A monitoring and early warning method and device for water environmental pollution and a storage medium

Abstract

The application discloses a monitoring and early warning method and device for water environmental pollution and a storage medium, and comprises the following steps: determining a plurality of target monitoring points pre-set in a target area, generating a first graph structure for representing the migration of pollutants and a second graph structure for representing the diffusion and degradation of the pollutants based on the plurality of target monitoring points; inputting the first graph structure into a pre-set first graph neural network to output a third graph structure; inputting the second graph structure into a pre-set second graph neural network to output a fourth graph structure; performing feature extraction and fusion on the third graph structure and the fourth graph structure, and generating a first pollutant concentration feature vector corresponding to each target monitoring point; inputting the pollutant concentration feature vector into a risk prediction model to determine the pollution degree corresponding to each target monitoring point, and determining whether to perform early warning based on the pollution degree. The technical effect of monitoring and early warning of water environmental pollution is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of water environment monitoring, in particular to a monitoring and early warning method and device for water environment pollution and a storage medium. BACKGROUND

[0002] Water, as a precious resource for human survival, its ecological environment and pollution degree are of great importance to humans. However, the current water pollution monitoring and early warning is still in a relatively primitive state, and the intelligent degree is low. For example, by investigating and evaluating the pollution source, the main pollutant in the water environment of the target area is determined. A third-party institution is commissioned to conduct sampling analysis to determine the pollution degree of the water environment in the target area. The transparency of the water environment in the target area is observed by the naked eye to determine the pollution degree.

[0003] However, the above-mentioned method of monitoring the pollution degree of the water environment in the target area has some defects. For example, although the main pollutant in the water environment of the target area can be determined by investigating and evaluating the pollution source, the pollution source cannot be located, and the water quality of the target area cannot be accurately evaluated and predicted. For another example, although the pollution degree of the water environment in the target area can be determined by commissioning a third-party institution to conduct sampling analysis, the water quality monitoring equipment can only collect water quality data at discrete sites and cannot obtain more comprehensive water quality data. For another example, since the water environment is open and complex, the pollutants will diffuse and migrate, and the interaction between various pollutants is complex, with many coupling factors, so how to accurately predict the change of the pollution degree of the water environment and conduct monitoring and early warning according to the prediction result is a problem to be solved.

[0004] A water quality monitoring and early warning method and system with publication number CN119005539A. It includes the following steps: collecting multi-dimensional water quality parameter data through multiple groups of sensors to obtain time series data, preprocessing to obtain preprocessed time series data; construct a multi-factor water quality prediction model, the multi-factor water quality prediction model includes a single-factor prediction module, a feature fusion module, a Transformer encoder module and a prediction output module, the single-factor prediction module is a single-factor time series monitoring model, the preprocessed time series data multi-factor water quality prediction model obtains the multi-dimensional water quality parameter prediction value of the future time step; construct an early warning model based on the multi-factor time series prediction result, the multi-dimensional water quality parameter prediction value is processed by the early warning model based on the multi-factor time series prediction result to generate an early warning signal.

[0005] A water ecological pollution monitoring method, device and system based on a time sequence network are disclosed in CN117491585A. The method includes obtaining topographic survey data of a target river section and building a two-dimensional river section model; determining a calculation area of the target river section; performing grid division on the calculation area of the target river section; setting relevant parameters for the two-dimensional river section model, performing water dynamic analysis on the target river section, and outputting water dynamic analysis result data; constructing a water quality prediction model based on a time sequence network; obtaining time sequence data sets of historical water quality indexes of each discharge port of the target river section from pollution source data generated based on the water dynamic analysis result data and historical monitoring data, inputting the time sequence data sets into the water quality prediction model based on the time sequence network for training and testing, and then predicting water quality monitoring data of the target river section; and generating monitoring report data based on the predicted water quality monitoring data.

[0006] The prior art has the technical problem that the change in the degree of water environmental pollution cannot be accurately predicted, and monitoring and early warning cannot be performed based on the prediction result. SUMMARY

[0007] Embodiments of the present disclosure provide a monitoring and early warning method, device and storage medium for water environmental pollution to at least solve the technical problem that the change in the degree of water environmental pollution cannot be accurately predicted, and monitoring and early warning cannot be performed based on the prediction result in the prior art.

[0008] According to one aspect of an embodiment of the present disclosure, a monitoring and early warning method for water environmental pollution is provided, which includes determining a plurality of target monitoring points pre-set in a target area, and based on the plurality of target monitoring points, respectively generating a first graph structure for representing migration and movement of pollutants and a second graph structure for representing diffusion and degradation of the pollutants; constructing a first graph neural network corresponding to the first graph structure, and inputting the first graph structure into the first graph neural network, thereby outputting a third graph structure; constructing a second graph neural network corresponding to the second graph structure, and inputting the second graph structure into the second graph neural network, thereby outputting a fourth graph structure; performing feature extraction and fusion on the third graph structure and the fourth graph structure, and generating a first pollutant concentration feature vector corresponding to each target monitoring point; and inputting the pollutant concentration feature vector into a pre-trained risk prediction model, determining a pollution degree corresponding to each target monitoring point, and based on the pollution degree corresponding to each target monitoring point, determining whether to perform early warning.

[0009] According to another aspect of an embodiment of the present disclosure, a storage medium is also provided, which includes a stored program, wherein when the program is executed by a processor, the method described in any one of the above embodiments is executed.

[0010] According to another aspect of the embodiments of the present disclosure, a monitoring and early warning device for water environmental pollution is also provided, which comprises: a graph structure generation module configured to determine a plurality of target monitoring points pre-set in a target area, and generate a first graph structure for representing migration of pollutants and a second graph structure for representing diffusion and degradation of the pollutants based on the plurality of target monitoring points; a first graph structure output module configured to construct a first graph neural network corresponding to the first graph structure, and input the first graph structure into the first graph neural network to output a third graph structure; a second graph structure output module configured to construct a second graph neural network corresponding to the second graph structure, and input the second graph structure into the second graph neural network to output a fourth graph structure; a fusion module configured to extract and fuse features of the third graph structure and the fourth graph structure, and generate a first pollutant concentration feature vector corresponding to each target monitoring point; and an early warning module configured to input the first pollutant concentration feature vector into a pre-trained risk prediction model, determine a pollution degree corresponding to each target monitoring point, and determine whether to perform early warning based on the pollution degree corresponding to each target monitoring point.

[0011] According to another aspect of the embodiments of the present disclosure, a monitoring and early warning device for water environmental pollution is also provided, which comprises: a processor; and a memory connected with the processor, configured to provide the processor with instructions for processing the following processing steps: determining a plurality of target monitoring points pre-set in a target area, and generating a first graph structure for representing migration of pollutants and a second graph structure for representing diffusion and degradation of the pollutants based on the plurality of target monitoring points; constructing a first graph neural network corresponding to the first graph structure, and inputting the first graph structure into the first graph neural network to output a third graph structure; constructing a second graph neural network corresponding to the second graph structure, and inputting the second graph structure into the second graph neural network to output a fourth graph structure; extracting and fusing features of the third graph structure and the fourth graph structure, and generating a first pollutant concentration feature vector corresponding to each target monitoring point; and inputting the first pollutant concentration feature vector into a pre-trained risk prediction model, determining a pollution degree corresponding to each target monitoring point, and determining whether to perform early warning based on the pollution degree corresponding to each target monitoring point.

[0012] The application provides a monitoring and early warning method for water environmental pollution. First, the processor determines a plurality of target monitoring points in a target area, and generates a first graph structure for representing the migration of pollutants and a second graph structure for representing the diffusion and degradation of pollutants based on the plurality of target monitoring points. Then, the processor constructs a first graph neural network corresponding to the first graph structure, and inputs the first graph structure into the first graph neural network, thereby outputting a third graph structure. At the same time, the processor constructs a second graph neural network corresponding to the second graph structure, and inputs the second graph structure into the second graph neural network, thereby outputting a fourth graph structure. Then, the third graph structure and the fourth graph structure are feature extracted and fused, and a first pollutant concentration feature vector corresponding to each target monitoring point is generated. Finally, the processor inputs the first pollutant concentration feature vector into a pre-trained risk prediction model, determines the pollution degree corresponding to each target monitoring point, and determines whether to perform early warning based on the pollution degree corresponding to each target monitoring point.

