A smart sponge city construction comprehensive prediction system and prediction method

Abstract

The application relates to the technical field of municipal administration, and discloses a comprehensive prediction system and method for smart sponge city construction; the method comprises the following steps: identifying sponge construction points from comprehensive construction points, drawing sponge areas in a to-be-measured region, collecting sponge construction data of the sponge areas in a sponge cycle, inputting the collected sponge construction data into a trained machine learning model for predicting sponge construction states, predicting the sponge construction states of the to-be-measured region, and formulating the sponge construction grades of the to-be-measured region; compared with the prior art, the application can realize the collection effect of multiple different dimension data in the smart sponge city construction, avoids the limitation caused by the collection of single dimension data, and combines the machine learning model to predict the high and low states of the smart sponge city construction quality, thereby avoiding the inefficiency problem caused by the prediction mode of analyzing and calculating different data one by one, and improving the prediction precision of the smart sponge city construction quality result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of municipal administration, more specifically, the present application relates to a comprehensive prediction system and method for intelligent sponge city construction. BACKGROUND

[0002] As a new generation of urban rainwater management concept, the sponge city aims to enable the city to adapt to environmental changes and cope with natural disasters caused by rainwater, etc. With the continuous development of modern intelligent sponge city construction, more and more sponge facilities are widely used in intelligent sponge city construction. In order to optimize and adjust the facilities of intelligent sponge city construction in the future, it is necessary to predict the quality of intelligent sponge city construction.

[0003] The patent application with publication number CN116681335A discloses a sponge city construction evaluation method, device, computer equipment and storage medium, which comprises: obtaining city construction data and underlying surface data of the to-be-evaluated region, dividing the to-be-evaluated region into several drainage zones based on the city construction data and underlying surface data, determining the city construction data and underlying surface data of each drainage zone, calculating the comprehensive runoff coefficient of the drainage zone based on the city construction data and underlying surface data of the drainage zone, calculating the annual runoff total amount control rate of the drainage zone based on the city construction data, underlying surface data and comprehensive runoff coefficient of the drainage zone, selecting the standard drainage zone that reaches the annual runoff total amount control rate target value based on the annual runoff total amount control rate of the drainage zone, calculating the area ratio of the standard drainage zone area in the to-be-evaluated region, and obtaining the sponge city construction area ratio of the to-be-evaluated region;

[0004] The existing sponge city construction in comprehensive prediction divides the sponge construction region into sub-regions, collects relevant data of single dimension in the sub-region, and integrates and analyzes the collected relevant data after calculating one by one to realize the effect of comprehensive prediction of sponge city construction. For example, in the above-mentioned patent application, the to-be-evaluated region is divided into drainage zones, and the construction data and underlying surface data of the drainage zones are collected, and the collected data is calculated one by one to obtain the sponge city construction area ratio. This comprehensive prediction method of sponge city construction can only collect a large amount of data of the same type in one dimension in the to-be-evaluated region, resulting in the problem of single dimension of the collected data dimension, which limits the prediction result of the sponge city construction, and the way of calculating and analyzing the collected data one by one is also prone to calculation errors, resulting in the problem of low efficiency of the prediction of the sponge city construction, which reduces the accuracy of the comprehensive prediction of the sponge city construction.

[0005] Therefore, the present application provides an intelligent sponge city construction comprehensive prediction system and method to solve the above problems. SUMMARY

[0006] In order to overcome the above-mentioned defects of the prior art, in order to achieve the above-mentioned purposes, the present application provides the following technical scheme: a comprehensive prediction system for smart sponge city construction, comprising:

[0007] A construction point identification module is configured to query the construction attributes of the comprehensive construction points in the to-be-tested area one by one, and identify the sponge construction points from the comprehensive construction points;

[0008] A region division module is configured to collect the point distance of the sponge construction points, calibrate the effective distance, and draw sponge regions in the to-be-tested area based on region drawing criteria, wherein the region drawing criteria are that the adjustment range of all sponge regions is consistent, and there is no overlapping or intersecting region between any two sponge regions;

[0009] A data collection module is configured to construct a sponge cycle and collect sponge construction data of the sponge regions in the sponge cycle, wherein the sponge construction data includes water level rising rate, runoff ratio, total recovery amount, and water accumulation settlement rate;

[0010] A model prediction module is configured to input the collected sponge construction data into a trained machine learning model for predicting the sponge construction state of the to-be-tested area, and determine whether there is an abnormal region in the to-be-tested area;

[0011] A prediction report module is configured to identify the abnormal region from the sponge region and develop a sponge construction level for the to-be-tested area.

[0012] Further, the identification method of the sponge construction point is:

[0013] In the electronic map, mark the positions of all sponge facilities in the to-be-tested area one by one, which are recorded as comprehensive construction points;

[0014] Query the attribute box of all comprehensive construction points one by one through the database, and identify the attribute semantics of the construction attributes in the attribute box one by one through natural language processing technology;

[0015] Record the construction attributes of the attribute semantics of underground water, runoff, utilization, and water accumulation as underground water attribute, runoff attribute, utilization attribute, and water accumulation attribute, and record the comprehensive construction points corresponding to the underground water attribute, runoff attribute, utilization attribute, and water accumulation attribute as sponge construction points.

[0016] Further, the calibration method of the effective distance is:

[0017] On the electronic map, measure the distance between any two sponge construction points one by one through the scale to obtain the point distance;

[0018] All the point spacing is compared one by one, the minimum value of the point spacing is screened out, and one third of the minimum value of the point spacing is recorded as the effective spacing.

[0019] Further, the sponge area includes a water storage area, a pipe diameter area, a recycling area and a water accumulation area.

[0020] The drawing method of the water storage area, the pipe diameter area, the recycling area and the water accumulation area is:

[0021] S2.1: On the electronic map, take the four sponge construction points as the centers of the circles respectively, and draw the circles with the effective spacing as the radius to obtain four initial areas.

