Method for determining parameters of water conservancy monitoring model and related device

Abstract

The application discloses a parameter determination method of a water conservancy monitoring model and related devices, and the method comprises the following steps: acquiring water conservancy data sequences corresponding to a plurality of monitoring points in a monitoring basin respectively, wherein the water conservancy data sequence comprises water conservancy data of the corresponding monitoring point in a current first time period, and the first time period comprises a plurality of sub time periods; performing error fusion on the water conservancy data sequence according to different sub time periods and different monitoring points to obtain target fusion data of the monitoring basin in different sub time periods; and taking the target fusion data as an input parameter of the water conservancy monitoring model. The application can improve the technical problems of professional barriers and high labor costs of parameter calibration in water conservancy monitoring in the related art.

Description

Technical Field

[0001] This application belongs to the field of hydrological monitoring technology, and in particular relates to a method, device, electronic equipment and computer storage medium for determining parameters of a water conservancy monitoring model. Background Technology

[0002] Water conservancy monitoring models are of great significance for watershed runoff calculation, flood analysis and forecasting, and the optimal allocation and scheduling of water resources. Besides considering the rationality of the model structure, parameter calibration is also a crucial step in the application of water conservancy monitoring models.

[0003] In related technologies, parameter calibration of water conservancy monitoring models is usually performed manually. However, this process is cumbersome and requires repeated adjustments to ensure that the parameters meet expectations. Therefore, the professional barriers and labor costs for parameter calibration are currently high. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, and computer storage medium for determining parameters of a water conservancy monitoring model, which can improve the technical problems of high professional barriers and high labor costs in parameter calibration during water conservancy monitoring.

[0005] Firstly, a method for determining the parameters of a water conservancy monitoring model is provided, which may include:

[0006] Obtain water conservancy data sequences corresponding to multiple monitoring points in the monitoring basin. The water conservancy data sequences include water conservancy data of the corresponding monitoring points within the first time period from the current time period. The first time period includes multiple sub-time periods.

[0007] Error fusion was performed on the water conservancy data sequence according to different sub-time periods and different monitoring points to obtain the target fused data of the monitoring basin in different sub-time periods;

[0008] The target fusion data is used as the input parameters for the water conservancy monitoring model.

[0009] This application embodiment acquires water conservancy data sequences corresponding to multiple monitoring points in the monitored watershed, and then performs error fusion on the water conservancy data sequences according to different sub-time periods and different monitoring points. The resulting target fused data of the monitored watershed within different sub-time periods is then used as the input parameters of the water conservancy monitoring model. Since the input parameters of the water conservancy monitoring model are the target fused data of the monitored watershed within different sub-time periods, which is obtained by performing error fusion on the water conservancy data of each monitoring point within the first time period based on different sub-time periods and different monitoring points, it can automatically fuse and eliminate errors in the calibration process. This reduces the dependence on the accuracy of parameter calibration, thereby reducing the degree of human intervention in the parameter calibration process. This improves the technical problems of high professional barriers and high labor costs in parameter calibration during water conservancy monitoring.

[0010] Optionally, error fusion is performed on the water conservancy data series according to different sub-time periods and different monitoring points to obtain target fused data of the monitored watershed within different sub-time periods, including:

[0011] The water conservancy data in multiple sub-periods of the water conservancy data sequence are sequentially fused and edge-processed to obtain the first fused data corresponding to the monitoring points in each sub-period.

[0012] The first fused data from different monitoring points in the same sub-period is processed by time period fusion to obtain the target fused data of the monitoring watershed in different sub-periods.

[0013] In these examples, by differentiating monitoring points and performing edge-mapping processing on the fusion of water conservancy data across multiple sub-periods, it is possible to minimize information loss from the same monitoring point across different sub-periods while also achieving data error fusion and elimination. Based on this, further time-period fusion processing can restore the water conservancy situation across the entire monitoring basin as accurately as possible within different sub-periods, obtaining a more complete set of input parameters required for the water conservancy monitoring model.

[0014] Optionally, the water conservancy data in multiple sub-periods of the water conservancy data sequence are sequentially fused and edge-processed to obtain the first fused data corresponding to the monitoring points in each sub-period, including:

[0015] Select the starting time period from multiple sub-time periods;

[0016] In water resources data series, a sliding window is used to gradually move forward from the water resources data of the initial time period;

[0017] Whenever the sliding window moves, the public water conservancy data and peripheral water conservancy data of the current time period relative to the previous time period are obtained from the sliding window. The water conservancy data includes public water conservancy data and peripheral water conservancy data.

