Water conservancy project construction management process optimization system based on big data

Abstract

The invention discloses a water conservancy project construction management process optimization system based on big data, and relates to the technical field of construction management processes, the water conservancy project construction management process optimization system comprises a water area division module and a water area management and control module, dividing a monitoring point group and a water area; then collecting river channel data and disaster situation data of a water area, dividing a secondary area, and determining the relevancy between a core monitoring point and the area; the water area management and control module collects spatial data and time-varying data of a secondary area, calculates and identifies an abnormal area, a fault area and a hidden danger area, performs real-time inspection on a main abnormal time area, performs high-frequency inspection on a time fault area, and performs time-period inspection on a time hidden danger area. Through fine division of the water area and two-dimensional precise control of space and time, pertinence and efficiency of water conservancy project construction management are improved, and risk prevention and control capability is enhanced.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of construction management processes, and in particular to a water conservancy project construction management process optimization system based on big data. BACKGROUND

[0002] As an important part of national infrastructure construction, water conservancy projects play a key role in economic development, rational use of water resources, and flood control and drought resistance, and therefore a water conservancy project construction management process optimization system based on big data is needed.

[0003] The prior art, namely the patent application with the announcement number CN111047072B, discloses a water system planning method for the middle and lower reaches of the Yangtze River based on the low-impact development theory, which belongs to the field of water conservancy planning and landscape ecology. The method uses a surface runoff overland flow model to extract a digital water system map of the target region, and through field investigation, the digital water system map is verified and modified, and finally a water system status map is drawn. The method optimizes the layout of the existing water system in accordance with the principles of "respecting the natural water system, following the river path, digging large and filling small, making the river straight and the bend small, bending along the bend, and increasing the dimension of the river network", and checks the river curvature after planning. The design cross-section elements ensure the flood control and drainage flow, and the regulation and storage lakes are reasonably arranged to ensure that the water surface rate is within a reasonable range. The application introduces the low-impact development theory to scientifically optimize the layout of the water system in the middle and lower reaches of the Yangtze River, effectively alleviates the phenomenon of "fighting for land with water" and poor river-lake connectivity in the process of urban construction in recent years, improves the flood control and drainage capacity of the city, and provides a reference for urban water system planning.

[0004] In view of the above scheme, the following technical problems exist: 1. The above scheme relies on the surface runoff overland flow model to extract the digital river network, although it combines field investigation and verification, the data collection dimension is relatively single, and only focuses on basic geographic information such as terrain and river network form, lacking systematic monitoring of key engineering parameters such as river channel silt thickness, dam distribution density and equipment operation state. Data updating mainly relies on periodic manual field investigation, and it is difficult to realize real-time dynamic updating, and it is difficult to capture the dynamic changes of the water system under the influence of climate change and human activities in time. At the same time, the data processing method mainly relies on model calculation and manual checking, lacking the fusion analysis ability of multi-source heterogeneous data, and it is difficult to correlate and integrate hydrological data, disaster data and engineering data, resulting in obvious short boards in the data sources for planning and decision-making.

[0005] 2. The core decision-making basis of the above scheme is historical hydrological data and fixed empirical formulas, such as using isoline maps to deduce design storms and using inference formulas to calculate peak flow. These static calculation methods are insufficient to cope with the real-world challenges of frequent extreme weather events. The calculation of flood control and drainage flows during the planning process is based on fixed design standards, lacking dynamic prediction of changes in hydrological extremes, making it impossible to identify potential risks in advance, and only able to passively respond to floods that have already occurred. Furthermore, this method does not establish an effective risk classification and precise response mechanism, and insufficiently identifies risk differences in different regions, resulting in a lack of targeted planning and difficulty in achieving early warning and efficient risk management.

