A water quality monitoring method and system based on Internet of Things technology

Abstract

The present application relates to the field of water quality monitoring technology, and in particular to a water quality monitoring method and system based on Internet of Things technology. The method comprises: obtaining multi-source water quality monitoring data of the monitoring area; analyzing the multi-source water quality monitoring data to determine whether there is a possibility of illegal sewage discharge; if so, obtaining the water pipe layout information and regional information of the monitoring area; analyzing the water pipe layout information to determine the water flow path association; based on the water flow path association, determining the pollution dissipation path information according to the multi-source water quality monitoring data; analyzing the regional information to determine the distribution characteristics of the plant area; determining the illegal sewage discharge point according to the water flow path association, the plant area distribution characteristics and the dissipation path information. Ensure the spatial consistency of the final positioning result with the physical pipe network layout, and eliminate false alarms caused by model errors.

Description

Technical Field

[0001] The present application relates to the field of water quality monitoring technology, and in particular to a water quality monitoring method and system based on Internet of Things technology. Background Art

[0002] With the rapid development of the Internet of Things (IoT), water quality monitoring has gradually transitioned from single-node monitoring to distributed intelligent monitoring networks. Traditional water quality monitoring systems rely on fixed-point data collection to establish pollutant identification systems by deploying fixed-point monitoring equipment at factory outlets or key nodes in municipal pipe networks.

[0003] However, existing technologies still have significant defects when dealing with complex urban sewage discharge scenarios. For example, under the working conditions of shared pipeline networks, traditional upstream and downstream comparative detection methods cannot achieve accurate tracing and rapid positioning of illegal sewage discharge behaviors. Summary of the Invention

[0004] This application provides a water quality monitoring method and system based on Internet of Things technology to solve the above problems.

[0005] In a first aspect, the present application provides a water quality monitoring method based on Internet of Things technology, the method comprising:

[0006] Obtaining multi-source water quality monitoring data in the monitoring area; analyzing the multi-source water quality monitoring data to determine whether there is a possibility of illegal discharge of pollutants;

[0007] If so, obtaining the water pipe layout information and regional information of the monitoring area; analyzing the water pipe layout information to determine the water flow path association;

[0008] Based on the water flow path association, determining pollution dissipation path information according to the multi-source water quality monitoring data;

[0009] Analyze the regional information to determine the distribution characteristics of the plant area;

[0010] Illegal sewage discharge points are determined based on the water flow path association, the plant area distribution characteristics and the dissipation path information.

[0011] Through this solution, multi-source water quality monitoring data in the monitoring area is obtained, eliminating the modeling error problem caused by inconsistent data time bases. Analyzing multi-source water quality monitoring data to determine whether there is a possibility of illegal sewage discharge helps avoid false triggering of a single parameter. If so, the water pipe layout information and regional information of the monitoring area are obtained, which helps eliminate the modeling defect of step changes in flow velocity caused by sudden changes in pipe diameter. Analyzing the water pipe layout information and determining the association of water flow paths helps improve the adaptability of complex pipe network topologies. Based on the association of water flow paths, according to multi-source water quality monitoring data, the pollution dissipation path information is determined, which helps to achieve spatial mapping of dissipation paths and concealed pipes. Analyzing regional information and determining the distribution characteristics of the plant area helps to improve the detection rate of concealed pipes. Based on the association of water flow paths, plant area distribution characteristics and dissipation path information, illegal sewage discharge points are determined to ensure the spatial consistency of the final positioning results with the physical pipe network layout, eliminating false alarms caused by model errors.

[0012] Optionally, analyzing the water pipe layout information to determine water flow path association includes:

[0013] Analyze the water pipe layout information to determine the water pipe intersection point, pipe diameter and layout slope;

[0014] Analyze the multi-source water quality monitoring data and determine the data sources;

[0015] Determine water quality monitoring points based on the data sources;

[0016] Analyze the multi-source water quality monitoring data and the real-time flow rate of each water quality monitoring point;

[0017] Constructing a dynamic weighted directed graph model according to the water pipe intersection, the pipe diameter, the layout slope and the real-time flow rate;

[0018] According to the dynamic weighted directed graph model, water flow path associations are determined.

[0019] Optionally, determining pollution dissipation path information based on the water flow path association and the multi-source water quality monitoring data includes:

[0020] Based on the water flow path association, a historical pollution-related data set is obtained; the historical pollution-related data set is analyzed to determine the historical pollution type, initial pollution concentration and dissipation time;

[0021] Establishing a pollution diffusion model according to the historical pollution type, the initial pollution concentration and the dissipation time;

[0022] Based on the pollution diffusion model and according to the multi-source water quality monitoring data, pollution dissipation path information is determined.

[0023] Optionally, analyzing the regional information to determine plant distribution characteristics includes:

[0024] Analyze the regional information and determine the factory coordinates;

[0025] Determining the physical distance between the water quality monitoring point and each plant area according to the plant area coordinates;

[0026] Based on the physical distance, a topological relationship matrix is ​​established between the water quality monitoring point and the factory coordinates;

[0027] The plant area distribution characteristics are determined according to the topological relationship matrix.

[0028] Optionally, determining illegal sewage discharge points according to the water flow path association, the plant area distribution characteristics, and the dissipation path information includes:

[0029] Based on the water flow path association and the pollution dissipation path information, a pollution source tracing probability graph model is constructed;

[0030] Determining the spatial correlation between each plant area and the pollution dissipation path according to the plant area distribution characteristics;

[0031] Obtaining plant area pollutant discharge permit information, and determining the plant area pollutant discharge probability based on the plant area pollutant discharge permit information and the spatial correlation;

[0032] The pollution discharge probability of the plant area is used as a priori probability and input into the pollution source tracing probability graph model to obtain an output result;

[0033] Calculating the output results through Bayesian reasoning to determine the posterior probability of each water quality monitoring point;

[0034] Comparing the posterior probability with a preset threshold value of each water quality monitoring point, and screening water quality monitoring points exceeding the preset threshold value as candidate illegal discharge points;

[0035] According to the water flow path association and the pollution dissipation path information, the candidate illegal discharge point is verified for path consistency. If the verification passes, the candidate illegal discharge point is determined to be an illegal discharge point.

[0036] Optionally, if the verification is successful, after determining that the candidate illegal pollution discharge point is an illegal pollution discharge point, the method further includes:

[0037] Obtain the factory building layout and municipal pipe network topology;

[0038] Analyze the municipal pipe network topology map and the plant building layout map to determine the public pipe network structure and the plant pipe network structure;

[0039] Determining the spatial position relationship between the factory area and the public pipe network according to the public pipe network structure and the factory area pipe network structure;

[0040] Determine potential concealed pipe laying paths based on the spatial position relationship;

[0041] Verify the possibility of the existence of the hidden pipe according to the change of the pollutant concentration gradient along the potential hidden pipe laying path according to the pollution dissipation path information;

[0042] Based on the possibility of the existence of the concealed pipe and according to the potential concealed pipe laying path, the concealed pipe drainage point is determined.

[0043] Optionally, determining a potential concealed pipe laying path according to the spatial position relationship includes:

[0044] Analyzing the public pipe network structure and determining public pipe network nodes;

[0045] Analyze the plant network structure and determine the spatial coordinates of the plant drainage facilities;

[0046] Calculate the Euclidean distance between each spatial coordinate and the nearest public pipe network node to obtain a distance set;

[0047] Obtaining plant area information, analyzing the plant area information, and determining the drainage needs of the plant area;

[0048] Constructing a path optimization function according to the distance set and the drainage demand of the plant area;

[0049] According to the path optimization function, the potential concealed pipe laying path is calculated.

[0050] Optionally, determining the sewage discharge point of the concealed pipe based on the possibility of the concealed pipe existence and according to the potential concealed pipe laying path includes:

[0051] Obtain and analyze historical cases of concealed pipe seizures to determine the path feature dataset;

[0052] Analyze the path feature data set to determine the path length, burial depth, and number of corners in each historical case of concealed pipe seizure;

[0053] Constructing a logistic regression model based on the path length, the burial depth, and the number of corner turns;

[0054] Inputting the possibility of the existence of the concealed pipe into the logistic regression model to determine whether there is at least one potential concealed pipe laying path with a confidence level higher than a confidence requirement;

[0055] If it exists, the potential concealed pipe laying path corresponding to the confidence level higher than the confidence requirement will be determined as the concealed pipe drainage point.

[0056] Optionally, the method further includes:

[0057] According to the plant coordinates, determine the coordinates of the pollution point and the administrative area to which the pollution discharge point belongs;

[0058] Determining the pollution diffusion range based on the pollution dissipation path information;

[0059] After the location of the pollution point is determined, early warning information is generated according to the coordinates of the pollution point and the pollution spread range;

[0060] According to the administrative area to which the pollution discharge point belongs, the warning information is routed to the corresponding supervision terminal, and the response timestamp of the supervision terminal is recorded to form a closed-loop management log.

[0061] In a second aspect, the present application provides a water quality monitoring system based on Internet of Things technology, the system comprising:

[0062] A data analysis module is used to obtain multi-source water quality monitoring data in the monitoring area; analyze the multi-source water quality monitoring data to determine whether there is a possibility of illegal discharge of pollutants;

[0063] An information analysis module, configured to obtain water pipe layout information and regional information of the monitoring area, if any; analyze the water pipe layout information to determine water flow path association;

[0064] a dissipation analysis module, configured to determine pollution dissipation path information based on the water flow path association and the multi-source water quality monitoring data;

[0065] A feature determination module, configured to analyze the regional information and determine the distribution features of the plant area;

[0066] The sewage discharge determination module is used to determine illegal sewage discharge points based on the water flow path association, the plant area distribution characteristics and the dissipation path information.

