Method and apparatus for monitoring node deployment optimization

Abstract

The application discloses a kind of monitoring node deployment optimization method and device, it is related to environmental monitoring technical field, the method comprises: obtaining the composition data and attribute data of pollutant at each pollution source discharge port in monitoring area, according to composition data and attribute data, construct pollution source feature vector, based on pollution source feature vector, determine the provenance attribution of pollutant, to generate pollution responsibility atlas with provenance attribution, determine the responsibility allocation coefficient of each pollution source based on pollution responsibility atlas, determine the Nash equilibrium value of each monitoring node based on responsibility allocation coefficient and initial monitoring node deployment strategy, optimize initial monitoring node deployment strategy according to Nash equilibrium value, generate target monitoring node deployment scheme. Through the above mode, the technical problem that the monitoring effect is poor due to the difficulty in adapting to the dynamic change of pollution source in the prior art is solved.

Description

Technical Field

[0001] This application relates to the field of environmental monitoring technology, and in particular to a method and apparatus for optimizing the deployment of monitoring nodes. Background Technology

[0002] There are two main ways to deploy environmental monitoring nodes: one is to use a fixed-space, uniform deployment method, which is simple and easy to implement but leads to an excessive number of monitoring nodes, high deployment costs, and a large number of redundant nodes and wasted resources when pollution sources are unevenly distributed or dynamically changing; the other is to deploy based on pollution diffusion models. This method relies on high-precision physical or statistical models to predict the diffusion path of pollutants. However, in practical applications, the accuracy of the model is easily affected by environmental factors, resulting in poor dynamic adaptability and difficulty in responding to sudden or moving pollution sources in a timely manner. This makes it difficult for the monitoring network to effectively control costs and ensure continuous and reliable coverage of key areas.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of this application is to provide a method and apparatus for optimizing the deployment of monitoring nodes, which aims to solve the technical problem in the prior art that it is difficult to adapt to the dynamic changes of pollution sources, resulting in poor monitoring effect.

[0005] To achieve the above objectives, this application provides a method for optimizing the deployment of monitoring nodes, the method comprising:

[0006] Acquire the composition and attribute data of pollutants at the emission outlets of each pollution source within the monitoring area, and construct a pollution source feature vector based on the composition and attribute data;

[0007] Based on the pollution source feature vector, the source attribution of the pollutants is determined, and a pollution responsibility map is generated based on the source attribution.

[0008] Based on the pollution responsibility map, the responsibility sharing coefficient of each pollution source is determined, and based on the responsibility sharing coefficient and the initial monitoring node deployment strategy, the Nash equilibrium value of each monitoring node is determined.

[0009] The initial monitoring node deployment strategy is optimized based on the Nash equilibrium value to generate a target monitoring node deployment scheme.

[0010] In one embodiment, the step of acquiring the composition data and attribute data of pollutants at the emission outlets of each pollution source within the monitoring area, and constructing a pollution source feature vector based on the composition data and the attribute data, includes:

[0011] Acquire component data, attribute data, and spectral data at the emission outlets of each pollution source within the monitoring area, and obtain the raw spectral dataset based on the spectral data;

[0012] After preprocessing the original spectral dataset, principal component analysis is performed to obtain the main spectral feature components;

[0013] The main spectral feature components, the component data, and the attribute data are vectorized and fused to generate a pollution source feature vector.

[0014] In one embodiment, the step of determining the source attribution of the pollutant based on the pollution source feature vector, and generating a pollution liability map based on the source attribution, includes:

[0015] A random forest classifier is trained based on a sample set of pollution source feature vectors with known attribution to obtain a pollutant source tracing model.

[0016] The pollution source feature vector is input into the pollutant source tracing model to obtain the source attribution of the pollutant, and the probability prediction result of each pollution source is determined based on the source attribution.

[0017] Based on the probability prediction results, the propagation trajectory and concentration distribution of the pollutants in the spatiotemporal range are simulated;

[0018] Based on the propagation trajectory and the concentration distribution, the pollution contribution of different geographical units within the monitoring area is determined, and a pollution responsibility map is generated based on the contribution.

[0019] In one embodiment, the step of determining the responsibility allocation coefficient for each pollution source based on the pollution responsibility map includes:

[0020] Based on the pollution liability map, the cumulative contribution of each pollution source identified as a major contributor to pollutants in the environment within a preset historical period is calculated.

[0021] The cumulative contribution is weighted and fused with the real-time emission flow of the corresponding pollution source to obtain the absolute pollution contribution.

[0022] The responsibility allocation coefficient is determined based on the absolute pollution contribution of all pollution sources.

[0023] In one embodiment, the step of determining the Nash equilibrium value of each monitoring node based on the responsibility sharing coefficient and the initial monitoring node deployment strategy includes:

[0024] Based on the pollution sources within the monitoring area and the responsibility sharing coefficient, a non-cooperative game model is constructed with the pollution sources as participants and the strategy of deploying or not deploying monitoring nodes as the strategy.

[0025] Based on deployment costs, actual costs adjusted by the aforementioned responsibility-sharing coefficients, changes in pollution exposure risk, and the benefits of collaborative governance, the payoff functions for each participant are obtained.

[0026] The initial strategy combination of the non-cooperative game model is set according to the initial monitoring node deployment strategy;

[0027] The initial strategy combination is updated according to the response iteration algorithm and the revenue function to obtain the stable Nash equilibrium state and corresponding Nash equilibrium value of all participants' strategies.

[0028] In one embodiment, the step of obtaining the benefit function for each participant based on deployment costs, actual costs adjusted by the responsibility-sharing coefficient, changes in pollution exposure risk, and collaborative governance benefits includes:

[0029] Based on the effective monitoring radius of the monitoring node, obtain the set of other participants within the monitoring coverage area of ​​any participant when the node is deployed.

[0030] Based on the pollution liability map, the responsibility sharing ratio of the participants in the deployment node for the pollution of other participants in the set of other participants is obtained;

[0031] Based on the preset collaborative weight coefficient and the responsibility sharing ratio, the collaborative governance benefit value generated by the participant due to the deployment of nodes is obtained;

[0032] Based on the deployment cost, the actual cost adjusted by the aforementioned responsibility sharing coefficient, the change in pollution exposure risk, and the aforementioned collaborative governance benefit value, the revenue function of each participant is obtained.

[0033] In one embodiment, the step of optimizing the initial monitoring node deployment strategy based on the Nash equilibrium value to generate a target monitoring node deployment scheme includes:

[0034] Based on the Nash equilibrium value, determine the collaborative and competitive relationships among the initial monitoring nodes in the initial monitoring node deployment strategy regarding pollution monitoring responsibilities;

[0035] Based on the cooperative and competitive relationships and the pollution liability map, the monitoring redundancy areas and monitoring blind spots in the initial monitoring node deployment strategy are evaluated, and the evaluation results are obtained.

