Water quality monitoring method and system based on multi-source data

Abstract

The application discloses a water quality monitoring method and system based on multi-source data, and the method comprises the following steps: acquiring a plurality of types of monitoring sensor data of a target water area; determining a plurality of pollution source positions of the target water area based on the monitoring sensor data belonging to a first monitoring level; screening associated sensor data belonging to a second monitoring level from all the monitoring sensor data based on the pollution source positions; and analyzing the water pollution situation of the target water area according to the associated sensor data and the pollution source positions. It can be seen that the application can realize accurate water pollution evaluation based on multi-level monitoring and multi-source data, improve the accuracy and response efficiency of water quality management of the target water area, and reduce the risk of pollution diffusion.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a water quality monitoring method and system based on multi-source data. Background Technology

[0002] With the rapid growth in demand for water resource protection and environmental monitoring, optimizing water quality management through accurate pollution assessment has become a key technical issue. Existing technologies typically assess water quality by collecting single-type monitoring sensor data from a water area and employing simple threshold analysis or fixed-area sampling methods. However, existing solutions lack dynamic screening of multi-level monitoring data and precise location analysis of pollution sources, making it difficult to accurately assess the complex relationship between correlated sensor data and pollution conditions. This results in insufficient accuracy in water pollution assessment and makes the pollution prone to spread due to delayed pollution source location or assessment bias, thus limiting the response efficiency and effectiveness of water quality management. Therefore, existing technologies have shortcomings that urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a water quality monitoring method and system based on multi-source data, which can realize accurate water pollution assessment based on multi-level monitoring and multi-source data, improve the accuracy and response efficiency of water quality management in target water areas, and reduce the risk of pollution spread.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses a water quality monitoring method based on multi-source data, the method comprising:

[0005] Acquire multiple types of monitoring sensor data for the target water area;

[0006] Based on the monitoring sensor data belonging to the first monitoring level, multiple pollution origin locations in the target water area are determined.

[0007] Based on the pollution origin location, relevant sensor data belonging to the second monitoring level are selected from all the monitoring sensor data;

[0008] Based on the associated sensor data and the location of the pollution origin, the water pollution situation in the target water area is analyzed.

[0009] As an optional implementation, in the first aspect of the present invention, the types of monitoring sensor data are spectral reflectance data, image data, sound data, water flow velocity data, temperature data, or humidity data.

[0010] As an optional implementation, in a first aspect of the invention, determining multiple pollution origin locations of the target water area based on the monitoring sensor data belonging to a first monitoring level includes:

[0011] For each type of monitoring sensor data, determine the ratio of the total data volume of all monitoring sensor data of that type to the reference data volume; the reference data volume is the average of the total data volume of all types.

[0012] Based on the historical pollution prediction records corresponding to this type, determine the data correlation parameters corresponding to this type.

[0013] Calculate the product of the ratio and the data correlation parameter to obtain the level parameter corresponding to the category;

[0014] Determine whether the level parameter is greater than the first parameter threshold. If so, determine that the monitoring sensor data of that type belongs to the first monitoring level.

[0015] All the monitoring sensor data belonging to the first monitoring level are input into the trained pollution area prediction model to obtain multiple pollution areas and corresponding pollution levels of the target water area; the pollution area prediction model is trained using a training dataset that includes multiple training multi-source sensor data and corresponding pollution area and pollution level labels.

[0016] Based on the multiple polluted areas and their corresponding pollution levels, the multiple pollution origin locations of the target water area are determined.

[0017] As an optional implementation, in the first aspect of the present invention, determining the data correlation parameter corresponding to the type based on the historical pollution prediction records corresponding to that type includes:

[0018] Obtain multiple historical pollution prediction records corresponding to the target water area;

[0019] Historical pollution prediction records that use this type of monitoring sensor data for prediction and whose prediction results are the same as the actual survey results are identified as associated prediction records.

[0020] Calculate the number of records for all the predicted associations to obtain the number of associated records;

[0021] The data correlation parameter is obtained by calculating the proportion of the number of associated records to the total number of all historical pollution prediction records.

[0022] As an optional implementation, in the first aspect of the present invention, determining multiple pollution origin locations of the target water area based on the multiple polluted areas and their corresponding pollution levels includes:

[0023] Based on the dynamic programming clustering algorithm, the polluted areas that meet the preset condition rules are clustered to obtain multiple sets of areas; the condition rules are used to limit the area sets to include multiple polluted areas that have border boundaries and whose pollution levels gradually increase along the arrangement direction.

[0024] The geometric center point of the polluted area with the highest pollution level in each set of regions is determined as the pollution origin location to obtain multiple pollution origin locations.

[0025] As an optional implementation, in the first aspect of the invention, the step of filtering relevant sensor data belonging to the second monitoring level from all the monitoring sensor data based on the pollution origin location includes:

[0026] From all the monitoring sensor data, data whose corresponding category and level parameter are greater than the second parameter threshold are selected to obtain multiple preferred sensor data; the second parameter threshold is greater than the first parameter threshold.

