Water quality monitoring method, device and equipment and storage medium

Abstract

The invention relates to a water quality monitoring method, device and equipment and a storage medium, and the method comprises the steps: firstly obtaining a first key influence factor of each first target water quality parameter through historical water quality data analysis; and determining a second key influence factor according to the importance degree of each first key influence factor. And further determining target parameter intervals of the key influence factors based on historical data of the target water quality problem. Then, by analyzing the incidence relation between the key influence factors, a key influence factor correlation combination is constructed; and finally, acquiring current water quality data in real time, and comparing the current water quality data with the key influence factor association combination so as to judge whether the target water area has a target water quality problem or not. According to the technical scheme, the efficiency and accuracy of water quality monitoring are improved, rapid early warning of the water quality problem of the target water area is achieved, and a new, more intelligent and efficient solution is provided for water quality monitoring of the river mouth entering the sea.

Description

Technical Field

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

[0002] Monitoring water quality at estuaries is crucial for protecting the ecological environment and ensuring the safety of human activities. However, estuary water quality is influenced by a complex array of factors, making traditional manual sampling and laboratory analysis methods inefficient and unable to meet the demands of real-time monitoring and rapid early warning. While technological advancements have significantly improved water quality monitoring technology, addressing this complex and volatile environment still requires more intelligent and efficient solutions. Summary of the Invention

[0003] Based on this, the purpose of this application is to provide a water quality monitoring method that can efficiently identify key influencing factors, realize real-time monitoring of water quality and rapid early warning.

[0004] The water quality monitoring method described in the embodiment of the present application includes the following steps:

[0005] Acquire first historical water quality data of a target water area; the first historical water quality data includes parameter values of a plurality of first target water quality parameters at a plurality of first historical time points;

[0006] Performing a key influencing factor analysis on the parameter values of the plurality of first target water quality parameters at a plurality of first historical time points to obtain a first key influencing factor for each of the first target water quality parameters;

[0007] Determining the importance of each first key influencing factor according to each first target water quality parameter; determining a second key influencing factor according to the importance of each first key influencing factor;

[0008] Obtaining second historical water quality data for the target water area, the second historical water quality data including parameter values of a plurality of second target water quality parameters at a plurality of second historical time points; the second target water quality parameter being a first target water quality parameter corresponding to the second key influencing factor, and the second historical time point being a historical time point at which the target water quality problem occurs; determining a plurality of target parameter intervals for the second key influencing factor based on the second historical water quality data; and determining a target parameter interval corresponding to the parameter value of the second key influencing factor at each first historical time point based on the plurality of target parameter intervals for the second key influencing factor;

[0009] Determining, based on the target parameter ranges of the second key influencing factors at the first historical time points, a correlation relationship between the second key influencing factors; the correlation relationship includes at least one second key influencing factor correlation combination; the second key influencing factor correlation combination includes at least one second key influencing factor and a target parameter range corresponding to the second key influencing factor;

[0010] Obtain current water quality data of the target water area; the current water quality data includes the current parameter values of each of the second key influencing factors; if the current parameter values of each of the second key influencing factors meet any associated combination of the second key influencing factors, it is prompted that there is a target water quality problem in the target water area.

[0011] The present application also provides a water quality monitoring device, comprising:

[0012] A first historical water quality data acquisition module is configured to acquire first historical water quality data of a target water area; the first historical water quality data includes parameter values of a plurality of first target water quality parameters at a plurality of first historical time points;

[0013] A first key influencing factor analysis module is used to perform a key influencing factor analysis on the parameter values of the first target water quality parameters at a plurality of first historical time points to obtain a first key influencing factor of each of the first target water quality parameters;

[0014] A second key influencing factor analysis module is configured to determine the importance of each first key influencing factor according to each first key influencing factor of the first target water quality parameter; and determine a second key influencing factor according to the importance of each first key influencing factor;

[0015] a target parameter interval determination module, configured to obtain second historical water quality data for the target water area, the second historical water quality data including parameter values of a plurality of second target water quality parameters at a plurality of second historical time points; the second target water quality parameter being a first target water quality parameter corresponding to the second key influencing factor, the second historical time point being a historical time point at which the target water quality problem occurs; determining a plurality of target parameter intervals for the second key influencing factor based on the second historical water quality data; and determining a target parameter interval corresponding to the parameter value of the second key influencing factor at each first historical time point based on the plurality of target parameter intervals for the second key influencing factor;

[0016] an association relationship mining module, configured to determine an association relationship between each of the second key influencing factors based on the target parameter interval of each of the second key influencing factors at each first historical time point; the association relationship includes at least one second key influencing factor association combination; the second key influencing factor association combination includes at least one second key influencing factor and a target parameter interval corresponding to the second key influencing factor;

[0017] The current water quality monitoring module is used to obtain the current water quality data of the target water area; the current water quality data includes the current parameter values of each of the second key influencing factors; if the current parameter values of each of the second key influencing factors meet any of the associated combinations of the second key influencing factors, it is prompted that there is a target water quality problem in the target water area.

[0018] An embodiment of the present application further provides an electronic device, comprising a processor, a memory, and a computer-readable program stored in the memory, wherein the computer-readable program, when executed by the processor, implements the steps of the method described in any one of the embodiments of the present application.

[0019] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed, the device where the computer-readable storage medium is located is controlled to implement a method as described in any one of the embodiments of the present application.