[0013] As can be known from the above, the application generates a first graph structure for representing the migration of pollutants and a second graph structure for representing the diffusion and degradation of pollutants. Since the migration of pollutants between adjacent two target monitoring points will affect each other, when the first graph structure is processed by the first graph neural network, the first correlation between the adjacent two nodes (corresponding to the target monitoring points) (i.e., the edge between the adjacent two nodes) can be retained, so that the third graph structure finally output not only retains the data information of each node, but also retains the structure information between the adjacent two nodes.

[0014] Similarly, since the diffusion of pollutants between adjacent two target monitoring points will affect each other, when the second graph structure is processed by the second graph neural network, the second correlation between the adjacent two nodes (corresponding to the target monitoring points) (i.e., the edge between the adjacent two nodes) can be retained, so that the fourth graph structure finally output not only retains the data information of each node, but also retains the structure information between the adjacent two nodes.

[0015] Therefore, when the third graph structure and the fourth graph structure are feature extracted and fused, the first pollutant concentration feature vector finally generated corresponding to each target monitoring point contains relatively comprehensive feature information. When the first pollutant concentration feature vector is input into the pre-trained risk prediction model, the risk prediction model can accurately predict the pollution degree corresponding to each target monitoring point. Finally, whether to perform early warning is selected based on the pollution degree corresponding to each target monitoring point.

[0016] This solves the technical problem in the existing technology that it is currently impossible to accurately predict changes in the degree of water pollution and to carry out monitoring and early warning based on the prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of this application. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation of the present disclosure. In the drawings:

[0018] Figure 1 is a hardware structure block diagram of a computing device for implementing the method according to embodiment 1 of the present application;

[0019] Figure 2 Schematic diagram of a water pollution monitoring and early warning system according to Example 1 of the present application;

[0020] Figure 3 This is a modular schematic diagram of the monitoring and early warning platform according to Example 1 of the present application;

[0021] Figure 4 1 is a flow chart of the method for monitoring and early warning of water pollution according to Example 1 of the present application;

[0022] Figure 5 is a schematic diagram of the first graph structure according to Example 1 of the present application;

[0023] Figure 6 is a schematic diagram of the second graph structure according to Example 1 of the present application;

[0024] Figure 7 is a schematic diagram of the risk prediction model described in Example 1 of the present application;

[0025] Figure 8 is a schematic diagram of a monitoring and early warning device for water environment pollution according to Example 2 of the present application; and

[0026] Figure 9 This is a schematic diagram of the monitoring and early warning device for water environment pollution described in Example 3 of the present application. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present disclosure.

[0028] It should be noted that the terms "first", "second", and the like in the description and in the claims of the present disclosure and the above-described accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular sequential or chronological order. It should be understood that the data thus used can be interchanged under appropriate circumstances so that the embodiments of the present disclosure described herein can be implemented in other sequences than those illustrated or described herein. In addition, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or apparatus including a list of steps or units does not necessarily limit those steps or units to those clearly listed, but can include other steps or units not clearly listed or inherent to such processes, methods, products, or apparatuses. Embodiment 1

[0029] According to the present embodiment, a method embodiment for monitoring and early warning of water environmental pollution is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0030] The method embodiment provided by the present embodiment can be executed in a mobile terminal, a computer terminal, a server, or a similar computing device. Figure 1 A hardware structure block diagram of a computing device for implementing a method for monitoring and early warning of water environmental pollution is shown. As shown in Figure 1 The computing device can include one or more processors (the processor can include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory for storing data, a transmission device for communication functions, and an input / output interface. The memory, the transmission device, and the input / output interface are connected to the processor through a bus. In addition, it can also include a display, a keyboard, and a cursor control device connected to the input / output interface. Those skilled in the art can understand that Figure 1 The structure shown is only schematic, and it does not limit the structure of the above-mentioned electronic device. For example, the computing device can include more or fewer components than those shown in Figure 1 or have a different configuration than that shown in Figure 1 .

[0031] It should be noted that the one or more processors and / or other data processing circuitry described above can be referred to herein generally as "data processing circuitry." The data processing circuitry can be embodied in whole or in part as software, hardware, firmware, or any combination thereof. Furthermore, the data processing circuitry can be a single standalone processing module, or it can be incorporated in whole or in part within any one of other elements of a computing device. As referred to in the embodiments of the present disclosure, the data processing circuitry functions as a processor to control, for example, selection of a variable resistance terminal path connected to an interface.

[0032] The memory can be used to store software programs of application software and modules, such as program instructions / data storage means corresponding to the monitoring and early warning method for water environmental pollution in the embodiments of the present disclosure. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, implements the monitoring and early warning method for water environmental pollution of the application program described above. The memory can include a high-speed random access memory, and can also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory can further include a memory remotely arranged with respect to the processor, which can be connected to the computing device through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0033] The transmission device is used to receive or send data via a network. Specific examples of the above-mentioned network can include a wireless network provided by a communication provider of the computing device. In one example, the transmission device includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet in a wireless manner.

[0034] The display can be, for example, a touch screen type liquid crystal display (LCD), which can enable a user to interact with the user interface of the computing device.

[0035] It should be noted that in some optional embodiments, the above-mentioned Figure 1 The computing device shown can include hardware elements (including circuitry), software elements (including computer code stored on a computer readable medium), or combinations of both hardware and software elements. It should be noted that in some embodiments, the functions of the above-mentioned Figure 1 is merely one example of a particular implementation and is intended to provide an example of the types of components that can be present in the computing device described above.

[0036] Figure 2is a schematic diagram of a monitoring and early warning system for water environmental pollution according to the embodiment. Referring to Figure 2 As shown in the figure, the system comprises a plurality of water quality detectors 10, a monitoring and early warning platform 20 in communication connection with the plurality of water quality detectors 10, and a GIS platform 30.

[0037] The GIS platform 30 is in communication connection with the monitoring and early warning platform 20, and the GIS platform 30 is configured to extract pollution information corresponding to the target region in combination with remote sensing images of the target region. The pollution information corresponding to the target region may include, for example, river water resource information of the target region, historical pollution source information of the target region, and pollutant development situation of the target region, etc. It is worth noting to those skilled in the art that the above is only an example of the pollution information corresponding to the target region, and the actual situation is not limited thereto.

[0038] In addition, the GIS platform 30 is further configured to select a monitoring point where the pollutant may appear based on the extracted pollution information corresponding to the target region, and take the selected monitoring point as a target monitoring point.

[0039] When the monitoring and early warning platform 20 receives information related to the target monitoring point sent by the GIS platform 30, the monitoring and early warning platform 20 sends the related information to the terminal device 40 corresponding to the staff, so that the staff can set the water quality detector 10 at the target monitoring point in the target region based on the information displayed by the terminal device 40.

[0040] The plurality of water quality detectors 10 are configured to detect the composition of various pollutants in the water environment corresponding to the target monitoring point.

[0041] When the plurality of water quality detectors 10 detect the composition of various pollutants in the water environment corresponding to the target monitoring point, the monitoring and early warning platform 20 acquires corresponding data information from the plurality of water quality detectors 10, and determines the pollution degree corresponding to each target monitoring point based on the collected data information. When the pollution degree is greater than a preset threshold, the monitoring and early warning platform 20 warns the staff through the terminal device 40.