[0027] For each of the preferred sensing data, the location correlation degree corresponding to the preferred sensing data is calculated based on the pollution origin location;

[0028] The preferred sensing data whose location correlation is greater than a preset correlation threshold is identified as correlated sensing data.

[0029] As an optional implementation, in the first aspect of the invention, calculating the location correlation degree corresponding to the preferred sensing data based on the pollution origin location includes:

[0030] The location correlation degree corresponding to the preferred sensing data is obtained by calculating the weighted sum of the location distances between the data acquisition location corresponding to the preferred sensing data and each pollution origin location; wherein, the weighted calculation weight corresponding to each location distance is proportional to the average pollution degree corresponding to all pollution areas in the region set corresponding to the pollution origin location.

[0031] As an optional implementation, in the first aspect of the present invention, the step of analyzing the water pollution status of the target water area based on the associated sensor data and the pollution origin location includes:

[0032] Each of the associated sensor data is input into the trained water quality prediction model to obtain the water quality prediction parameters corresponding to each of the associated sensor data; the water quality prediction model is trained using a training dataset that includes multiple training sensor data and corresponding water quality labels.

[0033] The water quality pollution status of the target water area is obtained by calculating the weighted sum of the water quality prediction parameters corresponding to all the associated sensor data; wherein, the weight of each water quality prediction parameter is proportional to the location correlation degree of the corresponding associated sensor data.

[0034] A second aspect of this invention discloses a water quality monitoring system based on multi-source data, the system comprising:

[0035] The acquisition module is used to acquire multiple types of monitoring sensor data for the target water area;

[0036] The determination module is used to determine multiple pollution origin locations in the target water area based on the monitoring sensor data belonging to the first monitoring level;

[0037] A filtering module is used to filter relevant sensor data belonging to the second monitoring level from all the monitoring sensor data based on the pollution origin location;

[0038] The analysis module is used to analyze the water pollution status of the target water area based on the associated sensor data and the location of the pollution origin.

[0039] As an optional implementation, in a second aspect of the invention, the types of monitoring sensor data are spectral reflectance data, image data, sound data, water flow velocity data, temperature data, or humidity data.

[0040] As an optional implementation, in a second aspect of the invention, the method by which the determining module determines the specific locations of multiple pollution sources in the target water area based on the monitoring sensor data belonging to the first monitoring level includes:

[0041] For each type of monitoring sensor data, determine the ratio of the total data volume of all monitoring sensor data of that type to the reference data volume; the reference data volume is the average of the total data volume of all types.

[0042] Based on the historical pollution prediction records corresponding to this type, determine the data correlation parameters corresponding to this type.

[0043] Calculate the product of the ratio and the data correlation parameter to obtain the level parameter corresponding to the category;

[0044] Determine whether the level parameter is greater than the first parameter threshold. If so, determine that the monitoring sensor data of that type belongs to the first monitoring level.

[0045] All the monitoring sensor data belonging to the first monitoring level are input into the trained pollution area prediction model to obtain multiple pollution areas and corresponding pollution levels of the target water area; the pollution area prediction model is trained using a training dataset that includes multiple training multi-source sensor data and corresponding pollution area and pollution level labels.

[0046] Based on the multiple polluted areas and their corresponding pollution levels, the multiple pollution origin locations of the target water area are determined.

[0047] As an optional implementation, in the second aspect of the invention, the specific method by which the determining module determines the data correlation parameter corresponding to the type based on the historical pollution prediction records corresponding to that type includes:

[0048] Obtain multiple historical pollution prediction records corresponding to the target water area;

[0049] Historical pollution prediction records that use this type of monitoring sensor data for prediction and whose prediction results are the same as the actual survey results are identified as associated prediction records.

[0050] Calculate the number of records for all the predicted associations to obtain the number of associated records;

[0051] The data correlation parameter is obtained by calculating the proportion of the number of associated records to the total number of all historical pollution prediction records.

[0052] As an optional implementation, in a second aspect of the invention, the determining module determines the specific method by which it determines the multiple pollution origin locations of the target water area based on the multiple polluted areas and their corresponding pollution levels, including:

[0053] Based on the dynamic programming clustering algorithm, the polluted areas that meet the preset condition rules are clustered to obtain multiple sets of areas; the condition rules are used to limit the area sets to include multiple polluted areas that have border boundaries and whose pollution levels gradually increase along the arrangement direction.

[0054] The geometric center point of the polluted area with the highest pollution level in each set of regions is determined as the pollution origin location to obtain multiple pollution origin locations.

[0055] As an optional implementation, in a second aspect of the invention, the specific method by which the screening module filters relevant sensor data belonging to the second monitoring level from all the monitoring sensor data based on the pollution origin location includes:

[0056] From all the monitoring sensor data, data whose corresponding category and level parameter are greater than the second parameter threshold are selected to obtain multiple preferred sensor data; the second parameter threshold is greater than the first parameter threshold.