[0020] The embodiment of the present application obtains the first historical water quality data of the target water area, including the parameter values of several first target water quality parameters at several first historical time points. These historical data are subjected to key influencing factor analysis to obtain the first key influencing factor of each first target water quality parameter. According to the importance of each first key influencing factor, the second key influencing factors are determined, which are the factors that have the most significant impact on the target water quality parameters. The second historical water quality data are obtained, which include the parameter values of the second target water quality parameters corresponding to the second key influencing factors at the historical time points when the target water quality problem occurs. Based on these data, several target parameter intervals of the second key influencing factors are determined. According to the parameter values of the second key influencing factors at each first historical time point, their target parameter intervals are determined, and the correlation relationship between these key influencing factors is further analyzed to form a second key influencing factor association combination. Finally, the current water quality data of the target water area is obtained in real time. If the current parameter values of each second key influencing factor meet any second key influencing factor association combination, it is prompted that there is a target water quality problem in the target water area. This technical solution not only improves the efficiency and accuracy of water quality monitoring, but also enables rapid early warning of water quality problems in target waters, providing a new, smarter and more efficient solution for water quality monitoring in estuaries entering the sea.

[0021] For better understanding and implementation, the present application is described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 Schematic diagram of the water quality monitoring method according to an embodiment of the present application;

[0023] Figure 2 Schematic diagram of the steps for obtaining the first historical water quality data of the target water area in an embodiment of the present application;

[0024] Figure 3 Schematic diagram of the steps for determining the first key influencing factor of the first target water quality parameter in an embodiment of the present application;

[0025] Figure 4 Schematic diagram of the steps for determining the importance of each first key influencing factor in an embodiment of the present application;

[0026] Figure 5 Schematic diagram of the steps for determining the target parameter range of each second key influencing factor in an embodiment of the present application;

[0027] Figure 6 A schematic diagram of a water quality monitoring device according to an embodiment of the present application;

[0028] Figure 7 This is a schematic structural diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0029] To make the objectives, technical solutions, and advantages of this application more clear, the following will further describe the embodiments of this application in detail with reference to the accompanying drawings. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements.

[0030] It should be understood that the embodiments described in the following examples do not represent all embodiments consistent with this application. Rather, they are merely examples of devices and methods consistent with certain aspects of this application, as detailed in the appended claims. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of this application without inventive effort are intended to fall within the scope of protection of this application.

[0031] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "the" and "the" used in this application are also intended to include plural forms, unless the context clearly indicates otherwise. In addition, in the description of this application, unless otherwise stated, "a plurality" refers to two or more. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items, for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone; the character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0032] It should be understood that although the terms first, second, third, etc. may be used in this application to describe various information, this information should not be limited to these terms. Moreover, these terms are only used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence, nor can they be understood to indicate or imply relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to the specific circumstances. Depending on the context, the words "if" / "if" used in this application can be interpreted as "at the time of" or "when" or "in response to determining".

[0033] Monitoring water quality at estuaries is crucial for protecting the ecological environment and ensuring the safety of human activities. However, estuary water quality is influenced by a complex array of factors, making traditional manual sampling and laboratory analysis methods inefficient and unable to meet the demands of real-time monitoring and rapid early warning. While technological advancements have significantly improved water quality monitoring technology, addressing this complex and volatile environment still requires more intelligent and efficient solutions.

[0034] Please refer to Figure 1 The water quality monitoring method described in the embodiment of the present application comprises the following steps:

[0035] S101: Acquire first historical water quality data of a target water area; the first historical water quality data includes parameter values of a plurality of first target water quality parameters at a plurality of first historical time points;

[0036] S102: performing a key influencing factor analysis on the parameter values of the plurality of first target water quality parameters at a plurality of first historical time points to obtain a first key influencing factor of each of the first target water quality parameters;

[0037] S103: determining the importance of each first key influencing factor according to each first target water quality parameter; and determining a second key influencing factor according to the importance of each first key influencing factor;

[0038] S104: Acquire second historical water quality data for the target water area, the second historical water quality data including parameter values of a plurality of second target water quality parameters at a plurality of second historical time points; the second target water quality parameter is a first target water quality parameter corresponding to the second key influencing factor, and the second historical time point is a historical time point at which the target water quality problem occurs; determine a plurality of target parameter intervals for the second key influencing factor based on the second historical water quality data; determine a target parameter interval corresponding to the parameter value of the second key influencing factor at each first historical time point based on the plurality of target parameter intervals for the second key influencing factor;

[0039] S105: Determine, based on the target parameter ranges of the second key influencing factors at the first historical time points, a correlation relationship between the second key influencing factors; the correlation relationship includes at least one second key influencing factor correlation combination; the second key influencing factor correlation combination includes at least one second key influencing factor and a target parameter range corresponding to the second key influencing factor;

[0040] S106: Obtain current water quality data of the target water area; the current water quality data includes the current parameter values of each of the second key influencing factors; if the current parameter values of each of the second key influencing factors meet any associated combination of the second key influencing factors, it is prompted that the target water area has a target water quality problem.

