Ecological environment quality monitoring and early warning method, product, equipment and medium

Abstract

The invention relates to the technical field of ecological environment monitoring, in particular to an ecological environment quality monitoring and early warning method, a product, equipment and a medium. The method comprises the steps of performing correlation analysis on historical environment data and historical influence factor data, and determining influence factor data with strong correlation in each environment index in the historical environment data; establishing a multi-output regression model; obtaining current influence factor data, performing prediction based on the current influence factor data to obtain predicted influence factor data, and inputting the predicted influence factor data into the multi-output regression model to obtain predicted environment data; and analyzing and predicting standard-exceeding environment indexes in the environment data, performing early warning on the standard-exceeding environment indexes, generating an influence factor list corresponding to the standard-exceeding environment indexes, and determining rectification measures based on the influence factor list. According to the invention, timely early warning and rectification guidance can be carried out on the condition that the ecological environment indexes exceed the standard, and scientific and effective decision support can be provided for environmental protection and treatment.

Description

Technical Field

[0001] The present application relates to the technical field of ecological environment monitoring, and in particular to an ecological environment quality monitoring and early warning method, product, equipment and medium. Background Art

[0002] In the field of ecological environment monitoring, with the widespread deployment of air quality monitoring stations and water quality monitoring stations, researchers are able to efficiently collect massive amounts of environmental data with the help of sensor technology. These data form a solid foundation for in-depth analysis of the spatial distribution of pollutants and their potential sources. However, the current intensification of global climate change and the continued and profound impact of human activities on the natural environment have made the quality characteristics of the ecological environment increasingly complex and variable.

[0003] As far as existing technologies are concerned, ecological environment monitoring mainly relies on fixed monitoring stations for data collection, supplemented by cutting-edge scientific and technological means such as satellite remote sensing to obtain more comprehensive and extensive environmental information. Although these methods can effectively reflect the overall environmental conditions to a certain extent, their limitation is that they can only be monitored when the environmental quality has deteriorated to a certain extent, making it difficult to achieve the function of early warning. Summary of the invention

[0004] In order to solve the problem that existing technologies are difficult to achieve early warning of the ecological environment, the present application provides an ecological environment quality monitoring and early warning method, product, equipment and medium.

[0005] In the first aspect, this application provides an ecological environment quality monitoring and early warning method, which adopts the following technical solutions: An ecological environment quality monitoring and early warning method, comprising: Acquire historical environmental data and historical influencing factor data, perform correlation analysis on the historical environmental data and the historical influencing factor data, and determine influencing factor data with strong correlation to each environmental indicator in the historical environmental data from the historical influencing factor data; Establishing a multi-output regression model based on the historical environmental data and the influencing factor data corresponding to each environmental indicator; Acquire current influencing factor data, perform prediction based on the current influencing factor data to obtain predicted influencing factor data, and input the predicted influencing factor data into the multi-output regression model to obtain predicted environmental data; Analyze the exceeded environmental indicators in the predicted environmental data, issue early warnings for the exceeded environmental indicators, generate a list of influencing factors corresponding to the exceeded environmental indicators, and determine corrective measures based on the list of influencing factors.

[0006] By adopting the above technical solutions, comprehensive historical environmental data and influencing factor data are collected, which helps to more accurately identify the relationship between environmental indicators and influencing factors. Through correlation analysis, it helps to screen out key variables from many influencing factors, reduce model complexity, improve model efficiency and accuracy, clarify the key influencing factors of each environmental indicator, and provide accurate independent variable selection for establishing a multi-output regression model. The model can predict multiple environmental indicators at the same time, improve prediction efficiency and practicality, obtain current influencing factor data in real time, and predict it, providing a basis for timely warning and decision-making. The predicted influencing factor data can reflect the environmental change trend in the future period, which helps to take measures in advance. Through model prediction, it is possible to understand the changes in future environmental indicators in advance, provide a time window for environmental protection and governance, warn of excessive environmental indicators, and generate a list of influencing factors corresponding to the excessive environmental indicators, which helps to quickly locate the cause of the excessive, provide direction for rectification measures, and form a closed loop of continuous improvement.