[0057] For each of the preferred sensing data, the location correlation degree corresponding to the preferred sensing data is calculated based on the pollution origin location;

[0058] The preferred sensing data whose location correlation is greater than a preset correlation threshold is identified as correlated sensing data.

[0059] As an optional implementation, in a second aspect of the invention, the specific method by which the screening module calculates the location correlation degree corresponding to the preferred sensing data based on the pollution origin location includes:

[0060] The location correlation degree corresponding to the preferred sensing data is obtained by calculating the weighted sum of the location distances between the data acquisition location corresponding to the preferred sensing data and each pollution origin location; wherein, the weighted calculation weight corresponding to each location distance is proportional to the average pollution degree corresponding to all pollution areas in the region set corresponding to the pollution origin location.

[0061] As an optional implementation, in a second aspect of the invention, the specific method by which the analysis module analyzes the water pollution situation of the target water area based on the associated sensor data and the pollution origin location includes:

[0062] Each of the associated sensor data is input into the trained water quality prediction model to obtain the water quality prediction parameters corresponding to each of the associated sensor data; the water quality prediction model is trained using a training dataset that includes multiple training sensor data and corresponding water quality labels.

[0063] The water quality pollution status of the target water area is obtained by calculating the weighted sum of the water quality prediction parameters corresponding to all the associated sensor data; wherein, the weight of each water quality prediction parameter is proportional to the location correlation degree of the corresponding associated sensor data.

[0064] A third aspect of this invention discloses another water quality monitoring system based on multi-source data, the system comprising:

[0065] Memory containing executable program code;

[0066] A processor coupled to the memory;

[0067] The processor calls the executable program code stored in the memory to execute some or all of the steps in the water quality monitoring method based on multi-source data disclosed in the first aspect of the present invention.

[0068] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the water quality monitoring method based on multi-source data disclosed in the first aspect of the present invention.

[0069] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0070] This invention acquires multiple types of monitoring sensor data of a target water area and determines the pollution origin location based on the first monitoring level data. It then filters the second monitoring level related sensor data from all the monitoring sensor data and combines the related sensor data with the pollution origin location to analyze the water pollution situation. This enables accurate water pollution assessment based on multi-level monitoring and multi-source data, improves the accuracy and response efficiency of water quality management in the target water area, and reduces the risk of pollution spread. Attached Figure Description

[0071] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0072] Figure 1 This is a schematic flowchart of a water quality monitoring method based on multi-source data disclosed in an embodiment of the present invention.

[0073] Figure 2 This is a schematic diagram of the structure of a water quality monitoring system based on multi-source data disclosed in an embodiment of the present invention.

[0074] Figure 3 This is a schematic diagram of another water quality monitoring system based on multi-source data disclosed in an embodiment of the present invention. Detailed Implementation

[0075] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0076] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0077] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0078] This invention discloses a water quality monitoring method and system based on multi-source data. By acquiring multiple types of monitoring sensor data from a target water area and determining the pollution origin location based on first-level monitoring data, it then filters second-level monitoring data from all monitoring sensor data. Combining the associated sensor data and the pollution origin location, it analyzes the water pollution situation. This enables accurate water pollution assessment based on multi-level monitoring and multi-source data, improving the accuracy and response efficiency of water quality management in the target water area and reducing the risk of pollution spread. Detailed explanations follow.

[0079] Example 1

[0080] Please see Figure 1 , Figure 1 This is a schematic flowchart of a water quality monitoring method based on multi-source data disclosed in an embodiment of the present invention. Figure 1 The described water quality monitoring method based on multi-source data can be applied to data processing systems / data processing equipment / data processing servers (wherein, the server includes local processing servers or cloud processing servers). For example... Figure 1 As shown, this water quality monitoring method based on multi-source data may include the following operations:

[0081] 101. Acquire multiple types of monitoring sensor data for the target water area.

[0082] Optionally, the monitoring sensor data may include temperature data, pH value data, dissolved oxygen data, turbidity data, or pollutant concentration data, and the present invention does not limit it.

[0083] Optionally, the target water area can be a river, lake, ocean area or reservoir, and the present invention does not limit it.

[0084] Optionally, this acquisition process can be achieved based on real-time sensor acquisition, satellite remote sensing, UAV monitoring, or manual sampling; this invention does not limit the scope of the acquisition.

[0085] 102. Based on monitoring sensor data belonging to the first monitoring level, determine the locations of multiple pollution sources in the target water area.

[0086] Optionally, the first monitoring level can be high-priority monitoring, low-frequency monitoring, or real-time monitoring; this invention does not impose any limitations.

[0087] Optionally, the pollution origin location can be a coordinate point, a regional range, or a pollution source identifier; this invention does not impose any limitations on this.

[0088] Optionally, this determination process can be implemented based on machine learning models, spatial analysis algorithms, or data fusion methods, and the present invention does not limit it.

[0089] 103. Based on the location of pollution origin, filter relevant sensor data belonging to the second monitoring level from all monitoring sensor data.