[0036] Based on the evaluation results, the redundant node identifiers to be removed, the suggested locations of new nodes, and the optimization range of the monitoring parameters of existing nodes are determined. Adjustment instructions are then generated based on the redundant node identifiers to be removed, the suggested locations of new nodes, and the optimization range of the monitoring parameters of existing nodes.

[0037] Based on the adjustment instructions, the initial monitoring node deployment strategy is adjusted to generate a target monitoring node deployment plan.

[0038] In one embodiment, after the step of generating a target monitoring node deployment scheme based on the initial monitoring node deployment strategy according to the Nash equilibrium value, the method further includes:

[0039] Based on the target monitoring node deployment plan, determine the coverage of key sensitive areas and the monitoring coverage of all pollution sources;

[0040] The comparison result is obtained by comparing the preset coverage threshold with the coverage and the monitoring coverage rate;

[0041] When the comparison results meet the adjustment requirements, the updated Nash equilibrium value is obtained by adjusting the game parameters or adding fixed nodes and recalculating the Nash equilibrium.

[0042] The target monitoring node is deployed and updated based on the updated Nash equilibrium value.

[0043] In one embodiment, the method further includes:

[0044] Based on the latest environmental data collected periodically, an updated pollution liability map and an updated liability sharing coefficient are obtained;

[0045] Based on the updated responsibility sharing coefficients, the updated payoff function of the game model is obtained;

[0046] The Nash equilibrium is recalculated based on the updated revenue function to obtain the recalculated Nash equilibrium value. Based on the recalculated Nash equilibrium value and the updated pollution liability map, a dynamically adjusted target monitoring node deployment scheme is obtained.

[0047] Furthermore, to achieve the above objectives, this application also proposes a monitoring node deployment optimization device, which includes:

[0048] The feature vector construction module is used to acquire the composition data and attribute data of pollutants at the emission outlets of each pollution source within the monitoring area, and to construct pollution source feature vectors based on the composition data and attribute data.

[0049] The responsibility map generation module is used to determine the source attribution of the pollutants based on the pollution source feature vector, and generate a pollution responsibility map based on the source attribution;

[0050] The responsibility game calculation module is used to determine the responsibility sharing 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 sharing coefficient and the initial monitoring node deployment strategy.

[0051] The deployment scheme determination module is used to optimize the initial monitoring node deployment strategy based on the Nash equilibrium value and generate a target monitoring node deployment scheme.

[0052] In addition, to achieve the above objectives, this application also proposes a monitoring node deployment optimization device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the monitoring node deployment optimization method described above.

[0053] In addition, to achieve the above objectives, the present invention also proposes a storage medium, which is a computer-readable storage medium, and stores a computer program on the storage medium. When the computer program is executed by a processor, it implements the steps of the monitoring node deployment optimization method described above.

[0054] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the monitoring node deployment optimization method described above.

[0055] This application provides a method for optimizing the deployment of monitoring nodes. It acquires the composition and attribute data of pollutants at the emission outlets of each pollution source within the monitoring area. Based on this data, it constructs pollution source feature vectors. Using these feature vectors, it determines the source attribution of pollutants, generates a pollution responsibility map, determines the responsibility allocation coefficient for each pollution source based on the pollution responsibility map, and determines the Nash equilibrium value for each monitoring node based on the responsibility allocation coefficient and the initial monitoring node deployment strategy. Finally, it optimizes the initial monitoring node deployment strategy based on the Nash equilibrium value to generate a target monitoring node deployment scheme. This method addresses the technical problem in existing technologies where poor monitoring performance is difficult to adapt to dynamic changes in pollution sources. Attached Figure Description

[0056] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0057] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 A flowchart illustrating an embodiment of the optimization method for deploying monitoring nodes in this application;

[0059] Figure 2This is a schematic diagram of a pollution liability map based on an embodiment of the monitoring node deployment optimization method of this application.

[0060] Figure 3 This is a schematic diagram of the module structure of the monitoring node deployment optimization device in an embodiment of this application;

[0061] Figure 4 This is a schematic diagram of the hardware operating environment involved in the monitoring node deployment optimization method in this application embodiment.

[0062] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0063] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0064] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0065] The main solution of this application embodiment is: to obtain the composition data and attribute data of pollutants at the emission outlets of each pollution source within the monitoring area, and to construct a pollution source feature vector based on the composition data and the attribute data;

[0066] Based on the pollution source feature vector, the source attribution of the pollutants is determined, and a pollution responsibility map is generated based on the source attribution.

[0067] Based on the pollution responsibility map, the responsibility sharing coefficient of each pollution source is determined, and based on the responsibility sharing coefficient and the initial monitoring node deployment strategy, the Nash equilibrium value of each monitoring node is determined.

[0068] The initial monitoring node deployment strategy is optimized based on the Nash equilibrium value to generate a target monitoring node deployment scheme.

[0069] Currently, there are two main deployment methods for environmental monitoring nodes: one is to deploy them uniformly at fixed intervals. Although this method is simple and easy to implement, it leads to an excessive number of monitoring nodes, high deployment costs, and a large number of redundant nodes and wasted resources when pollution sources are unevenly distributed or dynamically changing. The other method is to deploy them in a targeted manner based on pollution diffusion models. This method relies on high-precision physical or statistical models to predict the diffusion path of pollutants. However, in practical applications, the accuracy of the models is easily affected by environmental factors, resulting in poor dynamic adaptability and difficulty in responding to sudden or moving pollution sources in a timely manner. This makes it difficult for the monitoring network to effectively control costs and ensure continuous and reliable coverage of key areas.

[0070] This application provides a solution that acquires the composition and attribute data of pollutants at the emission outlets of each pollution source within a monitoring area. Based on this data, a pollution source feature vector is constructed. The source attribution of pollutants is determined using this feature vector, and a pollution responsibility map is generated. Based on this map, a responsibility allocation coefficient for each pollution source is determined. The Nash equilibrium value for each monitoring node is determined based on the responsibility allocation coefficient and the initial monitoring node deployment strategy. The initial monitoring node deployment strategy is then optimized based on the Nash equilibrium value to generate a target monitoring node deployment scheme. This approach addresses the technical problem in existing technologies where poor monitoring performance is difficult to adapt to dynamic changes in pollution sources.

[0071] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or monitoring node deployment optimization device capable of performing the above functions. This embodiment does not specifically limit it in this regard. The following uses a monitoring node deployment optimization device as an example to describe this embodiment and the following embodiments.

