Monitoring node deployment optimization method and device

Abstract

The invention discloses a monitoring node deployment optimization method and device, and relates to the technical field of environment monitoring, and the method comprises the steps: obtaining the component data and attribute data of pollutants at each pollution source discharge port in a monitoring region, constructing a pollution source feature vector according to the component data and the attribute data, and carrying out the deployment optimization of a monitoring node based on the pollution source feature vector, the method comprises the steps of determining source tracing affiliation of pollutants, generating a pollution responsibility map according to the source tracing affiliation, determining a responsibility allocation coefficient of each pollution source based on the pollution responsibility map, determining a Nash equilibrium value of each monitoring node based on the responsibility allocation coefficient and an initial monitoring node deployment strategy, and optimizing the initial monitoring node deployment strategy according to the Nash equilibrium value. And generating a target monitoring node deployment scheme. By means of the mode, the technical problem that the monitoring effect is poor due to the fact that dynamic changes of pollution sources are difficult to adapt in the prior art is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of environmental monitoring, and particularly relates to a monitoring node deployment optimization method and device. BACKGROUND

[0002] There are mainly two deployment modes of environmental monitoring nodes: one is to adopt a uniform deployment mode with fixed intervals, which is simple and easy to implement but leads to excessive number of monitoring nodes, high deployment cost, and easy redundancy of a large number of nodes and waste of resources when pollution sources are unevenly distributed or dynamically change; the other is targeted deployment based on a pollution diffusion model, which relies on a high-precision physical or statistical model to predict the diffusion path of pollutants, but in actual application, the model accuracy is easily affected by environmental factors, leading to poor dynamic adaptability and difficulty in responding to sudden or mobile pollution sources in a timely manner, so that the monitoring network cannot effectively control the cost and is difficult to guarantee the continuous and reliable coverage of key areas.

[0003] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0004] The main purpose of the present application is to provide a monitoring node deployment optimization method and device, aiming to solve the technical problem of poor monitoring effect caused by difficulty in adapting to dynamic changes of pollution sources in the prior art.

[0005] To achieve the above-mentioned purpose, the present application provides a monitoring node deployment optimization method, which comprises the following steps: obtaining component data and attribute data of pollutants at emission ports of each pollution source in a monitoring area, and constructing a pollution source feature vector according to the component data and the attribute data; determining the source attribution of the pollutants based on the pollution source feature vector, and generating a pollution responsibility map according to the source attribution; determining a responsibility allocation coefficient of each pollution source based on the pollution responsibility map, and determining a Nash equilibrium value of each monitoring node based on the responsibility allocation coefficient and an initial monitoring node deployment strategy; optimizing the initial monitoring node deployment strategy according to the Nash equilibrium value, and generating a target monitoring node deployment scheme.

[0006] In an embodiment, the step of obtaining component data and attribute data of pollutants at emission ports of each pollution source in a monitoring area, and constructing a pollution source feature vector according to the component data and the attribute data comprises: obtaining component data, attribute data and spectral data at emission ports of each pollution source in a monitoring area, and obtaining an original spectral data set according to the spectral data; performing principal component analysis on the original spectrum data set to obtain a principal spectrum feature component; vectorizing and fusing the principal spectrum feature component, the component data and the attribute data to generate a pollution source feature vector.

[0007] In an embodiment, the step of determining the source attribution of the pollutant based on the pollution source feature vector includes: training a random forest classifier based on a sample set of pollution source feature vectors with known attributions to obtain a pollutant source tracing model; inputting the pollution source feature vector into the pollutant source tracing model to obtain the source attribution of the pollutant, and determining a probability prediction result of each pollution source based on the source attribution; based on the probability prediction result, simulating the propagation trajectory and concentration distribution of the pollutant in the spatio-temporal range; determining the pollution contribution degree of different geographical units in the monitoring area according to the propagation trajectory and the concentration distribution, and generating a pollution responsibility map according to the contribution degree.

[0008] In an embodiment, the step of determining the responsibility allocation coefficient of each pollution source based on the pollution responsibility map includes: According to the pollution responsibility map, the cumulative contribution of each pollution source identified as the main contributor of the pollutant in the environment in a preset historical period is counted; weighting and fusing the cumulative contribution and the real-time emission flow of the corresponding pollution source to obtain the absolute pollution contribution degree; determining the responsibility allocation coefficient according to the absolute pollution contribution degree of all pollution sources.

[0009] In an embodiment, the step of determining the Nash equilibrium value of each monitoring node based on the responsibility allocation coefficient and the initial monitoring node deployment strategy includes: According to each pollution source in the monitoring area and the responsibility allocation coefficient, a non-cooperative game model is constructed with the pollution source as the participant and with the strategy of deploying or not deploying a monitoring node; According to the deployment cost, the actual cost adjusted by the responsibility allocation coefficient, the change of pollution exposure risk and the cooperative governance benefit, the payoff function of each participant is obtained; According to the initial monitoring node deployment strategy, the initial strategy combination of the non-cooperative game model is set; According to the response iteration algorithm and the payoff function, the initial strategy combination is updated to obtain the Nash equilibrium state and the corresponding Nash equilibrium value of the stable strategy of all participants.

[0010] In an embodiment, the step of obtaining a benefit function of each participant according to the deployment cost, the actual cost adjusted by the responsibility allocation coefficient, the pollution exposure risk change, and the synergistic governance benefit comprises: obtaining, according to an effective monitoring radius of a monitoring node, a set of other participants within a monitoring coverage of the monitoring node when any participant deploys a node; obtaining, according to the pollution responsibility map, a responsibility allocation proportion of the participant deploying the node to pollution of other participants in the set of other participants; obtaining, according to a preset synergistic weight coefficient and the responsibility allocation proportion, a synergistic governance benefit value of the participant due to deployment of the node; obtaining a benefit function of each participant according to the deployment cost, the actual cost adjusted by the responsibility allocation coefficient, the pollution exposure risk change, and the synergistic governance benefit value.

[0011] In an embodiment, the step of optimizing the initial monitoring node deployment strategy according to the Nash equilibrium value to generate a target monitoring node deployment scheme comprises: determining, according to the Nash equilibrium value, a synergistic and competitive relationship between initial monitoring nodes in the initial monitoring node deployment strategy in terms of pollution monitoring responsibility; based on the synergistic and competitive relationship and the pollution responsibility map, evaluating a monitoring redundant area and a monitoring blind area existing in the initial monitoring node deployment strategy to obtain an evaluation result; determining, according to the evaluation result, a redundant node identifier to be removed, a node position suggestion to be added, and a monitoring parameter optimization amplitude of an existing node, and generating an adjustment instruction according to the redundant node identifier to be removed, the node position suggestion to be added, and the monitoring parameter optimization amplitude of the existing node; adjusting the initial monitoring node deployment strategy based on the adjustment instruction to generate a target monitoring node deployment scheme.

