Environmental protection online monitoring method and system based on cloud computing and block chain technology

Abstract

The invention discloses an environmental protection on-line monitoring method and system based on cloud computing and block chain technology, and the method comprises the steps: building a graph neural network label through the fluctuation abnormity visual information of multi-source data in different seasons, and building a multi-source data fluctuation abnormity on-line monitoring algorithm through the graph neural network label; therefore, HiWoo SCADA visual information of the multi-source data is monitored on line by using a multi-source data fluctuation abnormity on-line monitoring algorithm, fluctuation abnormity unit time period peak data of the multi-source data under different altitudes and landforms are obtained, and environmental improvement measures of different funds and technologies are set through environmental damage risk judgment information. And environment optimization process processing is carried out based on environment improvement measures of different funds and technologies. According to the invention, the online monitoring precision of the online monitoring of the fluctuation abnormity of the multi-source data is improved.

Description

Technical Field

[0001] The present invention relates to the field of online fire and environmental protection monitoring, and in particular to an online environmental protection monitoring method and system based on cloud computing and blockchain technology. Background Art

[0002] As global environmental problems intensify, air, water, noise, and soil pollution pose a serious threat to the ecological environment and human health. Countries are strengthening their environmental monitoring systems to achieve real-time monitoring of pollutant emissions and intelligent analysis of environmental quality. Traditional environmental monitoring methods rely on Internet of Things (IoT) sensors and remote data collection technologies, but these methods suffer from low data security, limited data sharing, and insufficient storage and computing capabilities. To address these challenges, cloud computing and blockchain technologies are increasingly being applied to online environmental monitoring systems. Cloud computing provides efficient data storage and computing resources, supporting the real-time processing of large-scale multi-source data. Blockchain technology, with its immutable and decentralized nature, ensures the authenticity and traceability of monitoring data. This combination not only enhances the credibility of environmental data but also provides reliable technical support for collaborative multi-party monitoring. However, existing deep learning algorithms still have limitations when processing multimodal environmental data, affecting the accuracy and response speed of online monitoring systems.

[0003] Current online environmental monitoring methods primarily rely on IoT sensors, wireless communications, and cloud storage, enabling monitoring of air, water, noise, and soil quality through data collection, transmission, and analysis. However, traditional monitoring systems primarily rely on single-modality data inputs. For example, air quality sensors only detect concentrations of gases like PM2.5 and CO2, while noise monitoring relies on audio signal analysis. This single-modality monitoring approach results in data silos, making it difficult to effectively integrate data from different sensors, hindering the accurate identification of complex environmental changes. Furthermore, the application of current deep learning algorithms in monitoring systems is primarily focused on specific areas, such as PM2.5 prediction and pollution source identification, and lacks the ability to comprehensively process multimodal information. For example, when air quality fluctuates abnormally, predictions rely solely on historical air data without incorporating relevant factors such as water and soil quality, resulting in monitoring results that fail to fully reflect environmental fluctuations. Summary of the Invention

[0004] The present invention overcomes the shortcomings of the existing technology and provides an environmental online monitoring method and system based on cloud computing and blockchain technology.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is:

[0006] The first aspect of the present invention provides an environmental online monitoring method based on cloud computing and blockchain technology, comprising the following steps:

[0007] Establish an edge computing gateway for a cloud computing collaborative blockchain platform, configure the edge computing gateway for multimodal environmental protection parameters, obtain the edge computing gateway for the cloud computing collaborative blockchain platform after the multimodal environmental protection parameter calculation configuration, and use the edge computing gateway for the cloud computing collaborative blockchain platform to control the HiWoo SCADA visualization information of the cloud computing collaborative blockchain platform that integrates multi-source data; the multi-source data includes air quality, water quality, noise, and soil;

[0008] The environmental information database is used to integrate the visualization information of seasonal fluctuation anomalies of multi-source data, and a graph neural network label is established based on the visualization information of seasonal fluctuation anomalies of multi-source data. The graph neural network label is then used to establish an online monitoring algorithm for multi-source data fluctuation anomalies.

[0009] The HiWoo SCADA visualization information of multi-source data is monitored online using a multi-source data fluctuation anomaly online monitoring algorithm to obtain the peak value data of the fluctuation anomaly per unit period of the multi-source data at different altitudes and terrains. The environmental damage risk is then judged based on the peak value data of the fluctuation anomaly per unit period of the multi-source data at different altitudes and terrains, generating environmental damage risk judgment information.