[0042] Figure 3 is a modular diagram of the monitoring and early warning platform 20 according to the embodiment. Referring to Figure 3 As shown in the figure, the monitoring and early warning platform 20 comprises a data acquisition module, a first graph neural network module, a second graph neural network module, a fusion module, a risk prediction module, and an alarm module. The data acquisition module is configured to acquire the composition and concentration of various pollutants in the water environment of the target monitoring point from the plurality of water quality detectors 10, and generate a first graph structure for representing the migration of the pollutants and a second graph structure for representing the diffusion and degradation of the pollutants.

[0043] The data acquisition module is respectively connected to the first graph neural network module and the second graph neural network module for sending the first graph structure to the first graph neural network module and sending the second graph structure to the second graph neural network module.

[0044] The first graph neural network module and the second graph neural network module are respectively connected to the fusion module. The first graph neural network module is configured to generate a third graph structure based on the first graph structure and send the third graph structure to the fusion module. The second graph neural network module is configured to generate a fourth graph structure based on the second graph structure and send the fourth graph structure to the fusion module.

[0045] The fusion module is in communication with the risk prediction module. The fusion module is configured to extract a second pollutant concentration feature vector from the third graph structure, extract a third pollutant concentration feature vector from the fourth graph structure, and further fuse the second pollutant concentration feature vector with the third pollutant concentration feature vector to generate a first pollutant concentration feature vector.

[0046] The risk prediction module is in communication with the alarm module and is used to predict the pollution degree based on the first pollutant concentration feature vector.

[0047] The alarm module determines whether to issue an alarm to the staff through the terminal device 40 based on the received pollution level prediction result and the preset threshold.

[0048] Under the above operating environment, according to the first aspect of this embodiment, a monitoring and early warning method for water environment pollution is provided. The method comprises Figure 2 The system implementation shown in . Figure 4 A schematic diagram showing the process of the method is shown in FIG. Figure 4 As shown, the method includes:

[0049] S402: Determine a plurality of pre-set target monitoring points within the target area, and generate a first graph structure for representing pollutant migration and a second graph structure for representing pollutant diffusion and degradation based on the plurality of target monitoring points.

[0050] S404: Constructing a first graph neural network corresponding to the first graph structure, and inputting the first graph structure into the first graph neural network, thereby outputting a third graph structure;

[0051] S406: Constructing a second graph neural network corresponding to the second graph structure, and inputting the second graph structure into the second graph neural network, thereby outputting a fourth graph structure;

[0052] S408: extracting and fusing features of the third graph structure and the fourth graph structure, and generating a first pollutant concentration feature vector corresponding to each target monitoring point; and

[0053] S410: input the first pollutant concentration feature vector into the pre-trained risk prediction model, determine the pollution degree corresponding to each target monitoring point, and determine whether to issue a warning based on the pollution degree corresponding to each target monitoring point.

[0054] Specifically, first, the staff sends a pollution degree prediction request related to the target area to the monitoring and warning platform 20 through the terminal device 40, so that the monitoring and warning platform 20 sends a target monitoring point determination request to the GIS platform 30 in response to the pollution degree prediction request sent by the terminal device 40.

[0055] Therefore, the GIS platform 30 responds to the target monitoring point determination request sent by the monitoring and warning platform 20, and extracts the pollution information corresponding to the target area from the remote sensing image corresponding to the target area. The pollution information corresponding to the target area includes, for example, river water resource information of the target area, historical pollution source information of the target area, and pollution development of the target area. Then, the GIS platform 30 selects the monitoring point where the pollutant may appear based on the pollution information corresponding to the target area, and selects the monitoring point as the target monitoring point.

[0056] Further, the GIS platform 30 sends the location information of the target monitoring point to the monitoring and warning platform 20, and further sends the location information of the target monitoring point to the terminal device 40 when the monitoring and warning platform 20 receives the location information of the target monitoring point. Therefore, when the staff views the location information of the target monitoring point through the terminal device 40, the water quality detector 10 can be set at the relevant position in the target area according to the displayed location information. The water quality detector 10 is used to detect the composition and concentration of the pollutant at the corresponding position.

[0057] It is worth noting that the pollutant composition detected by the water quality detector 10 corresponds to the pre-determined pollutant index. For example, first, the GIS platform 30 collects the influence index related to the water environment pollution of the target area. The influence index includes, for example, PH, COD, suspended solids, ammonia nitrogen, oil and some heavy metals. Then, the GIS platform 30 sends the above influence index to the data collection module in the monitoring and warning platform 20, and further selects the above influence index when the data collection module receives the above influence index, so as to select the pollutant index that can reflect the water environment condition of the target area.

[0058] The data collection module includes but is not limited to using principal component analysis to screen the above influence indexes, and determining the contribution degree of each influence index to the water environment pollution of the target area, and selecting a larger contribution degree as a pollutant index. The data collection module can also use SPSS to determine the correlation between each influence index, and select a relatively independent and representative influence index as a pollutant index.

[0059] Thus, the data collection module in the monitoring and early warning module 20 can collect pollutant concentration data corresponding to each pollutant index in the current state from the plurality of water quality detectors 10 arranged in the target area. For example, the concentration corresponding to suspended solids, the concentration corresponding to heavy metals, the concentration corresponding to oil, etc.

[0060] And in the case where the data collection module collects pollutant concentration data corresponding to each pollutant index, based on the pollutant concentration data, a first graph structure for representing pollutant migration movement and a second graph structure for representing pollutant diffusion and degradation are generated respectively (S402).

[0061] Specifically, the first graph structure includes a plurality of nodes corresponding to each target monitoring point ~ And the edges between each adjacent node ~ In addition, it is worth noting that since the pollutant migration movement is often related to the water flow direction and the water flow speed ~ between each adjacent node ~ is used to represent the weight relationship between each adjacent node ~ and the water flow speed ~ relationship, and there is a directional relationship between each adjacent node.

[0062] Figure 5 is a schematic diagram of the first graph structure according to the embodiments of the present application. Referring to Figure 5 , for example, the water flow direction relationship between node and node is that water flows from node to node , and there is a weight relationship and a water flow speed between node and node . For another example, the water flow direction relationship between node and node is that water flows from node to node and node has a weight relationship with node and a water flow speed . Thus, due to the direction between node and node , and the direction between node and node are not the same, it can be known that the pollutant does not only migrate in a certain fixed direction, but can migrate in multiple different directions.

[0063] In addition, it is worth noting that, due to the limitation of the length, the above Figure 5 only shows node ~ It should be clear to those skilled in the art that there are other nodes ~ .

[0064] Specifically, the second graph structure includes a plurality of nodes ~ corresponding to each target monitoring point and edges ~ between each adjacent node. In addition, it is worth noting that, since the pollutant diffusion and degradation are irrelevant to the water flow speed and the water flow direction, and only related to the distance ~ between adjacent nodes (i.e., adjacent target monitoring points), the edges ~ between each adjacent node are used to represent the weight relationship ~ and the distance relationship ~ between each adjacent node, and there is no direction relationship between each adjacent node.

[0065] Figure 6 is a schematic diagram of the second graph structure according to the embodiments of the present application. As shown in Figure 6 , for example, node has a weight relationship and a distance relationship with node . For another example, node has a weight relationship and a distance relationship with node .

[0066] In addition, it is worth noting that, due to the limitation of the length, the above Figure 6 only shows node ~ It should be clear to those skilled in the art that there are other nodes

[0067] The specific operation steps for generating the first graph structure and the second graph structure will be described in detail later, and therefore will not be described here.

[0068] Then, the first graph neural network module in the monitoring and early warning platform 20 constructs a first graph neural network corresponding to the first graph structure, and inputs the first graph structure into the first graph neural network, thereby outputting a third graph structure (S404). Specifically, the first graph neural network module constructs the first graph neural network, and determines the calculation rule of the first graph neural network. The calculation rule of the first graph neural network is as follows, for the node The pollutant concentration under the n-th recursive iteration:

[0069]

[0070] Wherein, the reference Figure 5 and the above formula, it can be known that represents the pollutant concentration corresponding to the node under the n-th recursive iteration, represents the pollutant concentration corresponding to the node under the (n-1)-th recursive iteration, represents the pollutant concentration migrated from the node to the node under the n-th recursive iteration, represents the pollutant concentration migrated from the node to the node under the n-th recursive iteration. Wherein, n=1~N, and wherein, N represents the number of recursive iterations of the first graph neural network on the first graph structure.