[0041] The embodiment of the present application obtains the first historical water quality data of the target water area, including the parameter values of several first target water quality parameters at several first historical time points. These historical data are subjected to key influencing factor analysis to obtain the first key influencing factor of each first target water quality parameter. According to the importance of each first key influencing factor, the second key influencing factors are determined, which are the factors that have the most significant impact on the target water quality parameters. The second historical water quality data are obtained, which include the parameter values of the second target water quality parameters corresponding to the second key influencing factors at the historical time points when the target water quality problem occurs. Based on these data, several target parameter intervals of the second key influencing factors are determined. According to the parameter values of the second key influencing factors at each first historical time point, their target parameter intervals are determined, and the correlation relationship between these key influencing factors is further analyzed to form a second key influencing factor association combination. Finally, the current water quality data of the target water area is obtained in real time. If the current parameter values of each second key influencing factor meet any second key influencing factor association combination, it is prompted that there is a target water quality problem in the target water area. This technical solution not only improves the efficiency and accuracy of water quality monitoring, but also enables rapid early warning of water quality problems in target waters, providing a new, smarter and more efficient solution for water quality monitoring in estuaries entering the sea.

[0042] The water quality monitoring method of the embodiment of the present application is executed by a computer, and each step is described in detail below.

[0043] In step S101 , first historical water quality data of the target water area is obtained; the first historical water quality data includes parameter values of a plurality of first target water quality parameters at a plurality of first historical time points.

[0044] In this step, it is necessary to collect historical water quality data of the target water area, such as a specific estuary. The historical water quality data should include parameter values of multiple first target water quality parameters at multiple first historical time points. Among them, the first target water quality parameter can be any water quality parameter related to water quality, such as dissolved oxygen, pH value, temperature, heavy metal concentration, etc. The first historical time point refers to a historical time point in the past, such as monthly, weekly or daily in the past few years. These historical water quality data can be obtained through existing water quality monitoring stations, or collected through other data sources (such as scientific research institutions, environmental protection departments, etc.).

[0045] Please refer to Figure 2 In one embodiment, the step of obtaining the first historical water quality data of the target water area in step S101 includes:

[0046] Step S1011: obtaining original first water quality time series data of the target water area; the first water quality time series data includes parameter values of several water quality parameters at different time points;

[0047] This step obtains raw water quality time series data for the target water area from water quality monitoring equipment or databases. This data typically contains values of multiple water quality parameters (such as dissolved oxygen, pH, temperature, turbidity, and conductivity) at different time points. This data forms the basis for subsequent analysis.

[0048] Step S1012: Divide the first water quality time series data into preset time windows, determine the mean and real-time value of each water quality parameter in each time window; perform a mean rationality test and a real-time value validity test based on the mean and real-time value of each water quality parameter in each time window, and eliminate data that fails to pass both the mean rationality test and the real-time value validity test in each time window; thereby obtaining second water quality time series data;

[0049] To ensure data accuracy and reliability, the first water quality time series data is divided into preset time windows (such as daily, weekly, or monthly), and the mean and real-time values of each water quality parameter within each time window are calculated. Next, a mean rationality test and a real-time value validity test are performed. The mean rationality test verifies that the data falls within the expected fluctuation range, while the real-time value validity test identifies possible outliers or erroneous data. Data that fails both tests is discarded, resulting in more accurate and reliable second water quality time series data.

[0050] Step S1013: performing linear dimensionality reduction on the second water quality time series data using a principal component analysis method, and identifying water quality parameters that are independent of each other and have a significant impact on water quality changes as target water quality parameters;

[0051] This step uses principal component analysis (PCA) to perform linear dimensionality reduction on the second water quality time series data. PCA is a commonly used data dimensionality reduction technique that reduces the dimensionality of data by identifying principal components (i.e., independent water quality parameters that significantly influence water quality changes). PCA can be used to select the most sensitive and important water quality parameters from a wide range of water quality parameters, which serve as the target water quality parameters for subsequent analysis.

[0052] Step S1014: remove the data of other water quality parameters except the target water quality parameter from the second water quality time series data to obtain the first historical water quality data of the target water area.

[0053] Finally, the non-target water quality parameters in the second water quality time series data are removed, and only the target water quality parameters are retained. In this way, the first historical water quality data of the target water area is obtained, which will be used for subsequent key influencing factor analysis and early warning model construction.

[0054] In summary, this example ensures data accuracy and reliability by acquiring and preprocessing raw water quality time series data. Then, through principal component analysis, the most sensitive and important parameters to water quality changes were successfully selected from a wide range of water quality parameters. These parameters serve as the basis for subsequent analysis, achieving dimensionality reduction and simplification of the data, reducing the complexity and computational cost of subsequent analysis.

[0055] In step S102, a key influencing factor analysis is performed on the parameter values of the plurality of first target water quality parameters at a plurality of first historical time points to obtain a first key influencing factor of each of the first target water quality parameters.

[0056] In this step, the first historical water quality data can be analyzed using statistical methods such as correlation analysis, principal component analysis, etc. to determine the first key influencing factor for each first target water quality parameter. Generally speaking, the first key influencing factor may be other water quality parameters, or it may be an external factor (such as rainfall, temperature, etc.). In this embodiment, the first key influencing factor is other water quality parameters. In one example, monthly dissolved oxygen, pH value, temperature and heavy metal concentration data for the past three years were collected as the first historical water quality data. Through correlation analysis, it was found that the key influencing factors of dissolved oxygen include temperature and heavy metal concentration; the key influencing factors of pH value are mainly temperature and dissolved oxygen.