[0010] Based on the environmental damage risk assessment information, environmental remediation measures with different funds and technologies are set, and environmental optimization process processing is carried out based on the environmental remediation measures with different funds and technologies.

[0011] Furthermore, in this method, a cloud computing collaborative blockchain platform edge computing gateway is established, and multimodal environmental protection parameter calculation configuration is performed on the cloud computing collaborative blockchain platform edge computing gateway to obtain the cloud computing collaborative blockchain platform edge computing gateway after the multimodal environmental protection parameter calculation configuration, specifically including:

[0012] Establish an edge computing gateway for the cloud computing collaborative blockchain platform, test it, and obtain the jump interval characteristics of the cloud computing collaborative blockchain platform's environmental protection parameters in different seasons. Establish a boundary threshold assessment model for the environmental protection parameters of the cloud computing collaborative blockchain platform based on the Hadoop ecosystem model.

[0013] The cloud computing collaborative blockchain platform monitoring and procurement environmental protection parameter jump interval characteristics of the edge computing gateway of the cloud computing collaborative blockchain platform in different seasons are input into the cloud computing collaborative blockchain platform monitoring and procurement environmental protection parameter boundary threshold evaluation model for training, and the trained cloud computing collaborative blockchain platform monitoring and procurement environmental protection parameter boundary threshold evaluation model is obtained;

[0014] Obtain the jump interval characteristics of the cloud computing collaborative blockchain platform monitoring and environmental protection parameters of the cloud computing collaborative blockchain platform edge computing gateway within the preset time and input them into the trained cloud computing collaborative blockchain platform monitoring and environmental protection parameter boundary threshold evaluation model for evaluation, and obtain the cloud computing collaborative blockchain platform edge computing gateway cloud computing collaborative blockchain platform monitoring and environmental protection parameter boundary threshold of the unit timestamp;

[0015] Obtain the real-time cloud computing collaborative blockchain platform monitoring and environmental protection parameters of the cloud computing collaborative blockchain platform edge computing gateway. When the real-time cloud computing collaborative blockchain platform monitoring and environmental protection parameters are greater than the cloud computing collaborative blockchain platform monitoring and environmental protection parameter boundary threshold of the cloud computing collaborative blockchain platform edge computing gateway at the unit timestamp, adjust the real-time cloud computing collaborative blockchain platform monitoring and environmental protection parameters according to the cloud computing collaborative blockchain platform edge computing gateway at the unit timestamp, and obtain the cloud computing collaborative blockchain platform edge computing gateway after multimodal environmental protection parameter calculation configuration.

[0016] Furthermore, in this method, the environmental information database is used to integrate the visualization information of seasonal fluctuation anomalies of multi-source data, and a graph neural network label is established based on the visualization information of seasonal fluctuation anomalies of multi-source data. The graph neural network label is used to establish an online monitoring algorithm for fluctuation anomalies of multi-source data, which specifically includes:

[0017] The environmental information database is used to integrate the visualization information of seasonal fluctuation anomalies of multi-source data, and the fluctuation anomaly types are classified using the visualization information of seasonal fluctuation anomalies of multi-source data. The visualization information of each fluctuation anomaly type is obtained, and the graph neural network label of each fluctuation anomaly type is established based on the visualization information of each fluctuation anomaly type.

[0018] The visualization information in the graph neural network label of each fluctuation anomaly type is input into the peak Spark calculation model to obtain the fluctuation anomaly unit period peak value in the unit time visualization information. It is also determined whether the fluctuation anomaly unit period peak value in the visualization information is equal to or exceeds the preset value, and the long short-term memory network is introduced;

[0019] When the fluctuation abnormality unit period peak value in the visualization information is equal to or exceeds the preset value, the fluctuation abnormality unit period peak value corresponding to the fluctuation abnormality type peak value information of the unit time visualization information is obtained as the relevant fluctuation abnormality unit period peak value; when the fluctuation abnormality unit period peak value in the visualization information is less than the preset value, the fluctuation abnormality unit period peak value corresponding to the fluctuation abnormality type peak value information of the unit time visualization information is used as the relevant fluctuation abnormality unit period peak value;

[0020] The relevant fluctuation anomaly unit period peak is input into the long short-term memory network, so that the input dimension is concentrated in the relevant fluctuation anomaly unit period peak, and the time step is obtained. An online monitoring algorithm for fluctuation anomalies of multi-source data is established based on the deep neural network, and the time step in the graph neural network label is input into the online monitoring algorithm for fluctuation anomalies of multi-source data for Dropout regularization.