[0012] In an embodiment, after the step of optimizing the initial monitoring node deployment strategy according to the Nash equilibrium value to generate a target monitoring node deployment scheme, the method further comprises: determining, according to the target monitoring node deployment scheme, a coverage degree of a key sensitive area and a monitoring coverage rate of all pollution sources; comparing, according to a preset coverage threshold and the coverage degree and the monitoring coverage rate, to obtain a comparison result; when the comparison result meets an adjustment requirement, recalculating a Nash equilibrium value by adjusting a game parameter or adding a fixed node and recalculating a Nash equilibrium value; updating the target monitoring node deployment according to the updated Nash equilibrium value.

[0013] In an embodiment, the method further comprises: According to the latest environmental data collected periodically, an updated pollution responsibility map and an updated responsibility allocation coefficient are obtained; According to the updated responsibility allocation coefficient, an updated game model revenue function is obtained; According to the updated revenue function, Nash equilibrium is recalculated to obtain a recalculated Nash equilibrium value, and a dynamically adjusted target monitoring node deployment scheme is obtained according to the recalculated Nash equilibrium value and the updated pollution responsibility map.

[0014] In addition, to achieve the above-mentioned purposes, the present application also provides a monitoring node deployment optimization device, which comprises: A feature vector construction module is configured to obtain composition data and attribute data of pollutants at discharge outlets of each pollution source in a monitoring area, and to construct a pollution source feature vector according to the composition data and the attribute data; A responsibility map generation module is configured to determine the source attribution of the pollutants based on the pollution source feature vector, and to generate a pollution responsibility map based on the source attribution; A responsibility game calculation module is configured to determine the responsibility allocation coefficient of each pollution source based on the pollution responsibility map, and to determine the Nash equilibrium value of each monitoring node based on the responsibility allocation coefficient and an initial monitoring node deployment strategy; A deployment scheme determination module is configured to optimize the initial monitoring node deployment strategy according to the Nash equilibrium value, and to generate a target monitoring node deployment scheme.

[0015] In addition, to achieve the above-mentioned purposes, the present application also provides a monitoring node deployment optimization device, which comprises:

[0016] In addition, to achieve the above-mentioned purposes, the present application also provides a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program, which is executed by a processor to implement the steps of the monitoring node deployment optimization method as described above.

[0017] In addition, to achieve the above-mentioned purposes, the present application also provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the steps of the monitoring node deployment optimization method as described above.

[0018] The application provides a monitoring node deployment optimization method, which comprises the following steps: acquiring component data and attribute data of pollutants at emission outlets of each pollution source in a monitoring area; constructing a pollution source feature vector according to the component data and the attribute data; determining the source attribution of the pollutants based on the pollution source feature vector; generating a pollution responsibility graph based on the source attribution; determining a responsibility allocation coefficient of each pollution source based on the pollution responsibility graph; determining a Nash equilibrium value of each monitoring node based on the responsibility allocation coefficient and an initial monitoring node deployment strategy; optimizing the initial monitoring node deployment strategy according to the Nash equilibrium value; and generating a target monitoring node deployment scheme. In this way, the technical problem that the monitoring effect is poor due to the difficulty in adapting to the dynamic changes of pollution sources in the prior art is solved. BRIEF DESCRIPTION OF DRAWINGS

[0019] The accompanying drawings, which are incorporated herein and form a part of the specification, illustrate embodiments consistent with the present application and, together with the description, further serve to explain the principles of the application.

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings required to be used in the embodiments or prior art description will be briefly introduced. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without any creative effort.

[0021] Figure 1 A flowchart of the monitoring node deployment optimization method of the first embodiment of the present application; Figure 2 A pollution responsibility graph of the first embodiment of the monitoring node deployment optimization method of the present application; Figure 3 A module structure diagram of the monitoring node deployment optimization device of the embodiment of the present application; Figure 4 A device structure diagram of the hardware running environment involved in the monitoring node deployment optimization method in the embodiment of the present application.

[0022] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0023] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application, and are not used to limit the present application.

[0024] In order to better understand the technical solutions of the present application, the following will be described in detail in combination with the accompanying drawings and specific embodiments.

[0025] The main solution of the embodiment of the application is: obtaining composition data and attribute data of pollutants at emission outlets of each pollution source in a monitoring area, constructing a pollution source feature vector according to the composition data and the attribute data; Based on the pollution source feature vector, determining the source attribution of the pollutants, and generating a pollution responsibility graph according to the source attribution; Based on the pollution responsibility graph, determining a responsibility allocation coefficient of each pollution source, and determining a Nash equilibrium value of each monitoring node based on the responsibility allocation coefficient and an initial monitoring node deployment strategy; According to the Nash equilibrium value, optimizing the initial monitoring node deployment strategy to generate a target monitoring node deployment scheme.

[0026] At present, there are mainly two deployment methods for environmental monitoring nodes: one is to uniformly deploy at a fixed interval, which is simple and easy to implement but leads to excessive number of monitoring nodes, high deployment cost, and easy to cause a large number of node redundancies and resource waste when the distribution of pollution sources is uneven or dynamically changes; the other is to perform targeted deployment based on a pollution diffusion model, which relies on a high-precision physical or statistical model to predict the diffusion path of pollutants, but in actual application, the model accuracy is easily affected by environmental factors, resulting in poor dynamic adaptability and difficulty in responding to sudden or mobile pollution sources in time, so that the monitoring network cannot effectively control the cost and is difficult to guarantee the continuous and reliable coverage of key areas.

[0027] The application provides a solution, which obtains composition data and attribute data of pollutants at emission outlets of each pollution source in a monitoring area, constructs a pollution source feature vector according to the composition data and the attribute data, determines the source attribution of the pollutants based on the pollution source feature vector, generates a pollution responsibility graph according to the source attribution, determines a responsibility allocation coefficient of each pollution source based on the pollution responsibility graph, determines a Nash equilibrium value of each monitoring node based on the responsibility allocation coefficient and an initial monitoring node deployment strategy, optimizes the initial monitoring node deployment strategy according to the Nash equilibrium value, and generates a target monitoring node deployment scheme. Through the above method, the technical problem of poor monitoring effect caused by difficulty in adapting to dynamic changes of pollution sources in the prior art is solved.

[0028] It should be noted that the execution subject of the embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a monitoring node deployment optimization device, etc., and the embodiment does not make specific limitation thereon. The embodiment and each of the following embodiments will be described below taking the monitoring node deployment optimization device as an example.

[0029] All actions of obtaining signals, information or data in this application are carried out in compliance with the corresponding data protection regulations and policies of the country where the device is located, and with the authorization given by the corresponding device owner.