[0057] Please refer to Figure 3 In one embodiment, the step of performing key influencing factor analysis on the parameter values of the plurality of first target water quality parameters at a plurality of first historical time points to obtain a first key influencing factor of each of the first target water quality parameters in step S102 includes:

[0058] Step S1021, traversing each first target water quality parameter among the plurality of first target water quality parameters;

[0059] This step traverses all first target water quality parameters, and when any first target water quality parameter is traversed, the following steps are executed.

[0060] Step S1022: constructing a training data set using the currently traversed first target water quality parameter as the target variable and the remaining first target water quality parameters as feature variables; wherein the training data set includes a plurality of training samples and training labels for the training samples, each training sample includes parameter values of all feature variables at a single first historical time point, and the training label for each training sample is the parameter value of the target variable at the corresponding first historical time point;

[0061] This step constructs a training dataset using the first target water quality parameter currently traversed as the target variable and the remaining first target water quality parameters as feature variables. The training dataset consists of several training samples and a training label for each training sample. Each training sample contains the parameter values of all feature variables at a single first historical point in time, while the training label is the parameter value of the target variable at that first historical point in time. This training data can then be used to train a neural network model to identify key influencing factors.

[0062] Step S1023: training a preset neural network model according to the training data set to obtain a trained neural network model;

[0063] Use the constructed training dataset to train the pre-set neural network model. Neural network models are powerful machine learning algorithms that can learn the complex relationships between input data (feature variables) and output data (target variables). Through training, the neural network model learns which feature variables have a significant impact on changes in the target variable, i.e., the key influencing factors.

[0064] Step S1024, extracting the weight parameters corresponding to each of the characteristic variables from the trained neural network model; determining the first target water quality parameter corresponding to the characteristic variable whose absolute value of the weight parameter is greater than the preset weight threshold as the first key influencing factor of the currently traversed first target water quality parameter, and obtaining the first key influencing factor of each of the first target water quality parameters.

[0065] After training is complete, the weight parameters corresponding to each characteristic variable are extracted from the neural network model. The weight parameters reflect the degree of influence of the characteristic variable on the target variable. The first target water quality parameter corresponding to the characteristic variable whose absolute value of the weight parameter exceeds the preset weight threshold is determined as the first key influencing factor of the currently traversed first target water quality parameter. In this way, after traversing all first target water quality parameters, the first key influencing factor of each first target water quality parameter is obtained.

[0066] In summary, this embodiment uses a neural network model to train and analyze key influencing factors, effectively identifying the key influencing factors for each primary target water quality parameter. These key influencing factors are important for understanding the mechanisms of water quality variation, predicting water quality trends, and developing targeted water quality management strategies.

[0067] In one embodiment, the neural network model includes an input layer, a hidden layer, and an output layer; the input layer includes a plurality of input neurons corresponding one-to-one to the feature variables; and the hidden layer includes weight parameters corresponding one-to-one to the input neurons.

[0068] In this embodiment, the input layer includes a number of input neurons that correspond one-to-one to the feature variables. Each input neuron receives the parameter value of a feature variable as input to the neural network. The hidden layer is the core of the neural network and contains weight parameters that correspond one-to-one to the input neurons. These weight parameters are used to perform feature space mapping operations on the input data to extract key information from the input data. The hidden layer may include one or more layers, and the number of neurons in each layer can be adjusted according to actual conditions. The output layer receives the data output by the hidden layer and performs post-processing to obtain the final predicted value. In this embodiment, the predicted value of the output layer is the parameter value of the target variable.

[0069] In one embodiment, the input layer of the neural network model is:

[0070] X=[X1,X2,……X n ] T

[0071] Among them, X represents the feature variable, n represents the number of input neurons;

[0072] The hidden layer is:

[0073] Z l =W l A l-1 +b l

[0074] A l =g l (Z l )

[0075] Among them, l means there are l hidden layers, W l is the weight matrix of layer l, b l is the bias vector of the lth layer, A l-1 is the activation output of the previous layer, g l () is the activation function of layer l;

[0076] The output layer is:

[0077]

[0078] in, is the output value of the output layer, W l+1 and b l+1 are the weight matrix and bias vector of the output layer, A l is the activation output of the last hidden layer;

[0079] The loss value between the predicted value of each training sample and the corresponding training label is calculated using the following loss function:

[0080]

[0081] Among them, y is the training label corresponding to the training sample, and N is the number of samples.

[0082] In one embodiment, the step of training a preset neural network model according to the training data set to obtain a trained neural network model in step S1023 includes:

[0083] Step S10231: input the training sample into the input layer; input the parameter values of each feature variable of the training sample into the hidden layer through the input layer for feature space mapping operation processing; input the data obtained from the operation processing into the output layer for post-processing to obtain the predicted value output by the output layer;

[0084] The training sample is input to the input layer. The input layer passes the parameter values of each feature variable of the training sample to the hidden layer. The hidden layer performs feature space mapping operations on the input data based on the weight parameters to obtain processed data. The processed data is then input to the output layer for post-processing to obtain the predicted value of the output layer.

[0085] Step S10232, calculate the loss value of the predicted value and the training label corresponding to the training sample; adjust the weight parameter according to the loss value calculation result until the loss value is less than the preset loss threshold, and obtain a trained neural network model.

[0086] The loss value is calculated by comparing the predicted value output by the output layer with the training labels corresponding to the training samples. The loss value reflects the degree of discrepancy between the predicted value and the true value. Based on the loss value calculation results, the weight parameters (i.e., weight matrix) in the hidden layer are adjusted to reduce the discrepancy between the predicted value and the true value. This process is typically implemented using backpropagation and gradient descent algorithms. After adjusting the weight parameters, the training sample is again input into the neural network model for processing and a new loss value is calculated. This process is repeated until the loss value falls below the preset loss threshold, at which point the neural network model is considered trained.