[0021] Furthermore, in this method, the multi-source data fluctuation anomaly online monitoring algorithm is used to monitor the HiWooSCADA visualization information of the multi-source data online, and the fluctuation anomaly unit period peak data of the multi-source data at different altitudes and topography is obtained. The environmental damage risk is judged based on the fluctuation anomaly unit period peak data of the multi-source data at different altitudes and topography, and the environmental damage risk judgment information is generated, specifically including:

[0022] Input the HiWoo SCADA visualization information of multi-source data into the multi-source data fluctuation anomaly online monitoring algorithm for online monitoring, obtain the peak data of multi-source data fluctuation anomaly per unit time period at different altitudes and topography, and preset the environmental damage risk judgment level standard;

[0023] The environmental damage risk judgment level is divided into the environmental damage risk judgment level of the fluctuation abnormality unit period peak data of multi-source data at different altitudes and topography by using the environmental damage risk judgment level standard. The environmental damage risk judgment level of the fluctuation abnormality unit period peak data of multi-source data at different altitudes and topography is obtained, and the production and pollution emission information of the key environmental protection marked locations with fluctuation abnormality in multi-source data is integrated;

[0024] Environmental damage risk judgment information is generated by using the environmental damage risk judgment level of the peak value per unit period of the fluctuation abnormality of multi-source data at different altitudes and topography, the production and pollution emission information of the key environmental protection marked locations with fluctuation abnormality of multi-source data, and the peak value per unit period of the fluctuation abnormality of multi-source data at different altitudes and topography.

[0025] Furthermore, in this method, environmental remediation measures with different funding and technologies are set based on environmental damage risk assessment information, including:

[0026] By integrating the production and pollution emission information of key environmental protection marked locations with abnormal fluctuations in multi-source data through environmental damage risk judgment information, and establishing fixed-point pollution sources based on the production and pollution emission information of key environmental protection marked locations with abnormal fluctuations in multi-source data, the pollution trajectory is tracked through the fixed-point pollution sources, and the pollution area of multi-source data is integrated;

[0027] The structural information of the common residential population is obtained through the pollution area of multi-source data, and a heat map of the common residential population structure is established. The structural information of the common residential population is input into the heat map for visualization, and the visualization results of the population distribution from deep to shallow are obtained;

[0028] Based on the visualization results of population distribution from deep to shallow, environmental remediation measures with different funds and technologies are set in key environmental protection marked locations, and the environmental remediation measures with different funds and technologies are output.

[0029] Furthermore, in this method, environmental optimization process processing is carried out based on environmental remediation measures with different funds and technologies, specifically including:

[0030] Obtain the distribution characteristic information of disease types in pollution areas per unit time and the production and pollution emission information of environmental protection key marked locations with abnormal fluctuations in high-risk enterprises. Calculate the correlation coefficient between the areas where disease types in each pollution area are located and the production and pollution emission information of environmental protection key marked locations with abnormal fluctuations in multi-source data based on the distribution characteristic information of disease types in pollution areas per unit time and the production and pollution emission information of environmental protection key marked locations with abnormal fluctuations in multi-source data.

[0031] Generative adversarial networks are introduced, and weight matrices are set through them. The working area processing of disease types in pollution areas is initialized by the correlation coefficients between the areas where disease types in each pollution area are located and the production and pollution emission information of key environmental protection marked locations with abnormal fluctuations in multi-source data, and the environmental optimization process area of each disease type in pollution area is obtained;

[0032] Determine whether the correlation coefficient between the production and pollution emission information of the area where the disease type in the pollution area is located and the environmental protection key marked location with abnormal fluctuations in multi-source data is greater than the preset correlation coefficient. When the correlation coefficient between the production and pollution emission information of the area where the disease type in the pollution area is located and the environmental protection key marked location with abnormal fluctuations in multi-source data is not greater than the preset correlation coefficient, output the environmental optimization process area for each disease type in the pollution area;

[0033] When the correlation coefficient between the production and pollution emission information in the areas where the disease types in the pollution area are located and the environmental protection key marked locations with abnormal fluctuations in multi-source data is greater than the preset correlation coefficient, the environmental optimization process areas of each disease type in the pollution area will be screened until the correlation coefficient between the production and pollution emission information in the areas where the disease types in the pollution area are located and the environmental protection key marked locations with abnormal fluctuations in multi-source data is no greater than the preset correlation coefficient.