[0072] All actions involving the acquisition of signals, information, or data in this application are carried out in accordance with the relevant data protection laws and policies of the country where the application is located, and with the authorization of the owner of the relevant device.

[0073] This application provides a method for optimizing the deployment of monitoring nodes, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the monitoring node deployment optimization method of this application.

[0074] In this embodiment, the monitoring node deployment optimization method includes steps S10~S40:

[0075] Step S10: Obtain the composition data and attribute data of pollutants at the emission outlets of each pollution source within the monitoring area, and construct a pollution source feature vector based on the composition data and the attribute data.

[0076] It should be noted that a monitoring area refers to the geographical scope designated for real-time environmental monitoring based on management needs. It is the physical spatial boundary used to deploy monitoring networks, assess environmental quality, and trace pollution liability. A pollution source emission outlet refers to the specific location or channel through which pollutants are directly or indirectly discharged into the environment. Examples include factory chimneys, sewage pipes, and wastewater treatment plant effluents. Compositional data refers to data regarding the chemical or physical characteristics of the pollutants themselves, describing their type, concentration, isotope ratios, and characteristic spectral fingerprints. Attribute data refers to background information and static characteristic data related to the pollution source, typically including the geographical coordinates of the pollution source and the type of enterprise to which it belongs.

[0077] Understandably, the first step involves acquiring precise compositional data of pollutants, such as the concentration and proportion of specific chemical substances (e.g., benzene compounds, heavy metal ions), through online monitoring equipment deployed at the discharge outlets, such as mass spectrometers, chromatographs, or periodic sampling laboratory analysis. Simultaneously, attribute data related to the inherent characteristics of the pollution source are collected, such as the industry of the enterprise, production process, raw material information, and the status of treatment facilities. Subsequently, feature engineering methods, such as principal component analysis (PCA) to remove redundancy or one-heat coding to process classification attributes, are used to standardize and reduce the dimensionality of this heterogeneous data. Finally, these processed feature values ​​are combined according to weights into a unified, highly discriminative pollution source feature vector.

[0078] In one feasible implementation, the step of acquiring the composition and attribute data of pollutants at the emission outlets of each pollution source within the monitoring area, and constructing a pollution source feature vector based on the composition and attribute data, includes:

[0079] Acquire component data, attribute data, and spectral data at the emission outlets of each pollution source within the monitoring area, and obtain the raw spectral dataset based on the spectral data;

[0080] After preprocessing the original spectral dataset, principal component analysis is performed to obtain the main spectral feature components;

[0081] The main spectral feature components, the component data, and the attribute data are vectorized and fused to generate a pollution source feature vector.

[0082] In practical implementation, it is assumed that there are within the monitoring area. One pollution source. For each pollution source At its emission outlet Each sampling yields a sample containing... The spectrum of intensity values ​​at individual wavelengths or wavenumber points. Therefore, for pollution sources This yields a spectral data matrix. The spectral data from all pollution sources together constitute the original spectral dataset. Component data are denoted as vectors. ,in This represents the number of characteristic pollutants of interest (such as the concentration of SO2, NOx, specific VOCs, etc.). Attribute data is denoted as a vector. Where q represents the attribute dimension (such as longitude, latitude, emissions, industry category code, etc.).

[0083] Each spectrum in the original spectral dataset S is preprocessed to remove noise and baseline drift. Savitzky-Golay filtering is used. For a discrete spectral signal... The filtered value at wavelength point j It is calculated by linear combination of the original values ​​within its neighborhood window: Where w is half the window width, These are the coefficients determined by the fitted polynomial. Then, normalization is performed, for example, min-max normalization: This ensures that all intensity values ​​fall within the [0,1] interval. The preprocessed spectral data matrix is ​​denoted as... Where N = n * t is the total number of samples. PCA is used to reduce the dimensionality of the preprocessed spectral matrix X to extract the principal components that best characterize spectral differences and reduce data redundancy. The column mean vector μ of matrix X is calculated, and then the centered matrix is ​​obtained. (where 1 represents a column vector of all 1s), calculate the covariance matrix. Perform eigenvalue decomposition on the covariance matrix Σ: Where Λ is composed of eigenvalues The diagonal matrix formed, and the column vectors of V These are the corresponding eigenvectors (i.e., principal component directions). Projecting the original spectral data onto the first k principal component directions yields the dimensionality-reduced principal spectral eigencomponent matrix Z. Each row is a k-dimensional principal component score vector of a sample. For each sample, its principal component score vector, component data vector, and attribute data vector are concatenated to generate the final feature vector. This fused vector, representing the pollution source feature vector of the sample, integrates the spectral fingerprint, chemical composition, and source characteristic attributes of the pollutants, providing comprehensive input information for subsequent source tracing models.

[0084] Step S20: Based on the pollution source feature vector, determine the source attribution of the pollutants, and generate a pollution responsibility map based on the source attribution.

[0085] It should be noted that source attribution refers to the process and result of matching and classifying a pollutant sample from an unknown source to one or more of the most likely known pollution sources within a monitoring area through model calculations. A pollution liability map is a visual decision support tool that graphically displays the source attribution relationship and liability weight between pollutant samples and potential pollution sources. The map clearly shows the migration and diffusion paths of pollutants and the contribution rate of each pollution source, providing a clear basis for environmental law enforcement and precise pollution control.

[0086] Understandably, during the model training phase, the system uses a dataset of pollution source feature vectors with labeled origins to train a classification model. When analyzing newly detected unknown pollutants, 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; this probability distribution is the quantified result of "source attribution," as shown in the reference... Figure 2 , Figure 2 This is a schematic diagram of the pollution liability map. Finally, based on this attribution probability, pollutant concentration, geographical location, and other information, the system automatically generates a dynamic "pollution liability map." On the map, different colors, thicknesses, or area sizes are used to visually map the degree of responsibility and path relationships of each pollution source, thereby achieving rapid and accurate determination and display of pollution liability.

[0087] In one feasible implementation, the step of determining the source attribution of the pollutants based on the pollution source feature vector, and generating a pollution responsibility map based on the source attribution, includes:

[0088] A random forest classifier is trained based on a sample set of pollution source feature vectors with known attribution to obtain a pollutant source tracing model.

[0089] The pollution source feature vector is input into the pollutant source tracing model to obtain the source attribution of the pollutant, and the probability prediction result of each pollution source is determined based on the source attribution.

[0090] Based on the probability prediction results, the propagation trajectory and concentration distribution of the pollutants in the spatiotemporal range are simulated;

[0091] Based on the propagation trajectory and the concentration distribution, the pollution contribution of different geographical units within the monitoring area is determined, and a pollution responsibility map is generated based on the contribution.