[0030] The embodiment of the present application provides a monitoring node deployment optimization method, which refers to Figure 1 , Figure 1 FIG. 1 is a flowchart of a first embodiment of the monitoring node deployment optimization method of the present application.

[0031] In the embodiment, the monitoring node deployment optimization method comprises steps S10-S40: Step S10, obtain the composition data and attribute data of pollutants at the emission port of each pollution source in the monitoring area, and construct a pollution source feature vector according to the composition data and the attribute data.

[0032] It should be noted that the monitoring area refers to a geographical range for real-time environmental monitoring, which is a physical space boundary for deploying a monitoring network, evaluating environmental quality and tracing pollution responsibility, and is delimited according to management needs. The pollution source emission port refers to a specific location or channel through which pollutants are directly or indirectly discharged from a pollution source to the environment. For example, a chimney, a sewage pipe of a factory, and a water outlet of a sewage treatment plant. The composition data refers to data about the chemical or physical composition characteristics of the pollutants, which describes the types, concentrations, isotope ratios, and characteristic spectral fingerprints of the pollutants. The attribute data refers to background information and static feature data related to the pollution source, which usually includes the geographical coordinates of the pollution source and the type of the enterprise to which the pollution source belongs.

[0033] It can be understood that the accurate composition data of the pollutants, such as the concentration and proportion of specific chemical substances (such as benzene series and heavy metal ions), are first obtained through online monitoring equipment deployed at the emission port, such as a mass spectrometer, a chromatograph or periodic sampling laboratory analysis. At the same time, attribute data related to the inherent characteristics of the pollution source, such as the industry to which the enterprise belongs, the production process, the raw material information, and the status of the treatment facility, are collected. Thereafter, the heterogeneous data is standardized and dimensionally reduced by using feature engineering methods, such as principal component analysis PCA to remove redundancy or one-hot encoding processing of classification attributes, and finally the processed feature values are combined into a unified and high-distinguishability pollution source feature vector according to the weights.

[0034] In a feasible implementation manner, the step of obtaining the composition data and attribute data of pollutants at the emission port of each pollution source in the monitoring area, and constructing a pollution source feature vector according to the composition data and the attribute data comprises: Obtain the composition data, attribute data and spectrum data at the emission port of each pollution source in the monitoring area, and obtain an original spectrum data set according to the spectrum data; After preprocessing the original spectral dataset, principal component analysis is performed to obtain principal spectral feature components; The principal spectral feature components, the component data, and the attribute data are vectorized and fused to generate a pollution source feature vector.

[0035] In a specific implementation, it is assumed that there are pollution sources in the monitoring area. For each pollution source , sampling is performed at its discharge port times. Each sampling obtains a spectrum containing wavelength or wave number point intensity values. Therefore, for a pollution source , a spectral data matrix can be obtained. The spectral data of all pollution sources together constitute an original spectral dataset . The component data is denoted by a vector , where represents the number of characteristic pollution species of interest (such as the concentrations of SO2, NOx, and specific VOCs). The attribute data is denoted by a vector . Where q represents the attribute dimension (such as longitude, latitude, emission amount, industry category code, etc.).

[0036] Each spectrum in the original spectral dataset S is preprocessed to eliminate noise and baseline drift. Savitzky-Golay filtering is used. For a discrete spectral signal , the filtered value at wavelength point j is calculated by linear combination of the original values in the neighborhood window: , where w is the half window width, is the coefficient determined by the fitting polynomial. Subsequently, normalization is performed, such as minimum-maximum normalization: , so that all intensity values fall within the interval [0, 1]. The preprocessed spectral data matrix is denoted by , where N = n * t is the total number of samples. PCA dimensionality reduction is performed on the preprocessed spectral matrix X to extract principal components that best represent spectral differences and reduce data redundancy. The column mean vector μ of matrix X is calculated, and then the centralized matrix is obtained (where 1 is a column vector of all 1s), and the covariance matrix is calculated. The covariance matrix Σ is decomposed: . Where Λ is a diagonal matrix composed of eigenvalues , and the column vectors of V are the corresponding eigenvectors (i.e., principal component directions). The original spectral data is projected onto the first k principal component directions to obtain the reduced principal spectral feature component matrix Z, , where each row is a k-dimensional principal component score vector of a sample The principal component score vector, the component data vector and the attribute data vector of each sample are spliced to generate a final feature vector, and the fusion vector is a pollution source feature vector representing the sample, which integrates the spectral fingerprint, chemical composition and source feature attribute of the pollutant, and provides comprehensive input information for subsequent source tracing models.

[0037] In step S20, the source of the pollutant is determined based on the pollution source feature vector, and a pollution responsibility map is generated based on the source of the pollutant.

[0038] It should be noted that the source of the pollutant refers to the process and result of matching and dividing a pollutant sample from an unknown source to one or more known pollution sources in the monitoring area with the highest probability through model calculation. The pollution responsibility map is a visual decision support tool that visually displays the source tracing relationship and responsibility weight between the pollutant sample and the potential pollution source in a graphical manner. The migration and diffusion path of the pollutant and the contribution rate of each pollution source can be clearly presented on the map, providing a clear basis for environmental law enforcement and precise pollution control.

[0039] It can be understood that in the model training stage, the system uses a pollution source feature vector dataset with labeled attribution sources to train a classification model. When a newly detected unknown pollutant needs to be analyzed, the system first constructs a feature vector and then inputs it into the trained model. The model calculates the probability distribution of the sample belonging to each known pollution source, which is the quantitative result of the source of the pollutant. Refer to Figure 2 , Figure 2 The pollution responsibility map is shown in the figure. Finally, the system automatically generates a dynamic pollution responsibility map based on the attribution probability, concentration, geographical location and other information of the pollutant, and visually maps the responsibility size and path relationship of each pollution source on the map using different colors, line thicknesses or area sizes, so as to realize rapid and accurate determination and display of pollution responsibility.

[0040] In a feasible implementation, the step of determining the source of the pollutant based on the pollution source feature vector and generating a pollution responsibility map based on the source of the pollutant includes: training a random forest classifier based on a known attribution pollution source feature vector sample set to obtain a pollutant source tracing model; inputting the pollution source feature vector into the pollutant source tracing model to obtain the source of the pollutant, and determining the probability prediction result of each pollution source based on the source of the pollutant; based on the probability prediction result, simulating the propagation trajectory and concentration distribution of the pollutant in the space-time range; According to the propagation trajectory and the concentration distribution, a pollution contribution degree of different geographical units in a monitoring area is determined, and a pollution responsibility map is generated according to the contribution degree.