[0018] Data refinement is performed on peripheral water conservancy data, and public water conservancy data is fused with the refined peripheral water conservancy data to obtain the first fused data of the monitoring point in the current time period;

[0019] Update the water conservancy data in the sliding window to the first fused data of the monitoring point in the current time period.

[0020] These examples demonstrate a detailed implementation process for sequentially fusing and marginalizing water conservancy data from multiple sub-periods in a water conservancy data sequence to obtain the first fused data corresponding to each monitoring point in each sub-period. This process enables error fusion processing of data while minimizing information loss.

[0021] Optionally, the water conservancy data sequences corresponding to multiple monitoring points in the monitoring basin are obtained, including:

[0022] Obtain raw water resources data for the monitored watershed within the first time period from the current point in time;

[0023] Data preprocessing was performed on the raw water conservancy data of the same monitoring point in different sub-time periods to obtain water conservancy data sequences corresponding to multiple monitoring points.

[0024] In these examples, by preprocessing the raw water conservancy data, water conservancy data sequences corresponding to multiple monitoring points are obtained, which realizes data organization and standardization and reduces the difficulty of subsequent data error fusion.

[0025] Optionally, the raw water conservancy data of the same monitoring point in different sub-time periods are preprocessed to obtain water conservancy data sequences corresponding to multiple monitoring points, including:

[0026] The raw water conservancy data of the same monitoring point is divided into data windows to form multiple data windows corresponding to the monitoring points;

[0027] According to different sub-time periods, the raw water conservancy data in the data windows corresponding to multiple monitoring points are processed by matrix to obtain water conservancy data sequences corresponding to multiple monitoring points respectively.

[0028] In these examples, the data windows are divided by distinguishing monitoring points, and the raw water conservancy data within the data windows are processed into matrices according to multiple sub-periods. This facilitates subsequent data sorting, refinement, and error fusion, thereby reducing the data accuracy during parameter calibration.

[0029] Optionally, after forming data windows corresponding to multiple monitoring points, before performing matrix processing on the raw water conservancy data within the data windows corresponding to multiple monitoring points according to different sub-time periods, the process further includes:

[0030] The raw water conservancy data within the data window is processed to ensure that the time frequency of each raw water conservancy data point within the data window is consistent. This guarantees that the raw water conservancy data within the same data window have a uniform time frequency, achieving data processing and standardization, and reducing the difficulty of subsequent data error fusion.

[0031] Optionally, after using the target fusion data as input parameters for the water conservancy monitoring model, the model further includes:

[0032] By running the water conservancy monitoring model, the monitoring and forecasting results of the monitored watershed are obtained, thereby providing strong support for flood analysis and forecasting, as well as the optimal allocation and scheduling of water resources.

[0033] Secondly, a parameter determination device for a water conservancy monitoring model is provided, the device may include:

[0034] The acquisition module can be used to acquire water conservancy data sequences corresponding to multiple monitoring points in the monitoring basin. The water conservancy data sequences include water conservancy data of the corresponding monitoring points within the first time period from the current time period. The first time period includes multiple sub-time periods.

[0035] The error fusion module can be used to perform error fusion on water conservancy data sequences according to different sub-time periods and different monitoring points to obtain target fused data of the monitored watershed in different sub-time periods;

[0036] The settings module can be used to use target fusion data as input parameters for water conservancy monitoring models.

[0037] Thirdly, an electronic device is provided, comprising a memory, a processor, and a parameter determination program for a water conservancy monitoring model stored in the memory and running on the processor, the parameter determination program for the water conservancy monitoring model implementing the steps of the parameter determination method for the water conservancy monitoring model as described in the first aspect.

[0038] Fourthly, a computer storage medium is provided, which, when executed by a processor, implements the steps of the parameter determination method for the water conservancy monitoring model as described in the first aspect.

[0039] Fifthly, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the steps of the parameter determination method for the water conservancy monitoring model as described in the first aspect.