[0090] Optionally, the second monitoring level can be detailed monitoring, auxiliary monitoring, or verification monitoring, and the present invention does not limit it.

[0091] Optionally, the associated sensor data can be temperature data, chemical data, or biological data related to the origin of pollution; this invention does not limit this.

[0092] Optionally, this filtering process can be implemented based on location similarity, data relevance, or threshold filtering, and this invention does not limit it.

[0093] 104. Analyze the water pollution situation in the target water area based on the associated sensor data and the location of the pollution origin.

[0094] Optionally, the water pollution situation may include the type of pollution, the degree of pollution, the trend of pollution spread, or the assessment of pollution impact, which is not limited in this invention.

[0095] Optionally, the analysis process can be implemented based on statistical analysis, spatiotemporal models, or neural network algorithms, and this invention does not limit it.

[0096] As can be seen, the above-described embodiments of the invention acquire multiple types of monitoring sensor data of the target water area and determine the pollution origin location based on the first monitoring level data. Then, they filter the second monitoring level associated sensor data from all the monitoring sensor data and combine the associated sensor data with the pollution origin location to analyze the water pollution situation. This enables accurate water pollution assessment based on multi-level monitoring and multi-source data, improves the accuracy and response efficiency of water quality management in the target water area, and reduces the risk of pollution spread.

[0097] As an optional embodiment, the types of monitoring sensor data in the above steps are spectral reflectance data, image data, sound data, water flow velocity data, temperature data, or humidity data.

[0098] As can be seen, the above optional embodiments limit the types of monitoring sensor data to comprehensively characterize the water-related features in the region, assist in achieving accurate water pollution assessment based on multi-level monitoring and multi-source data, improve the accuracy and response efficiency of water quality management in target water areas, and reduce the risk of pollution spread.

[0099] As an optional embodiment, the step above, determining multiple pollution origin locations in the target water area based on monitoring sensor data belonging to the first monitoring level, includes:

[0100] For each type of monitoring sensor data, determine the ratio of the total amount of all monitoring sensor data of that type to the amount of reference data;

[0101] Optionally, the reference data size is the average of the total data size for all categories;

[0102] Based on the historical pollution prediction records corresponding to this type, determine the data correlation parameters corresponding to this type.

[0103] Calculate the product of the ratio and the data correlation parameter to obtain the level parameter corresponding to this category;

[0104] Determine if the level parameter is greater than the first parameter threshold. If so, determine that the monitoring sensor data of this type belongs to the first monitoring level.

[0105] All monitoring sensor data belonging to the first monitoring level are input into the trained pollution area prediction model to obtain multiple pollution areas and corresponding pollution levels in the target water area; optionally, the pollution area prediction model is trained using a training dataset that includes multiple training multi-source sensor data and corresponding pollution area and pollution level labels.

[0106] Based on multiple polluted areas and their corresponding pollution levels, the multiple pollution origin locations of the target water area are determined.

[0107] Optionally, the total data volume can be the number of data points, the data volume, or the number of data records; this invention does not impose any limitations on this.

[0108] Optionally, the reference data can be a simple average, a weighted average, or a median average; this invention does not impose any limitation.

[0109] Optionally, the ratio can be calculated based on numerical analysis, statistical methods, or data normalization, and this invention does not limit the calculation.

[0110] Optionally, the first parameter threshold can be a fixed threshold, a dynamic threshold, or a threshold adjusted based on the type of data; this invention does not impose any limitations.

[0111] Optionally, this judgment process can be implemented based on threshold comparison, classification model or logical reasoning, and the present invention does not limit it.

[0112] Optionally, the pollution area prediction model can be a deep learning model, a regression model, or a classification model; this invention does not impose any limitations.

[0113] Optionally, the contaminated area can be a coordinate area, a grid area, or a dynamic boundary area; the present invention does not limit this.

[0114] Optionally, the degree of pollution can be a pollution level, concentration value, or risk score; this invention does not limit this.

[0115] As can be seen, through the above optional embodiments, by calculating the product of the ratio of the data volume of the monitoring sensor data types and the data correlation parameter determined by the historical pollution prediction records as the level parameter, the first monitoring level data is screened and input into the pollution area prediction model to determine the pollution origin location, thereby realizing accurate monitoring level classification and origin location based on data volume and correlation, improving the pertinence and accuracy of water pollution assessment, and reducing the risk of pollution detection deviation caused by misclassification of levels.

[0116] As an optional embodiment, the step above, determining the data correlation parameter corresponding to the type based on the historical pollution prediction records, includes:

[0117] Obtain multiple historical pollution prediction records corresponding to the target water area;

[0118] Historical pollution prediction records that used this type of monitoring sensor data for prediction and whose prediction results were the same as the actual survey results were identified as associated prediction records.

[0119] Calculate the number of records for all associated predicted records to obtain the total number of associated records;

[0120] The data correlation parameter is obtained by calculating the proportion of the number of associated records to the total number of all historical pollution prediction records.