[0041] In a specific implementation, first, a pre-constructed knowledge base is relied on, that is, a large number of pollutant feature vectors known to be derived from a specific emission port are used as training samples to teach the random forest classifier to learn the unique characteristic patterns of different pollution sources, thereby forming a mature pollutant tracing model. When a newly captured unknown pollutant needs to be traced, the system inputs the corresponding feature vector of the pollutant into the model, and the model makes a collective decision through its internal numerous decision trees, and finally outputs a probability prediction result, which quantifies the possibility of the pollutant belonging to each known pollution source in the region. Subsequently, the system combines meteorological data, terrain information, and atmospheric diffusion models to simulate the propagation path and concentration decay distribution of the pollutant from the suspected source emission port within a specific time and space range. Finally, by superimposing the simulated concentration distribution map with administrative divisions or grid-based geographical units, the system calculates the proportion of pollution caused by each pollution source in each geographical unit, that is, the pollution contribution degree, and automatically generates a visualization map based on this, which clearly and intuitively shows the origin and development of the pollutant and the spatial distribution of the responsibility of each pollution source, that is, the pollution responsibility map.

[0042] In step S30, a responsibility allocation coefficient of each pollution source is determined based on the pollution responsibility map, and a Nash equilibrium value of each monitoring node is determined based on the responsibility allocation coefficient and an initial monitoring node deployment strategy.

[0043] It should be noted that the responsibility allocation coefficient refers to a proportional value obtained by quantifying the contribution degree of each pollution source to the overall pollution or a specific exceedance event based on the pollution responsibility map through a specific algorithm. This coefficient converts the probability result of pollution attribution into a specific numerical value that can be used for responsibility definition, cost accounting, or performance evaluation, and the sum of the responsibility allocation coefficients of all pollution sources is usually 1. The initial monitoring node deployment strategy refers to a pre-planned spatial layout scheme of monitoring points in the monitoring area, which clearly defines the geographical location and monitoring range of each monitoring node. This strategy may be an initial deployment state determined based on experience, administrative divisions, or preliminary risk assessment. The Nash equilibrium value is used to evaluate whether the current location strategy of a single monitoring node has reached the optimal state when the positions of other monitoring nodes remain unchanged. Specifically, when the Nash equilibrium value of a monitoring node reaches a certain threshold, it means that deploying monitoring equipment at this point can maximize its monitoring efficiency, and no unilateral change in position can bring greater benefits, indicating that the deployment strategy tends to be stable and effective.

[0044] It can be understood that, first, according to the pollution responsibility atlas, the pollution contribution proportion of each pollution source to one or more concerned areas, that is, the responsibility allocation coefficient, is calculated; then, the system regards each monitoring node as a rational decision maker, evaluates the pollution risk caused by each pollution source that can be effectively monitored by the monitoring node based on its location under the current initial deployment strategy, and calculates the Nash equilibrium value of the monitoring efficiency of the monitoring node, which is used to judge whether the current node layout has achieved the optimal monitoring efficiency under the given cost, or to identify which nodes need to adjust the position to achieve a more balanced and efficient global monitoring state, providing a quantitative basis for subsequent optimization.

[0045] In a feasible implementation, the step of determining the responsibility allocation coefficient of each pollution source based on the pollution responsibility atlas comprises: According to the pollution responsibility atlas, the cumulative contribution of each pollution source identified as the main contributor of pollutants in the environment within a preset historical period is counted; The cumulative contribution and the real-time emission flow of the corresponding pollution source are weighted and fused to obtain the absolute pollution contribution degree; The responsibility allocation coefficient is determined according to the absolute pollution contribution degree of all pollution sources.

[0046] In a specific implementation, first, all records of the pollution responsibility atlas within a preset historical period are called, and the total number or total contribution of each pollution source identified as the main contributor of pollutants in the environment during this period is calculated by data aggregation technology to form a historical responsibility file. Subsequently, the system accesses real-time emission monitoring data of each pollution source, and after standardizing the historical cumulative contribution and the real-time emission flow, which represent the past responsibility and the current activity level respectively, the two indicators are fused and calculated by a preset weight to generate an absolute pollution contribution degree for a more comprehensive evaluation of the impact of pollution sources. Finally, the absolute pollution contribution degrees of all pollution sources are normalized so that the sum of the contribution degree values of each pollution source is one, thereby obtaining the responsibility allocation coefficient for quantitatively dividing the specific responsibility proportion.

[0047] In a feasible implementation, the step of determining the Nash equilibrium value of each monitoring node based on the responsibility allocation coefficient and the initial monitoring node deployment strategy comprises: According to the pollution sources in the monitoring area and the responsibility allocation coefficient, a non-cooperative game model is constructed with the pollution sources as participants and the deployment or non-deployment of monitoring nodes as strategies; According to the deployment cost, the actual cost adjusted by the responsibility allocation coefficient, the change of pollution exposure risk, and the benefit of collaborative governance, the benefit function of each participant is obtained; According to the initial monitoring node deployment strategy, the initial strategy combination of the non-cooperative game model is set; According to the response iteration algorithm and the benefit function, the initial strategy combination is updated to obtain a Nash equilibrium state of all participants and a corresponding Nash equilibrium value.

[0048] In a specific implementation, first, the entire monitoring area is defined as a game arena, where each pollution source is regarded as an independent rational participant, and the strategy selection they face is to deploy or not to deploy a monitoring node at their location. Then the system constructs a benefit function for each participant, which is a comprehensive calculation model that not only considers the direct hardware and operation and maintenance costs of deploying a node, but also uses the responsibility allocation coefficient of the pollution source to weight the cost to reflect the principle that the greater the responsibility, the higher the governance investment should be. At the same time, the function also takes into account the reduced potential pollution exposure risk due to monitoring and the global governance benefits brought by the cooperation of multiple nodes. Next, the system sets the initial selection state of each participant according to the initial monitoring node deployment strategy. Finally, the system starts a response iteration algorithm that simulates the decision-making process in reality, allowing each participant to switch to a strategy that brings them higher benefits based on the current strategies of other participants. After multiple iterations, the entire system will reach a stable Nash equilibrium state, at which point no pollution source can obtain additional benefits by changing its deployment decision unilaterally, and the benefit value obtained by each participant at this time is the Nash equilibrium value under the system state.

[0049] Specifically, the pollution sources in the region are taken as game parties, and the deployment of monitoring nodes is taken as game strategies. A strategy space is created, where D represents "deploy a monitoring node", and U represents "do not deploy".

[0050] The benefit function of participant i considers the deployment cost, pollution exposure risk, and responsibility allocation mechanism:

[0051] Therefore, the benefit function can be defined as:

[0052] : Node deployment cost; : Pollution responsibility allocation coefficient, calculated based on historical emissions of the enterprise and pollution contribution.

[0053] : Pollution exposure risk of enterprise i when it does not deploy a monitoring node, related to the coverage range of the monitoring node. If enterprise i deploys a node , the pollution exposure risk of other enterprises within the coverage radius of the node is reduced, ; if it does not deploy , , is the number of non-covered pollution sources in the periphery, and N is the total number of pollution sources.