[0040] Compared with existing technologies, the parameter determination method and related apparatus for the water conservancy monitoring model provided in this application obtain water conservancy data sequences corresponding to multiple monitoring points in the monitoring basin, and then perform error fusion on the water conservancy data sequences according to different sub-time periods and different monitoring points. The resulting target fused data of the monitoring basin within different sub-time periods is then used as the input parameters of the water conservancy monitoring model. Since the input parameters of the water conservancy monitoring model are the target fused data of the monitoring basin within different sub-time periods, which are obtained by performing error fusion on the water conservancy data of each monitoring point within the first time period based on different sub-time periods and different monitoring points, the model can automatically fuse and eliminate errors during the calibration process. This reduces the dependence on the accuracy of parameter calibration, thereby reducing the degree of human intervention in the parameter calibration process. This improves upon the technical problems of high professional barriers and high labor costs in parameter calibration during water conservancy monitoring. Attached Figure Description

[0041] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a schematic flowchart of a method for determining parameters of a water conservancy monitoring model according to an embodiment of this application.

[0043] Figure 2 This is a schematic and detailed flowchart of S110 in the parameter determination method of a water conservancy monitoring model according to an embodiment of this application.

[0044] Figure 3 This is a schematic and detailed flowchart of step S220 in the parameter determination method of a water conservancy monitoring model according to an embodiment of this application.

[0045] Figure 4 This is a schematic and detailed flowchart of S120 in the parameter determination method of a water conservancy monitoring model according to an embodiment of this application.

[0046] Figure 5 This is a schematic and detailed flowchart of step S410 in the parameter determination method of a water conservancy monitoring model according to an embodiment of this application.

[0047] Figure 6 This is a schematic block diagram of a parameter determination device for a water conservancy monitoring model according to another embodiment of this application.

[0048] Figure 7 This is a schematic block diagram of an electronic device according to another embodiment of this application. Detailed Implementation

[0049] The features and exemplary embodiments of various aspects of this application will now be described in detail. Numerous specific details are set forth in the following detailed description in order to provide a comprehensive understanding of this application. However, it will be apparent to those skilled in the art that this application can be implemented without some of these specific details. The following description of embodiments is merely intended to provide a better understanding of this application by illustrating examples thereof.

[0050] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The embodiments will now be described in detail with reference to the accompanying drawings.

[0051] Water conservancy monitoring is of great significance for watershed runoff calculation, flood analysis and forecasting, and the optimal allocation and scheduling of water resources. The foundation of water conservancy monitoring is the accurate application of watershed hydrological models.

[0052] The aforementioned watershed hydrological model uses mathematical models to simulate the formation process of rainfall or snowmelt-runoff in the watershed. However, the watershed hydrological cycle system and the formation of rainfall and runoff involved in the model are very complex. Therefore, in addition to considering the rationality of the model's own structure, the calibration of model parameters is also a very important step.

[0053] Related technologies typically involve manually calibrating model parameters, which requires repeated adjustments to achieve the desired results. This necessitates that the calibration personnel possess sufficient expertise in water conservancy monitoring model algorithms, resulting in a high professional barrier and labor cost for parameter calibration in the field of hydrological monitoring.

[0054] Taking the Xin'anjiang model as an example of the watershed hydrological model, most parameters of the Xin'anjiang model have clear physical meanings, and in principle, the values ​​of each parameter can be directly quantified based on their physical meanings.

[0055] However, in the actual application of the Xin'anjiang model, due to the lack of actual measurement and experimental process of each element in the formation of rainfall runoff, the parameter values ​​can only be deduced based on the measured flow at the outlet section when calibrating the parameters.

[0056] Furthermore, due to the complex formation of watershed hydrological phenomena and the numerous parameters involved in hydrological monitoring, the correlation between these parameters is unstable or not unique, and the amount of information that can be obtained from each parameter is limited, making the process of parameter calibration extremely difficult.

[0057] This application provides a method, apparatus, electronic device, and computer storage medium for determining parameters of a water conservancy monitoring model to improve or solve the above-mentioned problems.

[0058] The following section first introduces the parameter determination method for the water conservancy monitoring model in this application. (See attached image) Figure 1 In one embodiment of the parameter determination method for the water conservancy monitoring model of this application, the method includes:

[0059] S110, acquire the water conservancy data sequences corresponding to multiple monitoring points in the monitoring basin.

[0060] The aforementioned water conservancy data sequence may include water conservancy data from the corresponding monitoring point within the current first time period, and the first time period may include multiple sub-time periods.