[0006] 3. While the aforementioned plan emphasizes respecting natural waterways in its optimized water system layout, its regional division method is rather crude and lacks a data-driven, refined zoning and management system. The planning process does not adequately consider the differentiated functions of water areas and fails to combine river data with disaster data for precise delineation of secondary zones at different risk levels. This results in an irrational allocation of resources, potentially leading to insufficient protection investment in high-risk areas and over-construction in low-risk areas. Furthermore, its overall planning of waterfront spaces, road networks, and green belts remains at the macro-level, lacking dynamic optimization methods for the comprehensive utilization of spatial resources, making it difficult to maximize the synergy of ecological, economic, and social benefits. Summary of the Invention

[0007] To address the aforementioned technical shortcomings, the present invention aims to provide a big data-based optimization system for water conservancy project construction management processes.

[0008] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: The present invention provides a water conservancy project construction management process optimization system based on big data, including the following modules: a water area division module, used to collect topographic data and water system connectivity data of each water area monitoring point, perform similarity fitting analysis on the topographic data and water system connectivity data of each water area monitoring point to obtain a group of monitoring points for each water area, and then divide the water area into various water areas, collect river data and disaster data of each water area, perform correlation analysis on the river data and disaster data of each water area to obtain the sub-areas of each water area.

[0009] The water area management module is used to collect spatial data of each sub-area of ​​each water area, analyze the spatial data of each sub-area of ​​each water area to carry out basic water area management, and collect time-varying data of each sub-area of ​​each water area, analyze the time-varying data of each sub-area of ​​each water area to carry out advanced water area management.

[0010] Preferably, the target water area monitoring point is set to obtain each water area monitoring point group, and the specific obtaining method is as follows: the target water area monitoring point is set, the target water area monitoring point and each type of regional state data of each water area monitoring point are normalized, and the weighted Euclidean distance method is used to calculate the similarity to obtain the regional state similarity of the target water area monitoring point and each water area monitoring point group.

[0011] With the target monitoring point as the core, the adjacent monitoring points with the regional state similarity greater than the regional state similarity threshold value are classified into the same class to form the initial monitoring point group of the target monitoring point, and then each water area monitoring point group is obtained.

[0012] Preferably, the spatial data of each secondary region of each water area region is analyzed, and the specific analysis process is as follows: the spatial data of each secondary region of each water area region includes the river channel deposition thickness average value, the terrain slope arithmetic average value and the emergency material reserve point coverage density of each secondary region of each water area region, and each type of spatial data normalization value of each secondary region of each water area region is obtained after normalization.

[0013] The weighted calculation is performed on each type of spatial data normalization value of each secondary region of each water area region to obtain the abnormal space index of each secondary region of each water area region, the abnormal space index of each secondary region of each water area region is arranged in descending order of the abnormal space index, the abnormal space sequence of each secondary region of each water area region is obtained, the first secondary region of the abnormal space sequence of each secondary region of each water area region is recorded as the main abnormal space region, and each secondary abnormal space region is recorded in the front of the preset number of each secondary region.

[0014] The distance from each secondary region of each water area region to the main abnormal space region is obtained from the database, the sequence number difference value corresponding to each distance is set to obtain the sequence number difference value of each secondary region of each secondary region of the water area region, the preset space sequence number of the main abnormal space region is added to the sequence number difference value of each secondary region of each secondary region of the water area region to obtain the space sequence number of each secondary region of each secondary region of the water area region.

[0015] Preferably, the spatial data of each secondary region of each water area region is analyzed, and the specific analysis process is as follows: according to the correlation degree of each secondary region of the main abnormal space region of each water area region, the correlation sequence number of each secondary region of each secondary region is set, the water regime sequence number of the main abnormal space region of each water area region is preset, and then the state sequence number difference value of each secondary region of each water area region is obtained according to the state sequence number difference value corresponding to each correlation degree. The water regime sequence number of the main abnormal space region of each water area region is added to the state sequence number difference value of each secondary region of each water area region to obtain the state sequence number of each secondary region of each water area region.

