High-similarity reservoir clipping method, device and equipment based on parallel computing

Through parallel computing technology, tasks are allocated to multiple computing node machines, and high-similar reservoirs are marked and cropped, which solves the problems of large calculation volume and low efficiency in reservoir cutting, and improves the efficiency of reservoir marking and cutting.

CN118570224BActive Publication Date: 2024-11-05POWERCHINA HUADONG ENG CORP LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411034269.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-29
Publication Date
2024-11-05
Estimated Expiration
2044-07-29

AI Technical Summary

Technical Problem

When the existing reservoir cutting method treats high-similar reservoirs, the calculation volume is large and the efficiency is low, resulting in low manual analysis efficiency.

Method used

Using a method based on parallel computing, the main controller allocates the tasks to be calculated to multiple idle computing node machines, and performs parallel computing to mark and crop high-similar reservoirs, improves the marking speed and cropping efficiency, and reduces the calculation complexity.

Benefits of technology

The efficiency of reservoir marking and cutting is significantly improved through parallel calculation, the amount of calculation data is reduced, and the problem of large calculation volume and low efficiency in the cutting methods of high similar reservoirs is solved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118570224B_ABST
    Figure CN118570224B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of reservoir clipping, and discloses a high-similarity reservoir clipping method, device and equipment based on parallel computing, which are applied to a main controller. The method comprises: obtaining uncalculated state reservoirs in high-similarity reservoirs; reading uncalculated state reservoirs one by one, and respectively allocating to-be-calculated tasks of the uncalculated state reservoirs to multiple idle computing node machines; controlling multiple idle computing node machines to mark the uncalculated state reservoirs through parallel computing, and obtaining reservoirs marked with deletion marks and reservoirs marked with retention marks; clipping the high-similarity reservoirs with uncalculated states based on the reservoirs marked with deletion marks and the reservoirs marked with retention marks. The present invention adopts multiple idle computing node machines to mark the reservoir states through parallel computing, thereby achieving the purpose of multiple computing nodes simultaneously marking the uncalculated state reservoirs, improving the reservoir marking speed, and thus improving the clipping efficiency, without the need for complex calculations, and reducing the amount of computing data.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of reservoir clipping, and in particular to a method, device and equipment for high-similarity reservoir clipping based on parallel computing. Background Art

[0002] At present, the reservoir dam site resource identification method based on terrain spatial data processing technology can comprehensively identify all reservoir dam sites that meet the requirements in the region according to the terrain. Among them, mountains are widely distributed, and the terrain conditions for reservoir formation in many areas are very good. A large number of reservoir dam sites can be identified in the upstream and downstream of the same river and in the main and tributary rivers. Many of these dam sites are located in close proximity and the reservoirs are highly overlapped. The reservoir surface morphology and storage capacity are very similar.

[0003] For reservoir graphics with high similarity, the existing reservoir graphic clipping method has a very large amount of calculation during clipping, and even with the help of computer analysis, the clipping efficiency is very low. Therefore, there is an urgent need for a clipping method that can overcome the defects of large amount of calculation and low efficiency. Summary of the invention

[0004] In view of this, the present invention provides a high-similarity reservoir clipping method, device and equipment based on parallel computing to solve the problem that the high-similarity reservoir clipping method has a very large amount of calculation and very low efficiency of manual analysis.

[0005] In a first aspect, the present invention provides a high-similarity reservoir pruning method based on parallel computing, which is applied to a main controller. The method comprises:

[0006] Obtain the uncalculated state reservoir in the high similarity reservoir;

[0007] Read the uncalculated state reservoir one by one, and assign the to-be-calculated tasks of the uncalculated state reservoir to multiple idle computing node machines respectively;

[0008] Control multiple idle computing node machines to mark the uncalculated state reservoirs through parallel computing, and obtain the reservoirs marked with deletion marks and the reservoirs marked with retention marks;

[0009] Based on the reservoirs with deleted marks and the reservoirs with retained marks, the reservoirs with high similarity of uncalculated states are pruned.

[0010] The high-similarity reservoir clipping method based on parallel computing provided by the present invention controls multiple idle computing node machines through parallel computing by a main controller to mark reservoirs in an uncalculated state, thereby obtaining reservoirs with marked deletion marks and reservoirs with marked retention marks. The high-similarity reservoirs in an uncalculated state are clipped based on the reservoirs with deleted marks and the reservoirs with retained marks. Multiple idle computing node machines are used to mark the reservoir states through parallel computing, thereby achieving the purpose of multiple computing nodes marking reservoirs in an uncalculated state at the same time, improving the reservoir marking speed, thereby improving the clipping efficiency, reducing the calculation complexity, reducing the amount of calculation data, and solving the problems of large amount of calculation and low efficiency of manual analysis in the high-similarity reservoir clipping method.

[0011] In an optional implementation, reading the uncalculated state reservoir one by one and assigning the to-be-calculated tasks of the uncalculated state reservoir to multiple idle computing node machines respectively includes:

[0012] Read the uncalculated reservoirs one by one, and publish each uncalculated reservoir as a task to be calculated to the task queue;

[0013] Obtain the load status of multiple computing node machines, and determine the computing node machine with a load status of 0 as an idle computing node machine;

[0014] The tasks to be calculated in the task queue are respectively allocated to multiple idle computing node machines.

[0015] The high-similarity reservoir pruning method based on parallel computing provided by the present invention publishes to-be-calculated tasks for each uncalculated reservoir through the main controller, and determines that the computing node machine is an idle computing node machine according to the load state of 0, and allocates to-be-calculated tasks in the task queue to multiple idle computing node machines respectively, thereby achieving the purpose of synchronous computing of multiple computing node machines and providing a basis for subsequent parallel computing.