[0054] is the responsibility sharing effect of the other enterprise deployment nodes on enterprise i; is the pollution responsibility sharing ratio of the enterprise j deployment node on enterprise i; is the responsibility coordination weight coefficient, reflecting the benefit of inter-enterprise coordination management; , and .

[0055] In a feasible implementation, the step of obtaining the benefit function of each participant according to the deployment cost, the actual cost adjusted by the responsibility sharing coefficient, the pollution exposure risk change, and the coordination management benefit includes: obtaining, according to the effective monitoring radius of the monitoring node, a set of other participants within the monitoring coverage of the monitoring node when any participant deploys a node; obtaining, according to the pollution responsibility map, the responsibility sharing ratio of the participant deploying a node to the pollution of other participants in the set of other participants; obtaining, according to the preset coordination weight coefficient and the responsibility sharing ratio, the coordination management benefit value generated by the participant due to the deployment of a node; obtaining the benefit function of each participant according to the deployment cost, the actual cost adjusted by the responsibility sharing coefficient, the pollution exposure risk change, and the coordination management benefit value.

[0056] In a specific implementation, first, geographical spatial analysis is performed according to the effective monitoring radius of each monitoring node. When a pollution source selects to deploy a node, the system automatically identifies all other pollution sources that can be covered by the node monitoring range through map calculation, forming a coordination monitoring set of the deployer. Subsequently, the system traces back the pollution responsibility map to analyze the responsibility ratio of the deployer for the pollution caused by other pollution sources in the set. Then, the system introduces a preset coordination weight coefficient, which represents the policy inclination to encourage joint management, and multiplies it by the responsibility ratio of the management object, thereby quantifying the additional coordination management benefit value obtained by the participant due to the deployment of a node to assist in the management of others. Finally, the system comprehensively operates this coordination management benefit value with the direct cost of deployment, the actual burden cost adjusted according to the responsibility sharing coefficient of the participant, and the local pollution exposure risk value reduced due to monitoring coverage, to construct a personalized benefit function that comprehensively reflects economic cost, individual risk, and social benefit.

[0057] Step S40, optimizing the initial monitoring node deployment strategy according to the Nash equilibrium value, and generating a target monitoring node deployment scheme.

[0058] It can be understood that the strategy combination corresponding to the Nash equilibrium state is compared and analyzed with the initial strategy, and those node positions that are preferentially selected for deployment by the participants in the equilibrium state are identified, which usually represent the optimal choice after balancing the cost, responsibility and risk. Based on this analysis, the system will automatically adjust the initial strategy, such as retaining high-yield nodes, replacing low-efficiency nodes or reallocating resources, so as to generate a target monitoring node deployment scheme that is more efficient, more stable and lacks unilateral deviation motivation for all pollution sources, which ensures the monitoring effect while optimizing the overall system cost and maximizing the governance benefit.

[0059] In a feasible implementation, the step of optimizing the initial monitoring node deployment strategy according to the Nash equilibrium value and generating a target monitoring node deployment scheme includes: determining the cooperative and competitive relationship between the initial monitoring nodes in the initial monitoring node deployment strategy in terms of pollution monitoring responsibility according to the Nash equilibrium value; based on the cooperative and competitive relationship and the pollution responsibility map, evaluating the monitoring redundant area and monitoring blind area existing in the initial monitoring node deployment strategy to obtain an evaluation result; determining the redundant node identification to be removed, the node position suggestion to be added, and the monitoring parameter optimization amplitude of the existing node according to the evaluation result, and generating an adjustment instruction according to the redundant node identification to be removed, the node position suggestion to be added, and the monitoring parameter optimization amplitude of the existing node; adjusting the initial monitoring node deployment strategy based on the adjustment instruction to generate a target monitoring node deployment scheme.

[0060] In a specific implementation, first, the Nash equilibrium value is deeply analyzed, thereby revealing the complex interactions between the monitoring nodes under the initial deployment strategy. They can form a collaborative relationship of responsibility sharing due to overlapping monitoring ranges, or a game relationship of resource competition due to jointly affecting a certain pollution source. Based on this dynamic relationship and the existing pollution responsibility map, the system comprehensively evaluates the initial layout through spatial superposition analysis technology, accurately identifies the monitoring redundant areas caused by the repeated coverage of multiple nodes, and the blind areas that are not effectively monitored due to the lack of nodes or too large spacing. According to the evaluation results, the system intelligently generates a set of specific adjustment instructions, including suggestions on which redundant nodes with low contribution rate to remove, coordinate suggestions for adding new nodes at key positions in the blind area, and optimization amplitude for fine-tuning the monitoring radius or sensitivity parameters of the retained nodes. Finally, the system automatically executes these adjustment instructions to iteratively optimize the initial strategy, thereby outputting a target monitoring node deployment scheme that is more reasonable in resource allocation, more comprehensive in monitoring coverage, and maximizes overall efficiency.

[0061] In a feasible implementation, the step of generating a target monitoring node deployment scheme according to the Nash equilibrium value based on the initial monitoring node deployment strategy further includes: determining the coverage degree of key sensitive areas and the monitoring coverage rate of all pollution sources according to the target monitoring node deployment scheme; comparing the coverage threshold with the coverage degree and the monitoring coverage rate according to the preset coverage threshold, to obtain a comparison result; when the comparison result meets the adjustment requirement, updating the Nash equilibrium value by adjusting the game parameters or adding fixed nodes and recalculating the Nash equilibrium; updating the target monitoring node deployment according to the updated Nash equilibrium value.

[0062] In a specific implementation, after the system generates the target deployment scheme, it immediately evaluates its coverage effect, the core of which is to calculate the effective coverage degree of the scheme on key sensitive areas such as residential areas or water sources, and the comprehensive monitoring coverage rate of all known pollution sources. Subsequently, the system automatically compares the two key indicators with the pre-set threshold. If the evaluation result shows that the coverage of sensitive areas or the overall monitoring coverage rate does not meet the pre-set requirements, the system will start the dynamic optimization process by adjusting the cost coefficient or responsibility allocation weight in the game model to change the decision-making tendency of the participants, or directly preset a small number of fixed monitoring nodes in the key blind area by the competent department; thereafter, the system will re-run the game calculation based on the adjusted conditions to obtain a new Nash equilibrium value reflecting the latest constraints. Finally, the system will iteratively adjust and optimize the existing target deployment scheme according to the updated equilibrium value, such as guiding participants to deploy nodes in uncovered areas, so as to ensure that the monitoring network meets the established coverage standards within the game framework.