[0016] The state sequence number and the space sequence number of each secondary region of each water area region are subjected to Euclidean distance calculation with the preset water regime sequence number and the preset space sequence number of the corresponding main abnormal space region, to obtain the Euclidean distance of each water area region, and each secondary abnormal space region with a Euclidean distance lower than a preset Euclidean distance in each water area region is recorded as each space failure region, and each normal space region with a Euclidean distance lower than a preset Euclidean distance in each water area region is recorded as each space hidden danger region.

[0017] The main abnormal space region of each water area region is constructed first, and then the space hidden danger region of each water area region is constructed, the space hidden danger region of each water area region is sorted in order from small to large according to the Euclidean distance, to obtain the construction order of the space failure region of each water area region, and finally the space hidden danger region of each water area region is constructed.

[0018] The beneficial effects of the present application are: 1. The present application collects multi-dimensional data such as terrain, water system connection, river channel and disaster situation, combines with precise algorithms such as normalization processing, weighted Euclidean distance method and cosine similarity analysis, breaks through the limitations of single data dimension and lag processing in traditional water conservancy planning, and has the fusion analysis ability of multi-source heterogeneous data, which not only realizes the accurate division of water area region and secondary region, but also effectively avoids the planning errors caused by incomplete data and judgment deviation, greatly improves the scientificity and foresight of water conservancy engineering decision.

[0019] 2. The present application accurately identifies the main abnormal region, the space failure region and the hidden danger region through the technical means of abnormal space index calculation and core monitoring point positioning, forms a three-level management and control system of region, secondary region and core monitoring point, based on the system, focuses on the construction and prevention and control investment of high-risk areas, avoids excessive construction in low-risk areas, ensures the protection strength of key areas, reduces resource waste, maximizes the governance efficiency of limited manpower, material resources and financial resources, and further improves the comprehensive utilization efficiency of waterfront space, road network and green belt.

[0020] 3. The present application can accurately identify abnormal conditions in time dimension such as equipment failure, hydrological extreme value and disaster response delay for real-time monitoring and analysis of time-varying data, establish a hierarchical inspection mechanism of real-time inspection, high-frequency inspection and periodical inspection, the present application can predict potential risks in advance, realize the transformation from post-disposal to pre-warning and in-process control, effectively shorten the disaster response time, reduce personnel casualties and economic losses caused by flood disasters, and greatly improve the risk resistance of water conservancy projects. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to make the technical solutions in the embodiments of the present application or the prior art clearer, the accompanying drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description only aim to some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative effort.

[0022] Figure 1 The figure is a schematic diagram of the system structure of the present application. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of the present application.

[0024] According to Figure 1 As shown in the figure, the present application provides a water conservancy project construction management process optimization system based on big data, comprising the following modules: water area division module, water area management and control module and database.

[0025] The water area division module is connected with the water area management and control module, and the water area division module and the water area management and control module are both connected with the database.

[0026] The water area division module is used to collect topographic data and water system connectivity data of each water monitoring point, perform similarity fitting analysis on the topographic data and water system connectivity data of each water monitoring point, obtain each water monitoring point group, and then divide the water area into each water area region, collect river data and disaster data of each water area region, and perform correlation degree analysis on the river data and disaster data of each water area region to obtain each secondary region of each water area region.

[0027] In one specific embodiment, the collection of topographic data and water system connectivity data of each water monitoring point is specifically as follows: the topographic data of each water monitoring point includes average elevation, terrain index, slope and slope direction of each water monitoring point, and the water system connectivity data includes river network fractal dimension, river density, concentration ratio and water system connectivity, the average elevation, slope and slope direction are collected by unmanned aerial vehicle aerial survey, the unit width catchment area and slope tangent value are collected by unmanned aerial vehicle aerial survey, the unit width catchment area is divided by the slope tangent value, the natural logarithm of the ratio is taken to obtain the terrain index.