[0034] A second aspect of the present invention provides an environmental online monitoring system based on cloud computing and blockchain technology. The system for online monitoring of multi-source data fluctuation anomalies and environmental damage risk assessment based on HiWoo SCADA monitoring includes a remote data computing service center and a multimodal information integrated supervision platform. The remote data computing service center includes a program for online monitoring of multi-source data fluctuation anomalies and environmental damage risk assessment based on HiWoo SCADA monitoring. When the program for online monitoring of multi-source data fluctuation anomalies and environmental damage risk assessment based on HiWoo SCADA monitoring is executed by the multimodal information integrated supervision platform, the following steps are implemented:

[0035] Establish an edge computing gateway for the cloud computing collaborative blockchain platform, and use it to perform multimodal environmental protection parameter calculation configuration, obtain the edge computing gateway for the cloud computing collaborative blockchain platform after the multimodal environmental protection parameter calculation configuration, and use the edge computing gateway for the cloud computing collaborative blockchain platform to control the HiWoo SCADA visualization information of the cloud computing collaborative blockchain platform that integrates multi-source data;

[0036] The environmental information database is used to integrate the visualization information of seasonal fluctuation anomalies of multi-source data, and a graph neural network label is established based on the visualization information of seasonal fluctuation anomalies of multi-source data. The graph neural network label is then used to establish an online monitoring algorithm for multi-source data fluctuation anomalies.

[0037] The HiWoo SCADA visualization information of multi-source data is monitored online using a multi-source data fluctuation anomaly online monitoring algorithm to obtain the peak value data of the fluctuation anomaly per unit period of the multi-source data at different altitudes and terrains. The environmental damage risk is then judged based on the peak value data of the fluctuation anomaly per unit period of the multi-source data at different altitudes and terrains, generating environmental damage risk judgment information.

[0038] Based on the environmental damage risk assessment information, environmental remediation measures with different funds and technologies are set, and environmental optimization process processing is carried out based on the environmental remediation measures with different funds and technologies.

[0039] Beneficial effects:

[0040] 1. The present invention utilizes the establishment of an edge computing gateway for a cloud computing collaborative blockchain platform, and utilizes the multimodal environmental protection parameter calculation configuration of the edge computing gateway for the cloud computing collaborative blockchain platform to obtain the edge computing gateway for the cloud computing collaborative blockchain platform after the multimodal environmental protection parameter calculation configuration, and utilizes the edge computing gateway for the cloud computing collaborative blockchain platform to control the HiWoo SCADA visualization information of the cloud computing collaborative blockchain platform that integrates multi-source data, and then utilizes the environmental protection information database to integrate the seasonal fluctuation anomaly visualization information of the multi-source data, and establishes a graph neural network label based on the seasonal fluctuation anomaly visualization information of the multi-source data, and establishes a multi-source data fluctuation anomaly online monitoring algorithm based on the graph neural network label, and then utilizes the multi-source data fluctuation anomaly online monitoring algorithm to monitor the HiWoo SCADA visualization information of the multi-source data online, obtain the fluctuation anomaly unit time period peak data of the multi-source data at different altitudes and topography, and perform environmental damage risk judgment based on the fluctuation anomaly unit time period peak data of the multi-source data at different altitudes and topography, and generate environmental damage risk judgment information, and finally set environmental remediation measures with different funds and technologies based on the environmental damage risk judgment information, and perform environmental optimization process processing based on the environmental remediation measures with different funds and technologies.