[0007] In a preferred example, the present application may be further configured as follows: determining a list of influencing factors from the influencing factors that are strongly associated with the excessive environmental indicators includes: Acquire the exceeding-standard influencing factors that are strongly correlated with the exceeding-standard environmental index, and determine the historical data corresponding to the exceeding-standard influencing factors from the historical influencing factor data as the exceeding-standard influencing factor data; Determine the number of the exceeding-standard influencing factors; If the number of the exceeding-standard influencing factors is one, obtaining a correlation coefficient matrix between the historical environmental data and the historical influencing factor data, and generating an influencing factor list based on the exceeding-standard influencing factors and the correlation coefficient matrix; If the number of the exceeding standard influencing factors is not one, the degree of freedom between each exceeding standard influencing factor and the corresponding exceeding standard influencing factor data is calculated, and the exceeding standard influencing factors are sorted from high to low according to the degree of freedom to obtain the influencing factor list.

[0008] By adopting the above technical solution, the key factors that lead to excessive environmental indicators can be accurately identified, and by analyzing the number of factors affecting the excessive standards and their degree of separation from historical data, a list of influencing factors can be generated according to the correlation. When the influencing factor is single, the list is directly generated using the correlation coefficient matrix to ensure relevance. When the influencing factors are diverse, they are sorted according to the degree of separation to highlight the factors with the greatest impact, providing strong support for the formulation of effective rectification measures.

[0009] In a preferred example, the present application may be further configured to: generate corrective measures corresponding to the list of influencing factors, including: Starting from the first influencing factor in the influencing factor list, adjusting steps are performed on each influencing factor in turn until there is no excessive environmental index in the updated predicted environmental data; Among them, the adjustment step includes: adjusting the influencing factor data corresponding to the current influencing factor in the predicted influencing factor data, inputting the adjusted predicted influencing factor data into the multi-output regression model to obtain updated predicted environmental data, and analyzing whether there are any excessive environmental indicators in the updated predicted environmental data.

[0010] By adopting the above technical solution, adjusting the factors in the list of influencing factors one by one, and using the multi-output regression model in real time to predict changes in environmental data, it is possible to systematically and specifically eliminate excessive environmental indicators, ensure the effectiveness and accuracy of rectification measures, and ultimately achieve the goal of improving environmental quality.

[0011] In a preferred example, the present application may be further configured as follows: the calculation of the degree of freedom between each exceeding standard influencing factor and the corresponding exceeding standard influencing factor data includes: For any exceeding standard influencing factor, calculate the average value and data fluctuation range of the exceeding standard influencing factor data corresponding to the exceeding standard influencing factor; The ratio of the absolute value of the difference between the exceeding standard influencing factor and the average value to the data fluctuation range is calculated as the degree of freedom between the exceeding standard influencing factor and the corresponding exceeding standard influencing factor data.

[0012] By adopting the above technical solution, the degree of deviation of the data of the factors affecting the exceeding of the standard relative to their average value and the ratio of the data fluctuation range can be quantitatively analyzed, which can accurately evaluate the discreteness and instability of the data of each factor affecting the exceeding of the standard, thereby effectively identifying the key factors with the greatest impact and the most unstable on the exceeding of environmental indicators.

[0013] In a preferred example, the present application may be further configured as follows: performing correlation analysis on the historical environmental data and the historical influencing factor data, and determining from the historical influencing factor data influencing factor data that each environmental indicator in the historical environmental data is strongly correlated with the influencing factor data, includes: Calculating a correlation coefficient matrix between the historical environmental data and the historical influencing factor data, wherein each row in the correlation coefficient matrix represents an environmental indicator and each column represents an influencing factor; Determine the initial influencing factors corresponding to the target environmental indicator based on the correlation coefficient matrix, extract data corresponding to the initial influencing factors from the historical influencing factor data as candidate features, and the target environmental indicator is any environmental indicator in the historical environmental data; Constructing a covariance matrix of the candidate features, and performing eigendecomposition on the covariance matrix to obtain eigenvalues ​​and eigenvectors; A principal component vector is determined from the eigenvalue based on the eigenvalue, and data corresponding to the principal component vector in the historical influencing factor data is projected onto the principal component vector to obtain influencing factor data that is strongly correlated with the target environmental indicator.

[0014] By adopting the above technical solution, calculating the correlation coefficient matrix, extracting candidate features, constructing the covariance matrix and performing feature decomposition, it is possible to accurately identify key influencing factor data that are highly correlated with the target environmental indicators. The projection results of these data effectively reveal the strong correlation between the influencing factors and environmental indicators.