[0087] In summary, the neural network model structure and training process of this embodiment can effectively learn and analyze the training dataset, thereby identifying the key influencing factors for each primary target water quality parameter. The neural network model possesses powerful nonlinear mapping and self-learning capabilities, enabling it to handle complex data relationships and improve the accuracy and efficiency of key influencing factor identification. Furthermore, by adjusting the structure and parameters of the neural network model, the model's performance can be further optimized to meet diverse water quality monitoring and analysis needs.

[0088] In step S103, the importance of each first key influencing factor is determined according to each first key influencing factor of the first target water quality parameter; and the second key influencing factor is determined according to the importance of each first key influencing factor.

[0089] In this step, the importance of each primary key influencing factor is determined based on its impact on the target water quality parameter, such as the magnitude of the correlation coefficient. Then, based on the importance, the secondary key influencing factors with the most significant impact on the target water quality parameter are selected. For example, after analysis, dissolved oxygen, temperature, and heavy metal concentration were identified as secondary key influencing factors because they have significant effects on multiple target water quality parameters.

[0090] Please refer to Figure 4In one embodiment, the step of determining the importance of each first key influencing factor according to each first key influencing factor of the first target water quality parameter in step S103 includes:

[0091] Step S1031 : Summarize the first key influencing factors corresponding to the first target water quality parameters to obtain a first key influencing factor set; and calculate the occurrence frequency of each first key influencing factor in the first key influencing factor set.

[0092] First, the first key influencing factors corresponding to each first target water quality parameter are aggregated to form a set of first key influencing factors. Next, the frequency of occurrence of each first key influencing factor in this set is calculated. The frequency of occurrence reflects the number of times a key influencing factor is identified as a key influencing factor for multiple first target water quality parameters, thereby reflecting its importance to a certain extent.

[0093] Step S1032: According to the several neural network models trained when each of the first key influencing factors is used as a characteristic variable, obtain the absolute values of the weight parameters of the first key influencing factors from the several neural network models respectively; and calculate the average value of the weight parameters of the first key influencing factors based on the absolute values of the several weight parameters.

[0094] Next, based on the neural network models trained with each first key influencing factor as a feature variable, the absolute values of the weight parameters for that key influencing factor in these models are obtained. Since a key influencing factor may be used as a feature variable in multiple neural network models, multiple absolute values of the weight parameters can be obtained. The average of these absolute values of the weight parameters is then calculated as the average weight parameter for that key influencing factor. The average weight parameter reflects the average degree of influence of the key influencing factor on the target variable and is another important indicator for assessing its importance.

[0095] Step S1033 : Obtaining the importance of each of the first key influencing factors according to the occurrence frequency of each of the first key influencing factors and the average value of the weight parameter.

[0096] Finally, the importance of each first-level key influencing factor is comprehensively assessed based on its frequency of occurrence and the average weight parameter. Specifically, a weighted sum or multiplication of the frequency of occurrence and the average weight parameter is performed to obtain a comprehensive score. This comprehensive score reflects the importance of each key influencing factor to water quality changes. By comparing the comprehensive scores of different key influencing factors, it is possible to determine which factors have the greatest impact on water quality changes, thus providing a basis for developing targeted water quality management strategies.

[0097] In summary, the importance assessment steps of this embodiment enable a comprehensive and objective assessment of the impact of each first-level key influencing factor on water quality changes. This approach combines the two metrics of frequency of occurrence and the average weight parameter, taking into account both the number of times a key influencing factor is identified and the average degree of its impact on the target variable, thereby improving the accuracy and reliability of the assessment.

[0098] For step S104, second historical water quality data of the target water area is obtained, where the second historical water quality data includes parameter values of several second target water quality parameters at several second historical time points; the second target water quality parameter is the first target water quality parameter corresponding to the second key influencing factor, and the second historical time point is the historical time point at which the target water quality problem occurs; based on the second historical water quality data, several target parameter intervals of the second key influencing factor are determined; based on the several target parameter intervals of the second key influencing factor, the target parameter interval corresponding to the parameter value of the second key influencing factor at each first historical time point is determined.

[0099] In this step, the target water quality issue can be determined based on the research objective. For example, it could be a water quality issue such as fish kills or algae blooms. The parameter values of the second target water quality parameter corresponding to the second key influencing factor at the historical time points when the target water quality issue occurred are collected. Based on this data, several target parameter ranges for the second key influencing factor are then determined. Simultaneously, the corresponding target parameter ranges are also determined based on the parameter values of the second key influencing factor at each first historical time point.

[0100] Please refer to Figure 5 In one embodiment, the step of determining the target parameter ranges of the second key influencing factor based on the second historical water quality data in step S104 includes:

[0101] Step S1041 : obtaining several densely distributed intervals of the parameter values of the second key influencing factor through parameter value distribution density cluster analysis based on the parameter values of the second key influencing factor at each second historical time point.