[0067] Optionally, when the information analysis module analyzes the water pipe layout information and determines the water flow path association, it is used to: analyze the water pipe layout information to determine the water pipe intersection point, pipe diameter and layout slope; parse the multi-source water quality monitoring data to determine the data source; determine the water quality monitoring point based on the data source; analyze the multi-source water quality monitoring data and the real-time flow rate of each water quality monitoring point; construct a dynamic weighted directed graph model based on the water pipe intersection point, the pipe diameter, the layout slope and the real-time flow rate; and determine the water flow path association based on the dynamic weighted directed graph model.

[0068] Optionally, when the dissipation analysis module determines the pollution dissipation path information based on the water flow path association and the multi-source water quality monitoring data, it is used to: obtain a historical related pollution data set based on the water flow path association; parse the historical related pollution data set to determine the historical pollution type, initial pollution concentration and dissipation time; establish a pollution diffusion model based on the historical pollution type, the initial pollution concentration and the dissipation time; and determine the pollution dissipation path information based on the pollution diffusion model and the multi-source water quality monitoring data.

[0069] Optionally, when the feature determination module analyzes the regional information and determines the plant area distribution characteristics, it is used to: analyze the regional information to determine the plant area coordinates; determine the physical distance between the water quality monitoring point and each plant area based on the plant area coordinates; establish a topological relationship matrix between the water quality monitoring point and the plant area coordinates based on the physical distance; and determine the plant area distribution characteristics based on the topological relationship matrix.

[0070] Optionally, when the pollution discharge determination module determines an illegal pollution discharge point based on the water flow path association, the plant area distribution characteristics and the dissipation path information, it is used to: construct a pollution source tracing probability graph model based on the water flow path association and the pollution dissipation path information; determine the spatial correlation between each plant area and the pollution dissipation path based on the plant area distribution characteristics; obtain the plant area pollution discharge permit information, and determine the plant area pollution discharge probability based on the plant area pollution discharge permit information and the spatial correlation; input the plant area pollution discharge probability as a priori probability into the pollution source tracing probability graph model to obtain an output result; calculate the output result through Bayesian reasoning to determine the posterior probability of each water quality monitoring point; compare the posterior probability with the preset threshold of each water quality monitoring point, and screen the water quality monitoring points that exceed the preset threshold as candidate illegal pollution discharge points; perform path consistency verification on the candidate illegal pollution discharge points based on the water flow path association and the pollution dissipation path information, and if the verification passes, determine the candidate illegal pollution discharge point as an illegal pollution discharge point.

[0071] Optionally, the water quality monitoring system based on Internet of Things technology also includes a concealed pipe determination module, which is used to: obtain a plant building layout map and a municipal pipe network topology map; analyze the municipal pipe network topology map and the plant building layout map to determine the public pipe network structure and the plant pipe network structure; determine the spatial position relationship between the plant and the public pipe network based on the public pipe network structure and the plant pipe network structure; determine the potential concealed pipe laying path based on the spatial position relationship; verify the possibility of the existence of concealed pipes based on the change in pollutant concentration gradient on the potential concealed pipe laying path according to the pollution dissipation path information; based on the possibility of the existence of concealed pipes, determine the concealed pipe discharge point according to the potential concealed pipe laying path.

[0072] Optionally, when the concealed pipe determination module determines the potential concealed pipe laying path based on the spatial position relationship, it is used to: parse the public pipe network structure to determine the public pipe network nodes; parse the plant area pipe network structure to determine the spatial coordinates of the plant area drainage facilities; calculate the Euclidean distance between each spatial coordinate and the nearest public pipe network node to obtain a distance set; obtain plant area information, analyze the plant area information, and determine the plant area drainage demand; construct a path optimization function based on the distance set and the plant area drainage demand; and calculate the potential concealed pipe laying path based on the path optimization function.

[0073] Optionally, when determining the concealed pipe drainage point based on the possibility of the concealed pipe existence and the potential concealed pipe laying path, the concealed pipe determination module is used to: obtain historical cases of concealed pipe seizure, analyze the historical cases of concealed pipe seizure, and determine a path feature data set; parse the path feature data set to determine the path length, burial depth, and number of turns in each historical case of concealed pipe seizure; construct a logistic regression model based on the path length, the burial depth, and the number of turns; input the possibility of the concealed pipe existence into the logistic regression model to determine whether there is at least one potential concealed pipe laying path whose confidence level is higher than the confidence requirement; if so, determine the potential concealed pipe laying path corresponding to the confidence level higher than the confidence requirement as a concealed pipe drainage point.

[0074] Optionally, the water quality monitoring system based on Internet of Things technology also includes a log formation module, which is used to: determine the coordinates of the pollution point and the administrative area to which the discharge point belongs based on the plant coordinates; determine the pollution diffusion range based on the pollution dissipation path information; after the location of the discharge point is determined, generate early warning information based on the coordinates of the pollution point and the pollution diffusion range; route the early warning information to the corresponding supervision terminal based on the administrative area to which the discharge point belongs, and record the response timestamp of the supervision terminal to form a closed-loop management log. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0076] Figure 1 A schematic diagram of an application scenario provided in one embodiment of the present application;

[0077] Figure 2 A flow chart of a water quality monitoring method based on Internet of Things technology provided in one embodiment of the present application;

[0078] Figure 3A schematic diagram of the structure of a water quality monitoring system based on Internet of Things technology is provided in one embodiment of the present application. DETAILED DESCRIPTION

[0079] To make the purpose, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0080] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document, unless otherwise specified, generally indicates an "or" relationship between the related objects.

[0081] The embodiments of the present application are described in further detail below with reference to the accompanying drawings.

[0082] Existing technologies still have significant defects when dealing with complex urban sewage discharge scenarios. For example, under the working conditions of shared pipeline networks, traditional upstream and downstream comparative detection methods cannot achieve accurate tracing and rapid positioning of illegal sewage discharge behaviors.

[0083] Based on this, the present application provides a water quality monitoring method and system based on Internet of Things technology, which obtains multi-source water quality monitoring data in the monitoring area and eliminates the modeling error problem caused by inconsistent data time bases. Analyzing multi-source water quality monitoring data to determine whether there is a possibility of illegal sewage discharge helps to avoid false triggering of a single parameter. If so, obtaining the water pipe layout information and regional information of the monitoring area helps to eliminate the modeling defect of step changes in flow velocity caused by sudden changes in pipe diameter. Analyzing the water pipe layout information and determining the water flow path association helps to improve the adaptability of complex pipe network topology. Based on the water flow path association, according to the multi-source water quality monitoring data, the pollution dissipation path information is determined, which helps to achieve spatial mapping of the dissipation path and the concealed pipe. Analyzing regional information and determining the distribution characteristics of the plant area helps to improve the detection rate of concealed pipes. According to the water flow path association, the plant area distribution characteristics and the dissipation path information, the illegal sewage discharge points are determined to ensure the spatial consistency of the final positioning result with the physical pipe network layout, and eliminate false alarms caused by model errors.

[0084] Figure 1 This is a schematic diagram of an application scenario provided by this application. When conducting water quality monitoring, the method provided by this application is applied.

[0085] Specifically, the method provided by the present application is applied to any server, and the server interacts with the sensor group to obtain multi-source water quality monitoring data of the monitoring area through the sensor group, analyze the multi-source water quality monitoring data, and determine whether there is a possibility of illegal sewage discharge. If so, the water pipe layout information and regional information of the monitoring area are obtained, the water pipe layout information is analyzed, and the water flow path association is determined. Based on the water flow path association, according to the multi-source water quality monitoring data, the pollution dissipation path information is determined to achieve spatial mapping of the dissipation path and the concealed pipe. The regional information is analyzed to determine the distribution characteristics of the plant area and improve the detection rate of concealed pipes. According to the water flow path association, the plant area distribution characteristics and the dissipation path information, the illegal sewage discharge points are determined to ensure the spatial consistency of the final positioning result with the physical pipe network layout, and eliminate false alarms caused by model errors.

[0086] For specific implementation methods, please refer to the following embodiments.

[0087] Figure 2 This is a flow chart of a water quality monitoring method based on Internet of Things technology provided in one embodiment of this application. The method of this embodiment can be applied to the server in the above scenario. Figure 2 As shown, the method includes:

[0088] S201. Obtain multi-source water quality monitoring data in the monitoring area; analyze the multi-source water quality monitoring data to determine whether there is a possibility of illegal discharge of pollutants;

[0089] The monitoring area can be a continuous spatial range that includes factory discharge outlets, public pipeline nodes, and natural water body monitoring points.

[0090] Multi-source water quality monitoring data can be a heterogeneous data set of three types of sensor groups.

[0091] Illegal discharge of pollutants may be an event of abnormal pollutant concentration.

[0092] Specifically, three types of sensor groups are deployed within the monitoring area: plant discharge outlet sensor groups, public pipe network monitoring nodes, and natural water body monitoring points. Multi-source water quality monitoring data from each group is then received through an IoT gateway. A moving baseline is established for each monitoring point. When real-time data deviates too much from the baseline, a primary alarm is triggered. Based on the law of conservation of fluid matter, a preset proportional relationship between the rate of change of conductivity and the rate of change of flow is established. Furthermore, multi-parameter correlation analysis is performed. When the direction of change of the plant discharge outlet sensor group and conductivity deviates from the preset proportional relationship, a secondary alarm is generated. Subsequently, based on the classification and regression tree algorithm in statistical learning theory, a decision tree model is trained and generated from a historical pollution event database using the principle of minimizing the Gini index. Finally, based on the composite conditions of turbidity and flow rate at the three types of monitoring points, the possibility of illegal discharge of pollutants is determined.