[0015] In a preferred example, the present application may be further configured as follows: the multi-output regression model is established based on the historical environmental data and the influencing factor data corresponding to each environmental indicator, including: An initial regression model is defined, wherein the initial regression model includes a time feature processing layer, wherein the time feature processing layer is used to extract time features from data received by a model input layer, and the number of neurons in an output layer of the initial regression model is consistent with the number of environmental indicators in the historical environmental data; The initial regression model is trained based on the historical environmental data and the influencing factor data corresponding to each environmental indicator to obtain a trained multi-output regression model.

[0016] By adopting the above technical solution, defining an initial regression model that includes a time feature processing layer and training it based on data, we can build a regression model that not only takes into account the temporal dynamic characteristics but also accurately matches the outputs of multiple environmental indicators, effectively improving the model's predictive ability and applicability for complex environmental changes.

[0017] In a preferred example, the present application can be further configured as follows: the method further includes: Monitor current environmental data in real time and determine whether there are any environmental indicators that exceed the standard in the current environmental data; When there are current exceeding environmental indicators in the current environmental data, determine the duration and degree of exceeding of the current exceeding environmental indicators, determine the exceeding level according to the duration and degree of exceeding, and issue an alarm signal corresponding to the exceeding level.

[0018] By adopting the above technical solutions, environmental deterioration can be quickly identified, and detailed information on exceeding standards can be provided in a timely manner, facilitating rapid response and effective measures, thereby effectively protecting the environment and public health.

[0019] In a second aspect, the present application provides a computer program product, which adopts the following technical solution: A computer program product includes a computer program. When the computer program is executed by a processor, it implements the ecological environment quality monitoring and early warning method as described in any one of the first aspects.

[0020] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: one or more processors; Memory; At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the ecological environment quality monitoring and early warning method as described in any one of the first aspects.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to execute the ecological environment quality monitoring and early warning method as described in any one of the first aspects.

[0022] In summary, this application includes the following beneficial technical effects: This application helps to more accurately identify the relationship between environmental indicators and influencing factors by collecting comprehensive historical environmental data and influencing factor data. Through correlation analysis, it helps to screen out key variables from numerous influencing factors, reduce model complexity, improve model efficiency and accuracy, clarify the key influencing factors of each environmental indicator, and provide accurate independent variable selection for establishing a multi-output regression model. The model can predict multiple environmental indicators at the same time, improve prediction efficiency and practicality, obtain current influencing factor data in real time, and predict it, providing a basis for timely warning and decision-making. The predicted influencing factor data can reflect the environmental change trend in the future period of time, which helps to take measures in advance. Through model prediction, it is possible to understand the changes in future environmental indicators in advance, provide a time window for environmental protection and governance, warn of excessive environmental indicators, and generate a list of influencing factors corresponding to the excessive environmental indicators, which helps to quickly locate the causes of the excessive standards, provide direction for rectification measures, and form a closed loop of continuous improvement. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flow chart of an ecological environment quality monitoring and early warning method provided in an embodiment of the present application; Figure 2 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The following is combined with Figure 1 -Attached Figure 2This application is described in further detail.

[0025] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make modifications to the present embodiment without any creative contribution as needed, but such modifications are protected by the patent law as long as they are within the scope of the claims of the present application.

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0027] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0028] It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the embodiments of the present application involve data related to the object, it needs to be obtained with the authorization and consent of the object, the authorization and consent of the relevant departments, and in compliance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiments, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained. The embodiments also need to be implemented with the authorization and consent of the object.

[0029] The present application embodiment provides an ecological environment quality monitoring and early warning method, such as Figure 1As shown, the method provided in the embodiment of the present application is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. The method includes steps S101 to S104, wherein: S101. Obtain historical environmental data and historical influencing factor data, perform correlation analysis on the historical environmental data and the historical influencing factor data, and determine influencing factor data with strong correlation to each environmental indicator in the historical environmental data from the historical influencing factor data.

[0030] Specifically, historical environmental data and historical influencing factor data can be pre-stored in the database. Historical environmental data refers to data on environmental conditions such as air quality, water quality, and soil pollution, including but not limited to: PM2.5 concentration, sulfur dioxide concentration, dissolved oxygen content in water, heavy metal content, etc. Historical influencing factor data refers to various factor data related to environmental conditions, including but not limited to: industrial emissions, meteorological conditions (temperature, humidity, rainfall, snowfall), traffic flow, intensity of agricultural activities, etc.