[0102] Based on the parameter values of the second key influencing factor at each second historical time point, a cluster analysis of the parameter value distribution density is performed. Cluster analysis is a technique that divides samples in a dataset into several groups or classes, so that samples within the same group are more similar, while samples between different groups are less similar. Here, density clustering methods such as DBSCAN (Density-Based Spatial Clustering of Applications with Noise) are used to divide the parameter values into several densely distributed intervals based on their distribution density. These intervals reflect the concentrated distribution of the parameter values of the second key influencing factor within different ranges.

[0103] Step S1042 , counting the occurrence frequencies of the parameter values of the second key influencing factors in the second historical water quality data within each of the parameter value densely distributed intervals.

[0104] Next, we counted the frequency of occurrence of the parameter values of the second key influencing factor within each densely distributed interval in the second historical water quality data. Frequency refers to the number of times a parameter value falls within a certain interval, reflecting the prevalence and representativeness of the parameter values within that interval. By counting frequency, we can understand the distribution of parameter values within different intervals and provide a basis for subsequently determining the target parameter range.

[0105] Step S1043 : determining the densely distributed interval of at least one parameter value whose occurrence frequency meets the preset frequency condition as the target parameter interval of the second key influencing factor.

[0106] Finally, the target parameter range for the second key influencing factor is determined as the interval with the most densely distributed parameter values that meets the preset frequency condition. The preset frequency condition can be set based on actual conditions, for example, selecting an interval with a high frequency of occurrence as the target parameter range. By determining the target parameter range, we can gain a more detailed understanding of the impact of the second key influencing factor on water quality within different parameter value ranges, thereby providing more specific guidance for developing targeted water quality management strategies.

[0107] In summary, this embodiment comprehensively and objectively determines the target parameter range for the second key influencing factor based on the second historical water quality data. This solution combines parameter value distribution density cluster analysis with frequency statistics, taking into account both the distribution of parameter values and their frequency within different ranges, thereby improving the accuracy and reliability of the target parameter range determination.

[0108] For step S105, the correlation relationship between each second key influencing factor is determined based on the target parameter range of each second key influencing factor at each first historical time point; the correlation relationship includes at least one second key influencing factor correlation combination; the second key influencing factor correlation combination includes at least one second key influencing factor and the target parameter range corresponding to the second key influencing factor.

[0109] In this step, the second key influencing factor parameter values and their corresponding target parameter intervals at each first historical time point are analyzed to determine the correlation relationships between these key influencing factors. These correlation relationships can form a second key influencing factor correlation combination. For example, through analysis, when dissolved oxygen and temperature simultaneously meet their respective corresponding target parameter intervals, target water quality problems will be caused, and a second key influencing factor correlation combination including dissolved oxygen and temperature is obtained. In this embodiment, an association rule mining algorithm such as the FP-growth algorithm can be used to mine and obtain the correlation relationships between each of the second key influencing factors.

[0110] For step S106, the current water quality data of the target water area is obtained; the current water quality data includes the current parameter values of each of the second key influencing factors; if the current parameter values of each of the second key influencing factors meet any of the associated combinations of the second key influencing factors, it is prompted that the target water area has a target water quality problem.

[0111] In this step, the current water quality data of the target water area is obtained in real time, including the current parameter values of each second key influencing factor. These parameter values are then compared with the associated combinations of the second key influencing factors. If the current parameter values of each second key influencing factor meet the conditions of any associated combination, it is indicated that the target water area has a target water quality problem. For example, assuming that the current real-time monitoring shows that the dissolved oxygen is 1.8 mg / L and the temperature is 32°C, both parameter values meet the previously determined target parameter range. Therefore, it is indicated that the target water area has a target water quality problem.

[0112] In one embodiment, after the step of prompting the target water area that a target water quality problem exists if the current parameter values of each of the second key influencing factors satisfy any associated combination of the second key influencing factors in step S106, the following steps are further included:

[0113] Step S1061 : generating warning information according to the current parameter values of each of the second key influencing factors and the target water quality problem, and sending the warning information to the target device.

[0114] Once it is detected that the current parameter values of each second key influencing factor meet any of the second key influencing factor association combinations and it is confirmed that the target water area has the target water quality problem, the early warning information generation stage will be entered. After the early warning information is generated, it will be automatically sent to the preset target devices. These target devices can include mobile devices of water quality management personnel (such as mobile phones, tablets), fixed workstations, and control consoles of water quality monitoring centers. Through various methods such as SMS, email, and in-app notifications, ensure that the early warning information can be quickly conveyed to relevant personnel.

[0115] Please refer to Figure 6 , the embodiment of the present application further provides a water quality monitoring device, comprising:

[0116] A first historical water quality data acquisition module 201 is configured to acquire first historical water quality data of a target water area; the first historical water quality data includes parameter values of a plurality of first target water quality parameters at a plurality of first historical time points;

[0117] A first key influencing factor analysis module 202 is configured to perform a key influencing factor analysis on the parameter values of the first target water quality parameters at the first historical time points to obtain a first key influencing factor for each of the first target water quality parameters;

[0118] A second key influencing factor analysis module 203 is configured to determine the importance of each first key influencing factor according to each first target water quality parameter; and determine a second key influencing factor according to the importance of each first key influencing factor;

[0119] The target parameter interval determination module 204 is configured to obtain second historical water quality data for the target water area, the second historical water quality data including parameter values of a plurality of second target water quality parameters at a plurality of second historical time points; the second target water quality parameter being the first target water quality parameter corresponding to the second key influencing factor, the second historical time point being the historical time point at which the target water quality problem occurred; determine a plurality of target parameter intervals for the second key influencing factor based on the second historical water quality data; and determine a target parameter interval corresponding to the parameter value of the second key influencing factor at each first historical time point based on the plurality of target parameter intervals for the second key influencing factor;