[0093] Among them, the first type of sensor group is deployed at the factory discharge outlet, including COD online analyzers, electromagnetic flow meters and explosion-proof pH meters; the second type of sensor group is deployed at the public pipeline monitoring nodes, equipped with Doppler flow meters, pressure transmitters and temperature-compensated conductivity sensors; the third type of sensor group is deployed at the natural water body monitoring points, using solar-powered turbidity sensors, dissolved oxygen probes and ammonia nitrogen analysis modules.

[0094] S202. If so, obtain water pipe layout information and regional information of the monitoring area; analyze the water pipe layout information to determine the water flow path association;

[0095] The water pipe layout information may be a public pipe network topology structure represented by a weighted directed graph.

[0096] The regional information can be a structured data set covering the geographical coordinate boundaries of the plant area, the declared drainage volume, and the location of the pipe network access points.

[0097] The water flow path association can be a collection of the main pollutant diffusion path and branch paths.

[0098] Specifically, if illegal discharge is suspected, the monitoring area's pipeline network vector data is imported from the municipal GIS via the OGC WFS service interface and converted into water pipe layout information. Next, a set of plant boundary coordinate points is extracted from the plant's CAD drawings. This set of coordinate points represents discrete location data of the plant's geographic outline, typically expressed in a two-dimensional or three-dimensional coordinate system. Based on these boundary coordinate points, a minimum bounding rectangle is calculated: one that completely encloses all boundary coordinate points and minimizes their area. The initial rectangle's boundaries are parallel to the coordinate axes, and the rectangle's orientation and size are iteratively adjusted to optimize inclusion, ensuring that the rectangle's vertices are defined by extreme points within the plant's boundary coordinates. Furthermore, using the plant's minimum bounding rectangle's center point as the starting point and each vertex in the pipeline network vertex set as the target location for calculation, the shortest feasible path (accumulated distance) is found among the physical paths connecting the starting point to each target location based on the network's physical topology. The accumulated distance is the desired shortest path distance. This establishes a plant-monitoring point association matrix, determining regional information. The specific method for establishing a plant-monitoring point association matrix involves creating a matrix data structure with rows representing plant sites (uniquely identified by the center point of their minimum enclosing rectangle) and columns representing pipe network vertices (specifically, the locations of water quality monitoring points). Each element in the matrix stores the shortest path distance from the corresponding plant site center point to that pipe network vertex (monitoring point). This matrix quantifies the connectivity distance, or strength of spatial association, between the plant site and each monitoring point in the pipe network topological space. The coordinates of the center point of the plant site's minimum enclosing rectangle are spatially matched with the set of pipe network vertices in the water pipe layout information to determine the water flow path association.

[0099] S203, based on the water flow path association and multi-source water quality monitoring data, determine the pollution dissipation path information;

[0100] Pollution dissipation path information can be the spatiotemporal migration trajectory of pollutants in the pipeline network.

[0101] Specifically, the dissipation coefficient, water flow velocity, and pipe curvature are obtained through training with field measured data to establish a pollutant concentration attenuation model; then, the moving time window algorithm is used to dynamically update the pollutant characteristic index; then, based on the Gaussian process regression algorithm, the moment when the pollution peak occurs is used as the starting point, and reverse diffusion simulation is performed in combination with the real-time water flow velocity field to generate pollution dissipation path information with an excessively high probability density.

[0102] S204, analyzing regional information to determine plant distribution characteristics;

[0103] The plant area distribution characteristics can be a topological matrix that quantitatively represents the spatial relationship between each plant area and the monitoring points.

[0104] Specifically, a multidimensional matrix is ​​constructed based on the number of plant areas and the number of monitoring nodes. Furthermore, by calculating the inverse of the product of the shortest water flow path length and the pipe diameter between the plant area and the monitoring node, the matrix elements representing the pipe network path connectivity between each plant area and each monitoring node are obtained. Subsequently, the center point coordinates of the minimum enclosing rectangle of the plant area generated in the previous step are used as the reference position for spatial analysis. The pollutant diffusion trajectory calculated based on water flow path association and multi-source water quality monitoring data is expressed as a continuous spatial path or a discrete high-probability point set in the pipe network. The boundary coordinates of the monitoring area are defined as the reference range for density calculation. With the coordinates of the center point of each plant area as the core position, a spatial influence function is defined. This function describes the attenuation law of the influence of the plant area on its surrounding space. It is usually expressed as a distribution form with the plant area center as the origin and smoothly attenuating with increasing distance. Within the monitoring area, for each spatial position (or discrete path point) covered by the pollution dissipation path, the superimposed spatial influence intensity value of all plant area center points is calculated. This intensity value reflects the comprehensive spatial proximity of the location to all plant areas. The spatial impact intensity values ​​covering the entire monitoring area are standardized and mapped to a geographic spatial grid to form a continuous spatial density distribution surface. This density distribution surface is visualized to generate a heat map. The darker (or warmer) the area in the heat map, the higher the comprehensive spatial correlation between the location and all plant areas, that is, the higher the potential spatial overlap with the pollution dissipation path. The generated heat map is overlaid with the spatial range of the pollution dissipation path for analysis, and the spatial density value corresponding to the location of each plant area center point in the heat map is calculated, and a spatial density threshold is set. Plant areas with spatial density values ​​exceeding the threshold are marked as suspicious objects, and plant areas with excessively high overlapping areas are screened as suspicious objects, thereby determining the distribution characteristics of the plant areas.

[0105] S205. Identify illegal discharge points based on water flow path association, plant area distribution characteristics, and dissipation path information.

[0106] The illegal discharge point may be the geographical coordinate point of the illegal discharge.

[0107] Specifically, a scoring system is constructed that includes water flow path associations, plant distribution characteristics, and dissipation path information; then, the threshold is determined based on the lower limit of the statistical confidence interval in the USEPA multi-source traceability study and the risk acceptance level parameters specified in the "Technical Guidelines for Risk Assessment of Contaminated Land"; finally, when the comprehensive score of the plant exceeds the threshold and there is a positive hidden pipe test, it is determined to be an illegal discharge point.

[0108] Through this solution, multi-source water quality monitoring data in the monitoring area is obtained, eliminating the modeling error problem caused by inconsistent data time bases. Analyzing multi-source water quality monitoring data to determine whether there is a possibility of illegal sewage discharge helps avoid false triggering of a single parameter. If so, the water pipe layout information and regional information of the monitoring area are obtained, which helps eliminate the modeling defect of step changes in flow velocity caused by sudden changes in pipe diameter. Analyzing the water pipe layout information and determining the association of water flow paths helps improve the adaptability of complex pipe network topologies. Based on the association of water flow paths, according to multi-source water quality monitoring data, the pollution dissipation path information is determined, which helps to achieve spatial mapping of dissipation paths and concealed pipes. Analyzing regional information and determining the distribution characteristics of the plant area helps to improve the detection rate of concealed pipes. Based on the association of water flow paths, plant area distribution characteristics and dissipation path information, illegal sewage discharge points are determined to ensure the spatial consistency of the final positioning results with the physical pipe network layout, eliminating false alarms caused by model errors.

[0109] In some embodiments, water pipe layout information is analyzed to determine the water pipe intersection point, pipe diameter and layout slope; multi-source water quality monitoring data is parsed to determine the data source; water quality monitoring points are determined based on the data source; multi-source water quality monitoring data is analyzed to determine the real-time flow rate of each water quality monitoring point; a dynamic weighted directed graph model is constructed based on the water pipe intersection point, pipe diameter, layout slope and real-time flow rate; and water flow path association is determined based on the dynamic weighted directed graph model.

[0110] The pipe junction can be the coordinates of the physical connection location of different sewage pipes.

[0111] The pipe diameter may be a measured physical parameter of the inner diameter of the sewage pipe.

[0112] The laying slope can be the inclination angle formed by the pipeline when it is laid with the horizontal plane.

[0113] The data source can be the category of equipment that generates multi-source water quality monitoring data.

[0114] Water quality monitoring points can be specific physical locations where water quality sensors are deployed.

[0115] The real-time flow rate can be the instantaneous movement rate of the water flow.

[0116] The dynamic weighted directed graph model can be a mathematical model for characterizing the diffusion path of pollutants.