[0031] Furthermore, correlation analysis of historical environmental data and historical influencing factor data can be achieved by calculating the correlation coefficient matrix and characteristic decomposition technology. The correlation technology matrix clarifies the degree of correlation between environmental indicators and influencing factors. Based on the characteristic decomposition technology, influencing factors and influencing factor data that are strongly correlated with each environmental indicator can be extracted from the historical influencing factor data.

[0032] S102: Establish a multi-output regression model based on historical environmental data and influencing factor data corresponding to each environmental indicator.

[0033] The historical environmental data and the influencing factor data corresponding to each environmental indicator are the data basis for model training. Since the historical environmental data and the historical influencing factor data are data with time characteristics, a time feature processing layer can be set in the multi-output regression model to extract features from the historical environmental data and historical influencing factor data received by the input layer. In order to enable the trained multi-output regression model to output the influencing factor data of each environmental indicator, the number of neurons in the model output layer can be defined to be equal to the number of environmental indicators in the historical environmental data.

[0034] S103, obtaining current influencing factor data, and performing prediction based on the current influencing factor data to obtain predicted influencing factor data, and inputting the predicted influencing factor data into a multi-output regression model to obtain predicted environmental data.

[0035] Specifically, after determining the influencing factor data corresponding to each environmental indicator based on historical environmental data and historical influencing factor data, the influencing factor data corresponding to each current environmental indicator can be collected in real time as current influencing factor data, so that the collected current influencing factor data can be determined as data that can affect the environmental indicator.

[0036] Furthermore, the current influencing factor data can be predicted using a time prediction algorithm (such as ARIMA, LSTM, etc.) to obtain predicted influencing factor data. The predicted influencing factor data is input into a multi-output regression model to obtain predicted environmental data for a period of time in the future. The duration of the predicted environmental data can be set according to actual needs, and this embodiment does not specifically limit it.

[0037] S104, analyzing and predicting the environmental indicators that exceed the standard in the environmental data, issuing early warnings for the environmental indicators that exceed the standard, and generating a list of influencing factors corresponding to the environmental indicators that exceed the standard, and determining rectification measures based on the list of influencing factors.

[0038] Specifically, the predicted environmental data includes the numerical changes of multiple environmental indicators over a period of time. For any environmental indicator, it is used as the target environmental indicator, and the predicted environmental data corresponding to the target environmental indicator is determined from the predicted environmental data. The preset safety standards of the target environmental indicators are extracted from the database. The preset safety standards corresponding to each environmental indicator can be set by technical personnel according to laws, regulations and actual experience and stored in the database. The predicted environmental data corresponding to the target environmental indicator are compared with the preset safety standards to find out whether the predicted environmental data at certain times exceeds the preset safety standards. If so, the target environmental indicator is determined to be an excessive environmental indicator. If not, the target environmental indicator is determined to be a normal environmental indicator. All excessive environmental indicators are searched. The number of excessive environmental indicators can be one or more, which is not limited in this embodiment.

[0039] If there are multiple environmental indicators that exceed the standard, a corresponding list of influencing factors and rectification measures are generated for each environmental indicator that exceeds the standard. Taking any environmental indicator that exceeds the standard as an example, the influencing factors associated with the environmental indicator that exceeds the standard are arranged from large to small according to the correlation to obtain a list of influencing factors. The rectification measures include pre-adjusting the influencing factors in the list of influencing factors.

[0040] This embodiment helps to more accurately identify the relationship between environmental indicators and influencing factors by collecting comprehensive historical environmental data and influencing factor data. Through correlation analysis, it helps to screen out key variables from numerous influencing factors, reduce model complexity, improve model efficiency and accuracy, clarify the key influencing factors of each environmental indicator, and provide accurate independent variable selection for establishing a multi-output regression model. The model can predict multiple environmental indicators at the same time, improve prediction efficiency and practicality, obtain current influencing factor data in real time, and predict it, providing a basis for timely warning and decision-making. The predicted influencing factor data can reflect the environmental change trend in the future period of time, which helps to take measures in advance. Through model prediction, it is possible to understand the changes in future environmental indicators in advance, provide a time window for environmental protection and governance, warn of excessive environmental indicators, and generate a list of influencing factors corresponding to the excessive environmental indicators, which helps to quickly locate the cause of the excessive, provide direction for rectification measures, and form a closed loop of continuous improvement.