[0022] S2.2: Take the preset adjustment amplitude as the adjustment standard, simultaneously increase the radius of the four initial areas, drive the boundary lines of the four initial areas to move outward and expand, and observe whether the boundary lines of any two initial areas exist overlap or intersection.

[0023] S2.3: Repeat S2.2 until the boundary lines of two initial areas exist overlap or intersection, simultaneously stop adjusting the radius of the four initial areas, and record the initial area before the boundary lines of the two initial areas exist overlap or intersection as the drawing area.

[0024] S2.4: Query the boundary coordinates of the four drawing areas one by one through the positioning system, record the area in the to-be-measured region located within the four boundary coordinates as the sponge area, and record the sponge area with the construction properties of the sponge construction points as underground water, runoff, utilization and water accumulation as the water storage area, the pipe diameter area, the recycling area and the water accumulation area respectively.

[0025] Further, the collection method of the water level rising rate is:

[0026] In the sponge period, query the rainfall starting time and the rainfall ending time of B rainfall events in the water storage area one by one through the time stamp, and record the time length between the rainfall starting time and the rainfall ending time as the rainfall time length to obtain B rainfall time lengths.

[0027] Detect the water level height of the underground river of the water storage area at the B rainfall starting time and the B rainfall ending time one by one through the water level sensor to obtain B starting height values and B ending height values.

[0028] Differences are made between the B ending height values and the B starting height values one by one, and the differences are compared with the B rainfall time lengths to obtain B sub-rising rates.

[0029] The expression of the sub-rising rate is:

[0030]

[0031] In the formula, SSzb is the bth sub-rising rate, b = 1, 2, …, B, GD jsb is the bth end height value, GD qsb is the bth start height value, SC jsb is the bth precipitation duration;

[0032] After removing the maximum and minimum values of the sub-rising rates, the remaining B-2 sub-rising rates are accumulated and averaged to obtain the water level rising rate;

[0033] The expression of the water level rising rate is:

[0034]

[0035] In the formula, SS sw is the water level rising rate, SS zc is the Cth sub-rising rate.

[0036] Further, the collection method of the runoff ratio is:

[0037] In the sponge cycle, D non-adjacent monitoring times are marked between the B precipitation start times and the B precipitation end times;

[0038] The flow rates of the water flow in the drainage pipeline in the D monitoring times are detected one by one by the flow rate sensor to obtain D water flow flow rates;

[0039] The cross-sectional area of the drainage pipeline is queried through the technical parameter table, and the cross-sectional area of the drainage pipeline is compared with the average value of the D water flow flow rates to obtain the runoff ratio;

[0040] The expression of the runoff ratio is:

[0041]

[0042] In the formula, JL bz is the runoff ratio, JM mj is the cross-sectional area of the drainage pipeline, SL lsd is the dth water flow flow rate.

[0043] Further, the collection method of the water accumulation settlement rate is:

[0044] The water accumulation depth of the water accumulation in the ground road is detected in real time, and the water accumulation with a water accumulation depth greater than the water accumulation lower limit value is recorded as effective water accumulation;

[0045] In the sponge cycle, the points where the effective water accumulation appears on the ground road are marked one by one to obtain E water accumulation points, and the water accumulation depths of the E water accumulation points are detected one by one to obtain E initial depth values;

[0046] After the preset settlement time, the water depth of the E water accumulation points is detected one by one, and E real-time depth values are obtained;

[0047] The E initial depth values are subtracted from the corresponding E real-time depth values, and the difference is accumulated and averaged to obtain a water accumulation settlement rate;

[0048] The expression of the water accumulation settlement rate is:

[0049]

[0050] In the formula, JS cj is the water accumulation settlement rate, SD cse is the e-th initial depth value, SD sse is the e-th real-time depth value.

[0051] Further, the sponge construction state includes a high construction state and a low construction state;

[0052] The training method of the machine learning model is:

[0053] A plurality of sets of sponge construction data in the high construction state and the low construction state of the to-be-tested region are pre-collected;

[0054] Each set of sponge construction data is marked as a training feature, and the sponge construction state of each set of training features is converted into a digital annotation, the high construction state is converted into 0, and the low construction state is converted into 1;

[0055] The annotated training features are divided into a training set and a test set, the training set is used to train the machine learning model, the test set is used to test the machine learning model, a preset error threshold is set, when the average of the prediction errors of all training features in the test set is less than the error threshold, the machine learning model is obtained.

[0056] The determination method of whether there is an abnormal area is:

[0057] When the output of the machine learning model is 0, the sponge construction state of the to-be-tested region is in the high construction state, and it is determined that there is no abnormal area in the to-be-tested region;

[0058] When the output of the machine learning model is 1, the sponge construction state of the to-be-tested region is in the low construction state, and it is determined that there is an abnormal area in the to-be-tested region.

[0059] Further, the identification method of the abnormal area is:

[0060] The water level rise rate, the runoff ratio, the total recovery amount value, and the water accumulation settlement rate are identified for abnormality, respectively;

[0061] When the water level rise rate is less than the water level calibration value, the water storage area is recorded as an abnormal area;

[0062] When the runoff ratio is greater than the runoff calibration value, the pipe diameter area is recorded as an abnormal area;

[0063] When the total recovery amount value is less than the recovery calibration value, the recovery area is recorded as an abnormal area;

[0064] When the water accumulation settlement rate is less than the water accumulation calibration value, the water accumulation area is recorded as an abnormal area;

[0065] The sponge construction grade includes a first construction grade, a second construction grade and a third construction grade, and the first construction grade, the second construction grade and the third construction grade are formulated in the following method:

[0066] The number of abnormal areas in the to-be-tested area is counted and recorded as an abnormal value;

[0067] When the abnormal value is 0, the first construction grade is formulated;

[0068] When the abnormal value is 1, the second construction grade is formulated;

[0069] When the abnormal value is 2 or 3 or 4, the third construction grade is formulated.