[0092] In its implementation, the system first relies on a pre-built knowledge base. This base uses a large number of known pollutant feature vectors from specific emission points as training samples to teach a random forest classifier to learn the unique patterns of different pollution sources, thus forming a mature pollutant source tracing model. When tracing the source of a newly discovered unknown pollutant, the system inputs its corresponding feature vector into the model. The model collectively makes decisions through numerous decision trees, ultimately outputting a probability prediction that quantifies the likelihood of the pollutant belonging to each known pollution source within the region. Subsequently, the system combines meteorological data, topographic information, and atmospheric diffusion models to simulate the pollutant's propagation path and concentration decay distribution within a specific time and space range, starting from the suspected emission point. Finally, by overlaying the simulated concentration distribution map with administrative divisions or gridded geographical units, the system calculates the proportion of pollution borne by each geographical unit and the pollution source responsible for it—the pollution contribution rate. Based on this, a visual map is automatically generated, clearly and intuitively showing the origin and spread of pollutants and the spatial distribution of responsibility for each pollution source—this is the pollution responsibility map.

[0093] Step S30: Determine the responsibility sharing coefficient of each pollution source based on the pollution responsibility map, and determine the Nash equilibrium value of each monitoring node based on the responsibility sharing coefficient and the initial monitoring node deployment strategy.

[0094] It should be noted that the responsibility allocation coefficient refers to a proportional value obtained by quantifying the contribution of each pollution source to the overall pollution or a specific exceedance event based on the pollution responsibility map using a specific algorithm. This coefficient transforms the probabilistic result of pollution attribution into a specific numerical value that can be used for responsibility delineation, cost accounting, or performance evaluation. Typically, the sum of the responsibility allocation coefficients of all pollution sources is 1. Initial monitoring node deployment strategy: This refers to a pre-planned spatial layout scheme of monitoring points within the monitoring area, which clarifies the geographical location and monitoring range of each monitoring node. This strategy may be based on experience, administrative divisions, or a preliminary risk assessment to determine the initial deployment state. The Nash equilibrium value is used to evaluate whether the current location strategy of a single monitoring node has reached its optimal level, given that the locations 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 that point maximizes its monitoring effectiveness, and no unilateral change in location would yield greater benefits, thus indicating that the deployment strategy tends to be stable and effective.

[0095] Understandably, the system first calculates the pollution contribution ratio of each pollution source to one or more areas of concern, i.e., the responsibility sharing coefficient, based on the pollution responsibility map. Then, the system treats each monitoring node as a rational decision-maker, assesses the pollution risks caused by each pollution source that it can effectively monitor based on its location under the current initial deployment strategy, and calculates the Nash equilibrium value of its monitoring effectiveness. This value is used to determine whether the current node layout has achieved optimal monitoring effectiveness under a given cost, or to identify which nodes need to be repositioned to achieve a more balanced and efficient global monitoring state, providing a quantitative basis for subsequent optimization.

[0096] In one feasible implementation, the step of determining the responsibility allocation coefficient for each pollution source based on the pollution responsibility map includes:

[0097] Based on the pollution liability map, the cumulative contribution of each pollution source identified as a major contributor to pollutants in the environment within a preset historical period is calculated.

[0098] The cumulative contribution is weighted and fused with the real-time emission flow of the corresponding pollution source to obtain the absolute pollution contribution.

[0099] The responsibility allocation coefficient is determined based on the absolute pollution contribution of all pollution sources.

[0100] In its implementation, the system first retrieves all records from the pollution responsibility map within a preset historical period. Using data aggregation technology, it calculates the total number of times or the total contribution of each pollution source was identified as a major contributor to pollutants in the environment during this period, forming a historical responsibility file. Next, the system accesses real-time emission monitoring data from each pollution source. It standardizes the aforementioned historical cumulative contribution and real-time emission flow—representing past responsibility and current activity levels, respectively—and then merges them using preset weights to generate a more comprehensive absolute pollution contribution rate for assessing the impact of pollution sources. Finally, the system normalizes the absolute pollution contribution rates of all pollution sources, ensuring that the sum of the contribution rates of each pollution source is one, thus obtaining a responsibility allocation coefficient used to quantify the specific proportion of responsibility.

[0101] In one feasible implementation, the step of determining the Nash equilibrium value of each monitoring node based on the responsibility sharing coefficient and the initial monitoring node deployment strategy includes:

[0102] Based on the pollution sources within the monitoring area and the responsibility sharing coefficient, a non-cooperative game model is constructed with the pollution sources as participants and the strategy of deploying or not deploying monitoring nodes as the strategy.

[0103] Based on deployment costs, actual costs adjusted by the aforementioned responsibility-sharing coefficients, changes in pollution exposure risk, and the benefits of collaborative governance, the payoff functions for each participant are obtained.

[0104] The initial strategy combination of the non-cooperative game model is set according to the initial monitoring node deployment strategy;

[0105] The initial strategy combination is updated according to the response iteration algorithm and the revenue function to obtain the stable Nash equilibrium state and corresponding Nash equilibrium value of all participants' strategies.

[0106] In its implementation, the entire monitoring area is first defined as a game, where each pollution source is considered an independent rational participant. Their strategic choice is to deploy or not deploy a monitoring node at their location. The system then constructs a payoff function for each participant. This function is a comprehensive calculation model that considers not only the direct hardware and maintenance costs of deploying nodes but also the cost weighting adjustment using the pollution source's responsibility-sharing coefficient to reflect the principle that greater responsibility requires greater governance investment. The function also incorporates the reduced potential pollution exposure risk due to effective monitoring and the overall governance benefits of multiple nodes working collaboratively. Next, the system sets the initial choice state for each participant based on the initial monitoring node deployment strategy. Finally, the system initiates a response iterative algorithm that simulates real-world decision-making processes. Each participant evaluates and switches to a strategy that yields higher payoffs based on the current strategies of other participants. After multiple iterations, the system reaches a stable Nash equilibrium state. At this point, no pollution source can gain additional benefits by unilaterally changing its deployment decision. The payoff value obtained by each participant at this state is the Nash equilibrium value of the system.

[0107] Specifically, pollution sources within the region are considered as players in a game, and monitoring nodes are deployed as game strategies. A strategy space is then created. Where D represents "deploy monitoring nodes" and U represents "do not deploy".

[0108] The payoff function for participant i comprehensively considers deployment costs, pollution exposure risks, and responsibility-sharing mechanisms:

[0109]

[0110] Therefore, a payoff function can be defined:

[0111]

[0112] Node deployment cost;

[0113] : This is the pollution liability sharing coefficient, calculated based on the company's historical emissions and pollution contribution.

[0114] The risk of pollution exposure for company i when no monitoring is deployed is related to the coverage area of ​​the monitoring nodes. If company i deploys nodes... The risk of pollution exposure to other enterprises within its coverage radius is reduced. If not deployed ,but , N represents the number of uncovered pollution sources in the surrounding area, and N represents the total number of pollution sources.