[0016] In an optional implementation, controlling a plurality of idle computing node machines to mark uncalculated state reservoirs through parallel computing to obtain reservoirs marked with deletion marks and reservoirs marked with retention marks includes:

[0017] Control multiple idle computing nodes to calculate the dam scale factor of the uncalculated reservoir through parallel computing;

[0018] Get the surface area of ​​each reservoir;

[0019] Based on the reservoir group belonging to the same water system in the preset high-similarity reservoirs, the dam scale factor and the reservoir area of ​​each reservoir, the high-similarity reservoirs in the uncalculated state are marked with deletion marks and retention marks to obtain the reservoirs marked with deletion marks and the reservoirs marked with retention marks.

[0020] The high-similarity reservoir pruning method based on parallel computing provided by the present invention controls multiple idle computing node machines to calculate the dam scale factor of the reservoir in the uncalculated state through parallel computing; obtains the reservoir surface area of ​​each reservoir; marks the deletion mark and the retention mark of the high-similarity reservoir in the uncalculated state based on the reservoir group belonging to the same water system in the preset high-similarity reservoirs, the dam scale factor and the reservoir surface area of ​​each reservoir, thereby improving the accuracy of marking the retention mark or the deletion mark for each reservoir, improving the computing efficiency by controlling the synchronous computing of multiple idle computing node machines, and being able to effectively clean up the redundant reservoirs in the high-similarity reservoirs.

[0021] In an optional implementation, controlling a plurality of idle computing nodes to calculate the dam scale factor of the uncalculated state reservoir through parallel computing includes:

[0022] Control multiple idle computing node machines to obtain the dam length and dam height of each corresponding uncalculated state reservoir from the high similarity reservoirs;

[0023] Calculate the mass factor for each corresponding uncalculated state reservoir based on the dam length and dam height.

[0024] The high-similarity reservoir pruning method based on parallel computing provided by the present invention controls multiple idle computing node machines to respectively obtain the dam length and dam height of each corresponding uncalculated reservoir from the high-similarity reservoirs; and calculates the large-scale factor of each corresponding uncalculated reservoir based on the dam length and dam height, thereby achieving the purpose of obtaining the dam scale factor through parallel computing and improving the computing efficiency. The calculated dam scale factor provides an indicator basis for the subsequent retention or deletion of the reservoir mark.

[0025] In an optional implementation, the reservoir group belonging to the same water system among the preset high-similarity reservoirs is obtained in the following manner: the water system where each reservoir in the high-similarity reservoirs is located is numbered by a spatial position analysis algorithm, and the reservoirs in the same watershed are marked with the same number to obtain multiple reservoir groups belonging to the same water system;

[0026] Controlling multiple idle computing nodes to mark uncalculated high-similarity reservoirs based on the reservoir group, dam scale factor and reservoir area of ​​each reservoir belonging to the same water system in the preset high-similarity reservoirs to delete and retain the marks includes:

[0027] Obtain the reservoir surface object of each reservoir, and use the reservoir surface object as the main spot map;

[0028] All reservoirs in the corresponding reservoir group that intersect with the main pattern are obtained through a spatial intersection analysis algorithm, and the reservoir surface objects of the reservoirs are used as sub-patterns corresponding to the main pattern;

[0029] Control multiple idle computing nodes to calculate the overlap rate between the main pattern and the corresponding sub-pattern;

[0030] For each reservoir marker, either keep the label or delete the label based on the overlap ratio, dam size factor, and reservoir surface area.

[0031] The high-similarity reservoir clipping method based on parallel computing provided by the present invention divides the high-similarity reservoirs into multiple reservoir groups belonging to the same water system, calculates the overlap rate of the main patch map and the corresponding sub-patch map for the reservoir group belonging to the same water system in each high-similarity reservoir, and controls multiple idle computing node machines to retain or delete the mark of each reservoir based on the overlap rate, dam scale factor and reservoir surface area, thereby improving the computing efficiency and the accuracy of retaining or deleting the mark for each reservoir, and can effectively clean up redundant reservoirs in the high-similarity reservoirs.

[0032] In an optional implementation, controlling a plurality of idle computing nodes to calculate the overlap rate of the main pattern and each sub-pattern includes:

[0033] Obtain the main pattern area and the corresponding sub-pattern area;

[0034] Control multiple idle computing node machines to perform superposition calculation on the area of ​​each corresponding sub-pattern and the area of ​​the main pattern, so as to obtain the overlapping area of ​​each sub-pattern and the main pattern;

[0035] The overlap ratio is calculated based on the overlap area, the main patch area and the corresponding sub-patch area.

[0036] The high-similarity reservoir clipping method based on parallel computing provided by the present invention controls multiple idle computing node machines to superimpose and calculate the area of ​​each corresponding sub-patch with the area of ​​the main patch respectively, to obtain the overlapping area of ​​each sub-patch with the main patch, and calculates the overlapping rate based on the overlapping area, the area of ​​the main patch and the area of ​​each corresponding sub-patch, so as to realize the rapid calculation of the overlapping situation of a large number of redundant high-similarity reservoirs, and provide data basis for the subsequent retention and deletion marks of the marked reservoirs.

[0037] In an optional implementation, retaining or deleting a mark for each reservoir mark based on the overlap rate, the dam scale factor, and the reservoir surface area includes:

[0038] Determining whether the overlap rate is greater than a first preset threshold;

[0039] When the overlap rate is less than a first preset threshold, the corresponding reservoir mark is reserved;

[0040] When the overlap rate is greater than a first preset threshold, the absolute value of the difference between the main spot area and the corresponding sub-spot area and the ratio of the smaller area between the main spot area and the corresponding sub-spot area are calculated, and it is determined whether the ratio is greater than a second preset threshold;

[0041] When the ratio is greater than a second preset threshold, the mark of the reservoir with the larger area between the main plot area and each sub-plot area is retained, and the mark of the reservoir with the smaller area between the main plot area and each sub-plot area is deleted;

[0042] When the ratio is less than the second preset threshold, the reservoir mark with the smaller dam scale factor between the main plot and each sub-plot is retained, and the reservoir mark with the larger dam scale factor between the main plot and each sub-plot is deleted.