[0071] For the node The pollutant concentration under the n-th recursive iteration:

[0072]

[0073] Wherein, the reference Figure 5 and the above formula, it can be known that represents the pollutant concentration corresponding to the node under the n-th recursive iteration, represents the pollutant concentration migrated from the node to the node under the (n-1)-th recursive iteration, represents the pollutant concentration migrated from the node​​​​ to the node the pollutant concentration migrated from the node to the node to the node the pollutant concentration migrated from the node

[0074] to the node the pollutant concentration at the n-th recursive iteration:

[0075] ;

[0076] wherein the reference Figure 5 and the above formula, to the node corresponding to the pollutant concentration at the n-th recursive iteration, to the node to the node the pollutant concentration migrated from the node to the node the pollutant concentration migrated from the node to the node the pollutant concentration migrated from the node to the node the pollutant concentration migrated from the node to the node the pollutant concentration migrated from the node to the node

[0077] to the node the pollutant concentration at the n-th recursive iteration:

[0078] ;

[0079] wherein the reference Figure 5 and the above formula, to the node corresponding to the pollutant concentration at the n-th recursive iteration, to the node to the node the pollutant concentration migrated from the node to the node the pollutant concentration migrated from the node to the node represents the pollutant concentration of the node at the n-th recursive iteration. migrated pollutant concentration. Wherein, n = 1 ~ N, and wherein, N represents the number of recursive iterations of the first graph neural network on the first graph structure.

[0080] By analogy, the pollutant concentration of the node at the n-th recursive iteration can be determined according to the above calculation rule. And it is worth noting that since the water quality detector 10 is arranged at each target monitoring point corresponding to each node, the initial concentration can be determined based on the pollutant composition detected by the water quality detector 10 and the concentration corresponding to the corresponding component. That is, in the present embodiment, when n = 1, the pollutant concentration of the node corresponding to the node corresponding to the node corresponding to the node corresponding to the node corresponding to the node can be determined based on the water quality detector 10.

[0081] Thus, in the case of N recursive iterations of the first graph structure by the first graph neural network, the third graph structure is output. And in the third graph structure, the pollutant concentration corresponding to the node is , the pollutant concentration corresponding to the node is , the pollutant concentration corresponding to the node is , the pollutant concentration corresponding to the node is .

[0082] Then, the second graph neural network module in the monitoring and early warning platform 20 constructs a second graph neural network corresponding to the second graph structure, and inputs the second graph structure into the second graph neural network, thereby outputting a fourth graph structure (S406). Specifically, the second graph neural network module constructs a second graph neural network and determines the calculation rule of the second graph neural network. Wherein the calculation rule of the second graph neural network is as follows, for the node the pollutant concentration at the n-th recursive iteration:

[0083] ;

[0084] Wherein, referring to Figure 6 and the above formula, it can be seen that represents the pollutant concentration of the node corresponding to the node the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node. Wherein, n = 1 ~ N, and wherein, N represents the number of times of recursive iteration of the second graph structure by the second graph neural network.

[0085] Wherein, it is worth noting that since the degradation process of the pollutant corresponding to each node is only related to the pollutant concentration of itself and is irrelevant to the pollutant concentrations of other nodes, when determining the calculation rule corresponding to the first graph neural network, only the degradation coefficient corresponding to the node and the pollutant concentration of the node at the last recursive iteration are used to calculate the pollutant concentration corresponding to the node at the current recursive iteration.

[0086] the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node

[0087] ;

[0088] Wherein, the reference Figure 6 and the above formula, the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node. Wherein, n = 1 ~ N, and wherein, N represents the number of times of recursive iteration of the second graph structure by the second graph neural network.

[0089] the pollutant concentration corresponding to the node the pollutant concentration corresponding to the node

[0090] ;

[0091] wherein the reference Figure 6 and the above formula, it can be known that denotes the pollutant concentration corresponding to the node at the n-th recursive iteration, denotes the pollutant concentration diffused from the node to the node at the n-1-th recursive iteration, denotes the pollutant concentration diffused from the node to the node at the n-1-th recursive iteration, denotes the pollutant concentration degraded by the node at the n-1-th recursive iteration, denotes the pollutant concentration diffused from the node to the node at the n-1-th recursive iteration, denotes the pollutant concentration diffused from the node to the node at the n-1-th recursive iteration. Wherein n = 1 ~ N, and wherein N denotes the number of recursive iterations of the second graph neural network on the second graph structure.

[0092] The pollutant concentration of the node at the n-th recursive iteration is:

[0093] ;

[0094] wherein the reference Figure 6 and the above formula, it can be known that denotes the pollutant concentration corresponding to the node at the n-th recursive iteration, denotes the pollutant concentration diffused from the node to the node at the n-1-th recursive iteration, denotes the pollutant concentration diffused from the node to the node at the n-1-th recursive iteration, denotes the pollutant concentration degraded by the node at the n-1-th recursive iteration, denotes the pollutant concentration diffused from the node to the node at the n-1-th recursive iteration. Wherein n = 1 ~ N, and wherein N denotes the number of recursive iterations of the second graph neural network on the second graph structure.

[0095] By analogy, the pollutant concentration of the node The pollutant concentration at the n-th recursive iteration. And it is worth noting that, since the water quality detector 10 is arranged at the target monitoring point corresponding to each node, the initial concentration can be determined based on the pollutant composition detected by the water quality detector 10 and the concentration corresponding to the respective component. That is, in the present embodiment, when n = 1, the node The corresponding pollutant concentration , the node The corresponding pollutant concentration ,..., the node The corresponding pollutant concentration can be determined based on the water quality detector 10.

[0096] Thus, in the case of N recursive iterations of the second graph structure using the second graph neural network, the fourth graph structure is output. And in the fourth graph structure, the pollutant concentration corresponding to the node is , the pollutant concentration corresponding to the node is , the pollutant concentration corresponding to the node is ,..., the pollutant concentration corresponding to the node is .

[0097] After the third graph structure is output based on the first graph structure using the first graph neural network module, and the fourth graph structure is output based on the second graph structure using the second graph neural network module, the fusion module further extracts features and fuses the third graph structure and the fourth graph structure, and generates the first pollutant concentration feature vector corresponding to each target monitoring point (S408). First, the third graph structure is extracted using a pre-trained neural network model, thereby generating a second pollutant concentration feature vector corresponding to each target monitoring point. Then, the fourth graph structure is extracted using a pre-trained neural network model, thereby generating a third pollutant concentration feature vector corresponding to each target monitoring point. Finally, the second pollutant concentration feature vector and the third pollutant concentration feature vector are fused using an MLP, thereby generating the first pollutant concentration feature vector. The above will be described in detail later, and therefore will not be described here.

[0098] Finally, in the case that the fusion module outputs the first pollutant concentration feature vector, the risk prediction module inputs the first pollutant concentration feature vector into a pre-trained risk prediction model (wherein the risk prediction model comprises, for example, an RNN model, a fully connected layer, and multiple sofmax classifiers), so as to determine the pollution degree corresponding to each target monitoring point. The pollution degree corresponding to each target monitoring point may be, for example, the probability of pollution and the probability of no pollution of the target monitoring point. The higher the probability of pollution, the greater the possibility of pollution and the more serious the pollution of the target monitoring point.

[0099] Thus, in the case that the risk prediction module outputs the pollution degree corresponding to each target monitoring point, the early warning module determines whether early warning is needed based on the pollution degree corresponding to each target monitoring point. For example, in the case that the early warning module determines that early warning is needed based on any one of the target monitoring points, the terminal device 40 warns the staff.