[0115] The effect of deploying nodes for other enterprises on the responsibility sharing of enterprise i;

[0116] The proportion of pollution liability sharing for enterprise i when deploying nodes for enterprise j;

[0117] This is the responsibility collaboration weighting coefficient, reflecting the benefits of collaborative governance among enterprises;

[0118] ,and .

[0119] In one feasible implementation, the step of obtaining the benefit function for each participant based on deployment costs, actual costs adjusted by the responsibility-sharing coefficient, changes in pollution exposure risk, and collaborative governance benefits includes:

[0120] Based on the effective monitoring radius of the monitoring node, obtain the set of other participants within the monitoring coverage area of ​​any participant when the node is deployed.

[0121] Based on the pollution liability map, the responsibility sharing ratio of the participants in the deployment node for the pollution of other participants in the set of other participants is obtained;

[0122] Based on the preset collaborative weight coefficient and the responsibility sharing ratio, the collaborative governance benefit value generated by the participant due to the deployment of nodes is obtained;

[0123] Based on the deployment cost, the actual cost adjusted by the aforementioned responsibility sharing coefficient, the change in pollution exposure risk, and the aforementioned collaborative governance benefit value, the revenue function of each participant is obtained.

[0124] In its implementation, the system first performs geospatial analysis based on the effective monitoring radius of each monitoring node. When a pollution source selects a deployment node, the system automatically identifies all other pollution sources within the node's monitoring range using map calculations, forming a collaborative monitoring set for that deployer. Subsequently, the system backtracks the pollution responsibility map to analyze the proportion of responsibility that the deployer should bear for pollution caused by other pollution sources within the set. Next, the system introduces a preset collaborative weighting coefficient, representing a policy inclination to encourage joint governance. This coefficient is multiplied by the responsibility proportion of the managed object to quantify the additional collaborative governance benefit value gained by the participant in assisting in the supervision of others due to the deployment of the node. Finally, the system comprehensively calculates this collaborative governance benefit value along with the direct cost of deployment, the actual cost adjusted according to its own responsibility sharing coefficient, and the reduced local pollution exposure risk value due to monitoring coverage, constructing a personalized benefit function that comprehensively reflects economic costs, individual risks, and social benefits.

[0125] Step S40: Optimize the initial monitoring node deployment strategy based on the Nash equilibrium value to generate a target monitoring node deployment scheme.

[0126] Understandably, by comparing and analyzing the strategy combinations corresponding to the Nash equilibrium state with the initial strategy, the system identifies the node locations that participants preferentially choose to deploy in the equilibrium state. These locations typically represent the optimal choice after balancing costs, responsibilities, and risks. Based on this analysis, the system automatically adjusts the initial strategy, such as retaining high-yield nodes, replacing inefficient nodes, or reallocating resources. This generates a more efficient and stable target monitoring node deployment scheme where all pollution sources lack a unilateral motivation to deviate. This scheme optimizes overall system costs and maximizes governance benefits while ensuring monitoring effectiveness.

[0127] In one feasible implementation, the step of optimizing the initial monitoring node deployment strategy based on the Nash equilibrium value to generate a target monitoring node deployment scheme includes:

[0128] Based on the Nash equilibrium value, determine the collaborative and competitive relationships among the initial monitoring nodes in the initial monitoring node deployment strategy regarding pollution monitoring responsibilities;

[0129] Based on the cooperative and competitive relationships and the pollution liability map, the monitoring redundancy areas and monitoring blind spots in the initial monitoring node deployment strategy are evaluated, and the evaluation results are obtained.

[0130] Based on the evaluation results, the redundant node identifiers to be removed, the suggested locations of new nodes, and the optimization range of the monitoring parameters of existing nodes are determined. Adjustment instructions are then generated based on the redundant node identifiers to be removed, the suggested locations of new nodes, and the optimization range of the monitoring parameters of existing nodes.

[0131] Based on the adjustment instructions, the initial monitoring node deployment strategy is adjusted to generate a target monitoring node deployment plan.

[0132] In its implementation, the system first delves into the Nash equilibrium value to reveal the complex interactions between monitoring nodes under the initial deployment strategy. These nodes may form a collaborative relationship of shared responsibility due to overlapping monitoring ranges, or they may engage in a game-theoretic relationship of resource competition due to their shared impact on a pollution source. Based on this dynamic relationship and the existing pollution responsibility map, the system comprehensively evaluates the initial layout using spatial overlay analysis technology. This accurately identifies redundant monitoring areas where multiple nodes repeatedly cover the same areas, resulting in resource waste, as well as blind spots that are not effectively monitored due to missing nodes or excessive spacing. Based on this evaluation, the system intelligently generates a set of specific adjustment instructions, including suggestions for removing redundant nodes with low contribution rates, coordinate suggestions for adding nodes at key locations in blind spots, and optimization ranges for fine-tuning parameters such as the monitoring radius or sensitivity of retained nodes. Finally, the system automatically executes these adjustment instructions, iteratively optimizing the initial strategy to produce a target monitoring node deployment scheme with more rational resource allocation, more comprehensive monitoring coverage, and maximized overall benefits.

[0133] In one feasible implementation, after the step of generating a target monitoring node deployment scheme based on the initial monitoring node deployment strategy according to the Nash equilibrium value, the method further includes:

[0134] Based on the target monitoring node deployment plan, determine the coverage of key sensitive areas and the monitoring coverage of all pollution sources;

[0135] The comparison result is obtained by comparing the preset coverage threshold with the coverage and the monitoring coverage rate;

[0136] When the comparison results meet the adjustment requirements, the updated Nash equilibrium value is obtained by adjusting the game parameters or adding fixed nodes and recalculating the Nash equilibrium.

[0137] The target monitoring node is deployed and updated based on the updated Nash equilibrium value.

[0138] In its implementation, after generating the target deployment plan, the system immediately evaluates its coverage effect. The core objective is to calculate the effective coverage of key sensitive areas such as residential areas or water sources, as well as the comprehensive monitoring coverage rate of all known pollution sources. Subsequently, the system automatically compares these two key indicators with pre-set compliance thresholds. If the evaluation results indicate that the coverage of sensitive areas or the overall monitoring coverage rate does not meet the preset requirements, the system initiates a dynamic optimization process. This involves adjusting parameters such as cost coefficients or responsibility-sharing weights in the game model to change the decision-making tendencies of the participants, or having the competent authority directly pre-set a small number of fixed monitoring nodes in key blind spots. Afterward, the system re-runs the game calculation based on the adjusted conditions to obtain a new Nash equilibrium value reflecting the latest constraints. Finally, the system iteratively adjusts and optimizes the existing target deployment plan based on this updated equilibrium value, for example, guiding participants to deploy nodes in uncovered areas, thereby ensuring that the monitoring network meets the established coverage standards within the game framework.