[0121] Optionally, the historical pollution prediction record may include the prediction time, prediction result, or prediction accuracy, which is not limited in this invention.

[0122] Optionally, this acquisition process can be implemented based on historical database queries, record extraction, or data interfaces; this invention does not impose any limitations.

[0123] Optionally, the historical pollution prediction record can be optimized by combining time range or type filtering, which is not limited in this invention.

[0124] As can be seen, through the above optional embodiments, by screening related prediction records that use this type of data and make accurate predictions based on historical pollution prediction records, and calculating their proportion as data correlation parameters, accurate correlation assessment based on historical accuracy is achieved, improving the reliability and practicality of calculating the level parameters of monitoring data types, and reducing the risk of level assessment errors caused by ignoring historical records.

[0125] As an optional embodiment, the step described above, determining multiple pollution origin locations of the target water area based on multiple polluted areas and corresponding pollution levels, includes:

[0126] Based on the dynamic programming clustering algorithm, polluted areas that meet the preset condition rules are clustered to obtain multiple sets of areas; optionally, the condition rules are used to limit the area sets to include multiple polluted areas with borders and corresponding pollution levels that gradually increase along the arrangement direction.

[0127] The geometric center point of the most polluted area in each region set is determined as the pollution origin location to obtain multiple pollution origin locations.

[0128] The dynamic programming clustering algorithm can be a hierarchical clustering algorithm, a density clustering algorithm, or a graph clustering algorithm; this invention does not limit the specific algorithm.

[0129] Optionally, the set of regions can be a continuous set of regions, a dispersed set of regions, or a dynamic set of regions; this invention does not impose any limitations.

[0130] Optionally, the clustering process can be optimized by incorporating contamination gradients, boundary overlaps, or region sizes; this invention does not impose any limitations on this.

[0131] Optionally, the geometric center point can be the centroid, weighted center, or boundary center; this invention does not impose any limitation.

[0132] Optionally, the process of determining the geometric center point can be based on geometric calculation, center point extraction, or optimization algorithms, and this invention does not limit it.

[0133] As can be seen, through the above optional embodiments, by clustering polluted areas that meet the conditions of border boundaries and gradually increasing pollution levels based on dynamic programming clustering algorithm, and taking the geometric center point of the area with the highest pollution level as the pollution origin location, accurate origin location identification based on regional correlation and degree analysis can be achieved, thereby improving the accuracy and comprehensiveness of water pollution assessment and reducing the risk of misjudgment of origin location due to improper regional clustering.

[0134] As an optional embodiment, the step described above, screening relevant sensor data belonging to the second monitoring level from all monitoring sensor data based on the pollution origin location, includes:

[0135] From all the monitored sensor data, select the data whose corresponding category and level parameter are greater than the second parameter threshold to obtain multiple preferred sensor data; optionally, the second parameter threshold is greater than the first parameter threshold.

[0136] For each preferred sensing data, the location correlation degree corresponding to the preferred sensing data is calculated based on the pollution origin location;

[0137] Preferred sensor data with a location correlation greater than a preset correlation threshold are identified as correlated sensor data.

[0138] Optionally, the second parameter threshold can be a fixed threshold, a dynamic threshold, or a threshold adjusted based on the monitoring type; the present invention does not impose any limitations on this.

[0139] As can be seen, through the above optional embodiments, by screening preferred sensor data whose level parameters exceed the second threshold and calculating their location correlation, data with correlation exceeding the threshold are determined as associated sensor data, thereby achieving accurate extraction of second monitoring level data based on level screening and location correlation, improving the pertinence and data quality of water pollution analysis, and reducing the risk of analysis errors caused by irrelevant data.

[0140] As an optional embodiment, the step above, calculating the location correlation degree corresponding to the preferred sensing data based on the pollution origin location, includes:

[0141] The location correlation degree corresponding to the preferred sensing data is obtained by calculating the weighted sum of the location distances between the data acquisition location and each pollution origin location. The weight of each location distance is proportional to the average pollution degree of all polluted areas in the region set corresponding to the pollution origin location.

[0142] As can be seen, through the above optional embodiments, by calculating the weighted average of the location distance between the preferred sensor data acquisition location and the pollution origin location as the location correlation degree, a precise location correlation assessment based on pollution degree weighting is achieved, which improves the accuracy and relevance of the correlation sensor data screening and reduces the risk of data selection bias caused by location omission.

[0143] As an optional embodiment, the step above, analyzing the water pollution status of the target water area based on associated sensor data and the location of pollution origin, includes:

[0144] Each associated sensor data is input into the trained water quality prediction model to obtain the water quality prediction parameters corresponding to each associated sensor data; optionally, the water quality prediction model is trained using a training dataset that includes multiple training sensor data and corresponding water quality labels.

[0145] The weighted sum of water quality prediction parameters corresponding to all associated sensor data is calculated to obtain the water pollution status of the target water area; wherein, the weight of each water quality prediction parameter is proportional to the location correlation of the corresponding associated sensor data.

[0146] Optionally, the water quality prediction model can be a regression model, a classification model, or a neural network model; this invention does not impose any limitations.