[0100] As described in the background, although the main pollutant in the water environment of the target area can be determined by investigating and evaluating the pollution source, the pollution source cannot be located, and the water quality of the target area cannot be accurately evaluated and predicted. For example, although the pollution degree in the water environment of the target area can be determined by entrusting a third-party agency to perform sampling analysis, the water quality monitoring device can only collect water quality data at discrete sites and cannot obtain more comprehensive water quality data. For example, because the water environment is open and complex, pollutants will diffuse and migrate, and the interaction between pollutants is complex and coupled, how to accurately predict the change of the pollution degree of the water environment and perform monitoring and early warning according to the prediction result is a problem to be solved.

[0101] Therefore, according to the above description, the present application generates a first graph structure for representing the migration of pollutants and a second graph structure for representing the diffusion and degradation of pollutants. Because the migration of pollutants between adjacent target monitoring points will affect each other, in the case of using the first graph neural network to process the data of the first graph structure, the correlation between adjacent nodes (corresponding to the target monitoring points) (i.e., the edge between adjacent nodes) can be retained, so that the third graph structure finally output not only retains the data information of each node, but also retains the structure information between adjacent nodes.

[0102] Similarly, since the diffusion of pollutants between two adjacent target monitoring points will affect each other, in the case of using the second graph neural network to process the data of the second graph structure, the association relationship (i.e., the edge between the two adjacent nodes) between the two adjacent nodes (corresponding to the target monitoring points) can be retained, so that the fourth graph structure finally output not only retains the data information of each node, but also retains the structural information between the two adjacent nodes.

[0103] Therefore, in the case of using the MLP to fuse the third graph structure and the fourth graph structure, the first pollutant concentration feature vector corresponding to each target monitoring point finally generated contains relatively comprehensive feature information. And in the case of inputting the first pollutant concentration feature vector into the pre-trained risk prediction model, the risk prediction model can accurately predict the pollution degree corresponding to each target monitoring point. Finally, based on the pollution degree corresponding to each target monitoring point, it is determined whether to perform early warning.

[0104] Further, the technical problem that the change of the water environment pollution degree cannot be accurately predicted and monitoring and early warning are performed according to the prediction result in the prior art is solved.

[0105] Optionally, the operation of inputting the first pollutant concentration feature vector into the pre-trained risk prediction model, determining the pollution degree corresponding to each target monitoring point, and determining whether to perform early warning based on the pollution degree corresponding to each target monitoring point includes: inputting the first pollutant concentration feature vector into the pre-trained risk prediction model, and outputting the pollution degree probability corresponding to each target monitoring node; determining whether the pollution degree probability corresponding to each target monitoring node is greater than a pre-set pollution degree threshold; and in the case that the pollution degree probability is greater than the pollution degree threshold, performing early warning.

[0106] Specifically, Figure 7 is a schematic diagram of the risk prediction model according to the embodiments of the present application. As shown in Figure 7 , the risk prediction model includes, for example, an RNN model, a fully connected layer, and a plurality of softmax classifiers. The fully connected layer includes 2f neurons. Therefore, in the case of inputting the first pollutant concentration feature vector into the risk prediction model, the fully connected layer can output a vector representing the pollution degree and a vector representing the non-pollution degree for each target monitoring point. Therefore, in the case of inputting the two vectors (i.e., the vector representing the pollution degree and the vector representing the non-pollution degree) corresponding to each target monitoring point into the corresponding softmax classifier, the softmax classifier can output the pollution degree probability corresponding to each target monitoring point based on the two vectors corresponding to each target monitoring point.

[0107] For example, the risk prediction model can output the pollution degree probability corresponding to each target monitoring point based on the first pollutant concentration feature vector described above. In this case, the risk prediction model can output two probabilities corresponding to each target monitoring point, respectively. Referring to Figure 7 the target monitoring point corresponds to a probability and a probability (i.e., the pollution degree probability). In this case, the probability indicates the probability that the target monitoring point is polluted to a certain degree, and the probability indicates the probability that the target monitoring point is not polluted to a certain degree. In this case, the sum of the probability and the probability is 100%.

[0108] In this case, the pollution degree probability output by the risk prediction module is further input to the alarm module.

[0109] The alarm module then determines whether the pollution degree probability corresponding to each target monitoring point is greater than a threshold value set in advance. For example, the target monitoring point corresponds to a probability and a probability (i.e., the pollution degree probability), and the alarm module has a pollution degree threshold value set in advance. The alarm module compares the probability with the pollution degree threshold value . If the probability is greater than the pollution degree threshold value set in advance, it means that the position corresponding to the target monitoring point may be polluted by pollutants, and thus the alarm module alarms the staff through the terminal device 40.

[0110] In addition, it is worth noting that the greater the probability is, the smaller the probability is, i.e., the greater the difference between the probability and the probability is, it means that the position corresponding to the target monitoring point is more seriously polluted by pollutants, and thus the alarm module alarms the staff through the terminal device 40.

[0111] If more than half of the target monitoring points in the target area show that they may be polluted, it means that most of the positions in the target area may be polluted by pollutants, and thus the alarm module alarms the staff through the terminal device 40. ​

[0112] Thus, by using the pre-set risk prediction model to predict the pollution degree probability of each target monitoring point, and based on the prediction result, judging whether the terminal device needs to alarm the staff, the technical effect of reflecting the possible pollution situation to the staff in time and reminding the staff to handle as soon as possible, thereby avoiding the water environment of the target area from being polluted, is achieved.

[0113] Optionally, the operation of feature extraction and fusion on the third graph structure and the fourth graph structure, and generating the first pollutant concentration feature vector corresponding to each target monitoring point, comprises: performing feature extraction on the third graph structure, and generating a second pollutant concentration feature vector corresponding to each target monitoring point; performing feature extraction on the fourth graph structure, and generating a third pollutant concentration feature vector corresponding to each target monitoring point; and using the MLP to fuse the second pollutant concentration feature vector and the third pollutant concentration feature vector, thereby generating the first pollutant concentration feature vector.

[0114] Specifically, in the case that the fusion module receives the third graph structure, the pre-trained neural network model is further used to perform feature extraction on the third graph structure. The third graph structure is used to indicate the graph structure generated after the first graph neural network module performs N times of recursive iteration on the first graph structure. Thus, the pollutant concentration corresponding to the node is , the pollutant concentration corresponding to the node is , the pollutant concentration corresponding to the node is ,..., the pollutant concentration corresponding to the node is , and the pollutant concentration corresponding to each target monitoring point after N times of recursive iteration can be determined based on the calculation rule corresponding to the first graph neural network.

[0115] Thus, after the pre-trained neural network model performs feature extraction on the third graph structure, the second pollutant concentration feature vector G corresponding to the plurality of target monitoring points can be obtained.

[0116] Similarly, in the case that the fusion module receives the fourth graph structure, the pre-trained neural network model is further used to perform feature extraction on the fourth graph structure. The fourth graph structure is used to indicate the graph structure generated after the second graph neural network module performs N times of recursive iteration on the second graph structure. Thus, the pollutant concentration corresponding to the node is , the pollutant concentration corresponding to the node is , the pollutant concentration corresponding to the node The corresponding pollutant concentration is ..., and the node The corresponding pollutant concentration is And the pollutant concentration corresponding to each target monitoring point after N times of recursive iteration can be determined based on the calculation rule corresponding to the second graph neural network.

[0117] Therefore, after the pre-trained neural network model extracts features from the fourth graph structure, the third pollutant concentration feature vector H corresponding to the plurality of target monitoring points can be obtained.

[0118] Finally, the MLP is used to fuse the second pollutant concentration feature vector G and the third pollutant concentration feature vector H , thereby generating the first pollutant concentration feature vector C . The first pollutant concentration feature vector contains pollutant migration information corresponding to the second pollutant concentration feature vector and pollutant diffusion and degradation information corresponding to the third pollutant concentration feature vector.