[0028] The river density is obtained by collecting the total length of all river channels in the window by the unmanned aerial vehicle, dividing the total length by the window area, and taking each monitoring point as a preset area analysis window. The confluence ratio is obtained by collecting the confluence of the sub-basin where the monitoring point is located and the total confluence of the corresponding upper basin, and the ratio of the confluence of the sub-basin where the monitoring point is located to the total confluence of the upper basin. The river network fractal dimension is calculated by the box dimension method, covering the river network with square grids of different sizes, counting the number of grids intersecting the river channel, and taking the size and the number of grids intersecting the river channel as double logarithm. The slope is calculated by linear regression, and the river network fractal dimension is recorded as the slope. The river channel is set as an edge, the river intersection point is set as a node, and the obstacle point such as the dam is set as an impedance node. The water system connectivity is obtained by dividing the length of the uninterrupted river channel by the total length of the river channel.

[0029] In one specific embodiment, the topographic data and water system connectivity data of each water area monitoring point are analyzed for similarity fitting. The specific analysis process is as follows: The topographic data of each water area monitoring point, including the average elevation, terrain index, slope, slope direction, river network fractal dimension, river density, confluence ratio, and water system connectivity of each water area monitoring point, are normalized to obtain the average elevation, terrain index, slope, slope direction, river network fractal dimension, river density, confluence ratio, and water system connectivity of each water area monitoring point. The normalized values are recorded as the normalized values of each type of regional state data of each water area monitoring point.

[0030] In one specific embodiment, the water area monitoring point group is obtained as follows: The target water area monitoring point is set, and the target water area monitoring point and the normalized values of each type of regional state data of each water area monitoring point are substituted into the weighted Euclidean distance method to calculate the similarity, and the regional state similarity of the target water area monitoring point and each water area monitoring point group is obtained.

[0031] Taking the target monitoring point as the core, the adjacent monitoring points with a regional state similarity greater than the regional state similarity threshold value are classified into the same class to form the initial monitoring point group of the target monitoring point, and then the water area monitoring point group is obtained.

[0032] In one specific embodiment, the water area is divided into water area regions as follows: For each monitoring point group, the spatial circumscribed polygon of each monitoring point group is extracted using image recognition technology, and the spatial circumscribed polygons of each monitoring point group are image fused to obtain each water area region.

[0033] In one specific embodiment, the river data and disaster data of each water area region are collected as follows: The river data of each water area region includes the cross-section flow, river silt thickness, and dam distribution density of each water area monitoring point of each water area region. The disaster data of each water area region includes the disaster-affected area proportion, disaster impact duration, and emergency disposal cost of each water area monitoring point of each water area region.

[0034] The cross-section flow is collected by a Doppler flowmeter, the river channel deposition thickness is collected by an ultrasonic depth finder, the sluice and dam amount in the preset area of the water area monitoring point is obtained through the construction record, the sluice and dam amount is divided by the preset area to obtain the sluice and dam distribution density.

[0035] The disaster area ratio is obtained by dividing the disaster area by the coverage area, the disaster starting timestamp and the disaster ending timestamp in the coverage range of each water area monitoring point are obtained from the historical disaster record, and then the disaster influence duration is collected, and the emergency disposal cost is obtained from the historical disaster record.

[0036] In one specific embodiment, the river channel data and disaster data of each water area region are analyzed, and the specific analysis process is as follows: selecting a target water area monitoring point of a target water area region, calculating the cosine similarity of the target water area monitoring point of the target water area region and the cross-section flow, the river channel deposition thickness, the sluice and dam distribution density, the disaster area ratio, the disaster influence duration and the emergency disposal cost corresponding to each historical disaster, obtaining the cosine similarity of the target water area monitoring point of the target water area region and the corresponding each water area monitoring point.

[0037] In one specific embodiment, each secondary region of each water area region is obtained, and the specific acquisition process is as follows: taking the target water area monitoring point of the target water area region as the core, the adjacent monitoring points with a cosine similarity greater than a cosine similarity threshold are classified into the same class to form an advanced monitoring point group of the target monitoring point of the target water area region, and then each advanced monitoring point group of each water area region is obtained.