[0147] Optionally, the water quality prediction parameter can be a water quality score, pollutant concentration, or pollution level; this invention does not limit this parameter.

[0148] Optionally, the training dataset may include historical sensor data, simulated data, or labeled data, and this invention does not impose any limitations.

[0149] As can be seen, through the above optional embodiments, water quality prediction parameters are obtained by inputting associated sensor data into the water quality prediction model, and the weighted sum is calculated based on the weight rule proportional to the location correlation to determine the water pollution status. This achieves accurate quantitative analysis of water pollution based on the prediction model and associated weighting, improves the scientificity and reliability of water quality assessment in the target water area, and reduces the risk of pollution deviation caused by unweighted parameters.

[0150] Example 2

[0151] Please see Figure 2 , Figure 2 This is a schematic diagram of a water quality monitoring system based on multi-source data disclosed in an embodiment of the present invention. Figure 2 The described water quality monitoring system based on multi-source data can be applied to data processing systems / data processing equipment / data processing servers (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 2 As shown, the water quality monitoring system based on multi-source data may include:

[0152] The acquisition module 201 is used to acquire multiple types of monitoring sensor data of the target water area.

[0153] The determination module 202 is used to determine the multiple pollution origin locations of the target water area based on monitoring sensor data belonging to the first monitoring level.

[0154] The filtering module 203 is used to filter relevant sensor data belonging to the second monitoring level from all monitoring sensor data based on the pollution origin location.

[0155] Analysis module 204 is used to analyze the water pollution situation in the target water area based on the associated sensor data and the location of the pollution origin.

[0156] As can be seen, the above-described embodiments of the invention acquire multiple types of monitoring sensor data of the target water area and determine the pollution origin location based on the first monitoring level data. Then, they filter the second monitoring level associated sensor data from all the monitoring sensor data and combine the associated sensor data with the pollution origin location to analyze the water pollution situation. This enables accurate water pollution assessment based on multi-level monitoring and multi-source data, improves the accuracy and response efficiency of water quality management in the target water area, and reduces the risk of pollution spread.

[0157] As an optional embodiment, the types of monitored sensor data include spectral reflectance data, image data, sound data, water flow velocity data, temperature data, or humidity data.

[0158] As can be seen, the above optional embodiments limit the types of monitoring sensor data to comprehensively characterize the water-related features in the region, assist in achieving accurate water pollution assessment based on multi-level monitoring and multi-source data, improve the accuracy and response efficiency of water quality management in target water areas, and reduce the risk of pollution spread.

[0159] As an optional embodiment, the determination module determines the specific methods by which it identifies multiple pollution origin locations in a target water area based on monitoring sensor data belonging to the first monitoring level, including:

[0160] For each type of monitoring sensor data, determine the ratio of the total data volume of all monitoring sensor data of that type to the reference data volume; optionally, the reference data volume is the average of the total data volume of all types.

[0161] Based on the historical pollution prediction records corresponding to this type, determine the data correlation parameters corresponding to this type.

[0162] Calculate the product of the ratio and the data correlation parameter to obtain the level parameter corresponding to this category;

[0163] Determine if the level parameter is greater than the first parameter threshold. If so, determine that the monitoring sensor data of this type belongs to the first monitoring level.

[0164] All monitoring sensor data belonging to the first monitoring level are input into the trained pollution area prediction model to obtain multiple pollution areas and corresponding pollution levels in the target water area; optionally, the pollution area prediction model is trained using a training dataset that includes multiple training multi-source sensor data and corresponding pollution area and pollution level labels.

[0165] Based on multiple polluted areas and their corresponding pollution levels, the multiple pollution origin locations of the target water area are determined.

[0166] As can be seen, through the above optional embodiments, by calculating the product of the ratio of the data volume of the monitoring sensor data types and the data correlation parameter determined by the historical pollution prediction records as the level parameter, the first monitoring level data is screened and input into the pollution area prediction model to determine the pollution origin location, thereby realizing accurate monitoring level classification and origin location based on data volume and correlation, improving the pertinence and accuracy of water pollution assessment, and reducing the risk of pollution detection deviation caused by misclassification of levels.

[0167] As an optional embodiment, the method by which the determining module determines the data correlation parameter corresponding to the category based on the historical pollution prediction records corresponding to that category includes:

[0168] Obtain multiple historical pollution prediction records corresponding to the target water area;

[0169] Historical pollution prediction records that used this type of monitoring sensor data for prediction and whose prediction results were the same as the actual survey results were identified as associated prediction records.

[0170] Calculate the number of records for all associated predicted records to obtain the total number of associated records;

[0171] The data correlation parameter is obtained by calculating the proportion of the number of associated records to the total number of all historical pollution prediction records.

[0172] As can be seen, through the above optional embodiments, by screening related prediction records that use this type of data and make accurate predictions based on historical pollution prediction records, and calculating their proportion as data correlation parameters, accurate correlation assessment based on historical accuracy is achieved, improving the reliability and practicality of calculating the level parameters of monitoring data types, and reducing the risk of level assessment errors caused by ignoring historical records.