[0119] Therefore, after the fusion module extracts features from the third graph structure and the fourth graph structure to generate the corresponding second pollutant concentration feature vector and the third pollutant concentration feature vector, the MLP can be further used to fuse the second pollutant concentration feature vector and the third pollutant concentration feature vector, thereby generating the first pollutant feature vector which includes both the pollutant migration information of the target region and the pollutant diffusion and degradation information of the target region. That is, since the first pollutant feature vector contains more comprehensive pollutant information, the prediction result generated based on the first pollutant feature vector is more accurate.

[0120] Optionally, based on the plurality of target monitoring points, the operation of generating the first graph structure for representing the pollutant migration motion comprises: determining a plurality of nodes for generating the first graph structure based on a plurality of target monitoring points preset; determining edges between adjacent nodes based on a first association relationship between the adjacent nodes, wherein the first association relationship is used to indicate a weight relationship and a water flow velocity relationship between the adjacent nodes; and generating the first graph structure after determining the plurality of nodes and the edges between the adjacent nodes.

[0121] Specifically, as can be known from the above description, since the plurality of target monitoring points in the target region are determined in advance, each target monitoring point can be determined as a plurality of nodes in the first graph structure. For example, the target monitoring point corresponds to the node in the first graph structure, the target monitoring point corresponds to the node Corresponding to,..., target monitoring point With the nodes in the first graph structure correspond.

[0122] When multiple nodes in the first graph structure are determined, the edges between adjacent nodes can be determined based on the weight relationship between adjacent nodes and the water flow velocity relationship. Figure 5 As shown, since pollutant migration is often related to water velocity and direction, the migration of pollutants between adjacent nodes is related to water velocity. Furthermore, since a node is often adjacent to multiple nodes, each adjacent node has a corresponding weight coefficient. It is worth noting that in the first graph structure, the weight relationship corresponds to the weight coefficient.

[0123] For example, the node Respectively with nodes and nodes adjacent, so the nodes With node There is a relationship between water velocity and weight relationship , and the node With node The relationship between water flow velocity and weight relationship Composition nodes With node The edges between nodes With node There is a relationship between water velocity and weight relationship , and the node With node The relationship between water flow velocity and weight relationship Composition nodes With node The edge between.

[0124] And so on, other nodes ~ There will also be edges between adjacent nodes in . Thus, when multiple nodes and edges between adjacent nodes are determined, a first graph structure can be generated.

[0125] Optionally, the operation of generating a second graph structure for representing the diffusion and degradation of pollutants based on multiple target monitoring points includes: determining multiple nodes for generating the second graph structure based on multiple pre-set target monitoring points; determining edges between each adjacent node based on a second association relationship between each adjacent node, wherein the second association relationship is used to indicate the weight relationship and distance between each adjacent node; and generating the second graph structure when the edges between multiple nodes and each adjacent node are determined.

[0126] Specifically, referring to the above-mentioned content, it can be known that since multiple target monitoring points in the target area are predetermined, each target monitoring point can be determined as multiple nodes in the first graph structure. With the nodes in the first graph structure Corresponding target monitoring point With the nodes in the first graph structure Corresponding to,..., target monitoring point With the nodes in the first graph structure correspond.

[0127] When determining multiple nodes in the second graph structure, the edges between the adjacent nodes can be determined based on the weight relationship and distance relationship between the adjacent nodes. Figure 6 As shown in the figure, since pollutant diffusion is often related to the distance between adjacent target monitoring points, the pollutant diffusion between each adjacent node is related to the distance. In addition, since a node is often adjacent to multiple nodes, there is a weight relationship between each adjacent node. It is worth noting that in the second graph structure, the weight relationship not only includes the weight coefficient between two adjacent nodes, but also includes the diffusion coefficient and degradation coefficient. Among them, the diffusion coefficient includes, for example, the molecular diffusion coefficient, the turbulent diffusion coefficient, and the dispersion coefficient.

[0128] For example, the node Respectively with nodes and nodes adjacent, so the nodes With node There is a distance relationship between and weight relationship , and the node With node The distance relationship between and weight relationship Composition nodes With node The edges between nodes With node There is a distance relationship between and weight relationship and the node distance relationship between the node and the node and the weight relationship composing node and the node edge between the node.

[0129] Similarly, edges exist between adjacent nodes in other nodes ~ Thus, when the plurality of nodes and the edges between the adjacent nodes are determined, the second graph structure can be generated.

[0130] Optionally, the operation of determining the plurality of target monitoring points in the target area includes: collecting a remote sensing image corresponding to the target area, and extracting pollution information corresponding to the target area from the remote sensing image by using a GIS system; and selecting a monitoring point where a pollutant appears based on the pollution information by using the GIS system, and taking the selected monitoring point as a target monitoring point.

[0131] Specifically, first, the monitoring and early warning platform 20 sends a target monitoring point determination request to the GIS platform 30 in response to a pollution degree detection request sent by the terminal device 40. The GIS platform 30 responds to the request and collects a remote sensing image corresponding to the target area. The GIS platform 30 is provided with a GIS system, and the remote sensing image may, for example, be pre-stored in the GIS system.

[0132] Further, the GIS platform 30 extracts pollution information corresponding to the target area from the remote sensing image corresponding to the target area. The pollution information may, for example, include river water resource information of the target area, historical pollution source information of the target area, and pollutant development of the target area, etc.

[0133] Then, the GIS platform 30 selects a monitoring point where a pollutant may appear or a monitoring point where a pollutant has appeared based on the pollution information corresponding to the target area, and takes the selected monitoring point as a target monitoring point.

[0134] Thus, by using the GIS platform to determine the target monitoring point, the technical effect of being able to guarantee the generation of the first graph structure and the second graph structure and providing a necessary basis for subsequent pollution degree prediction of the target area is achieved.

[0135] Thus, according to the first aspect of the embodiment, the technical effect of being able to accurately predict the change of the water environment pollution degree and monitoring and early warning according to the prediction result is achieved.

[0136] In addition, with reference to Figure 1As shown, according to a second aspect of the present embodiment, a storage medium is provided. The storage medium includes a stored program, wherein the program is executed by a processor when the program is running to perform any one of the above methods.

[0137] Thus, according to the present embodiment, the technical effect of being able to accurately predict the change of the pollution degree of the water environment and monitoring and warning according to the prediction result is achieved.

[0138] It should be noted that for the above-mentioned method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the order of the described actions, because according to the present application, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily necessary for the present application.

[0139] From the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be realized by means of software and the necessary general hardware platform, of course, it can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a plurality of instructions to make a terminal device (which can be a mobile phone, computer, server, or network device, etc.) execute the method described in each embodiment of the present application. Embodiment 2

[0140] Figure 8 The monitoring and warning device 800 for water environment pollution according to the present embodiment is shown, which corresponds to the method according to embodiment 1. Referring to Figure 8As shown, the apparatus 800 includes: a graph structure generation module 810, configured to determine a plurality of target monitoring points in a target region, and generate a first graph structure for representing migration of a pollutant and a second graph structure for representing diffusion and degradation of the pollutant based on the plurality of target monitoring points; a first graph structure output module 820, configured to construct a first graph neural network corresponding to the first graph structure, and input the first graph structure into the first graph neural network, so as to output a third graph structure; a second graph structure output module 830, configured to construct a second graph neural network corresponding to the second graph structure, and input the second graph structure into the second graph neural network, so as to output a fourth graph structure; a fusion module 840, configured to perform feature extraction and fusion on the third graph structure and the fourth graph structure, and generate a first pollutant concentration feature vector corresponding to each target monitoring point; and a warning module 850, configured to input the first pollutant concentration feature vector into a pre-trained risk prediction model, determine a pollution degree corresponding to each target monitoring point, and determine whether to perform a warning based on the pollution degree corresponding to each target monitoring point.