[0038] The spatial circumscribed polygon of each advanced monitoring point group of each water area region is extracted by using image recognition technology, and the spatial circumscribed polygon of each advanced monitoring point group of each water area region is image fused to obtain each secondary region of each water area region.

[0039] The monitoring point with the maximum region state similarity in each secondary region of each water area region is recorded as a core monitoring point, the cosine similarity of the core monitoring point of each secondary region of each water area region and each water area monitoring point of each other secondary region is obtained, and the correlation degree of each secondary region of each water area region and each other secondary region is obtained by mean calculation.

[0040] The water area region management and control module is used to collect the spatial data of each secondary region of each water area region, analyze the spatial data of each secondary region of each water area region, perform water area region basic management and control, collect the time-varying data of each secondary region of each water area region, analyze the time-varying data of each secondary region of each water area region, and perform water area region advanced management and control.

[0041] In one specific embodiment, the spatial data of each sub-region of each water area region is collected, and the collection process is as follows: the spatial data of each sub-region of each water area region includes the average river channel silt thickness, the arithmetic average of the terrain slope, and the emergency material reserve point coverage density of each sub-region of each water area region. The height difference between the silt surface and the water bottom is measured by a measuring rod to measure the silt thickness of each measuring point. The average river channel silt thickness is calculated. The vertical change and the horizontal distance are collected by a level, and the slope is obtained by dividing the vertical change by the horizontal distance. The slope of each measuring point is obtained. The arithmetic average of the terrain slope is calculated. The number of reserve points is obtained by collecting the geographic coordinates of the reserve points. The number of reserve points is divided by the area of the region to obtain the emergency material reserve point coverage density.

[0042] In one specific embodiment, the spatial data of each sub-region of each water area region is analyzed, and the analysis process is as follows: the spatial data of each sub-region of each water area region includes the average river channel silt thickness, the arithmetic average of the terrain slope, and the emergency material reserve point coverage density of each sub-region of each water area region. After normalization, the normalized values of various types of spatial data of each sub-region of each water area region are obtained.

[0043] The normalized values of various types of spatial data of each sub-region of each water area region are weighted and calculated to obtain the abnormal spatial index of each sub-region of each water area region. The abnormal spatial index of each sub-region of each water area region is arranged in descending order of the abnormal spatial index to obtain the abnormal spatial sequence of each sub-region of each water area region. The first sub-region of the abnormal spatial sequence of each sub-region of each water area region is recorded as the main abnormal spatial region. The first predetermined number of sub-regions of the abnormal spatial sequence of each sub-region of each water area region is recorded as each minor abnormal spatial region.

[0044] The distance from each sub-region of each water area region to the main abnormal spatial region is obtained from the database to set the sequence number difference value corresponding to each distance to obtain the sequence number difference value of each sub-region of each water area region. According to the preset spatial sequence number of the main abnormal spatial region, the preset spatial sequence number of the main abnormal spatial region is added to the sequence number difference value of each sub-region of each water area region to obtain the spatial sequence number of each sub-region of each water area region.

[0045] In one embodiment, the spatial data of each sub-region of each water area region is analyzed, and the specific analysis process is as follows: according to the correlation degree of each sub-region of the main abnormal spatial region of each water area region, the correlation serial number of each sub-region of each sub-region is set, the water regime serial number of the main abnormal spatial region of each water area region is preset, then the state serial number difference value of each sub-region of each water area region is obtained according to the state serial number difference value corresponding to each correlation degree, and the state serial number of each sub-region of each water area region is obtained by adding the water regime serial number of the main abnormal spatial region of each water area region to the state serial number difference value of each sub-region of each water area region.