[0061] S120, according to different sub-time periods and different monitoring points, performs error fusion on the water conservancy data sequence to obtain target fused data of the monitoring basin in different sub-time periods.

[0062] S130 uses the target fusion data as input parameters for the water conservancy monitoring model.

[0063] This application embodiment acquires water conservancy data sequences corresponding to multiple monitoring points in the monitored watershed, and then performs error fusion on the water conservancy data sequences according to different sub-time periods and different monitoring points. The resulting target fused data of the monitored watershed within different sub-time periods is then used as the input parameters of the water conservancy monitoring model. Since the input parameters of the water conservancy monitoring model are the target fused data of the monitored watershed within different sub-time periods, which is obtained by performing error fusion on the water conservancy data of each monitoring point within the first time period based on different sub-time periods and different monitoring points, it can automatically fuse and eliminate errors in the calibration process. This reduces the dependence on the accuracy of parameter calibration, thereby reducing the degree of human intervention in the parameter calibration process. This improves the technical problems of high professional barriers and high labor costs in parameter calibration during water conservancy monitoring.

[0064] The parameter determination method for the aforementioned water conservancy monitoring model can be applied to electronic devices, such as servers, computers, or monitoring systems composed of servers and computers. The following section will illustrate this method by applying it to a server.

[0065] The aforementioned water conservancy monitoring model can be a water conservancy dispatching early warning monitoring model based on a watershed hydrological model. The watershed hydrological model can include at least one of the Xin'anjiang model, Sacramento model, Stanford model, and water tank model.

[0066] In some optional examples of S110, multiple monitoring points can be set up in the monitoring basin. Each monitoring point can be equipped with monitoring equipment that can collect water conservancy data from the monitoring points in the monitoring basin.

[0067] The server can communicate with monitoring equipment at multiple monitoring points, collecting water resources data from each point and forming a time-ordered water resources data sequence. Each monitoring point has its own corresponding water resources data sequence.

[0068] Before conducting water conservancy monitoring and early warning, it is necessary to determine the parameters of the water conservancy monitoring model. At this time, the water conservancy data sequence corresponding to each monitoring point in the current first time period can be obtained.

[0069] It should be noted that, due to the time-sensitive nature of water conservancy monitoring, the duration of the first time period can be set according to actual needs. For example, the first time period can be set with reference to the water conservancy changes in the monitored watershed. For instance, the first time period mentioned above could be five hours from the present. In other examples, the first time period could also be one hour, two hours, or other time periods.

[0070] In some other optional examples, please see Figure 2 The acquisition of water conservancy data sequences corresponding to multiple monitoring points in the monitoring basin in S110 above may include:

[0071] S210: Obtain raw water conservancy data of the monitored watershed within the first time period from the current time.

[0072] S220 involves preprocessing the raw water conservancy data of the same monitoring point in different sub-time periods to obtain water conservancy data sequences corresponding to multiple monitoring points.

[0073] The aforementioned raw water resources data can be unprocessed initial water resources data collected from various monitoring points. After obtaining the raw water resources data for the first time period from each monitoring point in the monitored watershed, the server can distinguish the monitoring points and preprocess the raw water resources data according to different monitoring points.

[0074] For example, the preprocessing process may include: performing preliminary processing on the raw water conservancy data of each monitoring point to remove noise data from the raw water conservancy data, thereby reducing interference and helping to improve the accuracy of parameters of the water conservancy monitoring model.

[0075] For example, the preprocessing may include adjusting the raw water conservancy data of each monitoring point to a consistent data format, and may also include processing the raw water conservancy data to maintain consistency in statistical dimensions, such as time frequency.

[0076] In these examples, by preprocessing the raw water conservancy data, water conservancy data sequences corresponding to multiple monitoring points are obtained, which realizes data organization and standardization and reduces the difficulty of subsequent data error fusion.

[0077] In some additional optional examples, please see Figure 3 The process of preprocessing the raw water conservancy data of the same monitoring point in different sub-time periods to obtain water conservancy data sequences corresponding to multiple monitoring points may include the following steps S310 to S320.

[0078] S310 divides the raw water conservancy data of the same monitoring point into data windows, forming data windows corresponding to multiple monitoring points.