[0141] Optionally, the warning module 850 includes: a pollution degree probability output module, configured to input the pollutant concentration feature vector into the pre-trained risk prediction model, and output a pollution degree probability corresponding to each target monitoring node; a judgment module, configured to judge whether the pollution degree probability corresponding to each target monitoring node is greater than a pre-set pollution degree threshold; and a warning submodule, configured to perform a warning in a case where the pollution degree probability is greater than the pollution degree threshold.

[0142] Optionally, the fusion module 840 includes: a first feature extraction module, configured to perform feature extraction on the third graph structure, and generate a second pollutant concentration feature vector corresponding to each target monitoring point; a second feature extraction module, configured to perform feature extraction on the fourth graph structure, and generate a third pollutant concentration feature vector corresponding to each target monitoring point; and a fusion submodule, configured to fuse the second pollutant concentration feature vector and the third pollutant concentration feature vector by using an MLP, so as to generate the first pollutant concentration feature vector.

[0143] Optionally, the graph structure generation module 810 includes: a first node determination module, configured to determine a plurality of nodes for generating the first graph structure based on the pre-set plurality of target monitoring points; a first edge determination module, configured to determine edges between adjacent nodes based on a first correlation relationship between the adjacent nodes, where the first correlation relationship is used to indicate a weight relationship and a water flow velocity relationship between the adjacent nodes; and a first graph structure generation module, configured to generate the first graph structure in a case where the plurality of nodes and the edges between the adjacent nodes are determined.

[0144] Optionally, the graph structure generation module 810 comprises: a second node generation module configured to determine a plurality of nodes for generating a second graph structure based on a plurality of target monitoring points preset; a second edge generation module configured to determine edges between adjacent nodes based on a second correlation relationship between the adjacent nodes, wherein the second correlation relationship is used to indicate a weight relationship and a distance between the adjacent nodes; and a second graph structure generation module configured to generate the second graph structure in a case where the plurality of nodes and the edges between the adjacent nodes are determined.

[0145] Optionally, the graph structure generation module 810 comprises: a pollution information extraction module configured to collect a remote sensing image corresponding to a target region, and extract pollution information corresponding to the target region from the remote sensing image by using a GIS system; and a target monitoring point determination module configured to determine the target monitoring points by using the GIS system and based on the pollution information.

[0146] Thus, according to the embodiment, the technical effect of being able to accurately predict the change of the pollution degree of the water environment and monitoring and warning according to the prediction result is achieved. Embodiment 3

[0147] Figure 9 A monitoring and warning device 900 for water environment pollution according to the embodiment is shown. The device 900 corresponds to the method according to Embodiment 1. Referring to Figure 9 As shown, the device 900 comprises: a processor 910; and a memory 920 connected with the processor 910, configured to provide the processor 910 with instructions for processing the following processing steps: determining a plurality of target monitoring points preset in a target region, and respectively generating a first graph structure for indicating migration of pollutants and a second graph structure for indicating diffusion and degradation of the pollutants based on the plurality of target monitoring points; constructing a first graph neural network corresponding to the first graph structure, and inputting the first graph structure into the first graph neural network, thereby outputting a third graph structure; constructing a second graph neural network corresponding to the second graph structure, and inputting the second graph structure into the second graph neural network, thereby outputting a fourth graph structure; performing feature extraction and fusion on the third graph structure and the fourth graph structure, and generating a first pollutant concentration feature vector corresponding to each target monitoring point; and inputting the first pollutant concentration feature vector into a pre-trained risk prediction model, determining a pollution degree corresponding to each target monitoring point, and determining whether to perform a warning based on the pollution degree corresponding to each target monitoring point.

[0148] Optionally, the operation of inputting the first pollutant concentration feature vector into the pre-trained risk prediction model to determine the pollution degree corresponding to each target monitoring point and determining whether to perform the early warning based on the pollution degree corresponding to each target monitoring point comprises: inputting the first pollutant concentration feature vector into the pre-trained risk prediction model and outputting a pollution degree probability corresponding to each target monitoring node; determining whether the pollution degree probability corresponding to each target monitoring node is greater than a pre-set pollution degree threshold; and performing the early warning in the case that the pollution degree probability is greater than the pollution degree threshold.

[0149] Optionally, the operation of performing feature extraction and fusion on the third graph structure and the fourth graph structure and generating the first pollutant concentration feature vector corresponding to each target monitoring point comprises: performing feature extraction on the third graph structure and generating a second pollutant concentration feature vector corresponding to each target monitoring point; performing feature extraction on the fourth graph structure and generating a third pollutant concentration feature vector corresponding to each target monitoring point; and performing fusion on the second pollutant concentration feature vector and the third pollutant concentration feature vector by using the MLP, thereby generating the first pollutant concentration feature vector.

[0150] Optionally, the operation of generating the first graph structure for representing the migration movement of the pollutant based on the plurality of target monitoring points comprises: determining a plurality of nodes for generating the first graph structure based on the pre-set plurality of target monitoring points; determining edges between adjacent nodes based on a first correlation relationship between the adjacent nodes, wherein the first correlation relationship is used to indicate a weight relationship and a water flow velocity relationship between the adjacent nodes; and generating the first graph structure in the case that the plurality of nodes and the edges between the adjacent nodes are determined.

[0151] Optionally, the operation of generating the second graph structure for representing the diffusion and degradation of the pollutant based on the plurality of target monitoring points comprises: determining a plurality of nodes for generating the second graph structure based on the pre-set plurality of target monitoring points; determining edges between adjacent nodes based on a second correlation relationship between the adjacent nodes, wherein the second correlation relationship is used to indicate a weight relationship and a distance between the adjacent nodes; and generating the second graph structure in the case that the plurality of nodes and the edges between the adjacent nodes are determined.

[0152] Optionally, the operation of determining the pre-set plurality of target monitoring points in the target region comprises: collecting a remote sensing image corresponding to the target region and extracting pollution information corresponding to the target region from the remote sensing image by using a GIS system; and determining the target monitoring points by using the GIS system and based on the pollution information.

[0153] Thus, according to the present embodiment, the technical effect of being able to accurately predict the change in the degree of water environmental pollution and monitoring and warning according to the prediction result is achieved.

[0154] The above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0155] In the above-mentioned embodiments of the present application, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0156] In several embodiments provided in the present application, it should be understood that the disclosed technical content can be implemented by other ways. Among them, the above-mentioned device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division way, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, units or modules, which can be electrical or other forms.

[0157] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the present embodiment scheme.

[0158] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be realized in the form of hardware or in the form of software functional unit.

[0159] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to make a computer device (which can be a personal computer, a server or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0160] The above is only the preferred embodiment of the present application, it should be pointed out that, for those skilled in the art, without departing from the principles of the present application, can make a number of improvements and refinements, these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A monitoring and early warning method for water environmental pollution, characterized in that, The method comprises the following steps: determining a plurality of target monitoring points in a target area, and generating a first graph structure for representing the migration of pollutants and a second graph structure for representing the diffusion and degradation of pollutants based on the plurality of target monitoring points, wherein the first graph structure comprises a plurality of nodes corresponding to the target monitoring points and edges between adjacent nodes, the edges of the first graph structure have directionality, indicating the direction of water flow between adjacent nodes, and the edges of the first graph structure are also related to the weight relationship and the speed of water flow between adjacent nodes, and the second graph structure also comprises a plurality of nodes corresponding to the target monitoring points and edges between adjacent nodes, the edges of the second graph structure have no directionality and are related to the weight relationship and distance between adjacent nodes, wherein the operation of generating the first graph structure for representing the migration of pollutants based on the plurality of target monitoring points comprises: determining a plurality of nodes for generating the first graph structure based on the plurality of target monitoring points; determining the edges between adjacent nodes based on a first correlation relationship between the adjacent nodes, wherein the first correlation relationship is used to indicate the weight relationship and the water flow speed relationship between the adjacent nodes; and generating the first graph structure after determining the plurality of nodes and the edges between adjacent nodes, and wherein the operation of generating the second graph structure for representing the diffusion and degradation of pollutants based on the plurality of target monitoring points comprises: determining a plurality of nodes for generating the second graph structure based on the plurality of target monitoring points; determining the edges between adjacent nodes based on a second correlation relationship between the adjacent nodes, wherein the second correlation relationship is used to indicate the weight relationship and the distance between the adjacent nodes; and generating the second graph structure after determining the plurality of nodes and the edges between adjacent nodes; constructing a first graph neural network corresponding to the first graph structure, and inputting the first graph structure into the first graph neural network to output a third graph structure; constructing a second graph neural network corresponding to the second graph structure, and inputting the second graph structure into the second graph neural network to output a fourth graph structure; performing feature extraction and fusion on the third graph structure and the fourth graph structure, and generating a first pollutant concentration feature vector corresponding to each target monitoring point; and inputting the first pollutant concentration feature vector into a pre-trained risk prediction model to determine the pollution degree corresponding to each target monitoring point, and determining whether to issue a warning based on the pollution degree corresponding to each target monitoring point.