[0070] A kind of wisdom sponge city construction comprehensive prediction method is realized based on the above-mentioned wisdom sponge city construction comprehensive prediction system, comprising:

[0071] S1: the construction attribute of the comprehensive construction point in the to-be-tested area is queried one by one, and the sponge construction point is identified from the comprehensive construction point;

[0072] S2: the point distance of the sponge construction point is collected, the effective distance is calibrated, and the sponge area is drawn in the to-be-tested area based on the area drawing criterion;

[0073] S3: the sponge cycle is constructed, and the sponge construction data of the sponge area in the sponge cycle is collected, the sponge construction data includes water level rising rate, runoff ratio, total recovery amount value and water accumulation settlement rate;

[0074] S4: the collected sponge construction data is input into the trained machine learning model for predicting the sponge construction state, the sponge construction state of the to-be-tested area is predicted, and whether there is an abnormal area in the to-be-tested area is determined;

[0075] S5: if there is an abnormal area, the abnormal area is identified from the sponge area, and the sponge construction grade of the to-be-tested area is formulated.

[0076] The technical effect and advantages of the wisdom sponge city construction comprehensive prediction system and prediction method of the present application are:

[0077] The application can accurately identify the object that can be predicted for the construction of the smart sponge city from numerous and complex comprehensive construction points by querying the construction attributes of the comprehensive construction points in the to-be-tested region one by one and identifying the sponge construction points from the comprehensive construction points, improve the accuracy of subsequent data collection, and draw the sponge region in the to-be-tested region based on the region drawing criteria by collecting the point distance of the sponge construction point and calibrating the effective distance, so as to provide a reasonable time limit for the data collection of the smart sponge city construction prediction, ensure the rationality and accuracy of the collected data in the sponge cycle, and input the collected sponge construction data into the machine learning model trained to predict the sponge construction state, so as to realize the collection effect of multiple different dimension data in the smart sponge city construction, avoid the limitation of collecting single dimension data, and quickly and accurately predict the high and low state of the smart sponge city construction quality by combining the machine learning model, avoid the inefficiency problem caused by the prediction mode of analyzing and calculating different data one by one, improve the prediction accuracy of the smart sponge city construction quality result, and according to the abnormal region, the sponge construction grade of the to-be-tested region is determined, the final prediction result of the smart sponge city construction is reasonably output, and guidance is provided for the further development and optimization of the subsequent smart sponge city construction, and the efficient, accurate and reasonable prediction effect of the smart sponge city construction quality is realized. BRIEF DESCRIPTION OF DRAWINGS

[0078] Figure 1 A module schematic diagram of a smart sponge city construction comprehensive prediction system provided by the embodiment one of the application is provided.

[0079] Figure 2 A flowchart schematic diagram of a smart sponge city construction comprehensive prediction method provided by the embodiment two of the application is provided.

[0080] Figure 3 A structure schematic diagram of an electronic device provided by the embodiment three of the application is provided.

[0081] Figure 4 A structure schematic diagram of a computer readable storage medium provided by the embodiment four of the application is provided. DETAILED DESCRIPTION

[0082] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0083] Embodiment one: please refer to Figure 1As shown, the comprehensive prediction system for intelligent sponge city construction in the embodiment comprises:

[0084] The construction point identification module marks the comprehensive construction points in the region to be measured one by one, queries the construction attributes of the comprehensive construction points, and identifies the sponge construction points from the comprehensive construction points according to the construction attributes;

[0085] The region to be measured refers to the region range in the intelligent sponge city for which the quality of sponge construction needs to be comprehensively predicted, and serves as the corresponding range for subsequent related data collection. The comprehensive construction point refers to the specific point of the position of the sponge construction facility in the region to be measured, so that each comprehensive construction point corresponds to a separate sponge construction facility.

[0086] The construction attribute is used to represent the specific type of the sponge construction facility corresponding to the comprehensive construction point, that is, each different comprehensive construction point can be individually and accurately represented, and serves as the basis for further identification and analysis of the comprehensive construction point.

[0087] The sponge construction point refers to the position of the specific facility of the intelligent sponge city construction in the comprehensive construction point, and serves as the corresponding region for subsequent related data collection. Since the comprehensive construction point contains not only the specific facility of the intelligent sponge city construction, but also other specific facilities that do not belong to the intelligent sponge city construction, the sponge construction point needs to be accurately identified according to the construction attribute of the comprehensive construction point.

[0088] The identification method of the sponge construction point is as follows:

[0089] In the electronic map, mark the positions of all sponge facilities in the region to be measured one by one, which are recorded as comprehensive construction points;

[0090] Query the attribute boxes of all comprehensive construction points one by one through the database, and identify the attribute semantics of the construction attributes in the attribute boxes one by one through natural language processing technology. The attribute box is a content box for the specific facility of the sponge city construction corresponding to the comprehensive construction point, and the construction attribute is the corresponding note of the specific facility of the sponge city construction stored in the attribute box, which serves as the basis for judging the sponge construction point.

[0091] Record the construction attribute with the attribute semantics of underground water as the underground water attribute, and record the comprehensive construction point corresponding to the underground water attribute as the sponge construction point;

[0092] Record the construction attribute with the attribute semantics of runoff as the runoff attribute, and record the comprehensive construction point corresponding to the runoff attribute as the sponge construction point;

[0093] Record the construction attribute with the attribute semantics of utilization as the utilization attribute, and record the comprehensive construction point corresponding to the utilization attribute as the sponge construction point;

[0094] The construction attribute with the attribute semantics of water accumulation is denoted as a water accumulation attribute, and the comprehensive construction point corresponding to the water accumulation attribute is denoted as a sponge construction point.