[0139] In one feasible implementation, the method further includes:

[0140] Based on the latest environmental data collected periodically, an updated pollution liability map and an updated liability sharing coefficient are obtained;

[0141] Based on the updated responsibility sharing coefficients, the updated payoff function of the game model is obtained;

[0142] The Nash equilibrium is recalculated based on the updated revenue function to obtain the recalculated Nash equilibrium value. Based on the recalculated Nash equilibrium value and the updated pollution liability map, a dynamically adjusted target monitoring node deployment scheme is obtained.

[0143] In its implementation, the system periodically imports the latest environmental monitoring data, such as changes in pollutant concentrations or updates to enterprise emissions, to dynamically generate an updated pollution responsibility map reflecting the current pollution status and flow patterns. It also recalculates the responsibility allocation coefficients for each potential pollution source. Using these updated coefficients, the system continuously adjusts the payoff function of each participant in the game theory model to more accurately reflect the latest environmental responsibility relationships. Subsequently, based on the new payoff function, the system recalculates the Nash equilibrium to obtain an equilibrium solution that adapts to the current situation, reflecting the optimal strategy balance for each party under the current data. Finally, the system combines this newly calculated Nash equilibrium value with the latest pollution responsibility map to automatically adjust and optimize the existing monitoring node deployment scheme, such as reallocating node locations or adjusting monitoring priorities, thereby ensuring that the monitoring network can continuously and effectively adapt to the dynamic needs of environmental changes.

[0144] This embodiment provides a method for optimizing the deployment of monitoring nodes. It acquires the composition and attribute data of pollutants at the emission outlets of each pollution source within the monitoring area. Based on this data, it constructs pollution source feature vectors. Using these feature vectors, it determines the source attribution of pollutants, generates a pollution responsibility map, determines the responsibility allocation coefficient for each pollution source based on the pollution responsibility map, and determines the Nash equilibrium value for each monitoring node based on the responsibility allocation coefficient and the initial monitoring node deployment strategy. Finally, it optimizes the initial monitoring node deployment strategy based on the Nash equilibrium value to generate a target monitoring node deployment scheme. This method addresses the technical problem in existing technologies where poor monitoring performance is difficult to adapt to dynamic changes in pollution sources.

[0145] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the monitoring node deployment optimization method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0146] This application also provides a monitoring node deployment optimization device, please refer to... Figure 3 The monitoring node deployment optimization device includes:

[0147] The feature vector construction module 10 is used to acquire the composition data and attribute data of pollutants at the emission outlets of each pollution source within the monitoring area, and to construct pollution source feature vectors based on the composition data and the attribute data.

[0148] The responsibility map generation module 20 is used to determine the source attribution of the pollutants based on the pollution source feature vector, and generate a pollution responsibility map based on the source attribution;

[0149] The responsibility game calculation module 30 is used to determine the responsibility sharing 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 sharing coefficient and the initial monitoring node deployment strategy.

[0150] The deployment scheme determination module 40 is used to optimize the initial monitoring node deployment strategy based on the Nash equilibrium value and generate a target monitoring node deployment scheme.

[0151] In one feasible implementation, the feature vector construction module 10 is further used to acquire component data, attribute data and spectral data at the emission outlets of each pollution source within the monitoring area, and to obtain the original spectral dataset based on the spectral data;

[0152] After preprocessing the original spectral dataset, principal component analysis is performed to obtain the main spectral feature components;

[0153] The main spectral feature components, the component data, and the attribute data are vectorized and fused to generate a pollution source feature vector.

[0154] In one feasible implementation, the responsibility map generation module 20 is also used to train a random forest classifier based on a sample set of known-attributed pollution source feature vectors to obtain a pollutant source tracing model.

[0155] The pollution source feature vector is input into the pollutant source tracing model to obtain the source attribution of the pollutant, and the probability prediction result of each pollution source is determined based on the source attribution.

[0156] Based on the probability prediction results, the propagation trajectory and concentration distribution of the pollutants in the spatiotemporal range are simulated;

[0157] Based on the propagation trajectory and the concentration distribution, the pollution contribution of different geographical units within the monitoring area is determined, and a pollution responsibility map is generated based on the contribution.

[0158] In one feasible implementation, the responsibility game calculation module 30 is further used to calculate the cumulative contribution of each pollution source identified as a major contributor to pollutants in the environment within a preset historical period, based on the pollution responsibility map.

[0159] The cumulative contribution is weighted and fused with the real-time emission flow of the corresponding pollution source to obtain the absolute pollution contribution.

[0160] The responsibility allocation coefficient is determined based on the absolute pollution contribution of all pollution sources.

[0161] In one feasible implementation, the responsibility game calculation module 30 is further configured to construct a non-cooperative game model with the pollution sources as participants and the deployment or non-deployment of monitoring nodes as a strategy, based on each pollution source within the monitoring area and the responsibility sharing coefficient.

[0162] Based on deployment costs, actual costs adjusted by the aforementioned responsibility-sharing coefficients, changes in pollution exposure risk, and the benefits of collaborative governance, the payoff functions for each participant are obtained.

[0163] The initial strategy combination of the non-cooperative game model is set according to the initial monitoring node deployment strategy;

[0164] The initial strategy combination is updated according to the response iteration algorithm and the revenue function to obtain the stable Nash equilibrium state and corresponding Nash equilibrium value of all participants' strategies.

[0165] In one feasible implementation, the responsibility game calculation module 30 is further configured to obtain, based on the effective monitoring radius of the monitoring node, the set of other participants within the monitoring coverage area of ​​the monitoring node when any participant deploys a node;

[0166] Based on the pollution liability map, the responsibility sharing ratio of the participants in the deployment node for the pollution of other participants in the set of other participants is obtained;

[0167] Based on the preset collaborative weight coefficient and the responsibility sharing ratio, the collaborative governance benefit value generated by the participant due to the deployment of nodes is obtained;

[0168] Based on the deployment cost, the actual cost adjusted by the aforementioned responsibility sharing coefficient, the change in pollution exposure risk, and the aforementioned collaborative governance benefit value, the revenue function of each participant is obtained.

[0169] In one feasible implementation, the deployment scheme determination module 40 is further configured to determine the collaborative and competitive relationship between the initial monitoring nodes in the initial monitoring node deployment strategy in terms of pollution monitoring responsibility based on the Nash equilibrium value.