2. The method of claim 1, wherein, The operation of inputting the first pollutant concentration feature vector into a pre-trained risk prediction model to determine the pollution degree corresponding to each target monitoring point, and determining whether to issue a warning based on the pollution degree corresponding to each target monitoring point, comprises: inputting the first pollutant concentration feature vector into a pre-trained risk prediction model, and outputting a pollution degree probability corresponding to each target monitoring node; determining whether the pollution degree probability corresponding to each target monitoring node is greater than a pre-set pollution degree threshold; and in the case that the pollution degree probability is greater than the pollution degree threshold, performing a pre-warning.

3. The method of claim 2, wherein, The operation of performing feature extraction and fusion on the third graph structure and the fourth graph structure, and generating a first pollutant concentration feature vector corresponding to each target monitoring node, includes: performing feature extraction on the third graph structure, and generating a second pollutant concentration feature vector corresponding to each target monitoring node; performing feature extraction on the fourth graph structure, and generating a third pollutant concentration feature vector corresponding to each target monitoring node; and fusing the second pollutant concentration feature vector and the third pollutant concentration feature vector by using an MLP, so as to generate the first pollutant concentration feature vector.

4. The method of claim 3, wherein, The operation of determining a plurality of target monitoring points pre-set in a target region includes: collecting a remote sensing image corresponding to the target region, and extracting pollution information corresponding to the target region from the remote sensing image by using a GIS system; and determining the target monitoring points by using the GIS system and based on the pollution information.

5. A storage medium, characterized by The storage medium includes a stored program, wherein the program is executed by a processor when the program is running to perform the method of any one of claims 1 to 4.

6. A monitoring and early warning device for water environmental pollution, characterized in that, includes: The graph structure generation module is configured to determine a plurality of target monitoring points pre-set in a target region, and generate a first graph structure for representing migration of a pollutant and a second graph structure for representing diffusion and degradation of the pollutant based on the plurality of target monitoring points, wherein the first graph structure includes a plurality of nodes corresponding to each target monitoring point and edges between adjacent nodes, the edges of the first graph structure have directionality for indicating a direction of water flow between adjacent nodes, and the edges of the first graph structure are also related to a weight relationship between adjacent nodes and a speed of water flow, and the second graph structure also includes a plurality of nodes corresponding to each target monitoring point and edges between adjacent nodes, the edges of the second graph structure do not have directionality and are related to a weight relationship and a distance between adjacent nodes, wherein the graph structure generation module includes: a first node determination module configured to determine a plurality of nodes for generating the first graph structure based on the plurality of target monitoring points pre-set; a first edge determination module configured to determine edges between adjacent nodes based on a first correlation relationship between the adjacent nodes, wherein the first correlation relationship is used to indicate a weight relationship and a water flow speed relationship between the adjacent nodes; and a first graph structure generation module configured to generate the first graph structure in the case that the plurality of nodes and the edges between adjacent nodes are determined, and wherein The graph structure generation module comprises: a second node generation module configured to determine a plurality of nodes for generating the second graph structure based on a plurality of preset target monitoring points; a second edge generation module configured to determine edges between adjacent nodes based on a second correlation relationship between the adjacent nodes, wherein the second correlation relationship is used to indicate a weight relationship and a distance between the adjacent nodes; and a second graph structure generation module configured to generate the second graph structure based on the plurality of nodes and the edges between the adjacent nodes. a first graph structure output module configured to construct a first graph neural network corresponding to the first graph structure, and input the first graph structure into the first graph neural network, so as to output a third graph structure; a second graph structure output module configured to construct a second graph neural network corresponding to the second graph structure, and input the second graph structure into the second graph neural network, so as to output a fourth graph structure; a fusion module configured to perform feature extraction and fusion on the third graph structure and the fourth graph structure, and generate a first pollutant concentration feature vector corresponding to each target monitoring point; and 7. The apparatus of claim 6, wherein, a warning module configured to input the first pollutant concentration feature vector into a pre-trained risk prediction model, determine a pollution degree corresponding to each target monitoring point, and determine whether to perform a warning based on the pollution degree corresponding to each target monitoring point. The warning module comprises: a pollution degree probability output module configured to input the first pollutant concentration feature vector into a pre-trained risk prediction model, and output a pollution degree probability corresponding to each target monitoring node; a judgment module configured to determine whether the pollution degree probability corresponding to each target monitoring node is greater than a preset pollution degree threshold; 8. A monitoring and early warning device for water environmental pollution, characterized in that, a warning submodule configured to perform a warning in a case where the pollution degree probability is greater than the pollution degree threshold. comprise: a processor; and a memory connected with the processor, configured to provide the processor with instructions for processing the following processing steps: determine a plurality of preset target monitoring points in a target area, and generate a first graph structure for representing pollutant migration and a second graph structure for representing pollutant diffusion and degradation based on the plurality of target monitoring points, wherein the first graph structure comprises a plurality of nodes corresponding to each target monitoring point and edges between adjacent nodes, the edges of the first graph structure have directionality, are used to indicate the direction of water flow between adjacent nodes, and are also related to the weight relationship and the speed of water flow between adjacent nodes, and the second graph structure also comprises a plurality of nodes corresponding to each target monitoring point and edges between adjacent nodes, the edges of the second graph structure have no directionality and are related to the weight relationship and the distance between adjacent nodes, wherein the operation of generating the first graph structure for representing pollutant migration based on the plurality of target monitoring points comprises: determine a plurality of nodes for generating the first graph structure based on a plurality of preset target monitoring points; determine edges between the plurality of nodes and the respective adjacent nodes based on the first association relationship, wherein the first association relationship is used to indicate a weight relationship and a water flow velocity relationship between the respective adjacent nodes; and generate the first graph structure in a case where the edges between the plurality of nodes and the respective adjacent nodes are determined, and wherein operations of generating a second graph structure for representing pollutant diffusion and degradation based on a plurality of target monitoring points include: determine a plurality of nodes for generating the second graph structure based on a plurality of target monitoring points; determine edges between the plurality of nodes and the respective adjacent nodes based on the second association relationship, wherein the second association relationship is used to indicate a weight relationship and a distance between the respective adjacent nodes; and generate the second graph structure in a case where the edges between the plurality of nodes and the respective adjacent nodes are determined; construct a first graph neural network corresponding to the first graph structure, and input the first graph structure into the first graph neural network, thereby outputting a third graph structure; construct a second graph neural network corresponding to the second graph structure, and input the second graph structure into the second graph neural network, thereby outputting a fourth graph structure; perform feature extraction and fusion on the third graph structure and the fourth graph structure, and generate a first pollutant concentration feature vector corresponding to each target monitoring point; and input the first pollutant concentration feature vector into a pre-trained risk prediction model, determine a pollution degree corresponding to each target monitoring point, and determine whether to perform early warning based on the pollution degree corresponding to each target monitoring point.

Images