[0095] It should be noted that the groundwater attribute means that the sponge construction facility corresponding to the comprehensive construction point is to introduce the precipitation in the city into the underground river, the runoff attribute means that the sponge construction facility corresponding to the comprehensive construction point is to introduce the precipitation in the city into the drainage pipe for discharge, the utilization attribute means that the sponge construction facility corresponding to the comprehensive construction point is to treat the precipitation in the city and then reuse it, and the water accumulation attribute means that the sponge construction facility corresponding to the comprehensive construction point is to settle the road water accumulation after the precipitation in the city.

[0096] The region division module collects the point distance of the sponge construction point, calibrates the effective distance, and draws the sponge region in the to-be-tested area based on the region drawing criterion, wherein the sponge region includes a water storage region, a pipe diameter region, a recycling region, and a water accumulation region.

[0097] The point distance refers to the distance between any two sponge construction points, that is, a reference basis for the length of the distance between any two sponge construction points is provided, so that the point distance can be used as a drawing radius basis for subsequent drawing of the sponge region.

[0098] The effective distance refers to the initial drawing radius for drawing the sponge region, so as to ensure that each initial state drawing region can be used as a size adjustment object for the subsequent sponge region, thereby providing a basis for accurate drawing of the sponge region.

[0099] The calibration method of the effective distance is as follows:

[0100] On the electronic map, the distance between any two sponge construction points is measured one by one through the scale to obtain the point distance.

[0101] All the point distances are compared in size one by one, and the minimum value of the point distance is screened out, and one third of the minimum value of the point distance is denoted as the effective distance.

[0102] It should be noted that the size of the effective distance is only used as the drawing radius for the initial drawing of the subsequent sponge region, and is not used as the radius of the final sponge region, so the sponge region initially drawn needs to be adjusted in size.

[0103] The sponge region refers to the region range of the specific sponge construction facility drawn with the sponge construction point as the center point in the to-be-tested area, so that each sponge region only contains one type of sponge construction facility and corresponding data.

[0104] Since each sponge area corresponds to a specific sponge construction facility, any two sponge areas need to be kept independent, and in order to ensure that there is no overlapping area between any two sponge areas, the size of the sponge area needs to be adjusted under the limitation of the area drawing criterion;

[0105] The sponge area includes a water storage area, a pipe diameter area, a recycling area, and a water accumulation area. The water storage area refers to the area where the facilities that drain into underground rivers in sponge city construction are located. The pipe diameter area refers to the area where the drainage pipe diameter facilities in sponge city construction are located. The recycling area refers to the area where the recycling facilities in sponge city construction are located. The water accumulation area refers to the area where the urban road water accumulation position in sponge city construction is located.

[0106] The area drawing criterion is that the adjustment range of all sponge areas is consistent, and there is no overlapping or intersecting area between any two sponge areas. It can ensure that the initially drawn sponge area can maintain the consistency of the adjustment range during subsequent adjustment, and also ensure that any two adjusted sponge areas are independent of each other, thereby ensuring the singularity of the data type in each sponge area and avoiding mutual interference between different types of data.

[0107] The drawing method of the water storage area, the pipe diameter area, the recycling area, and the water accumulation area is:

[0108] S2.1: On the electronic map, draw a circle with the four sponge construction points as the center and the effective distance as the radius to obtain four initial areas.

[0109] S2.2: Increase the radius of the four initial areas by a preset adjustment range as the adjustment standard, drive the boundary lines of the four initial areas to move outward and expand, and observe whether the boundary lines of any two initial areas overlap or intersect. The preset adjustment range is the minimum length unit for increasing the radius of the initial area, which can ensure the synchronization and reasonableness of the initial area radius during the increasing adjustment, and avoid the phenomenon of large and small during the increasing adjustment of the initial area radius. Specifically, the preset adjustment range is usually much smaller than the effective distance. For example, the preset adjustment range is one tenth of the effective distance.

[0110] S2.3: Repeat S2.2 until the boundary lines of two initial areas overlap or intersect, and stop adjusting the radius of the four initial areas at the same time. The initial area before the boundary lines of the two initial areas overlap or intersect is recorded as the drawing area.

[0111] S2.4: The boundary coordinates of the four drawing areas are queried one by one through the positioning system, the area in the to-be-tested region located in the four boundary coordinates is recorded as a sponge area, and the construction attributes of the sponge construction point are recorded as a water storage area, a pipe diameter area, a recycling area and a water accumulation area respectively.

[0112] It should be noted that the identified water storage area, pipe diameter area, recycling area and water accumulation area are used to represent different dimensions and types of sponge city construction data, and meet the relative independence requirement between different dimensions and types of data.

[0113] The data collection module constructs a sponge cycle and collects sponge construction data of the sponge area in the sponge cycle, and the sponge construction data includes water level rising rate, runoff ratio, recycling total value and water accumulation settlement rate.

[0114] Sponge construction data refers to comprehensive data used to represent the quality and achievement of sponge city construction in different sponge areas, that is, it can provide calculation basis for the quality of subsequent sponge city construction. Since the number of sponge construction data corresponding to each sponge area is not unique, in order to ensure the uniqueness and accuracy of sponge construction data, it is necessary to ensure the accuracy and reasonableness of sponge construction data collection in each sponge area within the limit of sponge cycle.

[0115] Since the sponge cycle is used to represent the start time to the end time of the collection time of sponge construction data, when constructing the sponge cycle, the current time is taken as the end time of the cycle, the end time of the last sponge city construction prediction is taken as the start time of the cycle, and the period between the end time of the cycle and the start time of the cycle is recorded as the sponge cycle.

[0116] The sponge construction data includes water level rising rate, runoff ratio, recycling total value and water accumulation settlement rate.