[0079] S320: According to different sub-time periods, matrix processing is performed on the raw water conservancy data in the data window corresponding to multiple monitoring points to obtain water conservancy data sequences corresponding to multiple monitoring points respectively.

[0080] Monitoring points can be differentiated, and raw water conservancy data from the same monitoring point can be grouped into the same data window. Furthermore, the duration of the data window can be considered as a factor in dividing the window; for example, raw water conservancy data from the same monitoring point within a 4-hour period can be grouped into one data window, thus obtaining at least one data window for each monitoring point.

[0081] For example, the raw water conservancy data of monitoring point B within 4 hours of the current time can be divided into a data window, which forms a data set of various raw water conservancy data for at least 1 hour.

[0082] For example, we can assume that the data window is divided into N time slices, and each time slice stores M raw water conservancy data. The data duration of the M raw water conservancy data can be consistent with the sub-time period.

[0083] The raw water resources data within the formed data window can be processed into matrices, resulting in multiple matrices for each time slice. For example, assuming the error generated by each raw water resources data point follows the same random distribution across different data points, matrix processing can ultimately generate at least 2M*N matrices. These time-ordered raw water resources data, after matrix processing, with the data within each data window represented in matrix form and arranged chronologically, can ultimately form water resources data sequences corresponding to multiple monitoring points.

[0084] In these examples, the data windows are divided by distinguishing monitoring points, and the raw water conservancy data within the data windows are processed into matrices according to multiple sub-periods. This facilitates subsequent data sorting, refinement, and error fusion, thereby reducing the data accuracy during parameter calibration.

[0085] Based on the above example, in some alternative examples, after forming data windows corresponding to multiple monitoring points, the original water conservancy data in the data windows corresponding to multiple monitoring points can be processed according to different sub-time periods before matrix processing is performed, so as to make the time frequency of each original water conservancy data in the data window consistent.

[0086] In this example, the original water conservancy data within the same data window can be processed according to different data windows, so that the data time corresponding to the original water conservancy data is within the same time window. This ensures that the original water conservancy data within the same data window has a uniform time frequency, realizes data organization and standardization, and reduces the difficulty of subsequent data error fusion.

[0087] In some optional examples of S120, the above error fusion mainly eliminates the dependence on data accuracy in the parameter calibration process in the field of water conservancy monitoring through data refinement, data marginalization and data integration, so that the parameter calibration rate can meet the accuracy requirements of the water conservancy monitoring model.

[0088] In this example, by distinguishing between different sub-periods and different monitoring points, error fusion can be performed on the matrices in the obtained water conservancy data sequence to obtain the target fused data of the entire monitoring basin within different sub-periods.

[0089] The target fusion data has undergone error fusion processing, which automatically fused and eliminated errors in the calibration process, reducing the dependence on the accuracy of parameter calibration. This reduces the degree of human intervention in the parameter calibration process, thereby improving the technical problems of high professional barriers and high labor costs in parameter calibration during water conservancy monitoring.

[0090] In some other optional examples, please see Figure 4 The process in S120 above, which involves error fusion of water conservancy data sequences according to different sub-time periods and different monitoring points to obtain target fused data of the monitoring basin within different sub-time periods, may include:

[0091] S410, sequentially perform fusion and edge-processing on the water conservancy data of multiple sub-periods in the water conservancy data sequence to obtain the first fused data corresponding to the monitoring points in each of the multiple sub-periods.

[0092] S420 performs time-segment fusion processing on the first fusion data of different monitoring points in the same sub-time period to obtain the target fusion data of the monitoring basin in different sub-time periods.

[0093] The water resources data within the aforementioned multiple sub-periods can be obtained by processing the original water resources data within the data window using a matrix. The fusion and marginalization processing of this matrix-form water resources data refers to the process of retaining the common parts of each water resources data point in the water resources data sequence or matrix, and combining the marginalized parts refined through marginalization with the common parts.

[0094] For the same monitoring point, the water resources data of the current time period can be merged and edge-processed with the matrix-form water resources data generated in the previous time period according to the sub-time periods corresponding to each water resources data in the water resources data sequence. By sequentially merging and edge-processing the water resources data in all time periods in the water resources data sequence, the first fused data, which accumulates the common information of all water resources data before the current sub-time period and the characteristic information of each water resources data, can be obtained. After obtaining the first fused data corresponding to the same monitoring point in multiple sub-time periods, the first fused data of all monitoring points can be fused according to different sub-time periods to finally form the target fused data of the entire monitoring basin in different sub-time periods.