[0120] The association mining module 205 is configured to determine an association relationship between each of the second key influencing factors based on the target parameter range of each of the second key influencing factors at each first historical time point; the association relationship includes at least one second key influencing factor association combination; the second key influencing factor association combination includes at least one second key influencing factor and the target parameter range corresponding to the second key influencing factor;

[0121] The current water quality monitoring module 206 is used to obtain the current water quality data of the target water area; the current water quality data includes the current parameter values of each of the second key influencing factors; if the current parameter values of each of the second key influencing factors meet any of the associated combinations of the second key influencing factors, it is prompted that there is a target water quality problem in the target water area.

[0122] It should be noted that the water quality monitoring device provided in the above embodiment only uses the division of the above functional modules as an example when executing the water quality monitoring method. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the water quality monitoring device and the water quality monitoring method provided in the above embodiment belong to the same concept. The implementation process is detailed in the above water quality monitoring method embodiment, which will not be repeated here.

[0123] Please refer to Figure 7 , an embodiment of the present application also provides an electronic device 301, comprising: a processor 302, a memory 303, and a computer program 304 stored in the memory 303 and executable on the processor 302, wherein the processor 302 implements the steps of the method described in any one of the embodiments of the present application when executing the computer program 304.

[0124] The processor 302 may include one or more processing cores. The processor 302 utilizes various interfaces and circuits to connect various components within the electronic device 301. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 303, and by accessing data in the memory 303, the processor 302 performs various functions of the electronic device 301 and processes data. Optionally, the processor 302 may be implemented in the form of at least one hardware component selected from the group consisting of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 302 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content required to be displayed on the touch screen; and the modem is used to handle wireless communications. It is understood that the modem may not be integrated into the processor 302 and may be implemented separately on a single chip.

[0125] Among them, the memory 303 may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory 303 includes a non-transitory computer-readable storage medium. The memory 303 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 303 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch instructions, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 303 may also be optionally at least one storage device located away from the aforementioned processor 302.

[0126] The present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by the processor, it implements the steps of the method described in any one of the embodiments of the present application. That is, it will be understood by those skilled in the art that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The computer program may include computer program code, which may be in source code form, object code form, executable data or some intermediate form, etc. The aforementioned storage medium includes: any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium, etc. It should be noted that the content contained in computer-readable media can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media does not include electrical carrier signals and telecommunications signals.

[0127] The above embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the spirit of the present application, and the present application is intended to encompass such modifications and variations.

Claims

1. A water quality monitoring method, characterized in that: The following steps are involved: Acquire first historical water quality data of a target water area; the first historical water quality data includes parameter values of a plurality of first target water quality parameters at a plurality of first historical time points; Performing a key influencing factor analysis on the parameter values of the plurality of first target water quality parameters at a plurality of first historical time points to obtain a first key influencing factor for each of the first target water quality parameters; Determining the importance of each first key influencing factor according to each first target water quality parameter; determining a second key influencing factor according to the importance of each first key influencing factor; Obtaining second historical water quality data for the target water area, the second historical water quality data including parameter values of a plurality of second target water quality parameters at a plurality of second historical time points; the second target water quality parameter being a first target water quality parameter corresponding to the second key influencing factor, and the second historical time point being a historical time point at which the target water quality problem occurs; determining a plurality of target parameter intervals for the second key influencing factor based on the second historical water quality data; and determining a target parameter interval corresponding to the parameter value of the second key influencing factor at each first historical time point based on the plurality of target parameter intervals for the second key influencing factor; Determining, based on the target parameter ranges of the second key influencing factors at the first historical time points, a correlation relationship between the second key influencing factors; the correlation relationship includes at least one second key influencing factor correlation combination; the second key influencing factor correlation combination includes at least one second key influencing factor and a target parameter range corresponding to the second key influencing factor; Obtain current water quality data of the target water area; the current water quality data includes the current parameter values of each of the second key influencing factors; if the current parameter values of each of the second key influencing factors meet any associated combination of the second key influencing factors, it is prompted that there is a target water quality problem in the target water area.

2. The water quality monitoring method according to claim 1, characterized in that: The step of performing key influencing factor analysis on the parameter values of the plurality of first target water quality parameters at a plurality of first historical time points to obtain a first key influencing factor of each of the first target water quality parameters includes: Traversing each first target water quality parameter among the plurality of first target water quality parameters; A training data set is constructed by taking the first target water quality parameter currently being traversed as the target variable and the remaining first target water quality parameters as feature variables; wherein the training data set includes a plurality of training samples and training labels of the training samples, each of the training samples includes parameter values of all feature variables at a single first historical time point, and the training label of each training sample is the parameter value of the target variable at the corresponding first historical time point; Training a preset neural network model according to the training data set to obtain a trained neural network model; The weight parameters corresponding to each of the characteristic variables are extracted from the trained neural network model; the first target water quality parameter corresponding to the characteristic variable whose absolute value of the weight parameter is greater than the preset weight threshold is determined as the first key influencing factor of the currently traversed first target water quality parameter, and the first key influencing factor of each of the first target water quality parameters is obtained.