[0041] A possible implementation of the embodiment of the present application is to perform a correlation analysis on the historical environmental data and the historical influencing factor data, and determine the influencing factor data with which each environmental indicator in the historical environmental data is strongly correlated from the historical influencing factor data, including: Calculate the correlation coefficient matrix of historical environmental data and historical influencing factor data, where each row in the correlation coefficient matrix represents an environmental indicator and each column represents an influencing factor; Determine the initial influencing factors corresponding to the target environmental indicators based on the correlation coefficient matrix, extract the data corresponding to the initial influencing factors from the historical influencing factor data as candidate features, and the target environmental indicator is any environmental indicator in the historical environmental data; Construct the covariance matrix of the candidate features and perform eigendecomposition on the covariance matrix to obtain eigenvalues ​​and eigenvectors; The principal component vector is determined from the eigenvector based on the eigenvalue, and the data corresponding to the principal component vector in the historical influencing factor data is projected onto the principal component vector to obtain the influencing factor data that is strongly correlated with the target environmental indicator.

[0042] Specifically, the historical environmental data includes time series data of multiple environmental indicators, and the historical influencing factor data includes time series data of multiple factors that may affect the environmental indicators. The correlation coefficient between the historical environmental data and the historical influencing factor data is calculated using statistical methods such as the Pearson correlation coefficient and the Spearman rank correlation coefficient. The result is a correlation coefficient matrix. The values ​​in the correlation coefficient matrix represent the linear correlation strength between the environmental indicators and the influencing factors. The technical staff sets a correlation coefficient threshold based on actual needs or experience to screen out the initial influencing factors that have a significant correlation with the target environmental indicators. Based on the correlation coefficient matrix, the influencing factors whose correlation with the target environmental indicators exceeds the correlation coefficient threshold are screened as the initial influencing factors.

[0043] The covariance matrix reflects the strength and direction of the linear relationship between the candidate features. The eigenvalues ​​obtained by eigendecomposing the covariance matrix represent the variance of the data distribution on the corresponding eigenvector, that is, the amount of information in this direction. Based on the eigenvalues, a specific number of eigenvectors with larger eigenvalues ​​are selected as principal component vectors. The principal component vector contains the main information of the data. By calculating the dot product of the data and the principal component vector, the data corresponding to the principal component in the historical influencing factors can be projected onto the principal component vector. The projected data reflects the projection of the influencing factors in the direction of the principal component, that is, the strong correlation between the influencing factors and the target environmental indicators. The projected data with higher projection values ​​are selected as the influencing factor data that are strongly correlated with the target environmental indicators. The standard for judging whether it is a higher projection value and the number of principal component vectors can be flexibly set, and this embodiment does not make specific restrictions.

[0044] This embodiment can accurately identify key influencing factor data that are highly correlated with the target environmental indicators by calculating the correlation coefficient matrix, extracting candidate features, constructing the covariance matrix and performing feature decomposition. The projection results of these data effectively reveal the strong correlation between the influencing factors and the environmental indicators.

[0045] A possible implementation of the embodiment of the present application is to establish a multi-output regression model based on historical environmental data and influencing factor data corresponding to each environmental indicator, including: Define an initial regression model, which includes a time feature processing layer, which is used to extract time features from data received by the model input layer. The number of neurons in the output layer of the initial regression model is consistent with the number of environmental indicators in the historical environmental data. The initial regression model is trained based on historical environmental data and the influencing factor data corresponding to each environmental indicator to obtain a trained multi-output regression model.

[0046] In this embodiment, an initial regression model is defined, which includes an input layer, a time feature processing layer, a hidden layer and an output layer. The input layer is used to input historical environmental data and influencing factor data corresponding to each environmental indicator. The hidden layer is used to learn the nonlinear relationship in the data. The output layer is used to output the predicted value of the environmental indicator. Each neuron in the output layer corresponds to an environmental indicator.

[0047] The historical environmental data and the influencing factor data corresponding to each environmental indicator are divided into training set, validation set and test set. The initial regression model is trained using the training set data. The model parameters are continuously adjusted through optimization methods such as back propagation algorithm and gradient descent to minimize the loss function. The performance of the model is evaluated on the validation set, such as calculating the error between the predicted value and the true value, drawing the prediction curve, etc., to check whether the model is overfitting or underfitting, and adjusting the model structure or hyperparameters as needed. According to the verification results, the model is tuned to improve the prediction performance of the model. The trained multi-output regression model is applied to the actual environmental prediction, and the future environmental indicator values ​​are predicted based on the input influencing factor data.