[0117] Specifically, water pipe clustering information is extracted from GIS data to identify the coordinate sets of several water pipe intersections. The pipeline attribute database is then parsed to obtain the pipe diameter and slope of each pipe segment. Water quality monitoring data from multiple sources is received, including outfall sensor groups, public pipe network monitoring nodes, and natural water body monitoring points. The device ID, geographic coordinates, and deployment level information are extracted from the data packet header metadata. The data source is then determined by matching the device ID with a pre-set monitoring point registry. Based on the data source, a set of monitoring point spatial locations is constructed using the latitude and longitude coordinates associated with the device ID. Water quality monitoring points are then selected based on spatial coverage density requirements. Raw data from the flow velocity sensor at each water quality monitoring point is then extracted and filtered using a sliding window filter. The filtered baseline flow velocity values ​​are then compared with environmental parameters to calculate fluid dynamics. Based on the nonlinear effects of pipe wall friction, a slope-to-gravity compensation factor is introduced to dynamically adapt to flow regime changes caused by pipe diameter changes, outputting the actual flow velocity value. Furthermore, the water pipe intersection points and water quality monitoring points are taken as graph nodes, and adjacent nodes are connected along the water flow direction to form a directed edge set; the basic weight is determined according to the inverse of the pipe diameter and the layout slope; then, the benchmark flow velocity is determined based on the median of the historical flow velocity of the water pipe section; then, the dynamic correction factor is generated by the ratio of the real-time flow velocity to the benchmark flow velocity; then, a dynamic weight directed graph model is constructed through the basic weight and the dynamic correction factor. Finally, based on the dynamic weighted directed graph model, the starting monitoring point is set as the current node, and its cumulative resistance value is 0, and the cumulative resistance values ​​of other nodes are set to infinity; the loop is executed, and all downstream adjacent nodes of the current node are extracted according to the water flow direction. The resistance increment from the current node to the adjacent node is calculated by the basic weight, dynamic correction factor and pipe length. If the current node cumulative resistance + resistance increment < the existing cumulative resistance of the adjacent node, the cumulative resistance value of the adjacent node is updated, and the current node is recorded as the optimal predecessor node, and the current node is marked as optimized. The node with the smallest cumulative resistance is selected from the unoptimized nodes as the new current node. When all water quality monitoring points are completed, the loop is marked as the end; the minimum resistance path between any two water quality monitoring points is calculated in this way; the output path sequence includes the water pipe intersection number, water pipe section diameter and slope parameters passed through, forming a water flow path association.

[0118] Through this solution, water pipe layout information is analyzed to determine the water pipe intersection point, pipe diameter and layout slope, which helps to overcome the impact of ignoring pipe diameter mutation on flow velocity step change. Analyzing multi-source water quality monitoring data and determining the data source helps to eliminate the problem of missing quantification of spatial distribution characteristics. According to the data source, water quality monitoring points are determined to block loopholes for concealed pipes to bypass monitoring points, strengthen the spatial constraints on illegal pollution discharge, and increase the probability of capturing abnormal diffusion paths. Analyzing multi-source water quality monitoring data and the real-time flow velocity of each water quality monitoring point helps to eliminate the problem of inaccurate water flow model in areas with pipe diameter mutation. Based on the water pipe intersection point, pipe diameter, layout slope and real-time flow velocity, a dynamic weighted directed graph model is constructed to quantify the probability of pollutant transmission path selection, replacing the fixed parameter assumption of the linear model. Based on the dynamic weighted directed graph model, the water flow path association is determined, the rate of false connectivity judgment is reduced, and a spatial mapping basis is provided for concealed pipe detection.

[0119] In some embodiments, based on the association of water flow paths, a historical pollution-related data set is obtained; the historical pollution-related data set is analyzed to determine the historical pollution type, initial pollution concentration and dissipation time; a pollution diffusion model is established based on the historical pollution type, initial pollution concentration and dissipation time; based on the pollution diffusion model, pollution dissipation path information is determined based on multi-source water quality monitoring data.

[0120] The historical pollution-related dataset can be a set of historical pollution event data that has spatial correlation with the currently monitored water flow path.

[0121] The historical pollution type may be a category of historical pollution events.

[0122] The initial pollution concentration may be the actual measured value of the pollutant concentration when the pollution event is first detected by the sensor group.

[0123] Dissipation time can be the length of time it takes for the pollutant concentration to drop to its initial concentration.

[0124] The pollution diffusion model is a partial differential equation model that can describe the spatial attenuation law of pollutants along the pipeline network path.

[0125] Specifically, the intersection number, pipe diameter, and layout slope of each water pipe are extracted from the output path sequence of the dynamic weighted directed graph model to form a structured water flow path association table. Then, multi-source water quality monitoring data are associated according to the time dimension, and the COD, BOD, and NH3-N concentration data packets that match the monitoring point numbers in the water flow path association table are extracted to construct a spatiotemporally aligned historical pollution dataset. Furthermore, based on the historical pollution data set, K-means cluster analysis is performed on the COD and BOD concentration ratios to generate historical pollution types; subsequently, the concentration mutation point of each pollution event is located in the historical pollution data set, the multi-parameter monitoring sequence of the historical pollution events is aligned according to the time dimension, noise filtering is performed on the original data, and a time-concentration normalization curve is generated; a forward sliding analysis window is set on the pollution event time axis, and the window length is set based on the event duration. The concentration gradient change rate and fluctuation significance within the window are calculated in real time. When the gradient change rate > preset mutation threshold, fluctuation significance > 3 times the standard deviation of the historical fluctuation range, and duration ≥ the minimum effective mutation window are simultaneously satisfied, the concentration value corresponding to the center point of the first time window that meets the mutation conditions is taken and output as the initial concentration of the pollution event. At this time, the corresponding timestamp and position coordinates should also be output for subsequent use; further, the concentration drops to the initial concentration as the termination condition, combined with the pipe section flow rate in the water flow path association table, the dissipation time is calculated according to the exponential decay model. Then, the preset dissipation coefficient is called based on the historical pollution type. The initial pollution concentration is then used as the model's initial value and loaded into the grid cell of the pipe section where the pollution source is located. Based on the pipe diameter and slope in the water flow path association table, the following inherent physical properties of the pipe section (pipe diameter, laying slope, and pipe wall roughness) are extracted from the water flow path association table. By converting the slope value into a gravitational potential energy gradient, the water flow section characteristic parameters are calculated based on the pipe diameter, and the baseline flow velocity is calculated based on the pipeline fluid motion state. The dissipation coefficient is corrected based on the real-time water temperature and dissipation time, thereby constructing a pollution diffusion model. Multi-source water quality monitoring data is input into the pollution diffusion model, and parameters are updated based on plant discharge outlet data, public pipeline network node data, and natural water body monitoring point data. The residuals of the model's predicted concentration distribution and the actual monitoring data are then compared. If the residual exceeds the limit, the real-time flow velocity weight factor in the dynamic weighted directed graph model is adjusted inversely to determine the final pollution dissipation path information.

[0126] Through this solution, based on the association of water flow paths, historical pollution data sets are obtained, cross-regional data interference is eliminated, and training samples matching regional characteristics are provided for model construction. Historical pollution data sets are analyzed to determine the historical pollution type, initial pollution concentration and dissipation time, eliminating the problem that the threshold alarm mechanism cannot distinguish between legal and illegal pollution discharge, improving the efficiency of investigation and reducing the prediction error of dissipation time. According to the historical pollution type, initial pollution concentration and dissipation time, a pollution diffusion model is established to quantify the non-standard characteristics of the hidden pipe discharge path and improve the recognition coverage of the hidden pipe path. Based on the pollution diffusion model and multi-source water quality monitoring data, the pollution dissipation path information is determined to provide a traceable diffusion path evidence chain to support the missing illegal pollution discharge forensic needs.

[0127] In some embodiments, regional information is analyzed to determine the plant coordinates; based on the plant coordinates, the physical distance between the water quality monitoring point and each plant is determined; based on the physical distance, a topological relationship matrix between the water quality monitoring point and the plant coordinates is established; and based on the topological relationship matrix, the plant distribution characteristics are determined.

[0128] The plant coordinates can be the longitude and latitude values ​​of the geographical location of the pollutant-discharging unit.

[0129] A plant site may be a contiguous geographic area occupied by an industrial or commercial entity with a separate discharge permit.

[0130] The physical distance can be the straight-line Euclidean distance between the water quality monitoring point and the factory area.

[0131] The topological relationship matrix can be a two-dimensional data structure used to characterize the strength of spatial association.

[0132] Specifically, based on regional information, the coordinates of the plant areas within the target area are retrieved from the municipal pollutant discharge permit database. Then, based on the plant area coordinates, the planar Euclidean distance formula is used to calculate the physical distance between each water quality monitoring point and each plant area. Furthermore, based on the physical distance, a two-dimensional matrix is ​​constructed according to the total number of monitoring points and the number of valid plant areas; the inverse distance weighted method is used to quantify the spatial correlation strength to determine the matrix elements; then, Softmax normalization is performed on each matrix element; thereby establishing the final topological relationship matrix between the water quality monitoring points and the plant area coordinates. Then, DBSCAN clustering is performed based on the topological relationship matrix to determine the boundary polygons of the plant area clusters; finally, based on the number of plant areas and the cluster area, the spatial density is calculated to determine the distribution characteristics of the plant areas.

[0133] This solution analyzes regional information, determines plant coordinates, and eliminates spatial misalignment between plant coordinates and the pipeline network topology. Based on plant coordinates, the physical distance between water quality monitoring points and each plant is determined, revealing their spatial proximity. Based on physical distance, a topological relationship matrix is ​​established between water quality monitoring points and plant coordinates, quantifying the downstream association between plant areas and water quality monitoring points and improving the accuracy of identifying abnormal paths. The topological relationship matrix also identifies plant distribution characteristics, helping to indicate the presence of non-standard pipelines bypassing monitoring points.

[0134] In some embodiments, a pollution source tracing probability graph model is constructed based on water flow path association and pollution dissipation path information; the spatial correlation between each plant area and the pollution dissipation path is determined according to the plant area distribution characteristics; the plant area discharge permit information is obtained, and the plant area discharge probability is determined according to the plant area discharge permit information and the spatial correlation; the plant area discharge probability is used as a priori probability and input into the pollution source tracing probability graph model to obtain an output result; the output result is calculated through Bayesian reasoning to determine the posterior probability of each water quality monitoring point; the posterior probability is compared with the preset threshold of each water quality monitoring point, and the water quality monitoring points that exceed the preset threshold are screened as candidate illegal discharge points; the candidate illegal discharge points are verified for path consistency according to the water flow path association and pollution dissipation path information. If the verification passes, the candidate illegal discharge point is determined to be an illegal discharge point.

