Water quality assessment method, device, computer equipment and storage medium

Abstract

The present application relates to a water quality assessment method, device, computer equipment, storage medium and computer program product. The method comprises: obtaining a water area data set of a target water area; based on the water area data set, determining a target water pollution diffusion assessment model in a pre-constructed multidimensional model library; based on the target water pollution diffusion assessment model and the water area data set, determining the weight data of each water quality influencing factor index in the water area data set, and verifying each weight data based on a preset entropy weight method to obtain the verified weight data; based on the verified weight data and the water area data set, determining the water quality assessment result of the target water area in the future period. The use of this method can improve the accuracy and timeliness of the water quality assessment results.

Description

Technical Field

[0001] The present application relates to the technical field of water quality detection, and in particular to a water quality assessment method, device, computer equipment, storage medium and computer program product. Background Art

[0002] Water pollution prevention and control has always been an area of ​​key concern for the country. Therefore, it is necessary to regularly test and evaluate water quality in order to improve water pollution problems.

[0003] The current water quality assessment method usually obtains water quality data from the water environment management system, and uses the preset pollution prevention and control targets as the assessment standard, compares and judges the obtained water quality data with the pollution prevention and control targets, and thus determines the water quality assessment results.

[0004] However, when water quality is assessed using current water quality assessment methods, the water quality data obtained in the water environment management system is less timely, and the water quality assessment results obtained using current water quality assessment methods often lag behind the occurrence of water pollution incidents, which in turn leads to low accuracy and timeliness of water quality assessment results. Summary of the invention

[0005] Based on this, it is necessary to provide a water quality assessment method, device, computer equipment, computer readable storage medium and computer program product to address the above technical problems.

[0006] In a first aspect, the present application provides a water quality assessment method, comprising:

[0007] Obtain a water area dataset of the target water area;

[0008] Based on the water area data set, determining a target water pollution diffusion assessment model in a pre-built multidimensional model library;

[0009] Based on the target water pollution diffusion assessment model and the water area data set, determine the weight data of each water quality influencing factor index in the water area data set, and verify each of the weight data based on a preset entropy weight method to obtain verified weight data;

[0010] Based on the verified weight data and the water area data set, the water quality assessment result of the target water area in a future time period is determined.

[0011] In the above water quality assessment method, a target water pollution diffusion assessment model is determined in a pre-constructed multidimensional model library to adapt to the water environment scenario of the current target water area. The target water pollution diffusion assessment model is used to calculate the weight data of the water area data set of the monitored target water area, and the weight data of each water quality influencing factor indicator in the water area data set is obtained. The entropy weight method is used to verify the weight data to further improve the accuracy of the water quality assessment. Then, based on the verified weight data and the water area data set, the water quality assessment results of the target water area in the future period are predicted and evaluated, thereby improving the accuracy and timeliness of the water quality assessment results.

[0012] In one embodiment, the step of obtaining a water area dataset of a target water area includes:

[0013] Obtaining original water area data of the target water area;

[0014] The original water area data is subjected to data integration and missing value screening processing, and based on the water quality influencing factor indicators contained in the original water area data, the water area data corresponding to each water quality influencing factor indicator is standardized to obtain a water area data set.

[0015] In this embodiment, without the help of data storage platforms such as water environment management platforms, the water area data of the target water area is directly collected for water quality monitoring and evaluation to ensure the timeliness of the water area data, and the directly collected original water area data is processed to ensure the quality of the water area data and improve the accuracy of water quality evaluation.

[0016] In one embodiment, the water area data set includes water area data corresponding to each water quality influencing factor index and the measurement index, and the weight data are verified based on the preset entropy weight method to obtain the verified weight data, including:

[0017] For each water quality influencing factor index in the water area data set, normalizing the water area data of the water quality influencing factor index to obtain normalized water area data;

[0018] Based on a preset entropy weight algorithm, determine the proportion of each water area data in the water quality influencing factor index, and based on the proportion of each water area data, determine the entropy value of the water quality influencing factor index;

[0019] Determine the calibration weight corresponding to each water quality influencing factor indicator according to the entropy value of each water quality influencing factor indicator;

[0020] Based on the verification weight, the weight data of each of the water quality influencing factors is verified to obtain verified weight data.

[0021] In this embodiment, the weight of each water quality influencing factor index in the water area data set is recalculated by the entropy weight method to obtain the verification weight of each water quality influencing factor index, and then, the weight data of each water quality influencing factor index is verified based on each verification weight, so as to improve the accuracy of the weight data of each water quality influencing factor index, and then, improve the accuracy of the water quality assessment results.

[0022] In one embodiment, after determining the water quality assessment result of the target water area in a future period based on the verified weight data and the water area data set, the method further includes:

[0023] Acquire a monitoring water area data set, wherein the monitoring water area data set includes water area data corresponding to various water quality influencing factor indicators of the target area at a preset time granularity;

[0024] Based on a preset rank sum ratio algorithm and the monitored water area data set, determining the rank sum ratio and probability unit corresponding to each of the target areas;

[0025] Performing linear regression analysis based on the rank sum ratio and the probability unit corresponding to each of the target areas to obtain a linear regression equation, and determining the change trend of the water quality influencing factor index corresponding to each of the target areas based on the linear regression equation;

[0026] The water quality management result of the target water area is obtained according to the change trend of each water quality influencing factor indicator corresponding to each target area.

[0027] In this embodiment, after conducting a water quality assessment, the rank sum ratio and probability unit corresponding to each target area are determined based on the rank sum ratio algorithm and the monitored water area data set. Then, a linear regression analysis can be performed based on the rank sum ratio and probability unit corresponding to the target area to obtain a linear regression equation. Based on the linear regression equation, the management and prevention of water quality in the target area can be tracked and evaluated to obtain water quality management results, thereby improving the accuracy of water quality management.

[0028] In one embodiment, after performing linear regression analysis based on the rank sum ratio corresponding to each of the target areas and the probability unit to obtain a linear regression equation, the method further includes:

[0029] Based on the linear regression equation, determining a grading critical value;

[0030] Based on the grading critical value, the rank sum ratio corresponding to each of the target areas is graded to determine the grading results of the water quality treatment results of each of the target areas.

[0031] In this embodiment, based on the linear regression equation determined by the rank sum ratio algorithm, the critical value of the water quality treatment results is further determined, and then, based on the critical value of the water quality treatment results, the treatment level of the water quality treatment results in each target area is determined, thereby achieving a refined classification of the water quality treatment results and improving the scientificity and accuracy of water quality management.