3. The water quality monitoring method according to claim 2, characterized in that: The neural network model includes an input layer, a hidden layer, and an output layer; the input layer includes a plurality of input neurons corresponding one-to-one to the feature variables; the hidden layer includes weight parameters corresponding one-to-one to the input neurons; The step of training a preset neural network model according to the training data set to obtain a trained neural network model includes: Inputting the training sample into the input layer; Inputting the parameter values of each characteristic variable of the training sample into the hidden layer through the input layer for feature space mapping operation processing, inputting the data obtained from the operation processing into the output layer for post-processing to obtain the predicted value output by the output layer; The loss value is calculated for the predicted value and the training label corresponding to the training sample; the weight parameter is adjusted according to the loss value calculation result until the loss value is less than the preset loss threshold, thereby obtaining a trained neural network model.

4. The water quality monitoring method according to claim 1, characterized in that: The step of determining a plurality of target parameter ranges of the second key influencing factors based on the second historical water quality data includes: Obtaining, based on the parameter values of the second key influencing factors at each second historical time point, a plurality of densely distributed intervals of the parameter values of the second key influencing factors through a parameter value distribution density cluster analysis; Counting the occurrence frequencies of the parameter values of the second key influencing factors in the second historical water quality data within each of the parameter value densely distributed intervals; The densely distributed interval of at least one parameter value whose occurrence frequency meets the preset frequency condition is determined as the target parameter interval of the second key influencing factor.

5. The water quality monitoring method according to claim 2, characterized in that: The step of determining the importance of each first key influencing factor according to each first key influencing factor of the first target water quality parameter includes: Summarizing the first key influencing factors corresponding to each of the first target water quality parameters to obtain a first key influencing factor set; calculating the occurrence frequency of each of the first key influencing factors in the first key influencing factor set; According to the plurality of neural network models trained when each of the first key influencing factors is used as a characteristic variable, obtaining the absolute values of the weight parameters of the first key influencing factors from the plurality of neural network models respectively; and calculating the average value of the weight parameters of the first key influencing factors based on the absolute values of the weight parameters; The importance of each of the first key influencing factors is obtained according to the occurrence frequency of each of the first key influencing factors and the average value of the weight parameter.

6. The water quality monitoring method according to claim 1, characterized in that: The step of obtaining first historical water quality data of the target water area includes: Acquire original first water quality time series data of the target water area; the first water quality time series data includes parameter values of several water quality parameters at different time points; Dividing the first water quality time series data into preset time windows, determining the mean and real-time value of each water quality parameter in each time window; performing a mean rationality test and a real-time value validity test based on the mean and real-time value of each water quality parameter in each time window, and eliminating data in each time window that fails to pass both the mean rationality test and the real-time value validity test; thereby obtaining second water quality time series data; Performing linear dimensionality reduction on the second water quality time series data using a principal component analysis method, and identifying water quality parameters that are independent of each other and have a significant impact on water quality changes as target water quality parameters; Data of other water quality parameters other than the target water quality parameter in the second water quality time series data are eliminated to obtain first historical water quality data of the target water area.

7. The water quality monitoring method according to claim 1, characterized in that: After the step of prompting the target water area for the existence of a target water quality problem if the current parameter values of the second key influencing factors satisfy any associated combination of the second key influencing factors, the method further includes the following steps: An early warning message is generated according to the current parameter values of each of the second key influencing factors and the target water quality problem, and the early warning message is sent to the target device.

8. A water quality monitoring device, characterized in that: include: A first historical water quality data acquisition module is configured to acquire first historical water quality data of a target water area; the first historical water quality data includes parameter values of a plurality of first target water quality parameters at a plurality of first historical time points; A first key influencing factor analysis module is used to perform a key influencing factor analysis on the parameter values of the first target water quality parameters at a plurality of first historical time points to obtain a first key influencing factor of each of the first target water quality parameters; A second key influencing factor analysis module is configured to determine the importance of each first key influencing factor according to each first key influencing factor of the first target water quality parameter; and determine a second key influencing factor according to the importance of each first key influencing factor; a target parameter interval determination module, configured to obtain second historical water quality data for the target water area, the second historical water quality data including parameter values of a plurality of second target water quality parameters at a plurality of second historical time points; the second target water quality parameter being a first target water quality parameter corresponding to the second key influencing factor, the second historical time point being a historical time point at which the target water quality problem occurs; determining a plurality of target parameter intervals for the second key influencing factor based on the second historical water quality data; and determining a target parameter interval corresponding to the parameter value of the second key influencing factor at each first historical time point based on the plurality of target parameter intervals for the second key influencing factor; an association relationship mining module, configured to determine an association relationship between each of the second key influencing factors based on the target parameter interval of each of the second key influencing factors at each first historical time point; the association relationship includes at least one second key influencing factor association combination; the second key influencing factor association combination includes at least one second key influencing factor and a target parameter interval corresponding to the second key influencing factor; A current water quality monitoring module, configured to obtain current water quality data of the target water area; the current water quality data includes current parameter values of each of the second key influencing factors; If the current parameter values of each of the second key influencing factors satisfy any associated combination of the second key influencing factors, it is indicated that there is a target water quality problem in the target water area.

9. An electronic device, characterized in that: The method comprises a processor, a memory and a computer-readable program stored in the memory, wherein the computer-readable program implements the steps of the method according to any one of claims 1 to 8 when executed by the processor.

10. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed, the device where the computer-readable storage medium is located is controlled to implement the method according to any one of claims 1 to 8.

Images