[0135] The pollution source tracing probability graph model can be a directed graph structure used to quantify the probability distribution of pollution diffusion paths. The pollution dissipation path can be the dynamic trajectory information of pollutants migrating through the pipeline network. The spatial correlation can be the spatial proximity and topological correlation strength between the plant's geographical location and the pollution dissipation path. The plant's pollutant discharge permit information can be the plant's legal pollutant discharge qualification data. The plant's pollutant discharge probability can be a priori probability value generated by comprehensively evaluating the spatial correlation and pollutant discharge permit information. The priori probability can be a pre-set initial probability distribution. The output result can be the intermediate state data generated by the pollution source tracing probability graph model after calculation using a Bayesian network. Bayesian reasoning can be a statistical inference method based on conditional probability and prior probability. The posterior probability can be the updated probability value of each water quality monitoring point being determined to be an illegal discharge associated node. The preset threshold can be a pre-set dynamic judgment boundary value. Candidate illegal discharge points can be a set of water quality monitoring points whose posterior probability exceeds the preset threshold.

[0136] Verification passed can be the final confirmation status that the pipe section where the candidate point is located meets the concealed pipe feature judgment conditions.

[0137] Specifically, based on the association of water flow paths and pollution dissipation paths, each water quality monitoring point is treated as an independent node, and the weight of the directed edge is determined by the product of the water flow transmission time difference and the pollutant concentration gradient between the upstream and downstream monitoring points. Furthermore, a pollution source tracing probability graph model is constructed based on the independent nodes and the directed edge weights. The specific method for establishing the pollution source tracing probability graph model is as follows: the water quality monitoring points are set as pollution diffusion observation nodes; the plant coordinate points are set as potential pollution source nodes, and the weight of the directed edge is determined based on the water flow transmission time and the pollutant concentration gradient. Based on the distribution characteristics of the plant areas, the column vector of the target plant area in the topological relationship matrix is ​​extracted and the cosine similarity is calculated with the diffusion direction vector of the pollution dissipation path. Then, the spatial correlation between each plant area and the pollution dissipation path is calculated according to the formula based on the radial distance from the plant area to the center point of the path. The permitted emission amount and pollutant type list of each plant area are extracted from the pollution discharge permit information in the environmental regulatory department database. Furthermore, based on the plant area pollution discharge permit information and spatial correlation, a probability mapping function is established to determine the probability of plant area pollution discharge. Subsequently, the pollution discharge probability of the plant area is normalized and loaded into the corresponding node of the pollution source tracing probability graph model as a priori probability distribution. Then, the real-time data of the water quality monitoring points are converted into pollution diffusion matching parameters as the observation variables of the Bayesian network; then, the matching degree between the observation data of each monitoring point and the pollution diffusion path is calculated through Bayesian reasoning, and the posterior probability is output; the specific process is to align the observation data of the monitoring point with the pollution tracing probability graph model on the time axis and spatial grid based on the prior probability, the observation data of each monitoring point, and the pollution tracing probability graph model, and then construct a linear weighted pollution diffusion path conformity evaluation function through the concentration gradient consistency, flow velocity change synchronization rate, and pollutant attenuation consistency; the concentration gradient consistency extracts the pollutant concentration sequence of the target water quality monitoring point and its upstream adjacent monitoring points in the continuous time window from the multi-source water quality monitoring data, calculates the concentration gradient at each time point, and then aligns the measured gradient sequence with the predicted gradient sequence of the corresponding path in the pollution tracing probability graph model. The covariance of the measured gradient sequence and the predicted gradient sequence is divided by the product of the two standard deviations to obtain the correlation coefficient value. The value range is between -1 and 1, and the closer to 1, the higher the degree of fit. The flow rate change synchronization rate is based on multi-source water quality monitoring data. The real-time flow rate sequence of the target monitoring point and the associated pipe sections is obtained. At the same time, the pollutant concentration change rate sequence is extracted, and the similarity between the flow rate change sequence and the concentration change rate sequence is calculated through the dynamic time warping algorithm: the two sequences are stretched or compressed on the time axis to minimize the cumulative distance. The inverse of the minimum cumulative distance is normalized and used as the synchronization rate value, ranging from 0 to 1. The higher the value, the stronger the synchronization.Pollutant attenuation consistency selects the pollutant concentration attenuation curve from the multi-source water quality monitoring data, uses the measured data of the fitted attenuation to obtain the measured attenuation coefficient, obtains the predicted attenuation coefficient of the corresponding path from the pollution diffusion model, divides the absolute difference between the measured attenuation coefficient and the predicted attenuation coefficient by the predicted attenuation coefficient, and then subtracts the relative error from 1 to obtain the consistency score, which ranges from 0 to 1. The higher the value, the better the consistency. The probability of plant discharge is assigned to the associated monitoring points as the initial weight, and then the posterior probability is calculated using the product of the prior probability, the matching score, and the pipe network connectivity reliability coefficient. Subsequently, the posterior probability is compared with the preset threshold value of each corresponding water quality monitoring point. When the posterior probability value of a water quality monitoring point exceeds the preset threshold value of the area where it is located, the water quality monitoring point that exceeds the preset threshold value will be marked as a candidate illegal discharge point. Then, based on the spatiotemporal coupling relationship between the water flow path association and the pollution dissipation path information, the path consistency of the candidate illegal discharge points is verified to determine the illegal discharge points; first, the proportion of the overlapping length between the pipe section where the candidate illegal discharge point is located and the center line of the pollution dissipation path is calculated; secondly, the coordinate sets of several plant areas upstream of the candidate illegal discharge point are extracted to verify the angle between the pollution diffusion direction and the water flow direction of the pipeline network; then, the fit of the measured pollutant concentration attenuation curve of the candidate illegal discharge point and the model prediction curve is compared; finally, based on the proportion of overlapping length, angle and fit, the candidate illegal discharge point is determined to be an illegal discharge point.

[0138] This solution constructs a pollution source tracing probability graph model based on information about water flow path associations and pollution dissipation paths, helping to eliminate the problem of inconsistent spatiotemporal benchmarks across multi-source data. Based on the distribution characteristics of plant sites, the spatial correlation between each plant site and the pollution dissipation path is determined, enhancing the sensitivity of detecting hidden pipe detours. Plant site discharge permit information is obtained, and the probability of plant site discharge is determined based on this information and spatial correlation, avoiding probability distortion caused by inconsistent multi-source data benchmarks. The plant site discharge probability is used as a priori probability and input into the pollution source tracing probability graph model to generate an output, achieving spatiotemporal alignment of pollutant diffusion paths with monitoring data. Bayesian inference is used to calculate the output results and determine the posterior probability for each water quality monitoring point, avoiding probability fluctuations caused by pipe network loops. The posterior probability is compared with a preset threshold for each water quality monitoring point, and water quality monitoring points exceeding the preset threshold are selected as candidate illegal discharge points, helping to eliminate the problem of missed / false positives caused by fixed thresholds. Based on the water flow path association and pollution dissipation path information, the path consistency of the candidate illegal discharge point is verified. If the verification passes, the candidate illegal discharge point is determined to be an illegal discharge point, eliminating the misjudgment caused by pipe network backflow.

[0139] In some embodiments, a plant building layout map and a municipal pipe network topology map are obtained; the municipal pipe network topology map and the plant building layout map are analyzed to determine the public pipe network structure and the plant pipe network structure; based on the public pipe network structure and the plant pipe network structure, the spatial position relationship between the plant and the public pipe network is determined; based on the spatial position relationship, the potential concealed pipe laying path is determined; based on the pollution dissipation path information and the change in pollutant concentration gradient on the potential concealed pipe laying path, the possibility of the existence of the concealed pipe is verified; based on the possibility of the existence of the concealed pipe, the concealed pipe discharge point is determined according to the potential concealed pipe laying path.

[0140] A plant building layout map can be a vector drawing containing the coordinates of several buildings within the industrial plant, as well as the locations and elevation information of internal pipe network interfaces. A municipal pipe network topology map can be a digital map depicting the spatial connectivity of various pipe segments within the city's public drainage network. A public pipe network structure can be a network entity consisting of several pipe segments and their connecting nodes. A plant pipe network structure can be the physical configuration of the drainage pipes within the plant. A public pipe network can be data on the city's public drainage pipes. Spatial location relationships can be relative distances and orientations. Potential concealed pipe laying paths can be illegal underground connections between the plant and the public pipe network. Pollutant concentration gradient changes can be the rate of concentration change per unit distance along the pipeline's extension. The likelihood of concealed pipes can be a probability value quantified by the deviation between the measured gradient and the theoretical gradient. Concealed pipe discharge points can be locations of illegal discharge connections identified through a path tracing algorithm.