[0032] In one embodiment, before determining the target water pollution diffusion assessment model in a pre-built multidimensional model library based on the water area data set, the method further includes:

[0033] Acquire a sample water area data set; the sample water area data set includes water area data corresponding to various water quality influencing factor indicators at different time granularities;

[0034] Select water quality influencing factor indicators of each target dimension and measurement indicators corresponding to each water quality influencing factor indicator, and construct a target dimension water pollution diffusion assessment model based on the water quality influencing factors and the water area data corresponding to the measurement indicators;

[0035] Based on the water pollution diffusion assessment model of each target dimension, a multidimensional model library is constructed.

[0036] In this embodiment, a multidimensional model library is constructed in advance based on the sample water area data set. The water pollution diffusion assessment models of various dimensions contained in the multidimensional model library are adapted to the water field environment of various water areas. Furthermore, in the water quality assessment process, the target water pollution diffusion assessment model for the target water area is selected from the multidimensional model library to determine the weight data, thereby improving the processing efficiency and accuracy of the water quality assessment.

[0037] In one embodiment, the step of determining a target water pollution diffusion assessment model in a pre-built multi-dimensional model library based on the water area dataset includes:

[0038] Based on the water quality influencing factor indicators and measurement indicators contained in the water area data set and the time granularity of the water area data of the water quality influencing factor indicators, a target water pollution diffusion assessment model is determined in a pre-constructed multidimensional model library.

[0039] In this embodiment, a multidimensional model library is pre-constructed. When conducting water quality assessment, a target water pollution diffusion assessment model that matches the water field environment of the target water area can be selected based on the water field environment characteristics of the target water area reflected in the water area data set. Then, the weight data of each water quality influencing factor indicator is determined through the target water pollution diffusion assessment model, thereby improving the accuracy of water quality assessment.

[0040] In a second aspect, the present application also provides a water quality assessment device, comprising:

[0041] An acquisition module is used to acquire a water area dataset of a target water area;

[0042] A first determination module is used to determine a target water pollution diffusion assessment model in a pre-built multidimensional model library based on the water area data set;

[0043] A verification module, used to determine the weight data of each water quality influencing factor index in the water area data set based on the target water pollution diffusion assessment model and the water area data set, and verify each of the weight data based on a preset entropy weight method to obtain the verified weight data;

[0044] The second determination module is used to determine the water quality assessment result of the target water area in a future period based on the verified weight data and the water area data set.

[0045] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0046] Obtain a water area dataset of the target water area;

[0047] Based on the water area data set, determining a target water pollution diffusion assessment model in a pre-built multidimensional model library;

[0048] Based on the target water pollution diffusion assessment model and the water area data set, determine the weight data of each water quality influencing factor index in the water area data set, and verify each of the weight data based on a preset entropy weight method to obtain verified weight data;

[0049] Based on the verified weight data and the water area data set, the water quality assessment result of the target water area in a future time period is determined.

[0050] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0051] Obtain a water area dataset of the target water area;

[0052] Based on the water area data set, determining a target water pollution diffusion assessment model in a pre-built multidimensional model library;

[0053] Based on the target water pollution diffusion assessment model and the water area data set, determine the weight data of each water quality influencing factor index in the water area data set, and verify each of the weight data based on a preset entropy weight method to obtain verified weight data;

[0054] Based on the verified weight data and the water area data set, the water quality assessment result of the target water area in a future time period is determined.

[0055] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0056] Obtain a water area dataset of the target water area;

[0057] Based on the water area data set, determining a target water pollution diffusion assessment model in a pre-built multidimensional model library;

[0058] Based on the target water pollution diffusion assessment model and the water area data set, determine the weight data of each water quality influencing factor index in the water area data set, and verify each of the weight data based on a preset entropy weight method to obtain verified weight data;

[0059] Based on the verified weight data and the water area data set, the water quality assessment result of the target water area in a future time period is determined.

[0060] The water quality assessment method, device, computer equipment, storage medium and computer program product obtain a water area data set of the target water area; based on the water area data set, determine the target water pollution diffusion assessment model in a pre-constructed multidimensional model library; based on the target water pollution diffusion assessment model and the water area data set, determine the weight data of each water quality influencing factor index in the water area data set, and verify each of the weight data based on a preset entropy weight method to obtain the verified weight data; based on the verified weight data and the water area data set, determine the water quality assessment result of the target water area in the future period. Using this method, the target water pollution diffusion assessment model is determined in a pre-constructed multidimensional model library, adapted to the water environment scene of the current target water area, and the target water pollution diffusion assessment model is used to calculate the weight data of the water area data set of the monitored target water area, and the weight data of each water quality influencing factor index in the water area data set is obtained, and the entropy weight method is used to verify the weight data, so as to further improve the accuracy of water quality assessment, and then, based on the verified weight data and the water area data set, the water quality assessment result of the target water area in the future period is predicted and evaluated, so as to improve the accuracy and timeliness of the water quality assessment result. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0062] Figure 1is a schematic flow chart of a water quality assessment method in one embodiment;

[0063] Figure 2 A schematic diagram of a flow chart of the steps of obtaining a water area dataset of a target water area in one embodiment;

[0064] Figure 3 It is an architectural diagram of a water area dataset integration step in one embodiment;

[0065] Figure 4 A schematic diagram of a flow chart of a step of verifying weight data based on an entropy weight method in one embodiment;

[0066] Figure 5 A schematic diagram of a flow chart of steps for determining a water quality treatment result based on a rank sum ratio algorithm in one embodiment;

[0067] Figure 6 A variation trend curve fitting diagram in one embodiment;

[0068] Figure 7 A schematic diagram of a flow chart of a step of determining the grading results of water quality treatment results in one embodiment;

[0069] Figure 8 A schematic diagram of a process for constructing a multidimensional model library in one embodiment;

[0070] Fig. 9 A process flow diagram of a water quality assessment and method in one embodiment;

[0071] Fig.10 is a structural block diagram of a water quality assessment device in one embodiment;

[0072] Fig.11 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0073] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0074] In one embodiment, Figure 1 As shown, a water quality assessment method is provided. This embodiment uses the method applied to a terminal as an example. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps 102 to 106. Among them:

[0075] Step 102, obtaining a water area dataset of a target water area.

[0076] In the implementation, the terminal obtains a water area data set of the target water area. The water area data set is a multi-source water area data set, and its data source can come from different types of monitoring equipment such as sensors and detectors. The embodiment of the present application does not limit this, and the water area data set has been pre-processed, and impurity data such as missing values ​​have been removed, and the format of multi-source heterogeneous data has been unified.

[0077] Step 104, based on the water area data set, determine the target water pollution diffusion assessment model in a pre-built multi-dimensional model library.