[0043] The high-similarity reservoir clipping method based on parallel computing provided by the present invention screens out high-similarity reservoirs with a high overlap rate by comparing the overlap rate with a first preset threshold value, and then compares the absolute value of the difference between the main patch area and the corresponding sub-patch area and the ratio of the minimum area between the main patch area and the corresponding sub-patch area with a second preset threshold value, so that each reservoir in the same water system is marked with a retention mark or a deletion mark, which can effectively clean up redundant reservoirs in high-similarity reservoirs and provide a basis for subsequent clipping of high-similarity reservoirs and selection of the optimal reservoir dam site.

[0044] In a second aspect, the present invention provides a high-similarity reservoir clipping device based on parallel computing, the device comprising:

[0045] Acquisition module, used for uncalculated state reservoirs in high similarity reservoirs;

[0046] An allocation module is used to read the uncalculated state reservoir one by one, and allocate the to-be-calculated tasks of the uncalculated state reservoir to multiple idle computing node machines respectively;

[0047] A marking module is used to control multiple idle computing node machines to mark the uncalculated state reservoirs through parallel computing to obtain the reservoirs marked with deletion marks and the reservoirs marked with retention marks;

[0048] The trimming module is used to trim the high similarity reservoirs of the uncalculated states based on the reservoirs with deleted marks and the reservoirs with retained marks.

[0049] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the high-similarity reservoir clipping method based on parallel computing of the above-mentioned first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0050] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the high-similarity reservoir clipping method based on parallel computing of the above-mentioned first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 is a flow chart of a high-similarity reservoir pruning method based on parallel computing according to an embodiment of the present invention;

[0053] Figure 2 is a flow chart of another high-similarity reservoir pruning method based on parallel computing according to an embodiment of the present invention;

[0054] Figure 3 is a flow chart of another high-similarity reservoir clipping method based on parallel computing according to an embodiment of the present invention;

[0055] Figure 4 is a structural block diagram of a high-similarity reservoir clipping device based on parallel computing according to an embodiment of the present invention;

[0056] Figure 5 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0058] According to an embodiment of the present invention, an embodiment of a high-similarity reservoir clipping method based on parallel computing is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0059] In this embodiment, a high-similarity reservoir pruning method based on parallel computing is provided, which can be used in a main controller. Figure 1 is a flow chart of a high similarity reservoir pruning method based on parallel computing according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0060] Step S101, obtaining an uncalculated state reservoir in a high similarity reservoir.

[0061] Specifically, high-similarity reservoirs are stored in the pre-set reservoir data. The total uncalculated state reservoirs of high-similarity reservoirs include reservoirs that have never participated in the calculation and reservoirs that have participated in the calculation before and have not been marked for deletion. Selecting reservoirs in the uncalculated state can ensure that the data calculation amount is saved when the high-similarity reservoirs are subsequently trimmed, thereby improving the trimming efficiency. High-similarity reservoirs have the following characteristics: in many areas, the terrain conditions for reservoir formation are very good. In the upstream and downstream of the same river, the main and tributary rivers include a large number of reservoir dam sites. Many locations of reservoir dam sites are close to each other, and the reservoirs are highly overlapped. The similarity of reservoir surface morphology and reservoir capacity size is very high. Before trimming the high-similarity reservoirs, the reservoirs that have not been trimmed in the high-similarity reservoirs are obtained. These reservoirs are reservoirs in the uncalculated state. It should be noted that the uncalculated reservoirs in the obtained high-similarity reservoirs include the reservoir surface area of ​​each reservoir, the dam length of each reservoir, the dam height and other related parameters.

[0062] Step S102, reading the uncalculated state reservoir one by one, and respectively allocating the to-be-calculated tasks of the uncalculated state reservoir to a plurality of idle computing node machines.

[0063] Specifically, the main controller can be implemented by a main control computer, and the main control computer includes an engine management center. Exemplarily, the engine management center reads the uncalculated state reservoir one by one, and publishes each uncalculated state reservoir as a task to be calculated. When the load state of the computing node machine is busy, the main control computer does not assign the task to be calculated. When the load state of the computing node machine is idle, the computing node machine is determined to be an idle computing node machine, and the main control computer assigns the task to be calculated to the idle computing node machine.

[0064] Step S103, controlling a plurality of idle computing node machines to mark the uncalculated state reservoirs through parallel computing, and obtaining the reservoirs marked with deletion marks and the reservoirs marked with retention marks.

[0065] Specifically, when multiple idle computing node machines all have tasks to be calculated, multiple idle computing node machines can be controlled to mark the uncalculated reservoirs through parallel computing. Exemplarily, the marking principle can be set as follows: when comparing, if the reservoir areas in the high-similarity reservoirs are quite different, then the reservoir with the largest area is selected and marked with a retention mark, and the remaining reservoirs are marked with deletion marks; if the reservoir areas are not much different, then the reservoir with the smallest dam size is selected and marked as a retention mark, and the remaining reservoirs are marked as deletion marks. In this way, the main control computer controls multiple idle computing node machines to traverse all the uncalculated reservoirs in the high-similarity reservoirs to achieve marking of each reservoir.

[0066] Step S104, cutting out the high similarity reservoirs in the uncalculated state based on the reservoirs with deletion marks and the reservoirs with retention marks.

[0067] Specifically, all the reservoirs marked with deletion marks obtained in step S103 are deleted, the reservoirs marked with retention marks are summarized, and the dam sites of the reservoirs marked with retention marks are recorded, and the dam sites of the reservoirs marked with retention marks are used as the final reservoir dam sites. The number of reservoirs is greatly reduced, and reservoirs with more superior terrain conditions are selected to achieve the cutting of reservoirs with high similarity.