[0095] In these examples, by differentiating monitoring points and performing edge-mapping processing on the fusion of water conservancy data across multiple sub-periods, it is possible to minimize information loss from the same monitoring point across different sub-periods while also achieving data error fusion and elimination. Based on this, further time-period fusion processing can restore the water conservancy situation across the entire monitoring basin as accurately as possible within different sub-periods, obtaining a more complete set of input parameters required for the water conservancy monitoring model.

[0096] Please refer to Figure 5Based on the above examples, in some further alternative examples of this application, S410 may include:

[0097] S510: Select the starting time period from multiple sub-time periods.

[0098] S520 uses a sliding window to move forward gradually from the water resources data of the initial time period in the water resources data sequence.

[0099] S530: Whenever the sliding window moves, retrieve the public water resources data and peripheral water resources data for the current time period relative to the previous time period from within the sliding window. This water resources data may include both public and peripheral water resources data.

[0100] S540 extracts data from peripheral water conservancy data and merges public water conservancy data with the extracted peripheral water conservancy data to obtain the first fused data of the monitoring point in the current time period.

[0101] S550 updates the water conservancy data in the sliding window to the first fused data of the monitoring point in the current time period.

[0102] It should be noted that, initially, the aforementioned starting time period is typically the earliest time period among multiple sub-time periods for recording water conservancy data. When obtaining public and marginal water conservancy data for the current time period relative to the previous time period, the public information domain algorithm can be used. The refined public water conservancy data does not require further optimization, while the marginal water conservancy data can be refined and optimized using an edge-optimization algorithm, resulting in a new matrix.

[0103] The refined and optimized marginal water resources data can be fused with public water resources data containing common information to ensure minimal data loss. After moving through the sliding window, the first fused data becomes the new water resources data for the previous time period, which will be compared with the water resources data for the next sub-time period for common information.

[0104] As each piece of water resources data in the water resources data sequence is compared, refined, and fused using algorithms, the starting time period is continuously shifted backward. The water resources data in the water resources data sequence is also gradually updated to the first fused data of the monitoring point in the current time period. Finally, when the sliding window moves to the end of the water resources data sequence, the updated water resources data sequence stores the first fused data corresponding to the monitoring point in multiple sub-time periods.

[0105] It should also be noted that the specific types of public information domain algorithms, edge computing algorithms, and information fusion algorithms are not limited here. As long as they can distinguish between public water conservancy data and edge water conservancy data in the current time period relative to the previous time period, and achieve data optimization and information fusion, they are acceptable.

[0106] These examples demonstrate a detailed process for sequentially fusing and marginalizing water conservancy data from multiple sub-periods in a water conservancy data sequence to obtain the first fused data corresponding to each monitoring point in each sub-period. This process enables error fusion processing of data while minimizing information loss, thereby reducing the need for manual intervention in subsequent water conservancy monitoring.

[0107] In some optional examples of S130, target fusion data from different sub-periods of the monitored watershed can be used as input parameters for the water conservancy monitoring model, helping to reduce the workload of manual parameter calibration. The water conservancy monitoring model can then be run to obtain monitoring and forecasting results for the monitored watershed, providing strong support for flood analysis and forecasting, as well as the optimal allocation and scheduling of water resources.

[0108] The parameter determination method of the water conservancy monitoring model in the embodiments of this application has been described in detail above. The following will combine... Figure 6 This application describes in detail the parameter determination device for a water conservancy monitoring model according to an embodiment of the present application.

[0109] The acquisition module 610 can be used to acquire water conservancy data sequences corresponding to multiple monitoring points in the monitoring basin. The water conservancy data sequences include water conservancy data of the corresponding monitoring points within the first time period from the current time period. The first time period includes multiple sub-time periods.

[0110] The error fusion module 620 can be used to perform error fusion on water conservancy data sequences according to different sub-time periods and different monitoring points to obtain target fusion data of the monitored watershed in different sub-time periods;

[0111] The setting module 630 can be used to use target fusion data as input parameters for a water conservancy monitoring model.