[0046] The state serial number and the spatial serial number of each sub-region of each water area region are calculated by Euclidean distance with the preset water regime serial number and the preset spatial serial number of the corresponding main abnormal spatial region, to obtain the Euclidean distance of each water area region, and each secondary abnormal spatial region with a Euclidean distance lower than a preset Euclidean distance in each water area region is recorded as each spatial failure region, and each normal spatial region with a Euclidean distance lower than a preset Euclidean distance in each water area region is recorded as each spatial hidden danger region.

[0047] The main abnormal spatial region of each water area region is constructed first, and then the spatial hidden danger region of each water area region is constructed, the spatial hidden danger region of each water area region is sorted in order from small to large according to the Euclidean distance, to obtain the construction order of the spatial failure region of each water area region, and finally the spatial hidden danger region of each water area region is constructed.

[0048] In one embodiment, the time-varying data of each sub-region of each water area region is collected, and the specific collection process is as follows: the time-varying data of each sub-region of each water area region includes the equipment failure occurrence frequency, the hydrological extreme value occurrence time length, and the disaster response delay average time length of each sub-region of each water area region, the equipment failure occurrence frequency is obtained by statistical calculation through the fault record in the database, the threshold value of each type of hydrological data is preset, when a certain type of hydrological data exceeds the threshold value, it is recorded, and in this way the hydrological extreme value occurrence time length is obtained, the events related to the water area that need to start emergency response are counted, and the disaster response delay time length of each disaster is obtained from the disaster record by obtaining the actual time stamp of the disaster and the time stamp of the formal start of the emergency response, and then the disaster response delay average time length is obtained by average calculation.

[0049] In one embodiment, the time-varying data of each sub-region of each water area region is analyzed, and the specific analysis process is as follows: the time-varying data of each sub-region of each water area region includes the equipment failure occurrence frequency, the hydrological extreme value occurrence time length, and the disaster response delay average time length of each sub-region of each water area region, and the normalized values of each type of time-varying data of each sub-region of each water area region are obtained after normalization.

[0050] According to the acquisition method of the main abnormal spatial region and the minor abnormal spatial region of each sub-region of each water area region, the main abnormal time region and the minor abnormal time region of each sub-region of each water area region are acquired.

[0051] In one embodiment, the water area region advanced management is carried out, and the specific control process is as follows: according to the acquisition method of the spatial failure region and the spatial hidden danger region of each sub-region of each water area region, the time failure region and the time hidden danger region of each sub-region of each water area region are acquired.

[0052] The main abnormal time region of each water area region is subjected to real-time inspection, the time failure region of each water area region is subjected to high-frequency inspection, the time hidden danger region of each water area region is subjected to periodical inspection, and the inspection is carried out when a hydrological extreme value occurs.

[0053] A database is configured to store historical disaster records, failure records and distances from each sub-region of each water area region to the main abnormal spatial region.

[0054] The normalization processing method in the application is that the target value of the data is subtracted from the minimum value of the data, and then divided by the difference between the maximum value of the data and the minimum value of the data, so as to obtain the normalized value of the target value of the data.

[0055] The image recognition technology and the normalization processing in the application are prior art and can be obtained from the Internet, and thus are not described herein.

[0056] The examples in the application are not limited to the specific modes listed in the above embodiments, and the above examples are only exemplary descriptions provided for the convenience of understanding the application and do not constitute a limitation on the protection scope of the application. Any modification, equivalent replacement, etc. made within the spirit and principles of the application shall be included in the protection scope.

[0057] The above content is only an example and description of the concept of the application, and those skilled in the art can make various modifications, supplements or substitutions of similar modes to the described embodiments, as long as the modifications, supplements or substitutions do not deviate from the concept of the application or exceed the scope defined in the specification, and all the modifications, supplements or substitutions shall be included in the protection scope of the application.