[0068] The high-similarity reservoir clipping method based on parallel computing provided in this embodiment controls multiple idle computing node machines through parallel computing by a main controller to mark the reservoirs in the uncalculated state, and obtains the reservoirs marked with deletion marks and the reservoirs marked with retention marks. The high-similarity reservoirs in the uncalculated state are clipped based on the reservoirs with deletion marks and the reservoirs with retention marks. Multiple idle computing node machines are used to mark the reservoir states through parallel computing, so that the purpose of multiple computing nodes marking the reservoirs in the uncalculated state at the same time is achieved, the reservoir marking speed is improved, and then the clipping efficiency is improved, the calculation complexity is reduced, the amount of calculation data is reduced, and the problems of large amount of calculation and low efficiency of manual analysis in the high-similarity reservoir clipping method are solved.

[0069] In this embodiment, a high-similarity reservoir pruning method based on parallel computing is provided, which can be used in the above-mentioned main controller. Figure 2 is a flow chart of a high similarity reservoir pruning method based on parallel computing according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0070] Step S201, obtain the uncalculated state reservoir in the high similarity reservoir. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0071] Step S202, reading the uncalculated state reservoir one by one, and respectively allocating the to-be-calculated tasks of the uncalculated state reservoir to a plurality of idle computing node machines.

[0072] Specifically, the above step S202 includes:

[0073] Step S2021, read the reservoirs in the uncalculated state one by one, and publish each reservoir in the uncalculated state as a task to be calculated in the task queue.

[0074] Specifically, the main controller can be implemented by a main control computer, which includes an engine management center and a buffer service area. The engine management center reads the uncalculated state reservoirs one by one, publishes the read uncalculated state reservoirs as a task to be calculated, and adds each task to be calculated to the task queue in the main control computer cache service area. The engine management center reads the uncalculated state reservoirs one by one by first obtaining the contour lines of each reservoir, and then reads each uncalculated state reservoir one by one from upstream to downstream or from downstream to upstream based on the contour lines.

[0075] Step S2022, obtain the load status of multiple computing node machines, and determine the computing node machine with a load status of 0 as an idle computing node machine.

[0076] Specifically, the engine management center is also used to monitor the load status of multiple computing node machines. When the engine management center monitors that the load status of a computing node machine is not 0, it determines that the computing node machine is in a busy state; when the engine management center monitors that the load status of a computing node machine is 0, it determines that the computing node machine is an idle computing node machine.

[0077] Step S2023, respectively assign the tasks to be calculated in the task queue to multiple idle computing node machines.

[0078] Specifically, the engine management center does not assign tasks to busy computing node machines; when there are multiple idle computing node machines, the engine management center assigns tasks to be calculated to each idle computing node machine.

[0079] Step S203, control multiple idle computing nodes to mark the uncalculated state reservoirs through parallel computing, and obtain the reservoirs marked with deletion marks and the reservoirs marked with retention marks. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0080] Step S204: Crop the high similarity reservoirs in the uncalculated state based on the reservoirs with deletion marks and the reservoirs with retention marks. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0081] The high-similarity reservoir pruning method based on parallel computing provided in this embodiment publishes the to-be-calculated tasks for each uncalculated reservoir through the main controller, and determines the computing node machine as an idle computing node machine according to the load state of 0, and allocates the to-be-calculated tasks in the task queue to multiple idle computing node machines respectively, thereby achieving the purpose of synchronous computing of multiple computing node machines and providing a basis for subsequent parallel computing.

[0082] In this embodiment, a high-similarity reservoir pruning method based on parallel computing is provided, which can be used in the above-mentioned main controller. Figure 3 is a flow chart of a high similarity reservoir pruning method based on parallel computing according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0083] Step S301, obtain the uncalculated state reservoir in the high similarity reservoir. Figure 2 Step S201 of the illustrated embodiment will not be described in detail here.

[0084] Step S302, read the uncalculated state reservoir one by one, and assign the uncalculated state reservoir to be calculated tasks to multiple idle computing node machines respectively. Figure 2 Step S202 of the illustrated embodiment will not be described in detail here.

[0085] Step S303, controlling a plurality of idle computing node machines to mark the uncalculated state reservoirs through parallel computing, and obtaining the reservoirs marked with deletion marks and the reservoirs marked with retention marks.

[0086] Specifically, the above step S303 includes:

[0087] Step S3031, controlling multiple idle computing node machines to calculate the dam scale factor of the reservoir in the uncalculated state through parallel computing.

[0088] In some optional implementations, the above step S3031 includes:

[0089] Step a1, controlling a plurality of idle computing node machines to respectively obtain the dam length and dam height of each corresponding uncalculated state reservoir from the high similarity reservoirs.

[0090] Specifically, the dam length refers to the length between the two ends of the reservoir dam crest along the dam axis, and the reservoir dam height refers to the height from the lowest point of the reservoir dam foundation surface (excluding local deep grooves, wells or holes) to the dam crest, or refers to the height of the water retaining structure in the reservoir project. Control multiple idle computing node machines to obtain the dam length and dam height and reservoir area S of the reservoir corresponding to the corresponding task to be calculated from the high-similarity reservoir.

[0091] Step a2, calculating the large-scale factor of each corresponding uncalculated state reservoir based on the dam length and dam height.

[0092] Specifically, when each idle computing node obtains the dam length and dam height of the reservoir corresponding to the task to be calculated, the dam scale factor of each reservoir is calculated according to the dam scale factor calculation formula. Dam scale factor = dam length a ×Dam height b . The letters a and b are both constants, and their specific values ​​are set according to actual conditions. For example, a can be set to 1, and b can be set to 2.

[0093] The high-similarity reservoir pruning method based on parallel computing provided in this embodiment controls multiple idle computing node machines to obtain the dam length and dam height of each corresponding uncalculated reservoir from the high-similarity reservoirs respectively; and calculates the large-scale factor of each corresponding uncalculated reservoir based on the dam length and dam height, thereby achieving the purpose of obtaining the dam scale factor through parallel computing and improving the computing efficiency. The calculated dam scale factor provides an indicator basis for the subsequent retention or deletion of the reservoir mark.