[0078] In implementation, the terminal determines the target water pollution diffusion assessment model in a pre-built multidimensional model library based on the water area data set. Specifically, the terminal identifies the environmental characteristics of the water field environment of the target water area in the water area data set, and then, based on the characteristic data in the water area data set, determines the target water pollution diffusion assessment model adapted to the water field environment of the target water area in the pre-built multidimensional model library.

[0079] Optionally, the pre-built multidimensional model library contains a one-dimensional water pollution diffusion assessment model, a two-dimensional water pollution diffusion assessment model, ... an N-dimensional water pollution diffusion assessment model, and the types of models contained in the multidimensional model library may be regression prediction models, neural network models, etc. The embodiment of the present application does not limit the number of dimensions (water quality influencing factor indicators) and model types of the models in the multidimensional model library. The water quality influencing factor indicators contained in each water pollution diffusion assessment model in the specific multidimensional model library can be determined based on the water quality scenario environment and business needs.

[0080] Step 106, based on the target water pollution diffusion assessment model and the water area data set, determine the weight data of each water quality influencing factor indicator in the water area data set, and verify each weight data based on a preset entropy weight method to obtain the verified weight data.

[0081] In implementation, the water area data set includes various water quality influencing factor indicators and water area data corresponding to each water quality influencing factor indicator. The terminal determines the weight data of each water quality influencing factor indicator in the water area data set based on the target water pollution diffusion assessment model and the water area data set. Specifically, the target water pollution diffusion assessment model can calculate the weight data of each water quality influencing factor indicator contained in the water area data set based on the real value and predicted value of each water area data in the water area data set, and then verify the calculated weight data based on the preset entropy weight method to obtain the verified weight data.

[0082] Step 108, based on the verified weight data and the water area data set, determine the water quality assessment result of the target water area in the future period.

[0083] In implementation, since the time granularity characteristics of the water area data set can be, but are not limited to, based on hours, days, weeks, etc., the terminal can determine the water quality assessment results of the target water area in the future period based on the verified weight data and the current water area data set. Specifically. Based on the verified weight data and the water area data set, the terminal predicts the water area data of the future period under the time granularity of the target water area to obtain predicted water area data, and then, water quality assessment calculations can be performed based on the predicted water area data to determine the water quality assessment results of the target water area in the future period.

[0084] In the above water quality assessment method, a target water pollution diffusion assessment model is determined in a pre-constructed multidimensional model library to adapt to the water environment scenario of the current target water area. The target water pollution diffusion assessment model is used to calculate the weight data of the water area data set of the monitored target water area, and the weight data of each water quality influencing factor indicator in the water area data set is obtained. The entropy weight method is used to verify the weight data to further improve the accuracy of the water quality assessment. Then, based on the verified weight data and the water area data set, the water quality assessment results of the target water area in the future period are predicted and evaluated, thereby improving the accuracy and timeliness of the water quality assessment results.

[0085] In an exemplary embodiment, Figure 2 As shown, step 102 includes steps 202 to 204 .

[0086] in:

[0087] Step 202, obtaining the original water area data of the target water area.

[0088] In implementation, different monitoring dimensions and different types of water quality monitoring equipment will be set up for each monitored water area, so that each monitored water area can obtain multi-source heterogeneous original water area data. For example, the original water area data may include: spatial data related to water quality pollution, hydrological data, pollution data, monitoring data and vector data, etc. For the target water area to be analyzed, the terminal directly obtains the original water area data collected by the on-site monitoring equipment of the target water area to ensure the timeliness of the water area data.

[0089] Step 204 , performing data integration and missing value screening processing on the original water area data, and based on the water quality influencing factor indicators contained in the original water area data, performing standardization processing on the water area data corresponding to each water quality influencing factor indicator to obtain a water area data set.

[0090] In the implementation, the terminal performs preparatory work such as aggregation, processing, and extraction on the original water area data based on business needs. After the preparatory work is completed, the terminal integrates the water area data of the water field environment and screens missing values ​​for the original water area data, and based on the water quality influencing factor indicators contained in the original water area data, standardizes the water area data corresponding to each water quality influencing factor indicator to obtain a water area data set. Specifically, the terminal obtains the original water area data of the target water area and integrates the original data into a water area data set, such as Figure 3 As shown, the source of the original water area data of the target water area can be spatial data, monitoring data, hydrological data, vector data, etc. collected by space monitoring equipment (or space acquisition equipment). Through data processing methods such as standardization processing and topological calculation, the multi-source heterogeneous data can be integrated to obtain a processed water area data set. This water area data set can be used as data support for the water quality assessment process to participate in fitting value calculation, application of multi-dimensional data models, data analysis, data mining, etc.

[0091] Optionally, the terminal may also perform operations such as diffusion, dilution, and format conversion on the original water area data to improve the data quality of the original water area data. The embodiment of the present application does not limit the processing of the water area data by the terminal.

[0092] In this embodiment, without the aid of data storage platforms such as water environment management platforms, water area data of the target water area is directly collected for water quality monitoring and assessment to ensure the timeliness of the water area data, and the directly collected original water area data is processed to ensure the quality of the water area data and improve the accuracy of water quality assessment.

[0093] In an exemplary embodiment, the water area data set includes water area data corresponding to each water quality influencing factor index and the measurement index. In order to ensure the accuracy of the weight data of each water quality influencing factor index, after determining the weight data corresponding to each water quality influencing factor index in the water area data set, the weight data of each water quality influencing factor index can be verified based on the water area data corresponding to each water quality influencing factor index and the entropy weight method, such as Figure 4 As shown, step 106 includes steps 402 to 406. Among them:

[0094] Step 402 , for each water quality influencing factor index in the water area data set, normalize the water area data of the water quality influencing factor index to obtain the normalized water area data.

[0095] In implementation, since the water area data contained in the water area data set come from multiple types of data acquisition devices, and the water quality influencing factor indicators corresponding to the water area data are different, the format, dimension, etc. of each water area data may be different. Therefore, for each water quality influencing factor indicator in the water area data set, the terminal normalizes the water area data of the water quality influencing factor indicator to obtain the normalized water area data.

[0096] Step 404, based on a preset entropy weight algorithm, determine the proportion of each water area data in the water quality influencing factor index, and based on the proportion of each water area data, determine the entropy value of the water quality influencing factor index.