[0141] Specifically, the plant building layout map and municipal pipe network topology map of the target area are retrieved from the database of the environmental supervision department. Then, based on the municipal pipe network topology map, the direction of the main pipe section, the pipe diameter mutation point, the slope turning point and the monitoring point coverage blind area are analyzed to extract the public pipe network structure; at the same time, the coordinates of the access points of the internal drainage pipe network of the plant area are identified according to the building layout map, and the legal connection points with the public pipe network are marked to determine the plant area pipe network structure. Then, the main pipe section set in the public pipe network structure and the access point set of the plant area pipe network structure are analyzed, and the spatial position relationship between the plant area and the public pipe network is established based on the Euclidean distance between the plant area boundary and the pipe network node. Subsequently, the plant area-pipeline network node pairs are screened based on the spatial position relationship, and the potential concealed pipe laying path is generated by combining the concealed pipe laying characteristics in the historical concealed pipe case library. Then, dynamic verification is performed for each potential concealed pipe path: First, virtual monitoring points are inserted at equal intervals along the potential concealed pipe path, and the pollutant concentration gradient change at each virtual monitoring point is calculated. Then, the pollutant concentration gradient change is matched with the measured data of the candidate illegal discharge point through DTW dynamic time warping to verify the possibility of the concealed pipe. Finally, if the matching degree is high, the possibility of the concealed pipe is determined. Then, the endpoint of the verified potential concealed pipe path is backtracked to determine the concealed pipe discharge point: First, several plant coordinate point sets within the upstream range of the path end are obtained; then, the vertical distance from each plant coordinate point set to the centerline of the potential concealed pipe path is calculated; based on the vertical distance, the concealed pipe access point is determined; finally, the coordinate set of the concealed pipe access point is output as the concealed pipe discharge point.

[0142] This solution allows the acquisition of plant building layouts and municipal pipe network topology maps, eliminating coordinate drift errors during manual drawing comparison and providing a precise spatial benchmark for topological analysis. By analyzing the municipal pipe network topology map and plant building layout map, the public and plant pipe network structures are determined, overcoming the inability to perceive the real-time connection status of pipe segments when relying on static drawings. Based on the public and plant pipe network structures, the spatial relationship between the plant and public pipe networks is determined, replacing manual drawing comparison methods and improving processing efficiency. Based on this spatial relationship, potential concealed pipe laying paths are determined, helping to accurately capture the typical characteristics of concealed pipe projects. Based on the changes in pollutant concentration gradients along potential concealed pipe laying paths based on pollution dissipation path information, the possibility of concealed pipes being present is verified, helping to reduce the rate of path misjudgments. Based on the possibility of concealed pipes, the concealed pipe discharge points are determined based on the potential concealed pipe laying paths, addressing the accuracy defects of the municipal pipe network map due to insufficient resolution and ensuring that the positioning results meet the project acceptance standards.

[0143] In some embodiments, the public pipe network structure is parsed to determine the public pipe network nodes; the plant area pipe network structure is parsed to determine the spatial coordinates of the plant area drainage facilities; the Euclidean distance between each spatial coordinate and the nearest public pipe network node is calculated to obtain a distance set; the plant area information is obtained, analyzed, and the plant area drainage demand is determined; a path optimization function is constructed based on the distance set and the plant area drainage demand; and based on the path optimization function, the potential concealed pipe laying path is calculated.

[0144] Public pipe network nodes can be physical connection points between pipe segments in a municipal drainage system. Plant drainage facilities can be physical facilities within a plant that are directly involved in wastewater discharge. Spatial coordinates can be the three-dimensional location data of plant drainage facilities. Euclidean distance can be the straight-line distance between two coordinate points in three-dimensional space. A distance set can be a numerical set consisting of the Euclidean distance between each spatial coordinate and the nearest public pipe network node. Plant information can be static drainage-related data recorded in an enterprise's environmental assessment report. Plant drainage demand can be dynamic drainage requirements quantified through analysis of plant information. The path optimization function can be a multi-constraint mathematical model with the goal of minimizing the cost of laying a path.

[0145] Specifically, public pipe network nodes, such as main pipe intersections, branch line access points, and manhole centers, are extracted from the municipal pipe network topology. The planar coordinates of plant drainage facilities, such as outfalls, pretreatment tank outlets, and emergency discharge valves, are then identified from the plant network structure and converted to spatial coordinates consistent with those of the public pipe network nodes. A kd-tree spatial index query is then performed on the spatial coordinates of each plant drainage facility to identify nearby public pipe network nodes. The Euclidean distance between each spatial coordinate and the nearest public pipe network node is recorded to form a distance set. Subsequently, plant information is obtained from the company's environmental assessment report. This information is then analyzed to calculate the daily wastewater discharge, peak flow rate, and pollutant concentrations, thereby generating the plant drainage demand. A path optimization function is constructed based on the distance set and the dynamic flow parameters of the plant drainage demand. Finally, constraints are set within the path optimization function, and a candidate path set is generated based on the topological relationships of the public pipe network nodes. This candidate path set is then subjected to hierarchical filtering to identify potential concealed pipe installation paths.

[0146] This solution analyzes the public pipe network structure and identifies public pipe network nodes, eliminating node location ambiguity caused by insufficient drawing resolution and providing a precise reference coordinate set for spatial relationship calculations. The plant network structure is analyzed to determine the spatial coordinates of the plant drainage facilities, achieving reference alignment between the plant's local coordinate system and the public pipe network's global coordinate system. This eliminates spatial relationship calculation errors caused by coordinate discrepancies and ensures geometric consistency in distance calculations between plant drainage outlets and pipe network nodes. The Euclidean distance between each spatial coordinate and the nearest public pipe network node is calculated to generate a distance set, quantifying the spatial accessibility relationship between plant drainage points and the public pipe network. This overcomes the inefficiency of manual comparison of pipe network drawings and provides key distance parameter input for the path optimization function. Plant information is obtained and analyzed to determine the plant drainage requirements, eliminating model distortion caused by using only fixed thresholds. Based on the distance set and plant drainage requirements, a path optimization function is constructed to effectively filter out invalid paths that do not conform to concealed pipe installation rules. Based on the path optimization function, potential concealed pipe installation paths are calculated, enabling intelligent convergence from a vast number of possible paths to high-probability concealed pipe paths, improving path generation efficiency.

[0147] In some embodiments, historical cases of discovered concealed pipes are obtained, analyzed, and a path feature data set is determined; the path feature data set is parsed to determine the path length, burial depth, and number of turns in each historical case of discovered concealed pipes; a logistic regression model is constructed based on the path length, burial depth, and number of turns; the possibility of the existence of concealed pipes is input into the logistic regression model to determine whether there is at least one potential concealed pipe laying path with a confidence level higher than the confidence requirement; if so, the potential concealed pipe laying path corresponding to the confidence level higher than the confidence requirement is determined as a concealed pipe drainage point.

[0148] Historical cases of uncovered hidden pipes may be instances of illegal hidden pipe laying that have been verified and recorded by environmental law enforcement departments.

[0149] The path feature dataset may be a structured dataset including path length, buried depth, and number of corners.

[0150] The path length can be the total length of the broken line path from the start point to the end point of the concealed pipe. The buried depth can be the vertical distance from the top of the concealed pipe to the ground surface. The number of turns can be the number of turning points with angle changes in the plane of the concealed pipe. The logistic regression model can be a binary classification model with path length, buried depth, and number of turns as independent variables and the probability of the concealed pipe presence as the dependent variable. The confidence level can be the probability value of the concealed pipe presence output by the model. The confidence requirement can be a pre-set judgment threshold.

[0151] Specifically, historical cases of uncovered concealed pipes were retrieved from the environmental law enforcement database. GIS topology analysis tools were used to calculate the total length of the continuous pipe from its start point to its end point. Measured soil depths of the pipe tops were extracted from construction records, and where missing data were found, inversion was performed using geological radar detection reports. Finally, the number of turning points with angle changes in the pipeline's planar trajectory was counted. These data were combined to form a path feature dataset.

[0152] Among them, the total length of the continuous pipeline from the starting point to the end point of the concealed pipe is the path length, the measured value of the soil cover depth on the top of the pipe is the burial depth, and the number of turning points with angle changes in the plane direction of the pipeline is the number of turning points.

[0153] The path length, burial depth, and number of turns for each historically seized concealed pipe case were constructed as input vectors, and a label was output indicating whether a concealed pipe was present in the case. A logistic regression model was constructed using maximum likelihood estimation. The construction process involved retrieving historical cases of seized concealed pipes from the environmental law enforcement agency's database. These cases included confirmed instances of illegal concealed pipe installations. Each case contained detailed information about the pipe's route (e.g., construction drawings, geological radar survey reports, and field measurements). The total length of the pipe was defined as the actual length from the pipe's starting point (the plant's drainage facility) to its end point (the public pipe network access point). Calculation: Using a GIS topology analysis tool (such as ArcGIS's path length calculation function), the vector coordinate sequence of the concealed pipe's path (starting point, end point, and intermediate turning points) was imported. The Euclidean distance formula was used to calculate the distances between adjacent points, and the total length was then accumulated to obtain the total length (in meters). The vertical distance (in meters) was defined as the distance from the top of the concealed pipe to the ground surface. Measured values ​​were preferentially extracted from construction records or field measurement reports. If data were missing, depth was inverted from geological radar survey reports (e.g., calculating depth using the time difference of electromagnetic wave reflection). This is defined as the number of turning points in the plane direction of a concealed pipe with an angle change (≥30 degrees). The statistical method involves identifying directional abrupt changes from the path coordinate sequence (e.g., calculating the angle by the dot product of adjacent line segment vectors; if the angle is <150 degrees, it is counted as a turn). The path length, buried depth, and number of turns for each case are used as feature vectors, and a binary label (output variable) is added: a label of "1" indicates the presence of a concealed pipe (positive case), and a label of "0" indicates the absence of a concealed pipe (negative case, such as a legitimate shallow-buried pipeline or a false positive). To account for feature scale differences (large range of path lengths and small range of buried depths), each feature is normalized using the Z-score to achieve a mean of 0 and a variance of 1. The normalized features are combined into the input vector X. Each case corresponds to a feature vector: X = [normalized path length, normalized buried depth, normalized number of turns]. The output label y is directly binary (0 or 1). The probability of the presence of a concealed pipe (obtained from the previous step) is used as the model input. The probability of a concealed pipe's existence is a probability value (ranging from 0 to 1) calculated based on information about pollution dissipation paths (e.g., verified by changes in pollutant concentration gradients). The currently detected potential concealed pipe paths are standardized. Subsequently, the standardized feature vector is input into a trained logistic regression model to output the probability of concealed pipe existence. Then, based on ROC curve analysis, the confidence requirement is determined by maximizing the difference between the true positive rate and the false positive rate to determine whether there is at least one potential concealed pipe path with a confidence level higher than the confidence requirement. Finally, potential concealed pipe paths with a probability of concealed pipe existence higher than the confidence requirement are screened and sorted in descending order of confidence. High-confidence paths are superimposed with the plant's geographic information, and the locations of illegal discharge outlets along the potential concealed pipe paths are marked as concealed pipe discharge points.