[0094] Step S3032, obtaining the surface area of ​​each reservoir.

[0095] Specifically, the reservoirs in the high similarity reservoirs include the reservoir surface area of ​​each reservoir, and the main control computer controls the computing node machine to directly obtain the reservoir surface area of ​​each reservoir from the high similarity reservoirs. The reservoir surface area of ​​the reservoir refers to the water surface area corresponding to the maximum water storage level of the reservoir.

[0096] Step S3033, controls multiple idle computing node machines to mark the deletion marks and retention marks of the high-similarity reservoirs in the uncalculated state based on the reservoir groups belonging to the same water system in the preset high-similarity reservoirs, the dam scale factor and the reservoir area of ​​each reservoir, and obtains the reservoirs marked with deletion marks and the reservoirs marked with retention marks.

[0097] In some optional embodiments, the reservoir group belonging to the same water system among the preset high-similarity reservoirs is obtained in the following manner: the water system in which each reservoir in the high-similarity reservoirs is located is numbered by a spatial position analysis algorithm, and the reservoirs in the same river basin are marked with the same number to obtain multiple reservoir groups belonging to the same water system.

[0098] Specifically, the reservoir group belonging to the same water system among the high-similarity reservoirs is obtained in the following manner: the water system where each reservoir in the high-similarity reservoirs is located is numbered by a spatial position analysis algorithm, and the reservoirs in the same watershed are marked with the same number to obtain multiple reservoir groups belonging to the same water system. Exemplarily, the water system where each reservoir is located is numbered by spatial position analysis, and all reservoirs in the same watershed are marked with the same number. For example: the reservoir number is XY, where X is the number of the water system, and Y is the number of the reservoir in the X water system. Reservoirs with the same water system number are the same group of reservoirs.

[0099] The above step S3033 includes:

[0100] Step b1, obtaining the reservoir surface object of each reservoir, and using the reservoir surface object as the main pattern.

[0101] Specifically, each reservoir in the high-similarity reservoir is stored in the form of a reservoir surface object. For the reservoirs in the reservoir group belonging to the same water system, the reservoir surface object of any reservoir can be selected as the main spot. When cutting, the reservoir surface object is directly read from the stored reservoir surface object as the main spot.

[0102] Step b2, obtaining all reservoirs in the corresponding reservoir group that intersect with the main patch through a spatial intersection analysis algorithm, and using the reservoir surface objects of the reservoirs as sub-patterns corresponding to the main patch.

[0103] Specifically, the spatial intersection analysis algorithm includes spatial line segment intersection analysis, spatial vector intersection analysis and spatial area intersection analysis. According to the main map read in step b1, spatial intersection analysis is performed one by one with the reservoirs in the same group, and the reservoirs intersecting with the main map are read in using spatial area intersection analysis as the sub-map corresponding to the main map.

[0104] Step b3, controlling a plurality of idle computing node machines to calculate the overlap ratio between the main pattern and the corresponding sub-pattern.

[0105] In some optional implementations, the above step b3 includes:

[0106] Step b31, obtaining the main spot area and each corresponding sub-spot area.

[0107] Specifically, the main patch area S1 and each corresponding sub-patch area S2 selected in each reservoir group are obtained.

[0108] Step b32, controlling a plurality of idle computing node machines to perform superposition calculation on the area of ​​each corresponding sub-pattern and the area of ​​the main pattern, to obtain the overlapping area of ​​each sub-pattern and the main pattern.

[0109] Specifically, the main control computer controls a plurality of idle computing node machines to perform superposition calculations on each sub-image spot and the main image spot respectively, and obtains the overlapping area S' of each sub-image spot and the main image spot.

[0110] Step b33, calculating the overlap ratio based on the overlap area, the main patch area and each corresponding sub-patch area.

[0111] Specifically, the main plot area is compared with each corresponding sub-plot area, and the reservoir with the larger area is selected, and then the overlap ratio is calculated based on the overlap area and the selected larger area. The overlap ratio is expressed by the following formula: overlap ratio = S' / max(S1, S2).

[0112] Step b4, retaining or deleting the mark for each reservoir based on the overlap ratio, dam scale factor and reservoir area.

[0113] In some optional implementations, the above step b4 includes:

[0114] Step b41, determining whether the overlap rate is greater than a first preset threshold.

[0115] Specifically, the first preset threshold may be set to 1. If the overlap ratio is greater than the first preset threshold 1, step b43 is performed.

[0116] Step b42: when the overlap rate is less than the first preset threshold, the corresponding reservoir mark is retained.

[0117] Specifically, when the overlap rate is less than the first preset threshold value 1, the corresponding reservoir mark is directly reserved.

[0118] Step b43, when the overlap rate is greater than the first preset threshold, the ratio of the absolute value of the difference between the main spot area and the corresponding sub-spot area to the smaller area of ​​the main spot area and the corresponding sub-spot area is calculated, and it is determined whether the ratio is greater than the second preset threshold.

[0119] Specifically, the second preset threshold can be set to 0.1, first calculate the absolute value of the difference between the main spot area and each corresponding sub-spot area, then calculate the smaller area between the main spot area and the corresponding sub-spot area, and finally calculate the ratio of the absolute value of the difference to the minimum area, where the ratio is expressed by the following formula: Abs(S1-S2) / min(S1, S2). S1 is the main spot area, and S2 is the area of ​​each sub-spot corresponding to the main spot. If the overlap rate is greater than the first preset threshold of 0.5, it is determined whether the value of Abs(S1-S2) / min(S1, S2) is greater than the second preset threshold of 0.1.

[0120] Step b44, when the ratio is greater than the second preset threshold, the reservoir mark with the larger area between the main patch area and each sub-patch area is retained, and the reservoir mark with the smaller area between the main patch area and each sub-patch area is deleted.