[0097] In the implementation, the terminal determines the weight of each water area data in the water quality influencing factor index based on a preset entropy weight algorithm, and then determines the entropy value of the water quality influencing factor index based on the weight of each water area data. Specifically, the water area data corresponding to each water quality influencing factor index can form a matrix of water area data. For each water quality influencing factor index, the terminal determines the weight of each water area data relative to the water quality influencing factor index. For example, for the jth water area data corresponding to the i-th water quality influencing factor index, the terminal calculates the weight of the jth water area data. , the specific calculation formula is shown in the following formula (1):

[0098]

[0099] in, is the jth water area data corresponding to the i-th water quality influencing factor index, n represents the total number of water quality influencing factor indexes, and m represents the number of water area data included in the i-th water quality influencing factor index. Then, the terminal can calculate the entropy value (also called information entropy) of the water quality influencing factor index based on the proportion of each water area data of the water quality influencing factor index.

[0100] Step 406: Determine the verification weight corresponding to each water quality influencing factor indicator according to the entropy value of each water quality influencing factor indicator.

[0101] In implementation, the terminal determines the verification weight corresponding to each water quality influencing factor index according to the entropy value of each water quality influencing factor index. Specifically, the verification weight is the weight data of each water quality influencing factor index recalculated by the terminal in another way, and the recalculated weight data is used as the verification weight to verify the weight data calculated based on the target water pollution diffusion assessment model.

[0102] For example, the water quality influencing factor indicators include: the discharge of water pollution source A and the discharge of water pollution source N. The entropy weight method is used to calculate the calibration weight of the water quality influencing factor indicators, and the calculation results of the calibration weight of the water quality influencing factor indicators are obtained, as shown in Table 1 below:

[0103] Table 1

[0104]

[0105] Among them, the information entropy value is used to characterize the uncertainty measurement of information, and the information utility value is used to characterize the value of information for decision-making.

[0106] Step 408, based on the verification weight, verify the weight data of each water quality influencing factor to obtain verified weight data.

[0107] In implementation, the terminal verifies the weight data of each water quality influencing factor based on the verification weight to obtain the verified weight data. Specifically, based on the comparison of the weight data of each water quality influencing factor indicator and the corresponding verification weight, when the deviation between the weight data of the water quality influencing factor indicator and the verification weight corresponding to the weight data is greater than the second preset error threshold, it is determined that the weight data of the water quality influencing factor indicator does not meet the weight data requirements, and the weight data of each water quality influencing factor indicator contained in the overall water area data set needs to be re-determined to obtain the verified weight.

[0108] In this embodiment, the weight of each water quality influencing factor index in the water area data set is recalculated by the entropy weight method to obtain the verification weight of each water quality influencing factor index, and then, the weight data of each water quality influencing factor index is verified based on each verification weight, so as to improve the accuracy of the weight data of each water quality influencing factor index, and then, improve the accuracy of the water quality assessment results.

[0109] In an exemplary embodiment, after determining the water quality assessment result of the target water area in the future time period, the water quality of the target area can also be periodically tested and evaluated. For example, based on the determined water quality assessment result of the target area, a water quality control strategy corresponding to the water quality assessment result is executed. Then, in order to determine the effectiveness of the water quality control strategy, the water quality control effect of the target area can also be tested. Alternatively, before determining the water quality assessment result of the target water area in the future time period, the water quality of the target area can be pre-tested and evaluated based on the previous periodic water quality control result. Therefore, the present application adopts the RSR algorithm to determine the water quality control result, such as Figure 5 As shown, after step 108, the method further includes:

[0110] Step 502, obtaining a monitoring water area data set.

[0111] The monitored water area data set includes water area data corresponding to various water quality influencing factor indicators in the target area at a preset time granularity.

[0112] In implementation, the terminal obtains a monitoring water area data set. The monitoring water area data set is independent of the water area data set collected when the target water area is subjected to water quality assessment. The time period corresponding to the monitoring water area data set may be before or after the water area data set, or may overlap with the collection time period of the water area data set, which is not limited in the present embodiment of the application.

[0113] Step 504, based on the preset rank sum ratio algorithm and the monitored water area data set, determine the rank sum ratio and probability unit corresponding to each target area.

[0114] In implementation, the terminal determines the rank-sum ratio and the probability unit probit of each water quality influencing factor index based on a preset rank-sum ratio algorithm (RSR). Specifically, the rank-sum ratio is calculated for each water quality influencing factor index, that is, the water area data corresponding to the water quality influencing factor index are sorted, and the rank value (that is, the sorting number) corresponding to each water area data is determined according to the sorting order result. Then, the rank value corresponding to each water area data is used to replace the original data of each water area data, and the weight coefficient corresponding to each water area data is calculated. Then, the terminal calculates the rank-sum ratio of the water quality influencing factor index based on the rank value of each water area data and the weight coefficient of each water area data.

[0115] Optionally, the method for compiling the rank value of the water area data can be divided into two methods: integer rank sum ratio method and non-integer rank sum ratio method. Based on business calculation requirements, one of the calculation methods can be selected to determine the rank value of each water area data.

[0116] 1) Integer Rank Sum Ratio Method

[0117] Arrange the m indicators (i.e., the water quality influencing factor indicators in this application) of n evaluation objects (i.e., the multiple target waters for water quality control measures to be tested in this application) into an original data table with n rows and m columns. Compile the rank values ​​of each evaluation object for each indicator in the original data table, where evaluation indicators are sorted from small to large in rank value, and factual indicators are sorted from large to small in rank value. The average value is taken for the same indicator data. , and get the rank matrix.

[0118] 2) Non-integer rank sum ratio method

[0119] The calculation formula for determining the rank value corresponding to the rank value of each water quality influencing factor indicator for the evaluation indicator is:

[0120]

[0121] in, is the rank value of the jth water quality influencing factor index corresponding to the ith evaluation object, n is the number of evaluation objects, is the jth water area data in the i-th water quality influencing factor index, The minimum water area data is selected from all water area data corresponding to the index representing the i-th water quality influencing factor. The largest water area data is selected from all water area data corresponding to the index representing the i-th water quality influencing factor.

[0122] The calculation formula for determining the rank value of each indicator for fact-based indicators is:

[0123]

[0124] in, Represents the maximum water area data among all water area data corresponding to the i-th water quality influencing factor index.

[0125] After determining the rank value of the water area data corresponding to each water quality influencing factor indicator, the rank sum ratio corresponding to each evaluation object (the evaluation object is each target area in multiple target areas) can be calculated based on two methods.

[0126] Method 1: When the weights of the water quality influencing factors are the same, the rank values ​​of the water quality influencing factors of each evaluation object can be averaged to obtain the rank sum ratio corresponding to the evaluation object.