[0112] Optionally, the error fusion module 620 may include:

[0113] The processing unit can be used to sequentially perform fusion and edge-processing on water conservancy data in multiple sub-periods of the water conservancy data sequence to obtain the first fused data corresponding to the monitoring points in the multiple sub-periods; and to perform time-period fusion processing on the first fused data of different monitoring points in the same sub-period to obtain the target fused data of the monitoring basin in different sub-periods.

[0114] Optionally, the processing unit can also be used to select a starting time period from multiple sub-time periods; in the water conservancy data sequence, a sliding window is used to move forward step by step from the water conservancy data of the starting time period; whenever the sliding window moves, the public water conservancy data and marginal water conservancy data of the current time period relative to the previous time period are obtained from the sliding window, the water conservancy data includes public water conservancy data and marginal water conservancy data; the marginal water conservancy data is refined, and the public water conservancy data is fused with the refined marginal water conservancy data to obtain the first fused data of the monitoring point in the current time period; the water conservancy data in the sliding window is updated to the first fused data of the monitoring point in the current time period.

[0115] Optionally, the acquisition module 610 may include:

[0116] The acquisition unit can be used to acquire raw water conservancy data of the monitored watershed within the first time period from the current time.

[0117] The preprocessing unit can be used to preprocess the raw water conservancy data of the same monitoring point in different sub-time periods to obtain water conservancy data sequences corresponding to multiple monitoring points.

[0118] Optionally, the preprocessing unit can also be used to divide the raw water conservancy data of the same monitoring point into data windows to form multiple data windows corresponding to multiple monitoring points; according to different sub-time periods, matrix processing is performed on the raw water conservancy data in the data windows corresponding to multiple monitoring points to obtain water conservancy data sequences corresponding to multiple monitoring points respectively.

[0119] Optionally, the acquisition module 610 may also include:

[0120] The frequency adjustment unit is used to process the raw water conservancy data in the data window to make the time frequency of each raw water conservancy data in the data window consistent.

[0121] Optionally, the device may further include:

[0122] The operation unit is used to run the water conservancy monitoring model and obtain the monitoring and forecasting results of the monitored watershed.

[0123] Figure 7 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application is shown. The electronic device may include a processor 701 and a memory 702 storing computer program instructions.

[0124] Specifically, the processor 701 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0125] Memory 702 may include mass storage for data or instructions. For example, and not limitingly, memory 702 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 702 may include removable or non-removable (or fixed) media. Where appropriate, memory 702 may be internal or external to an electronic device. In a particular embodiment, memory 702 is a non-volatile solid-state memory.

[0126] Memory 702 may include read-only memory (ROM), flash memory device, random access memory (RAM), disk storage medium device, optical storage medium device, electrical, optical, or other physical / tangible memory storage device. Therefore, typically, memory 702 includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software that may include computer-executable instructions and, when executed (e.g., by one or more processors), is operable to perform the operations described with reference to the methods described above according to the foregoing aspects of this disclosure.

[0127] The processor 701 reads and executes computer program instructions stored in the memory 702 to implement the parameter determination method of any of the water conservancy monitoring models in the above embodiments.

[0128] In one example, the electronic device may also include a communication interface 703 and a bus 710. For example, Figure 7 As shown, the processor 701, memory 702, and communication interface 703 are connected through bus 710 and complete communication with each other.

[0129] The communication interface 703 is mainly used to realize communication between various modules, systems, devices, units and / or equipment in the embodiments of this application.

[0130] Bus 710 includes hardware, software, or both, that couples components of an electronic device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 710 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0131] This electronic device can achieve a combination of parameter determination methods based on water conservancy monitoring models. Figures 1 to 6 The method and apparatus for determining the parameters of the water conservancy monitoring model are described.

[0132] Based on the parameter determination method of the water conservancy monitoring model in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the parameter determination methods of the water conservancy monitoring model in the above embodiments.

[0133] Furthermore, in conjunction with the parameter determination method for the water conservancy monitoring model in the above embodiments, this application embodiment can provide a computer program product for implementation. This computer program product stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the parameter determination methods for the water conservancy monitoring model in the above embodiments.

[0134] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0135] It should be understood that in the embodiments of this application, "B corresponding to A" means that B is associated with A, and B can be determined based on A. However, it should also be understood that determining B based on A does not mean that B is determined solely based on A; B can also be determined based on A and / or other information.