[0048] This embodiment defines an initial regression model that includes a time feature processing layer and trains it based on data. It is able to construct a regression model that not only takes into account temporal dynamic characteristics but also accurately matches the outputs of multiple environmental indicators, effectively improving the model's predictive ability and applicability for complex environmental changes.

[0049] A possible implementation of the embodiment of the present application is to determine a list of influencing factors from influencing factors that are strongly associated with excessive environmental indicators, including: Obtaining the exceeding-standard influencing factors that are strongly correlated with the exceeding-standard environmental indicators, and determining the historical data corresponding to the exceeding-standard influencing factors from the historical influencing factor data as the exceeding-standard influencing factor data; Determine the number of factors that affect exceeding the standard; If the number of influencing factors exceeding the standard is one, a correlation coefficient matrix of historical environmental data and historical influencing factor data is obtained, and an influencing factor list is generated based on the influencing factors exceeding the standard and the correlation coefficient matrix; If the number of influencing factors exceeding the standard is not one, the degree of freedom between each influencing factor exceeding the standard and the corresponding influencing factor data exceeding the standard is calculated, and the influencing factors exceeding the standard are sorted from high to low according to the degree of freedom to obtain an influencing factor list.

[0050] The target environmental indicator that exceeds the standard represents any environmental indicator that exceeds the standard. In a possible case, the number of the exceeding influencing factors of the target environmental indicator that exceeds the standard is one, and the exceeding influencing factor is set as the first in the influencing factor list, and each influencing factor other than the exceeding influencing factor corresponding to the first that is associated with the target environmental indicator that exceeds the standard is determined from the correlation coefficient matrix, and each influencing factor is arranged after the first according to the correlation coefficient from large to small, and a list of influencing factors that have been arranged is obtained.

[0051] In another possible situation, if there are multiple influencing factors for the target environmental index exceeding the standard, these multiple influencing factors are arranged in descending order according to the degree of freedom to obtain an influencing factor list.

[0052] This embodiment can accurately identify the key factors that cause environmental indicators to exceed the standard, and generate a list of influencing factors according to the correlation by analyzing the number of influencing factors and the degree of separation from historical data. When the influencing factor is single, the list is directly generated using the correlation coefficient matrix to ensure the relevance; when the influencing factors are diverse, they are sorted according to the degree of separation to highlight the factors with the greatest impact, providing strong support for formulating effective rectification measures.

[0053] A possible implementation of the embodiment of the present application is to calculate the degree of freedom between each exceeding standard influencing factor and the corresponding exceeding standard influencing factor data, including: For any exceeding standard influencing factor, calculate the average value and data fluctuation range of the exceeding standard influencing factor data corresponding to the exceeding standard influencing factor; The ratio of the absolute value of the difference between the exceeding standard influencing factor and the average value and the data fluctuation range is calculated as the degree of freedom between the exceeding standard influencing factor and the corresponding exceeding standard influencing factor data.

[0054] Among them, the data fluctuation range is the data range between the minimum and maximum values ​​of the exceeding standard influencing factor data.

[0055] This embodiment quantitatively analyzes the degree of deviation of the data of the factors affecting the exceeding of the standard relative to their average value and the ratio of the data fluctuation range, and can accurately evaluate the discreteness and instability of the data of each factor affecting the exceeding of the standard, thereby effectively identifying the key factors with the greatest impact and the most unstable on the exceeding of environmental indicators.

[0056] A possible implementation of the embodiment of the present application generates rectification measures corresponding to the list of influencing factors, including: Starting from the first influencing factor in the influencing factor list, the adjustment steps are performed on each influencing factor in turn until there is no excessive environmental index in the updated predicted environmental data; Among them, the adjustment step includes: adjusting the influencing factor data corresponding to the current influencing factor in the predicted influencing factor data, inputting the adjusted predicted influencing factor data into the multi-output regression model to obtain updated predicted environmental data, and analyzing whether there are excessive environmental indicators in the updated predicted environmental data.

[0057] Specifically, each influencing factor corresponds to an adjustment value in advance, and the adjustment direction can be to increase or decrease. The adjustment value indicates the adjustment amount that can be achieved by adjusting the influencing factor data to reduce the exceeding index. The size of the adjustment value and the adjustment direction can be set according to actual needs. For example, for the influencing factor of industrial emissions, the adjustment direction can be pre-set to decrease, and for the influencing factor of green area, the adjustment direction can be pre-set to increase. The influencing factor data corresponding to the current influencing factor is adjusted based on the pre-set adjustment value and adjustment direction.