[0063] In a feasible implementation, the method further comprises: According to the latest environmental data collected periodically, an updated pollution responsibility map and an updated responsibility allocation coefficient are obtained; According to the updated responsibility allocation coefficient, an updated game model revenue function is obtained; According to the updated revenue function, Nash equilibrium is recalculated to obtain a recalculated Nash equilibrium value, and a dynamically adjusted target monitoring node deployment scheme is obtained according to the recalculated Nash equilibrium value and the updated pollution responsibility map.

[0064] In a specific implementation, the system will regularly import the latest environmental monitoring data, such as changes in pollutant concentration or updates in enterprise discharge, to dynamically generate an updated pollution responsibility map reflecting the current pollution situation and flow relationship, and recalculate the responsibility allocation coefficient corresponding to each potential pollution source. Using these updated coefficients, the system will real-time correct the revenue function of each participant in the game model, so that it more accurately reflects the latest environmental responsibility relationship. Subsequently, the system re-solves the Nash equilibrium based on the new revenue function to obtain an equilibrium solution that adapts to the current situation, which reflects the optimal strategy balance of each party under the current data. Finally, the system combines the newly calculated Nash equilibrium value with the latest pollution responsibility map to automatically adjust and optimize the existing monitoring node deployment scheme, such as re-allocating node positions or adjusting monitoring priorities, so as to ensure that the monitoring network can continuously and effectively adapt to the dynamic needs of environmental changes.

[0065] The embodiment provides a monitoring node deployment optimization method, which comprises the following steps: acquiring component data and attribute data of pollutants at emission outlets of each pollution source in a monitoring area; constructing a pollution source feature vector according to the component data and the attribute data; determining the provenance of the pollutants based on the pollution source feature vector; generating a pollution responsibility graph based on the provenance; determining a responsibility allocation coefficient of each pollution source based on the pollution responsibility graph; determining a Nash equilibrium value of each monitoring node based on the responsibility allocation coefficient and an initial monitoring node deployment strategy; optimizing the initial monitoring node deployment strategy according to the Nash equilibrium value; and generating a target monitoring node deployment scheme. In this way, the technical problem that the monitoring effect is poor due to the difficulty in adapting to dynamic changes of pollution sources in the prior art is solved.

[0066] It should be noted that the above examples are only used for understanding the present application and do not constitute a limitation on the monitoring node deployment optimization method of the present application. More forms of simple transformation based on the technical concept are within the protection scope of the present application.

[0067] The present application also provides a monitoring node deployment optimization device, please refer to Figure 3 The monitoring node deployment optimization device comprises: A feature vector construction module 10 is configured to acquire component data and attribute data of pollutants at emission outlets of each pollution source in a monitoring area, and construct a pollution source feature vector according to the component data and the attribute data. A responsibility graph generation module 20 is configured to determine the provenance of the pollutants based on the pollution source feature vector, and generate a pollution responsibility graph based on the provenance. A responsibility game calculation module 30 is configured to determine a responsibility allocation coefficient of each pollution source based on the pollution responsibility graph, and determine a Nash equilibrium value of each monitoring node based on the responsibility allocation coefficient and an initial monitoring node deployment strategy. A deployment scheme determination module 40 is configured to optimize the initial monitoring node deployment strategy according to the Nash equilibrium value, and generate a target monitoring node deployment scheme.

[0068] In a feasible implementation, the feature vector construction module 10 is further configured to acquire component data, attribute data and spectrum data at emission outlets of each pollution source in a monitoring area, and obtain an original spectrum data set according to the spectrum data. After the original spectrum data set is preprocessed, principal component analysis is performed to obtain a principal spectrum feature component. The principal spectrum feature component, the component data and the attribute data are vectorized and fused to generate a pollution source feature vector.

[0069] In an implementable embodiment, the responsibility map generation module 20 is further configured to train a random forest classifier based on a known attributed pollution source feature vector sample set to obtain a pollution source tracing model; input the pollution source feature vector into the pollution source tracing model to obtain a source attribution of the pollution, and determine a probability prediction result of each pollution source based on the source attribution; simulate a propagation trajectory and a concentration distribution of the pollution in a space-time range based on the probability prediction result; determine a pollution contribution degree of different geographical units in a monitoring area according to the propagation trajectory and the concentration distribution, and generate a pollution responsibility map according to the contribution degree.

[0070] In an implementable embodiment, the responsibility game calculation module 30 is further configured to, according to the pollution responsibility map, count a cumulative contribution amount of each pollution source being identified as a main contributor of a pollutant in the environment in a preset historical period; weight and fuse the cumulative contribution amount and a real-time emission flow of the corresponding pollution source to obtain an absolute pollution contribution degree; determine a responsibility allocation coefficient according to the absolute pollution contribution degrees of all pollution sources.

[0071] In an implementable embodiment, the responsibility game calculation module 30 is further configured to, according to each pollution source in the monitoring area and the responsibility allocation coefficient, construct a non-cooperative game model with the pollution sources as participants and with deployment or non-deployment of a monitoring node as a strategy; obtain a benefit function of each participant according to a deployment cost, an actual cost adjusted by the responsibility allocation coefficient, a pollution exposure risk change, and a collaborative governance benefit; set an initial strategy combination of the non-cooperative game model according to the initial monitoring node deployment strategy; update the initial strategy combination according to a response iteration algorithm and the benefit function to obtain a Nash equilibrium state and a corresponding Nash equilibrium value of a strategy stable of all participants.

[0072] In an implementable embodiment, the responsibility game calculation module 30 is further configured to, according to an effective monitoring radius of a monitoring node, obtain a set of other participants within a monitoring coverage range of the monitoring node when any participant deploys a node; obtain, according to the pollution responsibility map, a responsibility allocation proportion of the participant deploying a node to pollution of other participants in the set of other participants; obtain, according to a preset collaborative weight coefficient and the responsibility allocation proportion, a collaborative governance benefit value generated by the participant due to deployment of a node; According to the deployment cost, the actual cost adjusted by the responsibility allocation coefficient, the pollution exposure risk change, and the synergy governance benefit value, a benefit function of each participant is obtained.

[0073] In a feasible implementation, the deployment scheme determination module 40 is further configured to determine, according to the Nash equilibrium value, a synergy and competition relationship between the initial monitoring nodes in the initial monitoring node deployment strategy in pollution monitoring responsibility. Based on the synergy and competition relationship and the pollution responsibility map, a monitoring redundant area and a monitoring blind area existing in the initial monitoring node deployment strategy are evaluated to obtain an evaluation result. According to the evaluation result, a redundant node identifier to be removed, a node position suggestion to be added, and a monitoring parameter optimization amplitude of an existing node are determined, and an adjustment instruction is generated according to the redundant node identifier to be removed, the node position suggestion to be added, and the monitoring parameter optimization amplitude of the existing node. Based on the adjustment instruction, the initial monitoring node deployment strategy is adjusted to generate a target monitoring node deployment scheme.