Claims

1. A big data-based water conservancy project construction management process optimization system, characterized in that, Includes the following modules: The water area division module is used to collect topographic data and water system connectivity data of each water monitoring point, perform similarity fitting analysis on the topographic data and water system connectivity data of each water monitoring point to obtain the monitoring point group of each water area, and then divide the water area into each water area. It collects river data and disaster data of each water area, performs correlation analysis on the river data and disaster data of each water area to obtain the sub-areas of each water area. The water area management module is used to collect spatial data of each sub-area of ​​each water area, analyze the spatial data of each sub-area of ​​each water area to carry out basic water area management, and collect time-varying data of each sub-area of ​​each water area, analyze the time-varying data of each sub-area of ​​each water area to carry out advanced water area management.

2. The water conservancy project construction management process optimization system based on big data according to claim 1, characterized in that, The similarity fitting analysis of the topographic data and water system connectivity data of each water monitoring point is performed as follows: The topographic data of each water monitoring point includes the average elevation, topographic index, slope, and aspect of each monitoring point. The connectivity data of each water system includes the fractal dimension of the river network, channel density, runoff ratio, and water system connectivity. The topographic data of each water monitoring point, including the average elevation, topographic index, slope, aspect, fractal dimension of the river network, channel density, runoff ratio, and water system connectivity, are normalized to obtain the normalized values ​​of the average elevation, topographic index, slope, aspect, fractal dimension of the river network, channel density, runoff ratio, and water system connectivity of each monitoring point. These are recorded as the normalized values ​​of various regional status data of each water monitoring point.

3. The water conservancy project construction management process optimization system based on big data according to claim 2, characterized in that, The specific method for obtaining the monitoring point group for each water area is as follows: Set up target water area monitoring points, and then substitute the normalized values ​​of various regional state data of the target water area monitoring points and each water area monitoring point into the weighted Euclidean distance method to calculate the similarity, so as to obtain the regional state similarity between the target water area monitoring points and each water area monitoring point group. Taking the target monitoring point as the core, adjacent monitoring points with regional state similarity greater than the regional state similarity threshold are grouped into the same category to form the initial monitoring point group of the target monitoring point, and then the monitoring point groups of each water area are obtained.

4. The water conservancy project construction management process optimization system based on big data according to claim 3, characterized in that, The water area is divided into various water zones, and the specific division process is as follows: For each monitoring point group, image recognition technology is used to extract the spatial bounding polygon of each monitoring point group, and the spatial bounding polygons of each monitoring point group are fused to obtain each water area.

5. The water conservancy project construction management process optimization system based on big data according to claim 1, characterized in that, The correlation analysis of river channel data and disaster data in various water areas is performed, and the specific analysis process is as follows: River data for each water area includes cross-sectional flow, riverbed siltation thickness, and dam distribution density at each monitoring point in each water area. Disaster data for each water area includes the percentage of affected area, duration of disaster impact, and emergency response costs for each historical disaster at each monitoring point in each water area. Select target water area monitoring points in the target water area, calculate the cosine similarity between the target water area monitoring points in the target water area and the corresponding cross-sectional flow, river siltation thickness, dam distribution density, affected area ratio, disaster duration and emergency response cost for each historical disaster, and obtain the cosine similarity between the target water area monitoring points and the corresponding water area monitoring points.

6. The water conservancy project construction management process optimization system based on big data according to claim 5, characterized in that, The specific process for obtaining the sub-regions of each water area is as follows: Taking the target water area monitoring point as the core, adjacent monitoring points with a cosine similarity greater than the cosine similarity threshold are grouped into the same category to form an advanced monitoring point group of the target water area, and then the advanced monitoring point groups of each water area are obtained. Image recognition technology is used to extract the spatial bounding polygons of each advanced monitoring point group in each water area. The spatial bounding polygons of each advanced monitoring point group in each water area are then image-fused to obtain the secondary areas of each water area. The monitoring point with the highest regional state similarity in each sub-region of each water area is recorded as the core monitoring point. The cosine similarity between the core monitoring point of each sub-region of each water area and the monitoring points of each other sub-region is obtained. The mean is used to calculate the correlation between each sub-region of each water area and each other sub-region.