[0170] Based on the cooperative and competitive relationships and the pollution liability map, the monitoring redundancy areas and monitoring blind spots in the initial monitoring node deployment strategy are evaluated, and the evaluation results are obtained.

[0171] Based on the evaluation results, the redundant node identifiers to be removed, the suggested locations of new nodes, and the optimization range of the monitoring parameters of existing nodes are determined. Adjustment instructions are then generated based on the redundant node identifiers to be removed, the suggested locations of new nodes, and the optimization range of the monitoring parameters of existing nodes.

[0172] Based on the adjustment instructions, the initial monitoring node deployment strategy is adjusted to generate a target monitoring node deployment plan.

[0173] In one feasible implementation, the deployment scheme determination module 40 is further configured to determine the coverage of key sensitive areas and the monitoring coverage rate of all pollution sources based on the target monitoring node deployment scheme.

[0174] The comparison result is obtained by comparing the preset coverage threshold with the coverage and the monitoring coverage rate;

[0175] When the comparison results meet the adjustment requirements, the updated Nash equilibrium value is obtained by adjusting the game parameters or adding fixed nodes and recalculating the Nash equilibrium.

[0176] The target monitoring node is deployed and updated based on the updated Nash equilibrium value.

[0177] In one feasible implementation, the deployment scheme determination module 40 is further configured to obtain an updated pollution liability map and an updated liability sharing coefficient based on the latest environmental data collected periodically.

[0178] Based on the updated responsibility sharing coefficients, the updated payoff function of the game model is obtained;

[0179] The Nash equilibrium is recalculated based on the updated revenue function to obtain the recalculated Nash equilibrium value. Based on the recalculated Nash equilibrium value and the updated pollution liability map, a dynamically adjusted target monitoring node deployment scheme is obtained.

[0180] The monitoring node deployment optimization device provided in this application, employing the monitoring node deployment optimization method in the above embodiments, can solve the technical problem of poor monitoring effect caused by difficulty in adapting to dynamic changes in pollution sources. Compared with the prior art, the beneficial effects of the monitoring node deployment optimization device provided in this application are the same as those of the monitoring node deployment optimization method provided in the above embodiments, and other technical features in the monitoring node deployment optimization device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0181] This application provides a monitoring node deployment optimization device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; 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 execute the monitoring node deployment optimization method in the first embodiment described above.

[0182] The following is for reference. Figure 4 The diagram illustrates a structural schematic of a monitoring node deployment optimization device suitable for implementing embodiments of this application. The monitoring node deployment optimization device in these embodiments may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 4 The monitoring node deployment optimization device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0183] like Figure 4As shown, the monitoring node deployment optimization device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in ROM (Read Only Memory) 1002 or a program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the monitoring node deployment optimization device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touch screens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, LCDs (Liquid Crystal Displays), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows monitoring node deployment optimization equipment to communicate wirelessly or wiredly with other devices to exchange data. While the figure shows monitoring node deployment optimization equipment with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0184] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0185] The monitoring node deployment optimization device provided in this application, employing the monitoring node deployment optimization method in the above embodiments, can solve the technical problem of monitoring node deployment optimization. Compared with the prior art, the beneficial effects of the monitoring node deployment optimization device provided in this application are the same as the beneficial effects of the monitoring node deployment optimization method provided in the above embodiments, and other technical features in this monitoring node deployment optimization device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0186] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0187] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0188] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the monitoring node deployment optimization method in the above embodiments.

[0189] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory or Flash Memory), optical fibers, CD-ROM (CD-Read Only Memory), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may 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 may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0190] The aforementioned computer-readable storage medium may be included in the monitoring node deployment optimization device; or it may exist independently and not be assembled into the monitoring node deployment optimization device.

[0191] The aforementioned computer-readable storage medium carries one or more programs. When the aforementioned one or more programs are executed by the monitoring node deployment optimization device, the monitoring node deployment optimization device: acquires the composition data and attribute data of pollutants at the emission outlets of each pollution source within the monitoring area, and constructs a pollution source feature vector based on the composition data and the attribute data;

[0192] Based on the pollution source feature vector, the source attribution of the pollutants is determined, and a pollution responsibility map is generated based on the source attribution.

[0193] Based on the pollution responsibility map, the responsibility sharing coefficient of each pollution source is determined, and based on the responsibility sharing coefficient and the initial monitoring node deployment strategy, the Nash equilibrium value of each monitoring node is determined.

[0194] The initial monitoring node deployment strategy is optimized based on the Nash equilibrium value to generate a target monitoring node deployment scheme.

[0195] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including LAN (Local Area Network) or WAN (Wide Area Network)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0196] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0197] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0198] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described monitoring node deployment optimization method, and is capable of solving the technical problem of monitoring node deployment optimization. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the monitoring node deployment optimization method provided in the above embodiments, and will not be repeated here.

[0199] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the monitoring node deployment optimization method described above.

[0200] The computer program product provided in this application can solve the technical problem of monitoring node deployment optimization. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the monitoring node deployment optimization method provided in the above embodiments, and will not be repeated here.

[0201] The above are only some embodiments of this application and do not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for optimizing the deployment of monitoring nodes, characterized in that, The method for optimizing the deployment of monitoring nodes includes: The composition and attribute data of pollutants at the emission outlets of each pollution source within the monitoring area are acquired. Based on the composition and attribute data, a pollution source feature vector is constructed. The composition data refers to data on the chemical or physical composition characteristics of the pollutants themselves, used to describe the type, concentration, isotope ratio, and characteristic spectral fingerprint of the pollutants. The attribute data refers to background information and static characteristic data related to the pollution source, including at least the geographical coordinates of the pollution source and the type of enterprise to which it belongs. Based on the pollution source feature vector, the source attribution of the pollutants is determined, and a pollution responsibility map is generated based on the source attribution. Based on the pollution responsibility map, the responsibility sharing coefficient of each pollution source is determined, and based on the responsibility sharing coefficient and the initial monitoring node deployment strategy, the Nash equilibrium value of each monitoring node is determined. The initial monitoring node deployment strategy is optimized based on the Nash equilibrium value to generate a target monitoring node deployment scheme; The step of optimizing the initial monitoring node deployment strategy based on the Nash equilibrium value to generate the target monitoring node deployment scheme includes: Based on the Nash equilibrium value, determine the collaborative and competitive relationships among the initial monitoring nodes in the initial monitoring node deployment strategy regarding pollution monitoring responsibilities; Based on the cooperative and competitive relationships and the pollution liability map, the monitoring redundancy areas and monitoring blind spots in the initial monitoring node deployment strategy are evaluated, and the evaluation results are obtained. Based on the evaluation results, the redundant node identifiers to be removed, the suggested locations of new nodes, and the optimization range of the monitoring parameters of existing nodes are determined. Adjustment instructions are then generated based on the redundant node identifiers to be removed, the suggested locations of new nodes, and the optimization range of the monitoring parameters of existing nodes. Based on the adjustment instructions, the initial monitoring node deployment strategy is adjusted to generate a target monitoring node deployment plan.