[0173] As an optional embodiment, the method by which the determining module determines multiple pollution origin locations of a target water area based on multiple polluted areas and their corresponding pollution levels includes:

[0174] Based on the dynamic programming clustering algorithm, polluted areas that meet the preset condition rules are clustered to obtain multiple sets of areas; optionally, the condition rules are used to limit the area sets to include multiple polluted areas with borders and corresponding pollution levels that gradually increase along the arrangement direction.

[0175] The geometric center point of the most polluted area in each region set is determined as the pollution origin location to obtain multiple pollution origin locations.

[0176] As can be seen, through the above optional embodiments, by clustering polluted areas that meet the conditions of border boundaries and gradually increasing pollution levels based on dynamic programming clustering algorithm, and taking the geometric center point of the area with the highest pollution level as the pollution origin location, accurate origin location identification based on regional correlation and degree analysis can be achieved, thereby improving the accuracy and comprehensiveness of water pollution assessment and reducing the risk of misjudgment of origin location due to improper regional clustering.

[0177] As an optional embodiment, the specific method by which the screening module filters relevant sensor data belonging to the second monitoring level from all monitoring sensor data based on the pollution origin location includes:

[0178] From all the monitored sensor data, select the data whose corresponding category and level parameter are greater than the second parameter threshold to obtain multiple preferred sensor data; optionally, the second parameter threshold is greater than the first parameter threshold.

[0179] For each preferred sensing data, the location correlation degree corresponding to the preferred sensing data is calculated based on the pollution origin location;

[0180] Preferred sensor data with a location correlation greater than a preset correlation threshold are identified as correlated sensor data.

[0181] As can be seen, through the above optional embodiments, by screening preferred sensor data whose level parameters exceed the second threshold and calculating their location correlation, data with correlation exceeding the threshold are determined as associated sensor data, thereby achieving accurate extraction of second monitoring level data based on level screening and location correlation, improving the pertinence and data quality of water pollution analysis, and reducing the risk of analysis errors caused by irrelevant data.

[0182] As an optional embodiment, the screening module calculates the location correlation corresponding to the preferred sensing data based on the pollution origin location in the following specific ways:

[0183] The location correlation degree corresponding to the preferred sensing data is obtained by calculating the weighted sum of the location distances between the data acquisition location and each pollution origin location. The weight of each location distance is proportional to the average pollution degree of all polluted areas in the region set corresponding to the pollution origin location.

[0184] As can be seen, through the above optional embodiments, by calculating the weighted average of the location distance between the preferred sensor data acquisition location and the pollution origin location as the location correlation degree, a precise location correlation assessment based on pollution degree weighting is achieved, which improves the accuracy and relevance of the correlation sensor data screening and reduces the risk of data selection bias caused by location omission.

[0185] As an optional embodiment, the analysis module analyzes the water pollution situation of the target water area based on associated sensor data and the location of pollution origin in a specific way, including:

[0186] Each associated sensor data is input into the trained water quality prediction model to obtain the water quality prediction parameters corresponding to each associated sensor data; optionally, the water quality prediction model is trained using a training dataset that includes multiple training sensor data and corresponding water quality labels.

[0187] The weighted sum of water quality prediction parameters corresponding to all associated sensor data is calculated to obtain the water pollution status of the target water area; wherein, the weight of each water quality prediction parameter is proportional to the location correlation of the corresponding associated sensor data.

[0188] As can be seen, through the above optional embodiments, water quality prediction parameters are obtained by inputting associated sensor data into the water quality prediction model, and the weighted sum is calculated based on the weight rule proportional to the location correlation to determine the water pollution status. This achieves accurate quantitative analysis of water pollution based on the prediction model and associated weighting, improves the scientificity and reliability of water quality assessment in the target water area, and reduces the risk of pollution deviation caused by unweighted parameters.

[0189] Example 3

[0190] Please see Figure 3 , Figure 3 This is another water quality monitoring system based on multi-source data disclosed in the embodiments of the present invention. Figure 3 The described water quality monitoring system based on multi-source data is applied in a data processing system / data processing equipment / data processing server (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 3 As shown, the water quality monitoring system based on multi-source data may include:

[0191] Memory 301 storing executable program code;

[0192] Processor 302 coupled to memory 301;

[0193] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the water quality monitoring method based on multi-source data described in Embodiment 1.

[0194] Example 4

[0195] This invention discloses a computer read storage medium that stores a computer program for electronic data interchange, wherein the computer program causes a computer to execute the steps of the water quality monitoring method based on multi-source data described in Embodiment 1.

[0196] Example 5

[0197] This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of the water quality monitoring method based on multi-source data described in Embodiment 1.