7. The water conservancy project construction management process optimization system based on big data according to claim 1, characterized in that, The spatial data of each sub-region of each water area are analyzed, and the specific analysis process is as follows: The spatial data of each sub-region of each water area includes the average thickness of river channel siltation, the arithmetic mean of topographic slope, and the coverage density of emergency material reserve points in each sub-region of each water area. After normalization, the normalized values ​​of various spatial data of each sub-region of each water area are obtained. Weighted calculations are performed on the normalized values ​​of various spatial data in each sub-region of each water area to obtain the abnormal spatial index of each sub-region of each water area. The abnormal spatial indices of each sub-region of each water area are arranged in descending order of abnormal spatial index to obtain the abnormal spatial sequence of each sub-region of each water area. The first sub-region in the abnormal spatial sequence of each sub-region of each water area is recorded as the primary abnormal spatial region, and the first preset number of sub-regions in the abnormal spatial sequence of each sub-region of each water area are recorded as the secondary abnormal spatial regions. The distances from each sub-region of each water area to the main anomaly spatial area are obtained from the database. The sequence number difference corresponding to each distance is set accordingly to obtain the sequence number difference of each sub-region of each water area. Based on the preset spatial sequence number of the main anomaly spatial area, the preset spatial sequence number of the main anomaly spatial area is added to the sequence number difference of each sub-region of each water area to obtain the spatial sequence number of each sub-region of each water area.

8. The water conservancy project construction management process optimization system based on big data according to claim 7, characterized in that, The spatial data of each sub-region of each water area are analyzed, and the specific analysis process is as follows: Based on the correlation degree of each sub-region of the main anomaly spatial region of each water area, the correlation sequence number of each sub-region of each sub-region is set. First, the hydrological sequence number of the main anomaly spatial region of each water area is preset. Then, based on the difference in the state sequence number corresponding to each correlation degree, the difference in the state sequence number of each sub-region of each water area is obtained. The hydrological sequence number of the main anomaly spatial region of each water area is added to the difference in the state sequence number of each sub-region of each water area to obtain the state sequence number of each sub-region of each water area. The Euclidean distance between the state sequence number and spatial sequence number of each secondary area of ​​each water area and the preset hydrological sequence number and preset spatial sequence number of the corresponding main abnormal spatial area is calculated to obtain the Euclidean distance of each water area. The secondary abnormal spatial areas in each water area whose Euclidean distance is lower than the preset Euclidean distance are recorded as each spatial fault area, and the normal spatial areas in each water area whose Euclidean distance is lower than the preset Euclidean distance are recorded as each spatial hidden danger area. First, construct the main abnormal spatial areas of each water area, then construct the spatial hidden danger areas of each water area, sort the spatial hidden danger areas of each water area in ascending order of Euclidean distance to obtain the construction order of spatial fault areas of each water area, and finally construct the spatial hidden danger areas of each water area.

9. The water conservancy project construction management process optimization system based on big data according to claim 1, characterized in that, The analysis of time-varying data for each sub-region of each water area is described in the following process: The time-varying data of each sub-region of each water area include the frequency of equipment failure, the duration of hydrological extremes, and the average duration of disaster response delay in each sub-region of each water area. After normalization, the normalized values ​​of various time-varying data of each sub-region of each water area are obtained. Based on the methods for obtaining the main and secondary anomaly spatial regions of each sub-region of each water area, the main and secondary anomaly time regions of each sub-region of each water area are obtained.

10. The water conservancy project construction management process optimization system based on big data according to claim 9, characterized in that, The advanced control of the water area involves the following specific control process: Based on the methods for obtaining spatial fault areas and spatial hidden danger areas in each sub-region of each water area, obtain temporal fault areas and temporal hidden danger areas in each sub-region of each water area; Real-time inspections are conducted on the main abnormal time areas of each water area, high-frequency inspections are conducted on the fault areas of each water area at each time, and inspections are conducted on the potential danger areas of each water area at each time period. Inspections are also conducted when hydrological extreme values ​​occur.

Images