[0136] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for determining parameters of a water conservancy monitoring model, characterized in that, include: Obtain water conservancy data sequences corresponding to multiple monitoring points in the monitored watershed. The water conservancy data sequences include water conservancy data of the corresponding monitoring points within a first time period from the current time period. The first time period includes multiple sub-time periods. Select a starting time period from among the multiple sub-time periods; In the water conservancy data sequence, a sliding window is used to gradually move forward from the water conservancy data of the initial time period; Whenever the sliding window moves, public water conservancy data and peripheral water conservancy data for the current time period relative to the previous time period are obtained from the sliding window. The water conservancy data includes the public water conservancy data and the peripheral water conservancy data. The marginal water conservancy data is refined, and the public water conservancy data is fused with the refined marginal water conservancy data to obtain the first fused data of the monitoring point in the current time period; Update the water conservancy data in the sliding window to the first fused data of the monitoring point in the current time period; The first fused data from different monitoring points in the same sub-time period are subjected to time period fusion processing to obtain the target fused data of the monitored watershed in different sub-time periods; The target fusion data is used as the input parameters of the water conservancy monitoring model.

2. The method according to claim 1, characterized in that, The acquisition of water conservancy data sequences corresponding to multiple monitoring points in the monitored watershed includes: Obtain the raw water conservancy data of the monitored watershed within the first time period from the current point in time; Data preprocessing is performed on the original water conservancy data of the same monitoring point in different sub-time periods to obtain water conservancy data sequences corresponding to multiple monitoring points.

3. The method according to claim 2, characterized in that, The process of preprocessing the raw water conservancy data from the same monitoring point in different sub-time periods yields water conservancy data sequences corresponding to multiple monitoring points, including: The original water conservancy data of the same monitoring point is divided into data windows to form multiple data windows corresponding to the monitoring points; According to different sub-time periods, the original water conservancy data within the data window corresponding to multiple monitoring points are subjected to matrix processing to obtain water conservancy data sequences corresponding to multiple monitoring points respectively.

4. The method according to claim 3, characterized in that, After forming multiple data windows corresponding to the monitoring points, and before performing matrix processing on the raw water conservancy data within the data windows corresponding to the multiple monitoring points according to different sub-time periods, the method further includes: The raw water conservancy data within the data window are processed to ensure that the time frequency of each raw water conservancy data point within the data window is consistent.

5. The method according to claim 1, characterized in that, After using the target fused data as input parameters for the water conservancy monitoring model, the method further includes: The water conservancy monitoring model is run to obtain the monitoring and forecasting results for the monitored watershed.

6. A parameter determination device for a water conservancy monitoring model, characterized in that, The device includes: The acquisition module is used to acquire water conservancy data sequences corresponding to multiple monitoring points in the monitored watershed. The water conservancy data sequences include water conservancy data of the corresponding monitoring points within a first time period from the current time period, and the first time period includes multiple sub-time periods. A processing unit is configured to select a start time period from the plurality of said sub-time periods; The processing unit is also configured to use a sliding window to gradually move forward from the water conservancy data of the initial time period in the water conservancy data sequence. The processing unit is further configured to acquire, whenever the sliding window moves, the public water conservancy data and the edge water conservancy data of the current time period relative to the previous time period from the sliding window, wherein the water conservancy data includes the public water conservancy data and the edge water conservancy data; The processing unit is also used to refine the edge water conservancy data and fuse the public water conservancy data with the refined edge water conservancy data to obtain the first fused data of the monitoring point in the current time period; The processing unit is also used to update the water conservancy data in the sliding window to the first fused data of the monitoring point in the current time period; The processing unit is also used to perform time period fusion processing on the first fusion data of different monitoring points in the same sub-time period to obtain the target fusion data of the monitoring watershed in different sub-time periods; The setting module is used to use the target fusion data as input parameters for the water conservancy monitoring model.

7. An electronic device, characterized in that, The electronic device includes a memory, a processor, and a parameter determination program for a water conservancy monitoring model stored in the memory and running on the processor. The parameter determination program for the water conservancy monitoring model performs the steps of the parameter determination method for the water conservancy monitoring model as described in any one of claims 1 to 5.

8. A computer storage medium, characterized in that, When the computer storage medium is executed by the processor, it implements the steps of the parameter determination method for the water conservancy monitoring model according to any one of claims 1 to 5.

Images