[0198] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0199] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0200] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0201] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0202] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0203] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0204] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0205] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0206] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0207] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0208] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0209] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0210] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0211] Finally, it should be noted that the water quality monitoring method and system based on multi-source data disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A water quality monitoring method based on multi-source data, characterized in that, The method includes: Acquire multiple types of monitoring sensor data for the target water area; Based on the monitoring sensor data belonging to the first monitoring level, multiple pollution origin locations in the target water area are determined, including: For each type of monitoring sensor data, determine the ratio of the total data volume of all monitoring sensor data of that type to the reference data volume; the reference data volume is the average of the total data volume of all types. Based on the historical pollution prediction records corresponding to this type, determine the data correlation parameters corresponding to this type. Calculate the product of the ratio and the data correlation parameter to obtain the level parameter corresponding to the category; Determine whether the level parameter is greater than the first parameter threshold. If so, determine that the monitoring sensor data of that type belongs to the first monitoring level. All the monitoring sensor data belonging to the first monitoring level are input into the trained pollution area prediction model to obtain multiple pollution areas and corresponding pollution levels of the target water area; the pollution area prediction model is trained using a training dataset that includes multiple training multi-source sensor data and corresponding pollution area and pollution level labels. Based on the multiple polluted areas and their corresponding pollution levels, multiple pollution origin locations in the target water area are determined; Based on the pollution origin location, relevant sensor data belonging to the second monitoring level are selected from all the monitoring sensor data, including: From all the monitoring sensor data, data whose corresponding category and level parameter are greater than the second parameter threshold are selected to obtain multiple preferred sensor data; the second parameter threshold is greater than the first parameter threshold. For each of the preferred sensing data, the location correlation degree corresponding to the preferred sensing data is calculated based on the pollution origin location; The preferred sensing data whose location correlation is greater than a preset correlation threshold is determined as correlated sensing data; Based on the associated sensor data and the location of the pollution origin, the water pollution situation in the target water area is analyzed.

2. The water quality monitoring method based on multi-source data according to claim 1, characterized in that, The types of monitoring sensor data include spectral reflectance data, image data, sound data, water flow velocity data, temperature data, or humidity data.

3. The water quality monitoring method based on multi-source data according to claim 1, characterized in that, The determination of the data correlation parameter corresponding to this type based on the historical pollution prediction records includes: Obtain multiple historical pollution prediction records corresponding to the target water area; Historical pollution prediction records that use this type of monitoring sensor data for prediction and whose prediction results are the same as the actual survey results are identified as associated prediction records. Calculate the number of records for all the predicted associations to obtain the number of associated records; The data correlation parameter is obtained by calculating the proportion of the number of associated records to the total number of all historical pollution prediction records.

4. The water quality monitoring method based on multi-source data according to claim 1, characterized in that, The step of determining multiple pollution origin locations of the target water area based on the multiple polluted areas and their corresponding pollution levels includes: Based on the dynamic programming clustering algorithm, the polluted areas that meet the preset condition rules are clustered to obtain multiple sets of areas; the condition rules are used to limit the area sets to include multiple polluted areas that have border boundaries and whose pollution levels gradually increase along the arrangement direction. The geometric center point of the polluted area with the highest pollution level in each set of regions is determined as the pollution origin location to obtain multiple pollution origin locations.

5. The water quality monitoring method based on multi-source data according to claim 4, characterized in that, The calculation of the location correlation degree corresponding to the preferred sensing data based on the pollution origin location includes: The location correlation degree corresponding to the preferred sensing data is obtained by calculating the weighted sum of the location distances between the data acquisition location corresponding to the preferred sensing data and each pollution origin location; wherein, the weighted calculation weight corresponding to each location distance is proportional to the average pollution degree corresponding to all pollution areas in the region set corresponding to the pollution origin location.

6. The water quality monitoring method based on multi-source data according to claim 1, characterized in that, The step of analyzing the water pollution status of the target water area based on the associated sensor data and the pollution origin location includes: Each of the associated sensor data is input into the trained water quality prediction model to obtain the water quality prediction parameters corresponding to each of the associated sensor data; the water quality prediction model is trained using a training dataset that includes multiple training sensor data and corresponding water quality labels. The water quality pollution status of the target water area is obtained by calculating the weighted sum of the water quality prediction parameters corresponding to all the associated sensor data; wherein, the weight of each water quality prediction parameter is proportional to the location correlation degree of the corresponding associated sensor data.

7. A water quality monitoring system based on multi-source data, characterized in that, The system is used to perform the water quality monitoring method based on multi-source data as described in any one of claims 1-6, the system comprising: The acquisition module is used to acquire multiple types of monitoring sensor data for the target water area; The determination module is used to determine multiple pollution origin locations in the target water area based on the monitoring sensor data belonging to the first monitoring level; A filtering module is used to filter relevant sensor data belonging to the second monitoring level from all the monitoring sensor data based on the pollution origin location; The analysis module is used to analyze the water pollution status of the target water area based on the associated sensor data and the location of the pollution origin.

8. A water quality monitoring system based on multi-source data, characterized in that, The system includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the water quality monitoring method based on multi-source data as described in any one of claims 1-6.

Images