2. The method as described in claim 1, characterized in that, The step of acquiring the composition and attribute data of pollutants at the emission outlets of each pollution source within the monitoring area, and constructing pollution source feature vectors based on the composition and attribute data, includes: Acquire component data, attribute data, and spectral data at the emission outlets of each pollution source within the monitoring area, and obtain the raw spectral dataset based on the spectral data; After preprocessing the original spectral dataset, principal component analysis is performed to obtain the main spectral feature components; The main spectral feature components, the component data, and the attribute data are vectorized and fused to generate a pollution source feature vector.

3. The method as described in claim 1, characterized in that, The step of determining the source attribution of the pollutants based on the pollution source feature vector, and generating a pollution responsibility map based on the source attribution, includes: A random forest classifier is trained based on a sample set of pollution source feature vectors with known attribution to obtain a pollutant source tracing model. The pollution source feature vector is input into the pollutant source tracing model to obtain the source attribution of the pollutant, and the probability prediction result of each pollution source is determined based on the source attribution. Based on the probability prediction results, the propagation trajectory and concentration distribution of the pollutants in the spatiotemporal range are simulated; Based on the propagation trajectory and the concentration distribution, the pollution contribution of different geographical units within the monitoring area is determined, and a pollution responsibility map is generated based on the contribution.

4. The method as described in claim 1, characterized in that, The step of determining the responsibility allocation coefficient for each pollution source based on the pollution responsibility map includes: Based on the pollution liability map, the cumulative contribution of each pollution source identified as a major contributor to pollutants in the environment within a preset historical period is calculated. The cumulative contribution is weighted and fused with the real-time emission flow of the corresponding pollution source to obtain the absolute pollution contribution. The responsibility allocation coefficient is determined based on the absolute pollution contribution of all pollution sources.

5. The method as described in claim 1, characterized in that, The step of determining the Nash equilibrium value of each monitoring node based on the responsibility sharing coefficient and the initial monitoring node deployment strategy includes: Based on the pollution sources within the monitoring area and the responsibility sharing coefficient, a non-cooperative game model is constructed with the pollution sources as participants and the strategy of deploying or not deploying monitoring nodes as the strategy. Based on deployment costs, actual costs adjusted by the aforementioned responsibility-sharing coefficients, changes in pollution exposure risk, and the benefits of collaborative governance, the payoff functions for each participant are obtained. The initial strategy combination of the non-cooperative game model is set according to the initial monitoring node deployment strategy; The initial strategy combination is updated according to the response iteration algorithm and the revenue function to obtain the stable Nash equilibrium state and corresponding Nash equilibrium value of all participants' strategies.

6. The method as described in claim 5, characterized in that, The step of deriving the benefit function for each participant based on deployment costs, actual costs adjusted by the responsibility-sharing coefficient, changes in pollution exposure risk, and collaborative governance benefits includes: Based on the effective monitoring radius of the monitoring node, obtain the set of other participants within the monitoring coverage area of ​​any participant when the node is deployed. Based on the pollution liability map, the responsibility sharing ratio of the participants in the deployment node for the pollution of other participants in the set of other participants is obtained; Based on the preset collaborative weight coefficient and the responsibility sharing ratio, the collaborative governance benefit value generated by the participant due to the deployment of nodes is obtained; Based on the deployment cost, the actual cost adjusted by the aforementioned responsibility sharing coefficient, the change in pollution exposure risk, and the aforementioned collaborative governance benefit value, the revenue function of each participant is obtained.

7. The method as described in claim 1, characterized in that, After the step of generating a target monitoring node deployment scheme based on the initial monitoring node deployment strategy according to the Nash equilibrium value, the method further includes: Based on the target monitoring node deployment plan, determine the coverage of key sensitive areas and the monitoring coverage of all pollution sources; The comparison result is obtained by comparing the preset coverage threshold with the coverage and the monitoring coverage rate; When the comparison results meet the adjustment requirements, the updated Nash equilibrium value is obtained by adjusting the game parameters or adding fixed nodes and recalculating the Nash equilibrium. The target monitoring node is deployed and updated based on the updated Nash equilibrium value.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: Based on the latest environmental data collected periodically, an updated pollution liability map and an updated liability sharing coefficient are obtained; Based on the updated responsibility sharing coefficients, the updated payoff function of the game model is obtained; The Nash equilibrium is recalculated based on the updated revenue function to obtain the recalculated Nash equilibrium value. Based on the recalculated Nash equilibrium value and the updated pollution liability map, a dynamically adjusted target monitoring node deployment scheme is obtained.

9. A monitoring node deployment optimization device, characterized in that, The monitoring node deployment optimization device includes: The feature vector construction module is used to acquire the composition data and attribute data of pollutants at the emission outlets of each pollution source within the monitoring area, and construct pollution source feature vectors based on the composition data and attribute data. The composition data refers to data on the chemical or physical composition characteristics of the pollutants themselves, used to describe the type, concentration, isotope ratio, and characteristic spectral fingerprint of the pollutants; the attribute data refers to background information and static feature data related to the pollution source, including at least the geographical coordinates of the pollution source and the type of enterprise to which it belongs. The responsibility map generation module is used to determine the source attribution of the pollutants based on the pollution source feature vector, and generate a pollution responsibility map based on the source attribution; The responsibility game calculation module is used to determine the responsibility sharing 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 sharing coefficient and the initial monitoring node deployment strategy. The deployment scheme determination module is used to optimize the initial monitoring node deployment strategy based on the Nash equilibrium value and generate a target monitoring node deployment scheme; The step of optimizing the initial monitoring node deployment strategy based on the Nash equilibrium value to generate the target monitoring node deployment scheme includes: Based on the Nash equilibrium value, determine the collaborative and competitive relationships among the initial monitoring nodes in the initial monitoring node deployment strategy regarding pollution monitoring responsibilities; Based on the cooperative and competitive relationships and the pollution liability map, the monitoring redundancy areas and monitoring blind spots in the initial monitoring node deployment strategy are evaluated, and the evaluation results are obtained. Based on the evaluation results, the redundant node identifiers to be removed, the suggested locations of new nodes, and the optimization range of the monitoring parameters of existing nodes are determined. Adjustment instructions are then generated based on the redundant node identifiers to be removed, the suggested locations of new nodes, and the optimization range of the monitoring parameters of existing nodes. Based on the adjustment instructions, the initial monitoring node deployment strategy is adjusted to generate a target monitoring node deployment plan.

Images