[0121] Specifically, when the value of Abs(S1-S2) / min(S1, S2) is greater than the second preset threshold value 0.1, the reservoir mark with the larger area between the main patch area and each sub-patch area, that is, the reservoir mark with Max(S1, S2)) is retained; otherwise, the reservoir mark with the smaller area between the main patch area and each sub-patch area is deleted.

[0122] Step b45, when the ratio is less than the second preset threshold, the reservoir mark with the smaller dam scale factor between the main plot and each sub-plot is retained, and the reservoir mark with the larger dam scale factor between the main plot and each sub-plot is deleted.

[0123] Specifically, if the ratio of Abs(S1-S2) / min(S1, S2) is less than the second preset threshold value 0.1, the reservoir mark with the smaller dam scale factor between the main plot and the corresponding sub-plot is retained; otherwise, the reservoir mark with the larger dam scale factor between the main plot and each sub-plot is deleted.

[0124] It should be noted that, based on the marking results and screening results, the reservoirs with marked deletion marks will be recorded and will no longer be included in the subsequent calculations.

[0125] The high-similarity reservoir clipping method based on parallel computing provided in the present embodiment divides the high-similarity reservoirs into a plurality of reservoir groups belonging to the same water system, calculates the overlap rate between the main patch and the corresponding sub-patch for each reservoir group belonging to the same water system in the high-similarity reservoirs, screens out the high-similarity reservoirs with a high overlap rate by comparing the overlap rate with a first preset threshold, and then compares the absolute value of the difference between the main patch area and the corresponding sub-patch area and the ratio of the minimum area between the main patch area and the corresponding sub-patch area with a second preset threshold, so that each reservoir in the same water system is marked with a retaining mark or a deletion mark, which can effectively clean up the redundant reservoirs in the high-similarity reservoirs and provide a basis for the subsequent clipping of high-similarity reservoirs and the selection of the optimal reservoir dam site.

[0126] Step S304: based on the reservoirs with deletion marks and the reservoirs with retention marks, the reservoirs with high similarity in the uncalculated state are cut. Figure 2 Step S204 of the illustrated embodiment will not be described in detail here.

[0127] The high-similarity reservoir pruning method based on parallel computing provided in this embodiment controls multiple idle computing node machines to calculate the dam scale factor of the reservoir in the uncalculated state through parallel computing; obtains the reservoir surface area of ​​each reservoir; marks the deletion mark and the retention mark of the high-similarity reservoir in the uncalculated state based on the reservoir group belonging to the same water system in the preset high-similarity reservoirs, the dam scale factor and the reservoir surface area of ​​each reservoir, thereby improving the accuracy of marking the retention mark or the deletion mark for each reservoir, and improving the computing efficiency by controlling multiple idle computing node machines to calculate synchronously, and can effectively clean up the redundant reservoirs with close dam sites and high reservoir surface overlap.

[0128] It should be noted that the embodiments of the present invention control multiple idle computing nodes to perform parallel computing, including the following situations, which are as follows:

[0129] When the number of pending computing tasks to be processed is the same as the number of idle computing node machines, one pending computing task is assigned to each idle computing node machine, and computing can be performed simultaneously. For example, if there are 10 pending computing tasks to be processed, then there are 10 corresponding idle computing node machines, and one pending computing task is assigned to each idle computing node machine. At this time, all 10 computing node machines have computing tasks and can perform computing simultaneously, which improves computing efficiency.

[0130] When the number of pending tasks to be processed is inconsistent with the number of idle computing node machines, at least one pending task needs to be allocated according to the number of idle computing node machines, and the pending tasks need to be added to the task buffer until all pending tasks are allocated and processed. For example, there are 9 pending tasks to be processed, but there are only 3 idle computing node machines. After allocating 1 pending task to each idle computing node machine, there are 6 pending tasks left. At this time, the remaining 6 pending tasks are waiting to be allocated. If a computing node machine has processed the task and is idle, one of the 6 pending tasks will be allocated to this idle computing node machine. At this time, there are 5 pending tasks left, and so on, until all pending tasks are allocated and processed. For the same pending task, the pending tasks can be allocated to the idle computing node machines on average. For different pending tasks, the computing node machines take different time to process the tasks, so they are not allocated evenly according to the number of pending tasks.

[0131] In the present embodiment, a high similarity reservoir clipping device based on parallel computing is also provided, and the device is used to implement the above-mentioned embodiment and preferred implementation mode, and the description has been made no further. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.

[0132] This embodiment provides a high-similarity reservoir cutting device based on parallel computing, such as Figure 4 As shown, including:

[0133] The acquisition module 401 is used for the uncalculated state reservoir in the high similarity reservoir.

[0134] The allocation module 402 is used to read the uncalculated state reservoir one by one, and allocate the to-be-calculated tasks of the uncalculated state reservoir to multiple idle computing node machines respectively.

[0135] The marking module 403 is used to control multiple idle computing node machines to mark the uncalculated state reservoirs through parallel computing to obtain the reservoirs marked with deletion marks and the reservoirs marked with retention marks.

[0136] The trimming module 404 is used to trim the high similarity reservoirs of the uncalculated state based on the reservoirs with deletion marks and the reservoirs with retention marks.

[0137] In some optional implementations, the allocation module 402 includes:

[0138] The publishing unit is used to read the uncalculated state reservoirs one by one, and publish each uncalculated state reservoir as a task to be calculated to the task queue. The first acquisition unit is used to acquire the load status of multiple computing node machines, and determine the computing node machine with a load status of 0 as an idle computing node machine.

[0139] The allocation unit is used to allocate the tasks to be calculated in the task queue to multiple idle computing node machines respectively.

[0140] In some optional implementations, the marking module 403 includes:

[0141] The first computing unit is used to control a plurality of idle computing node machines to calculate the dam scale factor of the uncalculated state reservoir through parallel computing.

[0142] The second acquisition unit is used to acquire the reservoir area of ​​each reservoir.