[0074] In a feasible implementation, the deployment scheme determination module 40 is further configured to determine, according to the target monitoring node deployment scheme, a coverage degree of a key sensitive area and a monitoring coverage rate of all pollution sources. According to a preset coverage threshold and the coverage degree and the monitoring coverage rate, a comparison result is obtained. When the comparison result meets an adjustment requirement, an updated Nash equilibrium value is obtained by adjusting a game parameter or adding a fixed node and recalculating the Nash equilibrium. According to the updated Nash equilibrium value, the target monitoring node deployment is updated.

[0075] In a feasible implementation, the deployment scheme determination module 40 is further configured to obtain an updated pollution responsibility map and an updated responsibility allocation coefficient according to periodically collected latest environmental data. According to the updated responsibility allocation coefficient, an updated game model benefit function is obtained. According to the updated benefit function, the Nash equilibrium is recalculated to obtain a recalculated Nash equilibrium value, and a dynamically adjusted target monitoring node deployment scheme is obtained according to the recalculated Nash equilibrium value and the updated pollution responsibility map.

[0076] The monitoring node deployment optimization device provided in the present application adopts the monitoring node deployment optimization method in the above embodiment, and can solve the technical problem of poor monitoring effect caused by difficulty in adapting to dynamic changes of pollution sources. Compared with the prior art, the monitoring node deployment optimization device provided in the present application has the same beneficial effects as the monitoring node deployment optimization method provided in the above embodiment, and other technical features in the monitoring node deployment optimization device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0077] The present application provides a monitoring node deployment optimization device, which comprises at least one processor and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the monitoring node deployment optimization method in the above embodiment one.

[0078] Reference will be made to the following Figure 4 which shows a structural schematic diagram of a monitoring node deployment optimization device suitable for being used to implement the embodiments of the present application. The monitoring node deployment optimization device in the embodiments of the present application can include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistant), PADs (Portable Application Description), PMPs (Portable Media Player), vehicle-mounted terminals (for example, vehicle-mounted navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. Figure 4 The monitoring node deployment optimization device shown is only an example, and should not bring any limitation to the functions and use range of the embodiments of the present application.

[0079] As Figure 4As shown, the monitoring node deployment optimization device can include a processing apparatus 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to programs stored in a ROM (Read Only Memory) 1002 or programs loaded from a storage apparatus 1003 into a RAM (Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the monitoring node deployment optimization device are also stored. The processing apparatus 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: input apparatuses 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output apparatuses 1008 including, for example, an LCD (Liquid Crystal Display), a speaker, a vibrator, etc.; the storage apparatus 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication apparatus 1009. The communication apparatus 1009 can allow the monitoring node deployment optimization device to communicate with other devices wirelessly or by wire to exchange data. Although the monitoring node deployment optimization device having various systems is shown in the figure, it should be understood that all the shown systems are not required to be implemented or possessed. More or less systems can be alternatively implemented or possessed.

[0080] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program codes for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network through the communication apparatus, or installed from the storage apparatus 1003, or installed from the ROM 1002. When the computer program is executed by the processing apparatus 1001, the above-mentioned functions defined in the methods of the embodiments disclosed in the present application are performed.

[0081] The monitoring node deployment optimization device provided in the present application adopts the monitoring node deployment optimization method in the above-mentioned embodiments, and can solve the technical problem of monitoring node deployment optimization. Compared with the prior art, the monitoring node deployment optimization device provided in the present application has the same beneficial effects as the monitoring node deployment optimization method provided in the above-mentioned embodiments, and other technical features in the monitoring node deployment optimization device are the same as the features disclosed in the previous embodiment method, which will not be described here.

[0082] It should be understood that various aspects of the disclosure can be implemented in hardware, software, firmware, or combinations thereof, to achieve the various aspects of the disclosure. In the description above, specific features, structures, materials or characteristics can be combined in any suitable manner without necessarily being limited to one or more embodiments or examples.

[0083] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0084] The present application provides a computer readable storage medium having stored thereon computer readable program instructions (i.e. computer programs) for performing the monitoring node deployment optimization method in the above embodiments.

[0085] The computer readable storage medium provided by the present application may, for example, be a U disk, but is not limited to an electric, magnetic, optical, electromagnetic, infrared, or semiconductor system, system or device, or any combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electric connection with one or more conductive wires, a portable computer disk, a hard disk, a RAM (Random Access Memory), a ROM (Read Only Memory), an EPROM (Erasable Programmable Read Only Memory or flash memory), an optical fiber, a CD-ROM (CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present embodiment, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer readable storage medium can be transmitted by any suitable medium, including but not limited to: electric wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0086] The above computer readable storage medium can be contained in the monitoring node deployment optimization device; or can exist separately without being assembled into the monitoring node deployment optimization device.

[0087] The computer readable storage medium carries one or more programs, when the one or more programs are executed by the monitoring node deployment optimization device, the monitoring node deployment optimization device is caused to: acquire component data and attribute data of pollutants at emission outlets of each pollution source in a monitoring area, and construct a pollution source feature vector according to the component data and the attribute data; Based on the pollution source feature vector, determine the source attribution of the pollutants, and generate a pollution responsibility map according to the source attribution; Based on the pollution responsibility map, determine the responsibility allocation coefficient of each pollution source, and determine the Nash equilibrium value of each monitoring node based on the responsibility allocation coefficient and an initial monitoring node deployment strategy; According to the Nash equilibrium value, optimize the initial monitoring node deployment strategy to generate a target monitoring node deployment scheme.

[0088] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0089] The flow and block diagrams in the drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flow and block diagrams can represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may be executed in the reverse order, depending on the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0090] The modules involved in the embodiments of the present application can be implemented in software or in hardware. In some cases, the names of the modules do not limit the modules themselves.

[0091] The readable storage medium provided by the present application is a computer readable storage medium, which stores computer readable program instructions (i.e., a computer program) for executing the above-mentioned monitoring node deployment optimization method, and can solve the technical problem of monitoring node deployment optimization. Compared with the prior art, the computer readable storage medium provided by the present application has the same beneficial effects as the monitoring node deployment optimization method provided by the above-mentioned embodiments, which will not be repeated here.

[0092] The present application also provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the above-mentioned monitoring node deployment optimization method.

[0093] The computer program product provided by the present application can solve the technical problem of monitoring node deployment optimization. Compared with the prior art, the computer program product provided by the present application has the same beneficial effects as the monitoring node deployment optimization method provided by the above-mentioned embodiments, which will not be repeated here.

[0094] The above is only some embodiments of the present application, and does not limit the patent scope of the present application. Any equivalent structural transformation made by using the content of the present application specification and drawings, or direct / indirect application in other related technical fields is included in the patent protection scope of the present application.