[0058] After any adjustment, if there are still environmental indicators exceeding the standard in the updated predicted environmental data and the degree of exceeding the standard remains unchanged or even worsens, the adjustment of the current influencing factor data will be canceled and an attempt will be made to adjust the next influencing factor in the influencing factor list.

[0059] This embodiment adjusts the factors in the influencing factor list one by one and uses a multi-output regression model in real time to predict changes in environmental data, so as to systematically and specifically eliminate excessive environmental indicators, ensure the effectiveness and accuracy of rectification measures, and ultimately achieve the purpose of improving environmental quality.

[0060] In a possible implementation manner of the embodiment of the present application, the method further includes: Monitor current environmental data in real time and determine whether there are any environmental indicators that exceed the standard in the current environmental data; When there are current environmental indicators exceeding the standard in the current environmental data, the duration and degree of the exceeding of the current environmental indicators are determined, the exceeding level is determined according to the duration and degree of the exceeding, and an alarm signal corresponding to the exceeding level is issued.

[0061] Specifically, reasonable thresholds are set for each environmental indicator according to relevant laws and regulations, industry standards or expert advice, and exceeding these thresholds is considered to be exceeding the standard. Multiple numerical intervals of environmental indicators can be pre-set, and each interval corresponds to a basic level. The basic level indicates the degree of exceeding the standard. When an environmental indicator exceeding the standard is detected, the basic level corresponding to the exceeding indicator is determined, and the time when the exceeding standard starts is recorded. When the exceeding environmental indicator continues to exceed the standard for a preset time, the basic level is increased by one level. When the exceeding environmental indicator continues to exceed the standard for twice the preset time from the start of the exceeding, the basic level is increased by two levels, and so on, and an alarm signal corresponding to the exceeding level is dynamically issued. The preset time and the alarm signal corresponding to each exceeding level can be flexibly set according to actual needs, and this embodiment does not make specific limitations.

[0062] This embodiment can quickly identify environmental deterioration, provide detailed exceeding standard information in a timely manner, facilitate rapid response and take effective measures, thereby effectively protecting the environment and public health.

[0063] An embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the contents shown in the aforementioned ecological environment quality monitoring and early warning method embodiment are implemented.

[0064] An electronic device is provided in an embodiment of the present application, such as Figure 2 As shown, Figure 2 The electronic device 200 shown includes: a processor 201 and a memory 203. The processor 201 and the memory 203 are connected, such as through a bus 202. Optionally, the electronic device 200 may also include a transceiver 204. It should be noted that in actual applications, the transceiver 204 is not limited to one, and the structure of the electronic device 200 does not constitute a limitation on the embodiments of the present application.

[0065] The processor 201 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 201 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0066] The bus 202 may include a path to transmit information between the above components. The bus 202 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 202 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0067] The memory 203 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0068] The memory 203 is used to store the application code for executing the solution of the present application, and is controlled by the processor 201. The processor 201 is used to execute the application code stored in the memory 203 to implement the contents shown in the above-mentioned embodiment of the ecological environment quality monitoring and early warning method.

[0069] Figure 2 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0070] An embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer-readable storage medium is run on a computer, the computer can execute the contents shown in the aforementioned ecological environment quality monitoring and early warning method embodiment.

[0071] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0072] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for monitoring and early warning of ecological environment quality, characterized in that: include: Acquire historical environmental data and historical influencing factor data, perform correlation analysis on the historical environmental data and the historical influencing factor data, and determine influencing factor data with strong correlation to each environmental indicator in the historical environmental data from the historical influencing factor data; Establishing a multi-output regression model based on the historical environmental data and the influencing factor data corresponding to each environmental indicator; Acquire current influencing factor data, perform prediction based on the current influencing factor data to obtain predicted influencing factor data, and input the predicted influencing factor data into the multi-output regression model to obtain predicted environmental data; Analyze the exceeded environmental indicators in the predicted environmental data, issue early warnings for the exceeded environmental indicators, generate a list of influencing factors corresponding to the exceeded environmental indicators, and determine corrective measures based on the list of influencing factors.