[0154] Through this solution, historical cases of discovered concealed pipes are obtained, analyzed, and path feature data sets are determined, which helps eliminate the defects of relying on manual inspection of pipeline network drawings. The path feature data sets are analyzed to determine the path length, burial depth, and number of corners in each historical case of discovered concealed pipes, thereby enhancing the detection sensitivity of behaviors that bypass monitoring points, filtering out interference from legal shallowly buried pipelines, and improving the path matching degree under complex pipeline network topologies. Based on the path length, burial depth, and number of corners, a logistic regression model is constructed to eliminate the problem of insufficient accuracy of fixed parameter models. The possibility of the existence of concealed pipes is input into the logistic regression model to determine whether there is at least one potential concealed pipe laying path with a confidence level higher than the confidence requirement, which helps eliminate misjudgments caused by water flow disturbances. If so, the potential concealed pipe laying path corresponding to the confidence level higher than the confidence requirement is determined as a concealed pipe drainage point, which helps eliminate the problem of low efficiency of manual inspection.

[0155] In some embodiments, the coordinates of the pollution point and the administrative area to which the pollution discharge point belongs are determined based on the coordinates of the factory area; the pollution diffusion range is determined based on the pollution dissipation path information; after the location of the pollution discharge point is determined, early warning information is generated based on the coordinates of the pollution point and the pollution diffusion range; according to the administrative area to which the pollution discharge point belongs, the early warning information is routed to the corresponding supervision terminal, and the response timestamp of the supervision terminal is recorded to form a closed-loop management log.

[0156] The coordinates of the pollution point can be the coordinates for tracing the source of the pollutant. The administrative region to which the pollution point belongs can be the identifier of the administrative region to which the pollution point belongs. The pollution spread range can be the spatial distribution area of ​​the pollutant. The location of the pollution point can be the location of the source of illegal pollution discharge. The warning information can be a structured data message. The warning information path can be a targeted distribution mechanism for warning information. The supervision terminal can be an authorized access device of an agency with environmental supervision functions. The response timestamp can be the UTC timestamp generated when the supervision terminal returns the disposal instruction. The closed-loop management log can be an immutable record set stored in a blockchain.

[0157] Specifically, the National Geographic Coding Service API is called to convert the plant coordinates into WGS84 geographic coordinates. The coordinates of the polluted point are then calculated using a spatial interpolation algorithm. Then, based on the "Administrative Division Code" database, the spatial inclusion determination function ST_Contains is used to overlay the polluted point coordinates with the pre-set administrative division vector boundaries to determine the administrative region to which the discharge point belongs. Furthermore, a dynamic parameter matrix is ​​constructed based on the water velocity, pipe curvature radius, and pollutant half-life information from the pollution dissipation path. A finite volume method is used to simulate two-dimensional pollutant diffusion. The iteration termination condition is then set to the concentration gradient change rate. A pollution diffusion contour map is output, and the geometric envelope of the area with excessive concentration is extracted as the pollution diffusion range. Once the discharge point location is determined, the polluted point coordinates are converted into a standard address description (administrative division + road + azimuth distance). The boundary coordinates of the area with excessively high concentration within the pollution diffusion range are extracted, thereby generating a warning message. According to the administrative region to which the pollution discharge point belongs, the routing table of the environmental regulatory agency is queried to match the ID of the regulatory terminal with jurisdiction; then, the warning information is pushed to the corresponding regulatory terminal through the message queue middleware, and a digital signature and time validity identifier are attached; then, when capturing the response instruction returned by the regulatory terminal, the response timestamp and the coordinates of the pollution point are extracted to construct an associated index; finally, the warning information, routing path, and response delay data are written into the blockchain evidence storage module to generate an unalterable closed-loop management log.

[0158] Through this solution, the coordinates of the pollution point and the administrative area to which the discharge point belongs are determined based on the coordinates of the plant area, eliminating positioning deviations caused by inconsistent coordinate benchmarks and resolving jurisdictional disputes caused by blurred boundaries when manually comparing drawings. Based on the pollution dissipation path information, the pollution spread range is determined to overcome the impact of inconsistent time and space benchmarks and improve the accuracy of abnormal path identification. After the location of the discharge point is determined, early warning information is generated based on the coordinates of the pollution point and the pollution spread range, eliminating the problem of low efficiency in manual investigation, making the early warning location readable and facilitating rapid on-site positioning. Based on the administrative area to which the discharge point belongs, the early warning information is routed to the corresponding supervision terminal, and the response timestamp of the supervision terminal is recorded to form a closed-loop management log, eliminating the defects of easy tampering of paper logs and reversible editing of electronic logs.

[0159] Figure 3 This is a schematic diagram of a water quality monitoring system based on Internet of Things technology provided in one embodiment of the present application. Figure 3 As shown, the water quality monitoring system 300 based on the Internet of Things technology of this embodiment includes: a data analysis module 301, an information analysis module 302, a dissipation analysis module 303, a feature determination module 304, and a pollution discharge determination module 305.

[0160] The data analysis module 301 is used to obtain multi-source water quality monitoring data in the monitoring area; analyze the multi-source water quality monitoring data to determine whether there is a possibility of illegal discharge of pollutants;

[0161] The information analysis module 302 is used to obtain the water pipe layout information and regional information of the monitoring area, if any; analyze the water pipe layout information to determine the water flow path association;

[0162] a dissipation analysis module 303 for determining pollution dissipation path information based on the water flow path association and the multi-source water quality monitoring data;

[0163] A feature determination module 304 is used to analyze the regional information and determine the distribution features of the plant area;

[0164] The pollution discharge determination module 305 is used to determine illegal pollution discharge points based on the water flow path association, the plant area distribution characteristics and the dissipation path information.

[0165] Optionally, when the information analysis module 302 analyzes the water pipe layout information and determines the water flow path association, it is used to: analyze the water pipe layout information to determine the water pipe intersection point, pipe diameter and layout slope; parse the multi-source water quality monitoring data to determine the data source; determine the water quality monitoring point based on the data source; analyze the multi-source water quality monitoring data and the real-time flow rate of each water quality monitoring point; construct a dynamic weighted directed graph model based on the water pipe intersection point, the pipe diameter, the layout slope and the real-time flow rate; and determine the water flow path association based on the dynamic weighted directed graph model.

[0166] Optionally, when the dissipation analysis module 303 determines the pollution dissipation path information based on the water flow path association and the multi-source water quality monitoring data, it is used to: obtain a historical related pollution data set based on the water flow path association; parse the historical related pollution data set to determine the historical pollution type, initial pollution concentration and dissipation time; establish a pollution diffusion model based on the historical pollution type, the initial pollution concentration and the dissipation time; and determine the pollution dissipation path information based on the pollution diffusion model and the multi-source water quality monitoring data.

[0167] Optionally, when the feature determination module 304 analyzes the regional information and determines the plant area distribution characteristics, it is used to: analyze the regional information to determine the plant area coordinates; determine the physical distance between the water quality monitoring point and each plant area based on the plant area coordinates; establish a topological relationship matrix between the water quality monitoring point and the plant area coordinates based on the physical distance; and determine the plant area distribution characteristics based on the topological relationship matrix.

[0168] Optionally, when the pollution discharge determination module 305 determines an illegal pollution discharge point based on the water flow path association, the plant area distribution characteristics and the dissipation path information, it is used to: construct a pollution source tracing probability graph model based on the water flow path association and the pollution dissipation path information; determine the spatial correlation between each plant area and the pollution dissipation path based on the plant area distribution characteristics; obtain the plant area pollution discharge permit information, and determine the plant area pollution discharge probability based on the plant area pollution discharge permit information and the spatial correlation; input the plant area pollution discharge probability as a priori probability into the pollution source tracing probability graph model to obtain an output result; calculate the output result through Bayesian reasoning to determine the posterior probability of each water quality monitoring point; compare the posterior probability with the preset threshold of each water quality monitoring point, and screen the water quality monitoring points that exceed the preset threshold as candidate illegal pollution discharge points; perform path consistency verification on the candidate illegal pollution discharge points based on the water flow path association and the pollution dissipation path information, and if the verification passes, determine the candidate illegal pollution discharge point as an illegal pollution discharge point.