[0127] Method 2: For the case where the weights of various water quality influencing factors are different, the rank values ​​of various water quality influencing factors of each evaluation object can be weighted and calculated to obtain the RSR rank sum ratio corresponding to the evaluation object. The RSR rank sum ratio is dimensionless. In the interval [1 / n, 1], the terminal directly sorts the evaluation objects in order from small to large according to the RSR value. For the water area data corresponding to each evaluation object, the frequency of abnormal data (i.e., data reflecting water pollution) in the water area data that exceeds the water quality industry standard value at the preset time granularity is listed, and the cumulative frequency of abnormal data of each evaluation object is calculated. Then, the terminal determines the rank R and the average rank R- of the RSR rank sum ratio of each evaluation object. Then, the terminal calculates the cumulative frequency R- / n × 100% based on the average rank R-, and the last item of the cumulative frequency is corrected by (1 − 1 / 4 n) × 100%. Finally, the terminal queries the preset "Percentage and Probability Unit Comparison Table" according to the determined cumulative frequency of each evaluation object (ie, each target area) to find the corresponding probability unit Probit value.

[0128] In a specific embodiment, an example of specific data is given, and the original data is shown in Table 2 below:

[0129] Table 2

[0130]

[0131] Among them, the water quality influencing factor indicators include: X1: water pollution source A emission, R1: water pollution source A emission, X2: water pollution source N emission, R2: water pollution source N emission, index values ​​0, 1, 2 correspond to three evaluation objects. Based on the method in the above step 404, calculate the rank sum ratio RSR corresponding to each evaluation object, and rearrange the RSR in order from small to large to determine the cumulative frequency, rank and average rank corresponding to each evaluation object, and then determine the cumulative frequency of each evaluation object, and query the "Percentage and Probability Unit Comparison Table" based on the cumulative frequency to obtain the probability unit Probit corresponding to each evaluation object. As shown in Table 3 below:

[0132] Table 3

[0133]

[0134] Step 506 , performing linear regression analysis based on the rank sum ratio and probability unit of each target area to obtain a linear regression equation, and determining the change trend of each water quality influencing factor index corresponding to each target area based on the linear regression equation.

[0135] In the implementation, for each target area in each target area, a linear regression analysis is performed based on the rank sum ratio RSR and the probability unit Probit of the target area to obtain a linear regression equation, and based on the linear regression equation, the change trend of each water quality influencing factor index corresponding to each target area at a preset time granularity is determined. Specifically, the terminal calculates the change trend of each water quality influencing factor index corresponding to each target area at a preset time granularity, and the change trend can be reflected in the form of a change trend curve. In addition, each water quality influencing factor index corresponding to the target area corresponds to a preset industry water quality standard value, and the industry water quality standard value of the water quality influencing factor index within a preset time length is obtained, and the reference change trend curve corresponding to the industry water quality standard value is calculated. Therefore, the change trend curve corresponding to each water quality influencing factor index in the target area can be referenced and evaluated based on the reference change trend curve corresponding to the industry water quality standard value.

[0136] For example, taking the probability unit Probit as the independent variable and the RSR rank sum ratio as the dependent variable, and taking the data given in Table 3 as an example, the regression equation is calculated. From the analysis of the results of the F test, it can be obtained that the significant P value is a value, the level is significant, and the original hypothesis that the regression coefficient is 0 is rejected. At the same time, the model's goodness of fit R² is a value, and the regression equation performs relatively well. Therefore, the regression equation basically meets the requirements. For the performance of variable collinearity, VIF is all less than 10. Therefore, the regression equation has no multicollinearity problem and the model is well constructed. As shown in Table 4 below:

[0137] Table 4

[0138]

[0139] Step 508, obtaining the water quality management result of the target water area according to the change trend of each water quality influencing factor indicator corresponding to each target area.

[0140] During implementation, the terminal analyzes the degree of fit between the change trend curve corresponding to each water quality influencing factor index corresponding to the target area and the reference change trend curve for each target area in each target area, thereby determining the water quality management result of each target area. For example, if the change trend curve corresponding to each water quality influencing factor index corresponding to the target area has a high degree of fit with the reference change trend curve (i.e., it meets the preset degree of fit condition), then it is determined that the water quality management result of the target area is good. If the change trend curve corresponding to each water quality influencing factor index corresponding to the target area has a low degree of fit with the reference change trend curve (i.e., it does not meet the preset degree of fit condition), then it is determined that the water quality management result of the target area is poor. Specifically, the terminal performs fitting calculation based on the determined change trend curve of the water quality influencing factor index and the reference change trend curve corresponding to the industry standard value, such as Figure 6 As shown, Figure 6 The following is a schematic diagram of the fitting effect of a change trend curve. Figure 6 The fitting effect of the two change trend curves is good. Furthermore, based on the good fitting results of the change trend curve of the water quality influencing factor index and the reference change trend curve corresponding to the industry water quality standard value, it is determined that the water quality management result of the target water area is good.

[0141] In this embodiment, after conducting a water quality assessment, the rank sum ratio and probability unit corresponding to each target area are determined based on the rank sum ratio algorithm and the monitored water area data set. Then, a linear regression analysis can be performed based on the rank sum ratio and probability unit corresponding to the target area to obtain a linear regression equation. Based on the linear regression equation, the management and prevention of water quality in the target area can be tracked and evaluated to obtain water quality management results, thereby improving the accuracy of water quality management.

[0142] In one embodiment, Figure 7 As shown, after step 506, the method further includes:

[0143] Step 702, determining the binning threshold based on the linear regression equation.

[0144] During implementation, the terminal determines the critical values ​​of each water quality influencing factor based on the linear regression equation.

[0145] Step 704, based on the classification critical value, the rank sum ratio corresponding to each target area is classified into grades to determine the classification results of the water quality treatment results of each target area.

[0146] In the implementation, the terminal classifies the rank sum ratio of each target area based on the classification critical value, and determines the classification results of the water quality management results of each target area under the preset time granularity. Specifically, the water quality management results are graded based on the determined classification critical value of the rank sum ratio, so as to obtain the management level of the water quality management results of each evaluation object (i.e., the target area), and then clarify the advantages and disadvantages of the water quality management results.

[0147] In this embodiment, based on the linear regression equation determined by the rank sum ratio algorithm, the critical value of the water quality treatment results is further determined, and then, based on the critical value of the water quality treatment results, the treatment level of the water quality treatment results in each target area is determined, thereby achieving a refined classification of the water quality treatment results and improving the scientificity and accuracy of water quality management.

[0148] In one embodiment, Figure 8 As shown, before step 104, the method further includes:

[0149] Step 802, obtaining a sample water area data set.

[0150] Among them, the sample water area data set contains water area data corresponding to various water quality influencing factor indicators at different time granularities.