2. The ecological environment quality monitoring and early warning method according to claim 1 is characterized in that: The determining of the list of influencing factors from the influencing factors that are strongly associated with the excessive environmental indicators includes: Acquire the exceeding-standard influencing factors that are strongly correlated with the exceeding-standard environmental index, and determine the historical data corresponding to the exceeding-standard influencing factors from the historical influencing factor data as the exceeding-standard influencing factor data; Determine the number of the exceeding-standard influencing factors; If the number of the exceeding-standard influencing factors is one, obtaining a correlation coefficient matrix between the historical environmental data and the historical influencing factor data, and generating an influencing factor list based on the exceeding-standard influencing factors and the correlation coefficient matrix; If the number of the exceeding standard influencing factors is not one, the degree of freedom between each exceeding standard influencing factor and the corresponding exceeding standard influencing factor data is calculated, and the exceeding standard influencing factors are sorted from high to low according to the degree of freedom to obtain the influencing factor list.

3. The ecological environment quality monitoring and early warning method according to claim 2 is characterized in that: Generate corrective measures corresponding to the list of influencing factors, including: Starting from the first influencing factor in the influencing factor list, adjusting steps are performed on each influencing factor in turn until there is no excessive environmental index in the updated predicted environmental data; Among them, the adjustment step includes: adjusting the influencing factor data corresponding to the current influencing factor in the predicted influencing factor data, inputting the adjusted predicted influencing factor data into the multi-output regression model to obtain updated predicted environmental data, and analyzing whether there are any excessive environmental indicators in the updated predicted environmental data.

4. The ecological environment quality monitoring and early warning method according to claim 2 is characterized in that: The calculation of the degree of freedom between each exceeding standard influencing factor and the corresponding exceeding standard influencing factor data includes: For any exceeding standard influencing factor, calculate the average value and data fluctuation range of the exceeding standard influencing factor data corresponding to the exceeding standard influencing factor; The ratio of the absolute value of the difference between the exceeding standard influencing factor and the average value to the data fluctuation range is calculated as the degree of freedom between the exceeding standard influencing factor and the corresponding exceeding standard influencing factor data.

5. The ecological environment quality monitoring and early warning method according to claim 1 is characterized in that: The performing correlation analysis on the historical environmental data and the historical influencing factor data, and determining from the historical influencing factor data influencing factor data the influencing factor data with which each environmental indicator in the historical environmental data is strongly correlated, includes: Calculating a correlation coefficient matrix between the historical environmental data and the historical influencing factor data, wherein each row in the correlation coefficient matrix represents an environmental indicator and each column represents an influencing factor; Determine the initial influencing factors corresponding to the target environmental indicator based on the correlation coefficient matrix, extract data corresponding to the initial influencing factors from the historical influencing factor data as candidate features, and the target environmental indicator is any environmental indicator in the historical environmental data; Constructing a covariance matrix of the candidate features, and performing eigendecomposition on the covariance matrix to obtain eigenvalues ​​and eigenvectors; A principal component vector is determined from the eigenvector based on the eigenvalue, and data corresponding to the principal component vector in the historical influencing factor data is projected onto the principal component vector to obtain influencing factor data that is strongly correlated with the target environmental indicator.

6. The ecological environment quality monitoring and early warning method according to claim 1 is characterized in that: The establishing of a multi-output regression model based on the historical environmental data and the influencing factor data corresponding to each environmental indicator includes: An initial regression model is defined, wherein the initial regression model includes a time feature processing layer, wherein the time feature processing layer is used to extract time features from data received by a model input layer, and the number of neurons in an output layer of the initial regression model is consistent with the number of environmental indicators in the historical environmental data; The initial regression model is trained based on the historical environmental data and the influencing factor data corresponding to each environmental indicator to obtain a trained multi-output regression model.

7. The ecological environment quality monitoring and early warning method according to claim 1 is characterized in that: The method further comprises: Monitor current environmental data in real time and determine whether there are any environmental indicators that exceed the standard in the current environmental data; When there are current exceeding environmental indicators in the current environmental data, determine the duration and degree of exceeding of the current exceeding environmental indicators, determine the exceeding level according to the duration and degree of exceeding, and issue an alarm signal corresponding to the exceeding level.

8. A computer program product, characterized in that It includes a computer program, which, when executed by a processor, implements the steps of the ecological environment quality monitoring and early warning method described in any one of claims 1 to 7.

9. An electronic device, characterized in that: include: at least one processor; Memory; At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the ecological environment quality monitoring and early warning method described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the ecological environment quality monitoring and early warning method described in any one of claims 1 to 7.

Images