[0117] The water level rising rate refers to the rising rate of the underground water level in the water storage area per unit time, that is, it can represent the construction effect of precipitation drainage in sponge city construction. When the water level rising rate is larger, it means that the construction effect of precipitation drainage in sponge city construction is better.

[0118] The collection method of water level rising rate is as follows:

[0119] In the sponge cycle, the precipitation start time and precipitation end time of B precipitation events in the water storage area are queried one by one through the time stamp, and the time length between the precipitation start time and the precipitation end time is recorded as the precipitation time length, and B precipitation time lengths are obtained. Precipitation event refers to an event that can represent the comprehensive data of precipitation process in the water storage area, thereby providing a basis for the query and calculation of precipitation time.

[0120] The water level height of the underground river in the water storage area at the B rainfall starting time and the B rainfall ending time is detected by the water level sensor one by one, and the B starting height values and the B ending height values are obtained;

[0121] The B ending height values are subtracted from the B starting height values one by one, and the difference values are compared with the B rainfall durations, and the B sub-rising rates are obtained;

[0122] The expression of the sub-rising rate is:

[0123]

[0124] In the formula, SS zb is the bth sub-rising rate, b = 1, 2...B, GD jsb is the bth ending height value, GD qsb is the bth starting height value, SC jsb is the bth rainfall duration;

[0125] The maximum value and the minimum value of the sub-rising rate are removed, the remaining B-2 sub-rising rates are accumulated and averaged, and the water level rising rate is obtained;

[0126] The expression of the water level rising rate is:

[0127]

[0128] In the formula, SS sw is the water level rising rate, SS zc is the Cth sub-rising rate.

[0129] The runoff ratio refers to the ratio of the drainage pipe in the pipe diameter area to the water flow velocity in the pipe, that is, the pipe diameter drainage performance in the construction of the sponge city can be represented, and when the runoff ratio is larger, it means that the pipe diameter drainage performance in the construction of the sponge city is poorer;

[0130] The collection method of the runoff ratio is:

[0131] In the sponge cycle, D non-adjacent monitoring time points are marked at random between the B rainfall starting time and the B rainfall ending time; the non-adjacent monitoring time points can ensure the independence of the data collected at each monitoring time point, thereby avoiding the phenomenon of mutual adhesion between the collected data at the front and rear monitoring time points;

[0132] The flow velocity of the water flow in the drainage pipe in the pipe diameter area at the D monitoring time points is detected by the flow velocity sensor one by one, and D water flow velocities are obtained;

[0133] The cross-sectional area of the drainage pipe is queried through the technical parameter table, and the cross-sectional area of the drainage pipe is compared with the average value of the D water flow velocities, and the runoff ratio is obtained;

[0134] The expression of the runoff ratio is:

[0135]

[0136] In the formula, JL bz is the runoff ratio, JM mj is the cross-sectional area of the drainage pipe, SL lsd is the flow velocity of the dth water flow.

[0137] The total recovery value refers to the total amount of precipitation that is recycled and reused after being collected in the collection area, that is, the performance of precipitation reuse in the construction of a sponge city can be indicated. The greater the total recovery value, the stronger the performance of precipitation reuse in the construction of a sponge city. The total recovery value is obtained by querying the increase in water capacity of the water storage reservoir in the sponge cycle in the collection area.

[0138] The waterlogging settlement rate refers to the settlement rate of waterlogging on the ground road in the waterlogging area per unit time, that is, the performance of road drainage in the construction of a sponge city can be indicated. The greater the waterlogging settlement rate, the stronger the performance of road drainage in the construction of a sponge city.

[0139] The collection method of the waterlogging settlement rate is:

[0140] The waterlogging depth of the waterlogging on the ground road in the waterlogging area is detected in real time, and the waterlogging with a waterlogging depth greater than a waterlogging lower limit value is recorded as effective waterlogging. The waterlogging lower limit value refers to the minimum waterlogging depth on the ground road that will have a negative impact on traffic, thereby providing a basis for comparison for the identification of effective waterlogging.

[0141] In the sponge cycle, the points where effective waterlogging occurs on the ground road are marked one by one to obtain E waterlogging points, and the waterlogging depths of the E waterlogging points are detected one by one to obtain E initial depth values.

[0142] After a preset settlement duration, the waterlogging depths of the E waterlogging points are detected one by one to obtain E real-time depth values. The preset settlement duration refers to the minimum duration when the waterlogging depth of the effective waterlogging changes significantly, that is, it can ensure that the data of the waterlogging depth can be accurately collected after the preset settlement duration.

[0143] The E initial depth values are respectively subtracted from the corresponding E real-time depth values, and the difference values are accumulated and averaged to obtain the waterlogging settlement rate.

[0144] The expression of the waterlogging settlement rate is:

[0145]

[0146] In the formula, JS cj is the waterlogging settlement rate, SD csefor the e-th initial depth value, SD sse for the e-th real-time depth value.

[0147] a model prediction module, which inputs the collected sponge construction data into a trained machine learning model for predicting the sponge construction state of the to-be-tested region, and determines whether there is an abnormal area in the to-be-tested region;

[0148] The machine learning model is an artificial intelligence model for predicting the sponge construction state corresponding to the sponge construction data based on the sponge construction data, so that the machine learning model can predict the sponge construction state corresponding to the sponge construction data, and judge the quality of the sponge city construction of the to-be-tested region through the sponge construction state.

[0149] The sponge construction state includes a high construction state and a low construction state. The high construction state refers to that the quality of the sponge city construction of the to-be-tested region is high, and the low construction state refers to that the quality of the sponge city construction of the to-be-tested region is low. The high construction state and the low construction state are obtained by collecting a large number of sponge construction states corresponding to water level rise rates, runoff ratios, total recovery amounts and water accumulation settlement rates.