[0151] In implementation, the terminal obtains a sample water area data set. Specifically, the water area data contained in the sample water area data set may include, but are not limited to, water quality influencing factors such as hydrological morphology, hydrological flow, hydrological flow rate, river width, water depth, pollutants, pollution concentration, pollution index and diffusion coefficient. In addition, the water area data contained in the sample water area data set may come from multiple monitored water areas. When collecting water area data, it can also be collected according to different time granularities. Specifically, based on different time granularities, the water area data in the sample water area data set can be classified and processed, and the water area data can be stored in different library tables. Different library tables, for example, granularity selection can usually be divided into three categories. The finest granularity fact table usually records the information related to the pollution event that occurs at each moment. The fact table of periodic statistics records the status of each pollution event at the end of the period according to a certain period. The situation table is the coarsest granularity, recording the main information related to the pollution event. The granularity reflects the coarseness of the metric indicators in the water area data. The determination of the dimension is usually carried out after the granularity is determined. The finer the granularity, the more dimensions. The dimensions can cover aspects such as the time and location of the pollution incident, the subject of water pollution discharge, the address of the monitoring point, the cause of abnormal monitoring point and the cause of water pollution discharge incident, so as to determine these angles as indicators of various water quality influencing factors contained in the water area data.

[0152] Optionally, when actually collecting data, the time granularity may be instantaneous (i.e., real-time data collection), daily, weekly, monthly, etc. The water quality influencing factor indicators collected from different monitored waters may not be exactly the same. The water quality influencing factor indicators collected from the same monitored waters at different times may also be different. Therefore, the sample water area data set contains water area data corresponding to multiple water quality influencing factor indicators at different time granularities, thereby ensuring the comprehensiveness of the information in the sample water area data set.

[0153] Step 804, selecting water quality influencing factor indicators of each target dimension number and measurement indicators corresponding to each water quality influencing factor indicator, and constructing a target dimension water pollution diffusion assessment model based on the water area data corresponding to each water quality influencing factor and the measurement indicator.

[0154] In implementation, when constructing a multidimensional model library, the pollution events in the water field environment are usually taken as the starting point. The granularity is selected, the dimension is determined, and finally the technical means of measurement are determined. Specifically, based on a variety of different water field environments and the business needs corresponding to the water field environments, the terminal selects water quality influencing factor indicators of each target dimension and the measurement indicators corresponding to each water quality influencing factor indicator in the sample data set. Then, based on the selected water quality influencing factor indicators of each target dimension and the water area data corresponding to the measurement indicators, a target dimension water pollution diffusion assessment model can be constructed.

[0155] For example, a multidimensional model is constructed as follows:

[0156] Building a one-dimensional water pollution diffusion model

[0157] After determining the time granularity, a one-dimensional water pollution diffusion model is constructed using the (dimensional) water pollution monitoring index as the water quality influencing factor index and the emission index of the pollution source as the measurement index. The one-dimensional water pollution diffusion model can be a regression model or a neural network model trained based on the water area data corresponding to these two indicator data, which is not limited in the embodiments of the present application.

[0158] Building a two-dimensional water pollution diffusion model

[0159] After determining the time granularity, a two-dimensional water pollution diffusion model is constructed using (dimensional) water pollution monitoring indicators and river hydrological conditions as water quality influencing factor indicators and the emission of the main pollution source as the measurement indicator.

[0160] Building a multidimensional water pollution diffusion model

[0161] After determining the time granularity, a multidimensional water pollution diffusion model is constructed using (dimensional) water pollution monitoring indicators, river hydrological conditions, and other dimensions as water quality influencing factor indicators, and the emission of the main pollution source as a measurement indicator. This embodiment of the application does not limit the model type of the water pollution diffusion model.

[0162] Step 806: construct a multidimensional model library based on the water pollution diffusion assessment model of each target dimension.

[0163] In implementation, the terminal builds a multidimensional model library based on the water pollution diffusion assessment model of each target dimension. Figure 7 As shown, the water pollution diffusion assessment models of various dimensions constructed constitute a multidimensional model library. Therefore, during the water quality assessment process, a target water pollution diffusion assessment model that matches the water field environment of the target water area to be assessed can be selected from the multidimensional model library.

[0164] In this embodiment, a multidimensional model library is constructed in advance based on the sample water area data set. The water pollution diffusion assessment models of various dimensions contained in the multidimensional model library are adapted to the water field environment of various water areas. Furthermore, in the water quality assessment process, the target water pollution diffusion assessment model for the target water area is selected from the multidimensional model library to determine the weight data, thereby improving the processing efficiency and accuracy of the water quality assessment.

[0165] In one embodiment, the specific processing of step 104 includes:

[0166] Step 1041, based on the water quality influencing factor indicators and measurement indicators contained in the water area data set and the time granularity of the water area data of the water quality influencing factor indicators, determine the target water pollution diffusion assessment model in the pre-built multidimensional model library.

[0167] In implementation, the water quality influencing factor indicators, measurement indicators and time granularity of water area data contained in the water area data set can reflect the water field environmental characteristics of the target water area. Then, when conducting water quality assessment for the target water area, the terminal determines the target pollution diffusion assessment model that matches the target water area in the pre-built multidimensional model library based on the water quality influencing factor indicators, measurement indicators and time granularity of water area data of water quality influencing factor indicators contained in the water area data set. Specifically, based on the time granularity of water area data in the water area data set and the number of water quality influencing factor indicators (i.e., the number of dimensions), the terminal determines the candidate water pollution diffusion assessment model that meets the time granularity and dimension conditions in the multidimensional model library. Then, based on the substantial indicator content of water quality influencing factor indicators and measurement indicators, the target water pollution diffusion assessment model is determined in the candidate water pollution diffusion assessment model.

[0168] In this embodiment, a multidimensional model library is pre-constructed. When conducting water quality assessment, a target water pollution diffusion assessment model that matches the water field environment of the target water area can be selected based on the water field environment characteristics of the target water area reflected in the water area data set. Then, the weight data of each water quality influencing factor indicator is determined through the target water pollution diffusion assessment model, thereby improving the accuracy of water quality assessment.

[0169] In an optional embodiment, if Fig. 9 As shown in the figure, a water quality assessment and method processing flow diagram is given. Fig. 9 In the process, the original water area data are integrated to obtain the data set integration result, and then the target water pollution diffusion assessment model is selected in the pre-established multidimensional model library, and the weight data of each water quality influencing factor indicator in the water area data set of the target water area is determined based on the target water pollution diffusion assessment model, so that the water quality assessment can be further carried out based on the weight data and the water area data set, and the water quality management result of the target water area can be further determined based on the RSR rank sum ratio algorithm and the monitoring water area data set collected in the later monitoring, thereby improving the accuracy of water quality management.

[0170] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0171] Based on the same inventive concept, the embodiment of the present application also provides a water quality assessment device for implementing the water quality assessment method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more water quality assessment device embodiments provided below can refer to the limitations of the water quality assessment method above, and will not be repeated here.