[0169] Optionally, the water quality monitoring system based on Internet of Things technology also includes a concealed pipe determination module 306, which is used to: obtain a plant building layout map and a municipal pipe network topology map; analyze the municipal pipe network topology map and the plant building layout map to determine the public pipe network structure and the plant pipe network structure; determine the spatial position relationship between the plant and the public pipe network based on the public pipe network structure and the plant pipe network structure; determine the potential concealed pipe laying path based on the spatial position relationship; verify the possibility of the existence of concealed pipes based on the change in pollutant concentration gradient on the potential concealed pipe laying path according to the pollution dissipation path information; based on the possibility of the existence of concealed pipes, determine the concealed pipe discharge point according to the potential concealed pipe laying path.

[0170] Optionally, when the concealed pipe determination module 306 determines the potential concealed pipe laying path based on the spatial position relationship, it is used to: parse the public pipe network structure to determine the public pipe network nodes; parse the plant area pipe network structure to determine the spatial coordinates of the plant area drainage facilities; calculate the Euclidean distance between each spatial coordinate and the nearest public pipe network node to obtain a distance set; obtain plant area information, analyze the plant area information, and determine the plant area drainage demand; construct a path optimization function based on the distance set and the plant area drainage demand; and calculate the potential concealed pipe laying path based on the path optimization function.

[0171] Optionally, when determining the concealed pipe drainage point based on the possibility of the concealed pipe existence and the potential concealed pipe laying path, the concealed pipe determination module 306 is used to: obtain historical cases of concealed pipe seizure, analyze the historical cases of concealed pipe seizure, and determine a path feature data set; parse the path feature data set to determine the path length, burial depth, and number of turns in each historical case of concealed pipe seizure; construct a logistic regression model based on the path length, the burial depth, and the number of turns; input the possibility of the concealed pipe existence into the logistic regression model to determine whether there is at least one potential concealed pipe laying path whose confidence level is higher than the confidence requirement; if so, determine the potential concealed pipe laying path corresponding to the confidence level higher than the confidence requirement as a concealed pipe drainage point.

[0172] Optionally, the water quality monitoring system based on Internet of Things technology also includes a log formation module 307, which is used to: determine the coordinates of the pollution point and the administrative area to which the discharge point belongs based on the plant coordinates; determine the pollution diffusion range based on the pollution dissipation path information; after the location of the discharge point is determined, generate early warning information based on the coordinates of the pollution point and the pollution diffusion range; route the early warning information to the corresponding supervision terminal based on the administrative area to which the discharge point belongs, and record the response timestamp of the supervision terminal to form a closed-loop management log.

[0173] The system of this embodiment can be used to execute the method of any of the above embodiments. Its implementation principles and technical effects are similar and will not be described in detail here.

Claims

1. A water quality monitoring method based on Internet of Things technology, characterized in that: include: Obtain multi-source water quality monitoring data in the monitoring area; Analyze the multi-source water quality monitoring data to determine whether there is a possibility of illegal discharge of pollutants; The multi-source water quality monitoring data is a heterogeneous data set of three types of sensor groups; the three types of sensor groups are the factory discharge outlet sensor group, the public pipe network monitoring node and the natural water body monitoring point deployed in the monitoring area; If so, the water pipe layout information and regional information of the monitoring area are obtained; the water pipe layout information is analyzed to determine the water flow path association; the regional information is a structured data set covering the plant's geographic coordinate boundaries, reported drainage volume, and pipe network access point locations; the water flow path association is a set of main pollutant diffusion paths and branch paths; Based on the water flow path association, determining pollution dissipation path information according to the multi-source water quality monitoring data; Analyze the regional information to determine the distribution characteristics of the plant area; Determining illegal discharge points based on the water flow path association, the plant area distribution characteristics, and the dissipation path information; The analyzing the water pipe layout information to determine the water flow path association includes: Analyze the water pipe layout information to determine the water pipe intersection point, pipe diameter and layout slope; Analyze the multi-source water quality monitoring data and determine the data sources; Determine water quality monitoring points based on the data sources; Analyze the multi-source water quality monitoring data and the real-time flow rate of each water quality monitoring point; Constructing a dynamic weighted directed graph model according to the water pipe intersection, the pipe diameter, the layout slope and the real-time flow rate; Determining water flow path associations according to the dynamic weighted directed graph model; The determining of pollution dissipation path information based on the water flow path association and the multi-source water quality monitoring data includes: Based on the water flow path association, a historical pollution-related data set is obtained; the historical pollution-related data set is analyzed to determine the historical pollution type, initial pollution concentration and dissipation time; Establishing a pollution diffusion model according to the historical pollution type, the initial pollution concentration and the dissipation time; Determining pollution dissipation path information based on the pollution diffusion model and the multi-source water quality monitoring data; The analyzing the regional information to determine the distribution characteristics of the plant area includes: Analyze the regional information and determine the factory coordinates; Determining the physical distance between the water quality monitoring point and each plant area according to the plant area coordinates; Based on the physical distance, a topological relationship matrix is ​​established between the water quality monitoring point and the factory coordinates; Determining plant area distribution characteristics according to the topological relationship matrix; The determining of illegal discharge points based on the water flow path association, the plant area distribution characteristics, and the dissipation path information includes: Based on the water flow path association and the pollution dissipation path information, each water quality monitoring point is treated as an independent node, and the directed edge weight is determined according to the product of the water flow transmission time difference and the pollutant concentration gradient between the upstream and downstream monitoring points; then, a pollution tracing probability graph model is constructed based on the independent nodes and directed edge weights; Determining the spatial correlation between each plant area and the pollution dissipation path according to the plant area distribution characteristics; Obtaining plant area pollutant discharge permit information, and determining the plant area pollutant discharge probability based on the plant area pollutant discharge permit information and the spatial correlation; The pollution discharge probability of the plant area is used as a priori probability and input into the pollution source tracing probability graph model to obtain an output result; Calculating the output results through Bayesian reasoning to determine the posterior probability of each water quality monitoring point; Comparing the posterior probability with a preset threshold value of each water quality monitoring point, and screening water quality monitoring points exceeding the preset threshold value as candidate illegal discharge points; According to the water flow path association and the pollution dissipation path information, the candidate illegal discharge point is verified for path consistency. If the verification passes, the candidate illegal discharge point is determined to be an illegal discharge point.

2. The method according to claim 1, characterized in that If the verification is successful, then after determining that the candidate illegal pollution discharge point is an illegal pollution discharge point, the method further includes: Obtain the factory building layout and municipal pipe network topology; Analyze the municipal pipe network topology map and the plant building layout map to determine the public pipe network structure and the plant pipe network structure; Determining the spatial position relationship between the factory area and the public pipe network according to the public pipe network structure and the factory area pipe network structure; Determine potential concealed pipe laying paths based on the spatial position relationship; Verify the possibility of the existence of the hidden pipe according to the change of the pollutant concentration gradient along the potential hidden pipe laying path according to the pollution dissipation path information; Based on the possibility of the existence of the concealed pipe and according to the potential concealed pipe laying path, the concealed pipe drainage point is determined.

3. The method according to claim 2, characterized in that Determining a potential concealed pipe laying path based on the spatial position relationship includes: Analyzing the public pipe network structure and determining public pipe network nodes; Analyze the plant network structure and determine the spatial coordinates of the plant drainage facilities; Calculate the Euclidean distance between each spatial coordinate and the nearest public pipe network node to obtain a distance set; Obtaining plant area information, analyzing the plant area information, and determining the drainage needs of the plant area; Constructing a path optimization function according to the distance set and the drainage demand of the plant area; According to the path optimization function, the potential concealed pipe laying path is calculated.

4. The method according to claim 2, characterized in that The method of determining the sewage discharge point of the concealed pipe based on the possibility of the concealed pipe existence and the potential concealed pipe laying path includes: Obtain and analyze historical cases of concealed pipe seizures to determine the path feature dataset; Analyze the path feature data set to determine the path length, burial depth, and number of corners in each historical case of concealed pipe seizure; Constructing a logistic regression model based on the path length, the burial depth, and the number of corner turns; Inputting the possibility of the existence of the concealed pipe into the logistic regression model to determine whether there is at least one potential concealed pipe laying path with a confidence level higher than a confidence requirement; If it exists, the potential concealed pipe laying path corresponding to the confidence level higher than the confidence requirement will be determined as the concealed pipe drainage point.

5. The method according to claim 1, wherein The method further comprises: According to the plant coordinates, determine the coordinates of the pollution point and the administrative area to which the pollution discharge point belongs; Determining the pollution diffusion range based on the pollution dissipation path information; After the location of the pollution point is determined, early warning information is generated according to the coordinates of the pollution point and the pollution spread range; According to the administrative area to which the pollution discharge point belongs, the warning information is routed to the corresponding supervision terminal, and the response timestamp of the supervision terminal is recorded to form a closed-loop management log.

6. A water quality monitoring system based on Internet of Things technology, applied to the method according to any one of claims 1 to 5, characterized in that: include: Data analysis module, used to obtain multi-source water quality monitoring data in the monitoring area; Analyze the multi-source water quality monitoring data to determine whether there is a possibility of illegal discharge of pollutants; An information analysis module, configured to obtain water pipe layout information and regional information of the monitoring area, if any; analyze the water pipe layout information to determine water flow path association; a dissipation analysis module, configured to determine pollution dissipation path information based on the water flow path association and the multi-source water quality monitoring data; A feature determination module, configured to analyze the regional information and determine the distribution features of the plant area; The sewage discharge determination module is used to determine illegal sewage discharge points based on the water flow path association, the plant area distribution characteristics and the dissipation path information.

Images