[0150] The training method of the machine learning model is as follows:

[0151] a plurality of groups of sponge construction data under the high construction state and the low construction state of the to-be-tested region are collected in advance;

[0152] Each group of sponge construction data is marked as a training feature, and the sponge construction state of each group of training features is labeled. The labeling includes the high construction state and the low construction state, and the high construction state and the low construction state are converted into digital labels respectively. For example, the high construction state is converted into 0, and the low construction state is converted into 1.

[0153] The labeled training features are divided into a training set and a test set. 70% of the training features are used as the training set, and 30% of the training features are used as the test set. The training set is used to train the machine learning model, and the test set is used to test the machine learning model. A preset error threshold is set. When the average prediction error of all training features in the test set is less than the error threshold, the machine learning model is obtained.

[0154] For example, the machine learning model adopts any one of a support vector machine model or a random forest model. The preset error threshold is set according to the actual required accuracy of the machine learning model.

[0155] The abnormal area refers to a sponge area corresponding to specific sponge construction data of a low construction state of a to-be-tested area. The collected sponge construction data is input into the trained machine learning model, so that the sponge construction state corresponding to the sponge construction data can be predicted.

[0156] The determination method of whether there is an abnormal area is:

[0157] When the output of the machine learning model is 0, the sponge construction state of the to-be-tested area is a high construction state, and it is determined that there is no abnormal area in the to-be-tested area;

[0158] When the output of the machine learning model is 1, the sponge construction state of the to-be-tested area is a low construction state, and it is determined that there is an abnormal area in the to-be-tested area.

[0159] The prediction report module identifies the abnormal area from the sponge area, and formulates the sponge construction level of the to-be-tested area according to the abnormal area;

[0160] When it is determined that there is an abnormal area in the to-be-tested area, the sponge area corresponding to the abnormal area needs to be identified, so as to serve as a basis for subsequent analysis of the sponge city construction result;

[0161] The identification method of the abnormal area is:

[0162] The water level rise rate, the runoff ratio, the total recovery amount value and the water accumulation settlement rate are respectively subjected to abnormality identification. The abnormality identification is used to compare the size of the water level rise rate, the runoff ratio, the total recovery amount value and the water accumulation settlement rate to determine whether they are abnormal, thereby laying a foundation for the identification of the abnormal area;

[0163] When the water level rise rate is less than the water level calibration value, it indicates that the water storage area of the to-be-tested area has a low quality phenomenon, and the water storage area is recorded as an abnormal area. The water level calibration value refers to the minimum value of the water level rise rate when the water storage area is not marked as an abnormal area, thereby providing a numerical basis for abnormal identification of the water level rise rate;

[0164] When the runoff ratio is greater than the runoff calibration value, it indicates that the pipe diameter area of the to-be-tested area has a low quality phenomenon, and the pipe diameter area is recorded as an abnormal area. The runoff calibration value refers to the maximum value of the runoff ratio when the pipe diameter area is not marked as an abnormal area, thereby providing a numerical basis for abnormal identification of the runoff ratio;

[0165] When the total recovery amount value is less than the recovery calibration value, it indicates that the recovery area of the to-be-tested area has a low quality phenomenon, and the recovery area is recorded as an abnormal area. The recovery calibration value refers to the minimum value of the total recovery amount value when the recovery area is not marked as an abnormal area, thereby providing a numerical basis for abnormal identification of the total recovery amount value;

[0166] When the water accumulation settlement rate is less than the water accumulation calibration value, it indicates that the water accumulation area of the to-be-tested region has a low quality phenomenon, and the water accumulation area is marked as an abnormal area. The water accumulation calibration value refers to the minimum value of the water accumulation settlement rate when the water accumulation area is not marked as an abnormal area, thereby providing a numerical basis for the abnormal identification of the water accumulation settlement rate.

[0167] The sponge construction level is used to represent the level range corresponding to the quality of the sponge city construction of the to-be-tested region, thereby being able to display the final result of the sponge city construction of the to-be-tested region;

[0168] The sponge construction level includes a first construction level, a second construction level, and a third construction level. Specifically, the sponge city construction quality of the to-be-tested region corresponding to the first construction level is the highest, the sponge city construction quality of the to-be-tested region corresponding to the second construction level is medium, and the sponge city construction quality of the to-be-tested region corresponding to the third construction level is the lowest.

[0169] The method for formulating the first construction level, the second construction level, and the third construction level is as follows:

[0170] The number of abnormal areas in the to-be-tested region is counted and marked as an abnormal value.

[0171] When the abnormal value is 0, the sponge city construction quality of the to-be-tested region is the highest at this time, and the first construction level is formulated.

[0172] When the abnormal value is 1, the sponge city construction quality of the to-be-tested region is medium at this time, and the second construction level is formulated.

[0173] When the abnormal value is 2 or 3 or 4, the sponge city construction quality of the to-be-tested region is low at this time, and the third construction level is formulated.

[0174] In this embodiment, by querying the construction attributes of the comprehensive construction points in the to-be-tested region one by one, and identifying the sponge construction points from the comprehensive construction points, the objects that can be predicted for the smart sponge city construction can be accurately identified from numerous and complex comprehensive construction points, the accuracy of subsequent data collection is improved, the effective distance is calibrated by collecting the point distance of the sponge construction points, and the sponge region is drawn in the to-be-tested region based on the region drawing criteria, which can provide reasonable time limit for the data collection of the smart sponge city construction prediction, ensure the rationality and accuracy of the collected data in the sponge period, and by collecting the sponge construction data of the sponge region in the sponge period, the collected sponge construction data is input into the trained machine learning model for predicting the sponge construction state, so that the collection effect of multiple different dimension data in the smart sponge city construction can be realized, the limitation brought by collecting single dimension data is avoided, and the high and low state of the smart sponge city construction quality can be quickly and accurately predicted by combining the machine learning model, the inefficiency problem brought by the prediction mode of analyzing and calculating different data one by one is avoided, the prediction accuracy of the smart sponge city construction quality result is improved, and the sponge construction grade of the to-be-tested region is formulated according to the abnormal region, so that the final prediction result of the smart sponge city construction can be reasonably output, guidance for further development and optimization of the subsequent smart sponge city construction is provided, and efficient, accurate and reasonable prediction effect of the smart sponge city construction quality is realized.