[0172] In an exemplary embodiment, Fig.10 As shown, a water quality assessment device 1000 is provided, comprising: an acquisition module 1010, a first determination module 1020, a verification module 1030 and a second determination module 1040, wherein:

[0173] The acquisition module 1010 is used to acquire a water area dataset of a target water area.

[0174] The first determination module 1020 is used to determine a target water pollution diffusion assessment model in a pre-built multi-dimensional model library based on the water area data set.

[0175] Verification module 1030 is used to determine the weight data of each water quality influencing factor index in the water area data set based on the target water pollution diffusion assessment model and the water area data set, and verify each weight data based on a preset entropy weight method to obtain the verified weight data.

[0176] The second determination module 1040 determines the water quality assessment result of the target water area in the future period based on the verified weight data and the water area data set.

[0177] In one embodiment, the acquisition module 1010 is specifically used to acquire the original water area data of the target water area;

[0178] The original water area data are integrated and missing value screening is performed, and based on the water quality influencing factor indicators contained in the original water area data, the water area data corresponding to each water quality influencing factor indicator are standardized to obtain the water area data set.

[0179] In one embodiment, the water area data set includes water area data corresponding to each water quality influencing factor index and the measurement index, and the verification module 1030 is specifically used to normalize the water area data of the water quality influencing factor index for each water quality influencing factor index in the water area data set to obtain the normalized water area data;

[0180] Based on the preset entropy weight algorithm, the proportion of each water area data in the water quality influencing factor index is determined, and based on the proportion of each water area data, the entropy value of the water quality influencing factor index is determined;

[0181] According to the entropy value of each water quality influencing factor indicator, the calibration weight corresponding to each water quality influencing factor indicator is determined;

[0182] Based on the verification weight, the weight data of each water quality influencing factor is verified to obtain the verified weight data.

[0183] In one embodiment, the apparatus 1000 further includes:

[0184] The second acquisition module is used to acquire a monitoring water area data set, where the monitoring water area data set contains water area data corresponding to various water quality influencing factor indicators in the target area at a preset time granularity;

[0185] A third determination module is used to determine the rank sum ratio and probability unit corresponding to each target area based on a preset rank sum ratio algorithm and a monitored water area data set;

[0186] The fourth determination module is used to perform linear regression analysis based on the rank sum ratio and probability unit corresponding to each target area to obtain a linear regression equation, and determine the change trend of the water quality influencing factor index corresponding to each target area based on the linear regression equation;

[0187] The processing module is used to obtain the water quality management results of each target water area according to the change trend of each water quality influencing factor indicator corresponding to each target area.

[0188] In one embodiment, the apparatus 1000 further includes:

[0189] A fifth determination module, used to determine the grading critical value based on a linear regression equation;

[0190] The sixth determination module is used to classify the rank sum ratios corresponding to each target area based on the classification critical value, and determine the classification results of the water quality treatment results of each target area.

[0191] In one embodiment, the apparatus 1000 further includes:

[0192] The third acquisition module is used to obtain a sample water area data set; the sample water area data set includes water area data corresponding to various water quality influencing factor indicators at different time granularities;

[0193] The first construction module is used to select water quality influencing factor indicators of each target dimension and measurement indicators corresponding to each water quality influencing factor indicator, and construct a target dimension water pollution diffusion assessment model based on the water area data corresponding to each water quality influencing factor and measurement indicator;

[0194] The second construction module is used to construct a multidimensional model library based on the water pollution diffusion assessment model of each target dimension.

[0195] In one embodiment, the first determination module 1020 is specifically used to determine the target water pollution diffusion assessment model in a pre-built multidimensional model library based on the water quality influencing factor indicators, measurement indicators and time granularity of the water area data of the water quality influencing factor indicators contained in the water area data set.

[0196] Each module in the above-mentioned water quality assessment device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0197] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig.11As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a water quality assessment method is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0198] Those skilled in the art will understand that Fig.11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0199] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0200] Obtain a water area dataset of the target water area;

[0201] Based on the water area data set, determining a target water pollution diffusion assessment model in a pre-built multidimensional model library;

[0202] Based on the target water pollution diffusion assessment model and the water area data set, determine the weight data of each water quality influencing factor index in the water area data set, and verify each of the weight data based on a preset entropy weight method to obtain verified weight data;

[0203] Based on the verified weight data and the water area data set, the water quality assessment result of the target water area in a future time period is determined.

[0204] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0205] Obtaining original water area data of the target water area;

[0206] The original water area data is subjected to data integration and missing value screening processing, and based on the water quality influencing factor indicators contained in the original water area data, the water area data corresponding to each water quality influencing factor indicator is standardized to obtain a water area data set.

[0207] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0208] For each water quality influencing factor index in the water area data set, normalizing the water area data of the water quality influencing factor index to obtain normalized water area data;

[0209] Based on a preset entropy weight algorithm, determine the proportion of each water area data in the water quality influencing factor index, and based on the proportion of each water area data, determine the entropy value of the water quality influencing factor index;

[0210] Determine the calibration weight corresponding to each water quality influencing factor indicator according to the entropy value of each water quality influencing factor indicator;

[0211] Based on the verification weight, the weight data of each of the water quality influencing factors is verified to obtain verified weight data.

[0212] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0213] Acquire a monitoring water area data set, wherein the monitoring water area data set includes water area data corresponding to various water quality influencing factor indicators of the target area at a preset time granularity;

[0214] Based on a preset rank sum ratio algorithm, determine the rank sum ratio and probability unit of each of the water quality influencing factor indicators;

[0215] Performing a linear regression analysis based on the rank sum ratio of each of the water quality influencing factor indicators and the probability unit to obtain a linear regression equation, and determining the change trend corresponding to each of the water quality influencing factor indicators at the preset time granularity based on the linear regression equation;

[0216] According to the change trends corresponding to the indicators of each water quality influencing factor, the water quality treatment results of the target water area are obtained.

[0217] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0218] Based on the linear regression equation, determining the critical value of each water quality influencing factor index;

[0219] Based on the grading critical value, the rank sum ratio of each water quality influencing factor index is graded to determine the grading result of each water quality influencing factor index at the preset time granularity.

[0220] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0221] Acquire a sample water area data set; the sample water area data set includes water area data corresponding to various water quality influencing factor indicators at different time granularities;

[0222] Select water quality influencing factor indicators of each target dimension and measurement indicators corresponding to each water quality influencing factor indicator, and construct a target dimension water pollution diffusion assessment model based on the water quality influencing factors and the water area data corresponding to the measurement indicators;

[0223] Based on the water pollution diffusion assessment model of each target dimension, a multidimensional model library is constructed.