[0143] The marking unit is used to mark the deletion mark and the retention mark of the high-similarity reservoirs in the uncalculated state based on the reservoir group belonging to the same water system in the preset high-similarity reservoirs, the dam scale factor and the reservoir area of ​​each reservoir, and obtain the reservoirs with the deletion mark and the retention mark.

[0144] In some optional implementations, the first computing unit includes:

[0145] The first acquisition subunit is used to control multiple idle computing node machines to respectively acquire the dam length and dam height of each corresponding uncalculated state reservoir from the high-similarity reservoirs.

[0146] The first calculation subunit is used to calculate the large-scale factor of each corresponding uncalculated state reservoir based on the dam length and the dam height.

[0147] In some optional embodiments, the labeling unit includes:

[0148] The second acquisition subunit is used to acquire the reservoir surface object of each reservoir and use the reservoir surface object as the main spot map.

[0149] The third acquisition subunit is used to acquire all reservoirs in the corresponding reservoir group that intersect with the main spot map through a spatial intersection analysis algorithm, and use the reservoir surface objects of the reservoirs as the sub-spot map corresponding to the main spot map.

[0150] The second computing subunit is used to control a plurality of idle computing node machines to calculate the overlap rate of the main pattern and the corresponding sub-pattern.

[0151] The tag subunit is used to retain or delete tags for each reservoir tag based on the overlap ratio, dam size factor, and reservoir surface area.

[0152] In some optional implementations, the second computing subunit includes:

[0153] Get the submodule, get the main pattern area and the corresponding sub-pattern area.

[0154] The first calculation submodule is used to control a plurality of idle computing node machines to perform superposition calculation on the area of ​​each corresponding sub-pattern and the area of ​​the main pattern to obtain the overlapping area of ​​each sub-pattern and the main pattern.

[0155] The second calculation submodule is used to calculate the overlap rate based on the overlap area, the main pattern area and the corresponding sub-pattern area.

[0156] In some optional embodiments, the marker subunit comprises:

[0157] The judging submodule is used to judge whether the overlap rate is greater than a first preset threshold.

[0158] The first marking submodule is used to retain the mark of the corresponding reservoir mark when the overlap rate is less than a first preset threshold.

[0159] The third calculation submodule is used to calculate the ratio of the absolute value of the difference between the main spot area and the corresponding sub-spot area to the smaller area of ​​the main spot area and the corresponding sub-spot area when the overlap rate is greater than the first preset threshold, and determine whether the ratio is greater than the second preset threshold.

[0160] The second marking submodule is used to retain the mark of the reservoir with the larger area between the main plot area and each sub-plot area, and delete the mark of the reservoir with the smaller area between the main plot area and each sub-plot area when the ratio is greater than the second preset threshold.

[0161] The third marking submodule is used to retain the mark of the reservoir with the smaller dam scale factor between the main plot and each sub-plot when the ratio is less than the second preset threshold, and delete the mark of the reservoir with the larger dam scale factor between the main plot and each sub-plot.

[0162] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0163] The high-similarity reservoir cropping device based on parallel computing in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0164] The embodiment of the present invention also provides a computer device having the above Figure 4 The high similarity reservoir clipping device based on parallel computing is shown.

[0165] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 5 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0166] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0167] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0168] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0169] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0170] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0171] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device may be a touch screen.

[0172] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0173] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A high-similarity reservoir pruning method based on parallel computing, characterized in that: Applied in a main controller, the method comprises: Obtain the uncalculated state reservoir in the high similarity reservoir; Read the uncalculated state reservoir one by one, and assign the to-be-calculated tasks of the uncalculated state reservoir to multiple idle computing node machines respectively; Controlling the plurality of idle computing node machines to mark the uncalculated state reservoirs through parallel computing to obtain a reservoir with a mark deletion mark and a reservoir with a mark retention mark; controlling the plurality of idle computing node machines to mark the uncalculated state reservoirs through parallel computing to obtain a reservoir with a mark deletion mark and a reservoir with a mark retention mark includes: Controlling the plurality of idle computing node machines to calculate the dam scale factor of the uncalculated state reservoir through parallel computing; Get the surface area of ​​each reservoir; Based on the reservoir group belonging to the same water system in the preset high-similarity reservoirs, the dam scale factor and the reservoir area of ​​each reservoir, the high-similarity reservoirs in the uncalculated state are marked with deletion marks and retention marks, to obtain the reservoirs marked with deletion marks and the reservoirs marked with retention marks; The controlling the plurality of idle computing nodes to calculate the dam scale factor of the uncalculated state reservoir through parallel computing comprises: Control the plurality of idle computing node machines to respectively obtain the dam length and dam height of each corresponding uncalculated state reservoir from the high similarity reservoirs; Calculate the large-scale factor of each corresponding uncalculated state reservoir based on the dam length and dam height; The reservoir group belonging to the same water system in the preset high-similarity reservoirs is obtained in the following manner: the water system where each reservoir in the high-similarity reservoirs is located is numbered by a spatial position analysis algorithm, and the reservoirs in the same watershed are marked with the same number to obtain multiple reservoir groups belonging to the same water system; Controlling the plurality of idle computing nodes to mark the uncalculated high-similar reservoirs with deletion marks and retention marks based on the reservoir group belonging to the same water system in the preset high-similar reservoirs, the dam scale factor and the reservoir area of ​​each reservoir includes: Obtain a reservoir surface object of each reservoir, and use the reservoir surface object as a main spot map; Obtain all reservoirs in the corresponding reservoir group that intersect with the main pattern through a spatial intersection analysis algorithm, and use the reservoir surface objects of the reservoirs as sub-patterns corresponding to the main pattern; Controlling a plurality of idle computing node machines to calculate the overlap rate between the main pattern and the corresponding sub-pattern; retaining or deleting a mark for each reservoir marker based on the overlap ratio, the dam size factor, and the reservoir surface area; Keeping or deleting a mark for each reservoir mark based on the overlap ratio, the dam scale factor and the reservoir surface area includes: Determining whether the overlap rate is greater than a first preset threshold; When the overlap rate is less than a first preset threshold, the corresponding reservoir mark is reserved; When the overlap rate is greater than a first preset threshold, the absolute value of the difference between the main spot area and the corresponding sub-spot area and the ratio of the smaller area between the main spot area and the corresponding sub-spot area are calculated, and it is determined whether the ratio is greater than a second preset threshold; When the ratio is greater than a second preset threshold, the mark of the reservoir with the larger area between the main plot area and each sub-plot area is retained, and the mark of the reservoir with the smaller area between the main plot area and each sub-plot area is deleted; When the ratio is less than a second preset threshold, the mark of the reservoir with the smaller dam scale factor between the main plot and each sub-plot is retained, and the mark of the reservoir with the larger dam scale factor between the main plot and each sub-plot is deleted; Based on the reservoir with the deletion mark and the reservoir with the retention mark, the reservoir with high similarity in the uncalculated state is trimmed.