Claims

1. A method for optimizing the deployment of monitoring nodes, characterized in that, The monitoring node deployment optimization method comprises: obtaining component data and attribute data of pollutants at emission outlets of each pollution source in a monitoring area, and constructing a pollution source feature vector according to the component data and the attribute data; determining the source attribution of the pollutants based on the pollution source feature vector, and generating a pollution responsibility graph based on the source attribution; determining a responsibility allocation coefficient of each pollution source based on the pollution responsibility graph, and determining a Nash equilibrium value of each monitoring node based on the responsibility allocation coefficient and an initial monitoring node deployment strategy; optimizing the initial monitoring node deployment strategy according to the Nash equilibrium value to generate a target monitoring node deployment scheme.

2. The method of claim 1, wherein, The step of obtaining component data and attribute data of pollutants at emission outlets of each pollution source in a monitoring area, and constructing a pollution source feature vector according to the component data and the attribute data comprises: obtaining component data, attribute data and spectral data at emission outlets of each pollution source in a monitoring area, and obtaining an original spectral data set according to the spectral data; performing principal component analysis on the original spectral data set after preprocessing to obtain a main spectral feature component; vectorizing and fusing the main spectral feature component, the component data and the attribute data to generate a pollution source feature vector.

3. The method of claim 1, wherein, The step of determining the source attribution of the pollutants based on the pollution source feature vector, and generating a pollution responsibility graph based on the source attribution comprises: training a random forest classifier based on a known sample set of pollution source feature vectors to obtain a pollutant source tracing model; inputting the pollution source feature vector into the pollutant source tracing model to obtain the source attribution of the pollutants, and determining a probability prediction result of each pollution source based on the source attribution; simulating the propagation trajectory and concentration distribution of the pollutants in a space-time range based on the probability prediction result; determining the pollution contribution degree of different geographical units in the monitoring area according to the propagation trajectory and the concentration distribution, and generating a pollution responsibility graph according to the contribution degree.

4. The method of claim 1, wherein, The step of determining a responsibility allocation coefficient of each pollution source based on the pollution responsibility graph comprises: statistically determining the cumulative contribution of each pollution source identified as a main contributor of pollutants in the environment in a preset historical period according to the pollution responsibility graph; weighting and fusing the cumulative contribution and the real-time emission flow of the corresponding pollution source to obtain an absolute pollution contribution degree; determining the responsibility allocation coefficient according to the absolute pollution contribution degree of all pollution sources.

5. The method of claim 1, wherein, The step of determining a Nash equilibrium value of each monitoring node based on the responsibility allocation coefficient and an initial monitoring node deployment strategy comprises: constructing a non-cooperative game model taking the pollution sources as participants and taking deployment or non-deployment of monitoring nodes as strategies according to each pollution source in the monitoring area and the responsibility allocation coefficient; obtaining a benefit function of each participant according to the deployment cost, the actual cost adjusted by the responsibility allocation coefficient, the change of pollution exposure risk and the collaborative governance benefit; setting an initial strategy combination of the non-cooperative game model according to the initial monitoring node deployment strategy; According to the response iteration algorithm and the benefit function, the initial strategy combination is updated to obtain a Nash equilibrium state of all participant strategies and a corresponding Nash equilibrium value.

6. The method of claim 5, wherein, The step of obtaining the benefit function of each participant according to the deployment cost, the actual cost adjusted by the responsibility allocation coefficient, the pollution exposure risk change, and the collaborative governance benefit comprises: According to the effective monitoring radius of the monitoring node, a set of other participants within the monitoring coverage of the monitoring node when any participant deploys a node is obtained; According to the pollution responsibility map, a responsibility allocation proportion of the participant deploying a node to pollution of other participants in the set of other participants is obtained; According to a preset collaborative weight coefficient and the responsibility allocation proportion, a collaborative governance benefit value generated by the participant due to the deployment of a node is obtained; According to the deployment cost, the actual cost adjusted by the responsibility allocation coefficient, the pollution exposure risk change, and the collaborative governance benefit value, the benefit function of each participant is obtained.

7. The method of claim 1, wherein, The step of optimizing the initial monitoring node deployment strategy according to the Nash equilibrium value to generate a target monitoring node deployment scheme comprises: According to the Nash equilibrium value, a collaborative and competitive relationship between the initial monitoring nodes in the initial monitoring node deployment strategy in terms of pollution monitoring responsibility is determined; Based on the collaborative and competitive relationship and the pollution responsibility map, a monitoring redundant area and a monitoring blind area existing in the initial monitoring node deployment strategy are evaluated to obtain an evaluation result; According to the evaluation result, a redundant node identifier to be removed, a node position suggestion to be added, and a monitoring parameter optimization amplitude of an existing node are determined, and an adjustment instruction is generated according to the redundant node identifier to be removed, the node position suggestion to be added, and the monitoring parameter optimization amplitude of the existing node; Based on the adjustment instruction, the initial monitoring node deployment strategy is adjusted to generate a target monitoring node deployment scheme.

8. The method of claim 1, wherein, The step of optimizing the initial monitoring node deployment strategy according to the Nash equilibrium value to generate a target monitoring node deployment scheme further comprises: According to the target monitoring node deployment scheme, a coverage degree of a key sensitive area and a monitoring coverage rate of all pollution sources are determined; According to a preset coverage threshold and the coverage degree and the monitoring coverage rate, a comparison result is obtained; When the comparison result meets an adjustment requirement, a Nash equilibrium value is obtained by adjusting a game parameter or adding a fixed node and recalculating the Nash equilibrium; The target monitoring node deployment is updated according to the updated Nash equilibrium value.

9. The method of any one of claims 1 to 8, wherein, The method further comprises: According to periodically collected latest environmental data, an updated pollution responsibility map and an updated responsibility allocation coefficient are obtained; According to the updated responsibility allocation coefficient, an updated game model benefit function is obtained; According to the updated benefit function, a Nash equilibrium is recalculated to obtain a recalculated Nash equilibrium value, and a dynamically adjusted target monitoring node deployment scheme is obtained according to the recalculated Nash equilibrium value and the updated pollution responsibility map.

10. A monitoring node deployment optimization apparatus, characterized by, The monitoring node deployment optimization device comprises: The feature vector construction module is configured to acquire composition data and attribute data of pollutants at emission outlets of each pollution source in the monitoring area, and construct a pollution source feature vector according to the composition data and the attribute data; The responsibility graph generation module is configured to determine the source of the pollutants based on the pollution source feature vector, and generate a pollution responsibility graph based on the source of the pollutants; The responsibility game calculation module is configured to determine a responsibility allocation coefficient of each pollution source based on the pollution responsibility graph, and determine a Nash equilibrium value of each monitoring node based on the responsibility allocation coefficient and an initial monitoring node deployment strategy; The deployment scheme determination module is configured to optimize the initial monitoring node deployment strategy according to the Nash equilibrium value, and generate a target monitoring node deployment scheme.

Images