[0175] Embodiment two: please refer to Figure 2 The embodiment does not describe some parts in detail, please refer to the description of embodiment one, a smart sponge city construction comprehensive prediction method is provided, which is realized based on a smart sponge city construction comprehensive prediction system, comprising:

[0176] S1: query the construction attributes of the comprehensive construction points in the to-be-tested region one by one, and identify the sponge construction points from the comprehensive construction points;

[0177] S2: collect the point distance of the sponge construction points, calibrate the effective distance, and draw the sponge region in the to-be-tested region based on the region drawing criteria;

[0178] S3: construct the sponge period, and collect the sponge construction data of the sponge region in the sponge period, the sponge construction data includes water level rising rate, runoff ratio, total recovery amount and water settlement rate;

[0179] S4: input the collected sponge construction data into the trained machine learning model for predicting the sponge construction state, predict the sponge construction state of the to-be-tested region, and determine whether there is an abnormal region in the to-be-tested region;

[0180] S5: if there is an abnormal region, identify the abnormal region from the sponge region, and formulate the sponge construction grade of the to-be-tested region.

[0181] Embodiment three: please refer to Figure 3 As shown in the embodiment, the embodiment discloses an electronic device, comprising a processor and a memory;

[0182] The memory stores a computer program that can be called by the processor;

[0183] The processor executes the computer program stored in the memory to realize the method.

[0184] Since the electronic device introduced in the embodiment is the electronic device used to implement the method of the embodiment two, the specific implementation of the electronic device and its various changes can be understood by those skilled in the art based on the method of the embodiment. Therefore, the method of the embodiment will not be introduced in detail. As long as the electronic device used to implement the method of the embodiment is implemented by those skilled in the art, it belongs to the scope of protection of the present application.

[0185] Embodiment four: please refer to Figure 4 As shown in the embodiment, the embodiment discloses a computer readable storage medium, which stores a computer program that can be erased;

[0186] When the computer program is run, the method is realized.

[0187] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited to this. Any skilled person in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A comprehensive prediction system for smart sponge city construction, characterized in that, The method comprises the following steps: A construction point identification module is used to query the construction attributes of the comprehensive construction points in the area to be tested one by one, and sponge construction points are identified from the comprehensive construction points; The identification method of the sponge construction point is as follows: In the electronic map, the positions of all sponge facilities in the area to be tested are marked one by one as comprehensive construction points; The attribute boxes of all the comprehensive construction points are queried from the database one by one, and the attribute semantics of the construction attributes in the attribute boxes are identified one by one through natural language processing technology; The construction attributes with the attribute semantics of underground water, runoff, utilization and water accumulation are recorded as underground water attributes, runoff attributes, utilization attributes and water accumulation attributes, and the comprehensive construction points corresponding to the underground water attributes, runoff attributes, utilization attributes and water accumulation attributes are recorded as sponge construction points; A region division module is used to collect the point distance of the sponge construction points, to calibrate the effective distance, and to draw sponge regions in the area to be tested based on region drawing criteria, wherein the region drawing criteria are that the adjustment range of all sponge regions is consistent, and there is no overlapping or intersecting region between any two sponge regions; A data collection module is used to construct a sponge cycle and to collect sponge construction data of the sponge regions in the sponge cycle, wherein the sponge construction data includes water level rising rate, runoff ratio, total recovery amount and water accumulation settlement rate; A model prediction module is used to input the collected sponge construction data into a trained machine learning model for predicting the sponge construction state of the area to be tested, and to determine whether there is an abnormal region in the area to be tested; A prediction report module is used to identify the abnormal region from the sponge regions and to develop a sponge construction grade for the area to be tested. 2.The intelligent sponge city construction comprehensive prediction system according to claim 1, characterized in that, The calibration method of the effective distance is as follows: In the electronic map, the distance between any two sponge construction points is measured one by one through the scale to obtain the point distance; All the point distances are compared one by one to screen out the minimum value of the point distance, and one third of the minimum value of the point distance is recorded as the effective distance. 3.The comprehensive prediction system for intelligent sponge city construction according to claim 2, characterized in that, The sponge region includes a water storage region, a pipe diameter region, a recovery region and a water accumulation region; The drawing method of the water storage region, the pipe diameter region, the recovery region and the water accumulation region is as follows: S2.1: In the electronic map, four initial regions are obtained by taking four sponge construction points as centers and the effective distance as radii; S2.2: The radii of the four initial regions are increased simultaneously as the adjustment standard of the preset adjustment range, the boundary lines of the four initial regions are driven to move outward and expand, and whether the boundary lines of any two initial regions overlap or intersect is observed; S2.3: S2.2 is repeatedly executed until the boundary lines of two initial regions overlap or intersect, at which time the radii of the four initial regions are stopped adjusting, and the initial regions before the boundary lines of the two initial regions overlap or intersect are recorded as drawing regions; S2.4: The boundary coordinates of the four drawing regions are queried one by one through the positioning system, the regions in the area to be tested located within the four boundary coordinates are recorded as sponge regions, and the sponge regions with the construction attributes of underground water, runoff, utilization and water accumulation of the sponge construction points are recorded as water storage regions, pipe diameter regions, recovery regions and water accumulation regions respectively. 4.The comprehensive prediction system for intelligent sponge city construction according to claim 3, characterized in that, The collection method of the water level rising rate is: In the sponge cycle, the starting time and the ending time of the B rainfall events in the water storage area are queried one by one through the time stamp, and the time length between the starting time and the ending time of the rainfall is recorded as the rainfall time length, to obtain B rainfall time lengths; The water level heights of the underground rivers in the water storage area at the B starting times and the B ending times of the rainfall are detected one by one through the water level sensor, to obtain B starting height values and B ending height values; The B ending height values are subtracted from the B starting height values one by one, and the difference values are compared with the B rainfall time lengths, to obtain B sub-rising rates; The expression of the sub-rising rate is: ； In the formula, is the first is the first is the first is the first is the first is the first is the first is the first is the first The maximum and minimum of the sub-rates are removed, the remaining sub-rates are accumulated and averaged to obtain the water level rising rate. The maximum and minimum of the sub-rates are removed, the remaining sub-rates are accumulated and averaged to obtain the water level rising rate. The expression of the water level rising rate is: ； In the formula, is the water level rise rate, is the first sub-rising rate. 5.The comprehensive prediction system for intelligent sponge city construction according to claim 4, characterized in that, The collection method of the runoff ratio is: In the sponge cycle, randomly mark out non-adjacent monitoring instants between the B precipitation start instants and the B precipitation end instants. The flow rate of water in the drainage pipe in the pipe diameter region is detected one by one by the flow rate sensor at a monitoring moment to obtain the flow rate of water flow. flow rate.​ The cross-sectional area of ​​the drainage pipe was obtained from the technical parameter table, and then compared with... The runoff ratio is obtained by comparing the average values ​​of the individual water flow velocities. The expression of the runoff ratio is: ； wherein is the runoff ratio, is the cross-sectional area of the drain pipe, is the first water flow velocity. 6.The comprehensive prediction system for intelligent sponge city construction according to claim 5, characterized in that, The collection method of the waterlogging settlement rate is: The waterlogging depth of the ground road in the waterlogging area is detected in real time, and the waterlogging with the waterlogging depth greater than the waterlogging lower limit value is recorded as effective waterlogging; In the sponge cycle, mark the point of effective water on the ground road one by one, obtain Water point, and detect the water depth of Water point one by one, obtain Initial depth value; After a preset settlement time, the water depth of each water accumulation point is detected one by one, and real-time depth values are obtained. After a preset settlement time, the water depth of each water accumulation point is detected one by one, and real-time depth values are obtained. After a preset settlement time, the water depth of each water accumulation point is detected one by one, and real-time depth Will Each initial depth value is respectively associated with the corresponding The difference between each real-time depth value is calculated, and the average of the sums of the differences is obtained to get the water accumulation settlement rate. The expression of the waterlogging settlement rate is: ； wherein is the water accumulation settlement rate, is the first initial depth value, is the first real-time depth value.

