 1, characterized in that: The step 2 comprises: Step 21: retrieve historical precipitation information of the geographical location of the city to be tested, determine a number of first preset precipitation intensity data according to the historical precipitation information, search for a number of rainstorm disaster precipitation information in big data, determine a number of second preset precipitation intensity data according to the rainstorm disaster precipitation information, and establish a precipitation training database for the city to be tested according to the first precipitation intensity data and the second preset precipitation intensity data; Step 22: Use each training data in the precipitation training database to perform time-length iterative cycle precipitation training on the urban drainage model, obtain a number of training results corresponding to each training data, and establish the time-domain drainage information and time-domain waterlogging information corresponding to each training data of the urban drainage model based on the training results; Step 23: Determine the training precipitation intensity corresponding to each iteration cycle according to the number of iteration cycles corresponding to each training data to construct a precipitation information axis, and use the precipitation information axis corresponding to the same training data to dynamically analyze the time-domain drainage information and the time-domain waterlogging information to obtain the first drainage volume and the first waterlogging volume corresponding to the city under test at different time-length precipitation intensities; Step 24: Establish a number of dynamic precipitation intensity data based on the precipitation training database, use the dynamic precipitation intensity data to perform dynamic precipitation training on the urban drainage model, obtain the second drainage volume and the second water accumulation volume corresponding to the urban drainage model under different dynamic precipitation intensities, establish the urban drainage information of the city to be tested based on the number of the first drainage volumes and the second drainage volumes, and establish the urban water accumulation information of the city to be tested based on the number of the first water accumulation volumes and the second water accumulation volumes.

6. A method for predicting urban ground waterlogging points based on large model technology as claimed in claim 5, characterized in that: Also includes: Determine, according to the urban waterlogging information, a number of information points in the city to be tested where the amount of urban waterlogging is greater than the standard amount of waterlogging; Determine a training precipitation pattern corresponding to each of the information points based on the urban waterlogging information, and establish a warning trigger tag for the information point based on the training precipitation pattern; When the current precipitation pattern of the city to be tested is the same as the training precipitation pattern, the warning trigger tag is activated, and a warning message is generated and displayed.

7. The method for predicting urban ground waterlogging points based on large model technology according to claim 1, characterized in that: The step 3 comprises: Step 31: establishing a plurality of drainage flow paths of the city to be tested according to the urban drainage information corresponding to each of the precipitation intensity data, and establishing a plurality of water accumulation flow paths of the city to be tested under the corresponding precipitation intensity data according to the urban water accumulation information; Step 32: Divide the city to be tested into a plurality of urban areas according to the urban planning of the city to be tested, respectively obtain first coincidence information between each of the urban areas and different drainage flow paths, and respectively obtain second coincidence information between each of the urban areas and different ponding flow paths; Step 33: establishing the regional water accumulation corresponding to the urban area under the corresponding precipitation intensity data according to the first overlap information and the second overlap information, and determining the water flow accumulation characteristics of the corresponding urban area according to the first overlap information and the second overlap information; Step 34: Record the urban areas where the regional waterlogging volume is higher than the preset standard waterlogging volume as waterlogged urban areas, and use the water flow accumulation characteristics and the regional waterlogging volume to determine the corresponding waterlogging distribution information of each waterlogged urban area under the corresponding precipitation intensity data and display it.

8. The method for predicting urban ground waterlogging points based on large model technology as claimed in claim 1, characterized in that: The step 4 comprises: Step 41: using the waterlogging distribution information to establish a number of waterlogging points corresponding to different precipitation intensities in the city to be tested, and counting waterlogging flow information corresponding to each of the waterlogging points; Step 42: Draw the dynamic water flow corresponding to each of the urban areas according to the water accumulation points corresponding to each of the precipitation intensities and the water accumulation flow information; Step 43: Determine the collective position of water flows in each corresponding urban area according to the dynamic water flow, and generate a precipitation-waterlogging point distribution map of the city to be tested.

9. The method for predicting urban ground waterlogging points based on large model technology according to claim 1, characterized in that: Also includes: The urban drainage model of the city to be tested is updated according to the real-time facility construction information of the city to be tested.

10. The method for predicting urban ground waterlogging points based on large model technology according to claim 1, characterized in that: Also includes: A protection deployment plan corresponding to each precipitation intensity is established and displayed based on the precipitation-waterlogging point distribution map.

Images