[0224] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0225] Based on the water quality influencing factor indicators and measurement indicators contained in the water area data set and the time granularity of the water area data of the water quality influencing factor indicators, a target water pollution diffusion assessment model is determined in a pre-constructed multidimensional model library.

[0226] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0227] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0228] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0229] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0230] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A water quality assessment method, characterized in that: The method comprises: Obtain a water area dataset of the target water area; Based on the water area data set, determining a target water pollution diffusion assessment model in a pre-built multidimensional model library; Based on the target water pollution diffusion assessment model and the water area data set, determine the weight data of each water quality influencing factor index in the water area data set, and verify each of the weight data based on a preset entropy weight method to obtain verified weight data; Determine the water quality assessment result of the target water area in a future period based on the verified weight data and the water area data set; the water area data set includes indicators of various water quality influencing factors and water area data corresponding to the measurement indicators; The method of verifying each of the weight data based on a preset entropy weight method to obtain verified weight data includes: For each water quality influencing factor index in the water area data set, normalizing the water area data of the water quality influencing factor index to obtain normalized water area data; Based on a preset entropy weight algorithm, determine the proportion of each water area data in the water quality influencing factor index, and based on the proportion of each water area data, determine the entropy value of the water quality influencing factor index; Determine the calibration weight corresponding to each water quality influencing factor indicator according to the entropy value of each water quality influencing factor indicator; Based on the verification weight, the weight data of each of the water quality influencing factors are verified to obtain verified weight data; Before determining the target water pollution diffusion assessment model in a pre-built multidimensional model library based on the water area data set, the method further includes: Acquire a sample water area data set; the sample water area data set includes water area data corresponding to various water quality influencing factor indicators at different time granularities; Select water quality influencing factor indicators of each target dimension and measurement indicators corresponding to each water quality influencing factor indicator, and construct a target dimension water pollution diffusion assessment model based on the water quality influencing factors and the water area data corresponding to the measurement indicators; Based on the water pollution diffusion assessment model of each target dimension, a multidimensional model library is constructed.

2. The method according to claim 1, characterized in that The step of obtaining a water area dataset of a target water area includes: Obtaining original water area data of the target water area; The original water area data is subjected to data integration and missing value screening processing, and based on the water quality influencing factor indicators contained in the original water area data, the water area data corresponding to each water quality influencing factor indicator is standardized to obtain a water area data set.

3. The method according to claim 1, characterized in that After determining the water quality assessment result of the target water area in a future period based on the verified weight data and the water area data set, the method further includes: Acquire a monitoring water area data set, wherein the monitoring water area data set includes water area data corresponding to various water quality influencing factor indicators of the target area at a preset time granularity; Based on a preset rank sum ratio algorithm and the monitored water area data set, determining the rank sum ratio and probability unit corresponding to each of the target areas; Performing linear regression analysis based on the rank sum ratio and the probability unit corresponding to each of the target areas to obtain a linear regression equation, and determining the change trend of the water quality influencing factor index corresponding to each of the target areas based on the linear regression equation; According to the change trends of the water quality influencing factor indicators corresponding to the target areas, the water quality management results of the target water areas are obtained.

4. The method according to claim 3, characterized in that After performing linear regression analysis based on the rank sum ratio corresponding to each of the target areas and the probability unit to obtain a linear regression equation, the method further includes: Based on the linear regression equation, determining a grading critical value; Based on the grading critical value, the rank sum ratio corresponding to each of the target areas is graded to determine the grading results of the water quality treatment results of each of the target areas.

5. The method according to claim 1, characterized in that Determining a target water pollution diffusion assessment model in a pre-built multidimensional model library based on the water area data set includes: Based on the water quality influencing factor indicators and measurement indicators contained in the water area data set and the time granularity of the water area data of the water quality influencing factor indicators, a target water pollution diffusion assessment model is determined in a pre-constructed multidimensional model library.

6. A water quality assessment device, characterized in that: The device comprises: A first acquisition module is used to acquire a water area dataset of a target water area; A first determination module is used to determine a target water pollution diffusion assessment model in a pre-built multidimensional model library based on the water area data set; A verification module, used to determine the weight data of each water quality influencing factor index in the water area data set based on the target water pollution diffusion assessment model and the water area data set, and verify each of the weight data based on a preset entropy weight method to obtain the verified weight data; A second determination module is used to determine the water quality assessment result of the target water area in a future period based on the verified weight data and the water area data set; The water area data set contains water area data corresponding to each water quality influencing factor index and the measurement index; the verification module is specifically used to normalize the water area data of the water quality influencing factor index for each water quality influencing factor index in the water area data set to obtain the normalized water area data; based on a preset entropy weight algorithm, determine the proportion of each water area data in the water quality influencing factor index, and based on the proportion of each water area data, determine the entropy value of the water quality influencing factor index; according to the entropy value of each water quality influencing factor index, determine the verification weight corresponding to each water quality influencing factor index; based on the verification weight, verify the weight data of each water quality influencing factor to obtain the verified weight data; The device further comprises: a third acquisition module, which is used to acquire a sample water area data set; the sample water area data set comprises water area data corresponding to each water quality influencing factor index at different time granularities; The first construction module is used to select water quality influencing factor indicators of each target dimension and measurement indicators corresponding to each water quality influencing factor indicator, and construct a target dimension water pollution diffusion assessment model based on the water quality influencing factors and the water area data corresponding to the measurement indicators; The second construction module is used to construct a multidimensional model library based on the water pollution diffusion assessment model of each target dimension.

7. The device according to claim 6, characterized in that The first acquisition module is specifically used to acquire the original water area data of the target water area; The original water area data is subjected to data integration and missing value screening processing, and based on the water quality influencing factor indicators contained in the original water area data, the water area data corresponding to each water quality influencing factor indicator is standardized to obtain a water area data set.

8. The device according to claim 6, characterized in that The device also includes: A second acquisition module is used to acquire a monitoring water area data set, wherein the monitoring water area data set contains water area data corresponding to various water quality influencing factor indicators of the target area at a preset time granularity; A third determination module is used to determine the rank sum ratio and probability unit corresponding to each of the target areas based on a preset rank sum ratio algorithm and the monitored water area data set; A fourth determination module is used to perform a linear regression analysis based on the rank sum ratio and the probability unit corresponding to each of the target areas to obtain a linear regression equation, and determine the change trend of the water quality influencing factor index corresponding to each of the target areas based on the linear regression equation; The processing module is used to obtain the water quality treatment results of each target water area according to the change trend of each water quality influencing factor indicator corresponding to each target area.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images