7. The comprehensive prediction system for smart sponge city construction according to claim 6, characterized in that, The sponge construction state includes a high construction state and a low construction state; The training method of the machine learning model is: A plurality of sets of sponge construction data under the high construction state and the low construction state of the to-be-tested area are collected in advance; Each set of sponge construction data is marked as a training feature, and the sponge construction state of each set of training feature is converted into a digital annotation, the high construction state is converted into 0, and the low construction state is converted into 1; The marked training features are divided into a training set and a test set, the machine learning model is trained using the training set, and the machine learning model is tested using the test set, a preset error threshold is set, when the mean value of the prediction errors of all training features in the test set is less than the error threshold, the machine learning model is obtained; The determination method of whether there is an abnormal area is: When the output of the machine learning model is 0, the sponge construction state of the to-be-tested area is the high construction state, and it is determined that there is no abnormal area in the to-be-tested area; When the output of the machine learning model is 1, the sponge construction state of the to-be-tested area is the low construction state, and it is determined that there is an abnormal area in the to-be-tested area. 8.The comprehensive prediction system for intelligent sponge city construction according to claim 7, characterized in that, The identification method of the abnormal area is: The abnormality of the water level rising rate, the runoff ratio, the total recovery amount value, and the waterlogging settlement rate is identified respectively; When the water level rising rate is less than the water level calibration value, the water storage area is recorded as an abnormal area; When the runoff ratio is greater than the runoff calibration value, the pipe diameter area is recorded as an abnormal area; When the total recovery amount value is less than the recovery calibration value, the recovery area is recorded as an abnormal area; When the waterlogging settlement rate is less than the waterlogging calibration value, the waterlogging area is recorded as an abnormal area; The development method of the sponge construction grade includes a first construction grade, a second construction grade, and a third construction grade, and the development method of the first construction grade, the second construction grade, and the third construction grade is: The number of abnormal areas in the to-be-tested area is counted and recorded as an abnormal value; When the abnormal value is 0, the first construction grade is developed; When the abnormal value is 1, the second construction grade is developed; When the abnormal value is 2 or 3 or 4, the third construction grade is developed.

9. A comprehensive prediction method for smart sponge city construction, realized based on the comprehensive prediction system for smart sponge city construction according to any one of claims 1-8, characterized in that, It includes: S1: The construction attributes of the comprehensive construction points in the to-be-tested area are queried one by one, and the sponge construction points are identified from the comprehensive construction points; S2: Collect the distance between the sponge construction points, calibrate the effective distance, and based on the regional drawing criteria, draw the sponge area in the area to be tested; S3: Construct the sponge cycle and collect the sponge construction data of the sponge area in the sponge cycle, including the water level rise rate, runoff ratio, total recovery amount value and water settlement rate; S4: Input the collected sponge construction data into the trained machine learning model for predicting the sponge construction state, predict the sponge construction state of the area to be tested, and determine whether there is an abnormal area in the area to be tested; S5: If there is an abnormal area, identify the abnormal area from the sponge area and develop the sponge construction level of the area to be tested.

Images