2. The method according to claim 1, characterized in that The step of reading the uncalculated state reservoir one by one and assigning the uncalculated state reservoir to-be-calculated tasks to a plurality of idle computing node machines respectively comprises: Read the uncalculated state reservoirs one by one, and publish each uncalculated state reservoir as a task to be calculated to the task queue; Obtain the load status of multiple computing node machines, and determine the computing node machine with a load status of 0 as an idle computing node machine; The tasks to be calculated in the task queue are respectively allocated to a plurality of idle computing node machines.

3. The method according to claim 1, characterized in that The controlling of a plurality of idle computing nodes to calculate the overlap rate between the main pattern and each sub-pattern comprises: Obtain the main pattern area and the corresponding sub-pattern area; Controlling a plurality of idle computing node machines to respectively perform superposition calculation on the area of ​​each corresponding sub-pattern and the area of ​​the main pattern, so as to obtain the overlapping area of ​​each sub-pattern and the main pattern; The overlap ratio is calculated based on the overlap area, the main patch area and the corresponding sub-patch area.

4. A high-similarity reservoir cutting device based on parallel computing, characterized in that: The device comprises: Acquisition module, used for uncalculated state reservoirs in high similarity reservoirs; An allocation module, used for reading the uncalculated state reservoir one by one, and respectively allocating the to-be-calculated tasks of the uncalculated state reservoir to a plurality of idle computing node machines; The marking module is used to control the plurality of idle computing node machines to mark the uncalculated state reservoirs through parallel computing to obtain a reservoir with a mark deletion mark and a reservoir with a mark retention mark; the control of the plurality of idle computing node machines to mark the uncalculated state reservoirs through parallel computing to obtain a reservoir with a mark deletion mark and a reservoir with a mark retention mark includes: Controlling the plurality of idle computing node machines to calculate the dam scale factor of the uncalculated state reservoir through parallel computing; Get the surface area of ​​each reservoir; Based on the reservoir group belonging to the same water system in the preset high-similarity reservoirs, the dam scale factor and the reservoir area of ​​each reservoir, the high-similarity reservoirs in the uncalculated state are marked with deletion marks and retention marks, to obtain the reservoirs marked with deletion marks and the reservoirs marked with retention marks; The controlling the plurality of idle computing nodes to calculate the dam scale factor of the uncalculated state reservoir through parallel computing comprises: Control the plurality of idle computing node machines to respectively obtain the dam length and dam height of each corresponding uncalculated state reservoir from the high similarity reservoirs; Calculate the large-scale factor of each corresponding uncalculated state reservoir based on the dam length and dam height; The reservoir group belonging to the same water system in the preset high-similarity reservoirs is obtained in the following manner: the water system where each reservoir in the high-similarity reservoirs is located is numbered by a spatial position analysis algorithm, and the reservoirs in the same watershed are marked with the same number to obtain multiple reservoir groups belonging to the same water system; Controlling the plurality of idle computing nodes to mark the uncalculated high-similar reservoirs with deletion marks and retention marks based on the reservoir group belonging to the same water system in the preset high-similar reservoirs, the dam scale factor and the reservoir area of ​​each reservoir includes: Obtain a reservoir surface object of each reservoir, and use the reservoir surface object as a main spot map; Obtain all reservoirs in the corresponding reservoir group that intersect with the main pattern through a spatial intersection analysis algorithm, and use the reservoir surface objects of the reservoirs as sub-patterns corresponding to the main pattern; Controlling a plurality of idle computing node machines to calculate the overlap rate between the main pattern and the corresponding sub-pattern; retaining or deleting a mark for each reservoir marker based on the overlap ratio, the dam size factor, and the reservoir surface area; Keeping or deleting a mark for each reservoir mark based on the overlap ratio, the dam scale factor and the reservoir surface area includes: Determining whether the overlap rate is greater than a first preset threshold; When the overlap rate is less than a first preset threshold, the corresponding reservoir mark is reserved; When the overlap rate is greater than a first preset threshold, the absolute value of the difference between the main spot area and the corresponding sub-spot area and the ratio of the smaller area between the main spot area and the corresponding sub-spot area are calculated, and it is determined whether the ratio is greater than a second preset threshold; When the ratio is greater than a second preset threshold, the mark of the reservoir with the larger area between the main plot area and each sub-plot area is retained, and the mark of the reservoir with the smaller area between the main plot area and each sub-plot area is deleted; When the ratio is less than a second preset threshold, the mark of the reservoir with the smaller dam scale factor between the main plot and each sub-plot is retained, and the mark of the reservoir with the larger dam scale factor between the main plot and each sub-plot is deleted; The trimming module is used to trim the high-similarity reservoirs in the uncalculated state based on the reservoirs with deletion marks and the reservoirs with retention marks.

5. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the high-similarity reservoir clipping method based on parallel computing as described in any one of claims 1 to 3 by executing the computer instructions.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the high-similarity reservoir clipping method based on parallel computing according to any one of claims 1 to 3.