[0041] 2. The present invention uses a long short-term memory network to process the target fluctuation anomaly unit period peak in the graph neural network label, so that the input dimension is concentrated in the target fluctuation anomaly unit period peak in the graph neural network label, which can suppress the interference of multi-scale features on the multi-source data fluctuation anomaly online monitoring algorithm, and can improve the online monitoring accuracy of multi-source data fluctuation anomaly online monitoring. The present invention has the advantages of high efficiency, accuracy, security and traceability. Cloud computing provides powerful storage and computing capabilities, supports real-time processing of massive multimodal environmental data (multi-source data, etc.), and improves the computing efficiency and response speed of the monitoring system. At the same time, cloud-based intelligent analysis combined with deep learning models can fully integrate environmental data from different sources and optimize the accuracy of pollution prediction and anomaly identification. Blockchain technology ensures the security and credibility of monitoring data, uses distributed ledgers and smart contracts to achieve data immutability and traceability, and enhances data sharing and transparency among governments, enterprises and the public.

[0042] 3. Blockchain combined with cloud computing can effectively reduce the security risks of centralized storage, prevent malicious tampering, and enhance the fairness and credibility of environmental data management. This approach can also optimize real-time monitoring through edge computing, enabling rapid identification and response to abnormal pollutant changes. Overall, this system provides efficient, secure, and accurate data support for intelligent environmental monitoring, contributing to environmental governance and the achievement of sustainable development goals. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1Shown is an overall flow chart of the method of the present invention;

[0044] Figure 2 Shown is a block diagram of the composition of the system of the present invention. DETAILED DESCRIPTION

[0045] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0046] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0047] like Figure 1 As shown, the first aspect of the present invention provides an environmental online monitoring method based on cloud computing and blockchain technology, comprising the following steps:

[0048] S1: Establish an edge computing gateway for a cloud computing collaborative blockchain platform, and use the edge computing gateway for multimodal environmental protection parameter calculation configuration, obtain the edge computing gateway for the cloud computing collaborative blockchain platform after the multimodal environmental protection parameter calculation configuration, and use the edge computing gateway for the cloud computing collaborative blockchain platform to control the HiWoo SCADA visualization information of the cloud computing collaborative blockchain platform integrating multi-source data; the multi-source data includes air quality, water quality, noise, soil, etc.;

[0049] S2: Using the environmental information database to integrate seasonal fluctuation anomaly visualization information of multi-source data, and using this information to establish a graph neural network label, an online monitoring algorithm for multi-source data fluctuation anomaly is established based on the graph neural network label.

[0050] S3: Using the multi-source data fluctuation anomaly online monitoring algorithm to monitor the HiWoo SCADA visualization information of multi-source data online, obtain the fluctuation anomaly unit period peak data of multi-source data at different altitudes and topography, and use the fluctuation anomaly unit period peak data of multi-source data at different altitudes and topography to judge environmental damage risks and generate environmental damage risk judgment information;

[0051] S4: Set environmental remediation measures with different funds and technologies based on environmental damage risk assessment information, and carry out environmental optimization process processing based on environmental remediation measures with different funds and technologies.

[0052] It should be noted that the present invention uses a long short-term memory network to process the target fluctuation anomaly unit period peak in the graph neural network label, so that the input dimension is concentrated in the target fluctuation anomaly unit period peak in the graph neural network label, which can suppress the interference of multi-scale features on the multi-source data fluctuation anomaly online monitoring algorithm and improve the online monitoring accuracy of multi-source data fluctuation anomaly online monitoring.

[0053] Furthermore, in this method, a cloud computing collaborative blockchain platform edge computing gateway is established, and multimodal environmental protection parameter calculation configuration is performed on the cloud computing collaborative blockchain platform edge computing gateway to obtain the cloud computing collaborative blockchain platform edge computing gateway after the multimodal environmental protection parameter calculation configuration, specifically including:

[0054] Establish an edge computing gateway for the cloud computing collaborative blockchain platform, test it, and obtain the jump interval characteristics of the cloud computing collaborative blockchain platform's environmental protection parameters in different seasons. Establish a boundary threshold assessment model for the environmental protection parameters of the cloud computing collaborative blockchain platform based on the Hadoop ecosystem model.

[0055] The cloud computing collaborative blockchain platform monitoring and procurement environmental protection parameter jump interval characteristics of the edge computing gateway of the cloud computing collaborative blockchain platform in different seasons are input into the cloud computing collaborative blockchain platform monitoring and procurement environmental protection parameter boundary threshold evaluation model for training, and the trained cloud computing collaborative blockchain platform monitoring and procurement environmental protection parameter boundary threshold evaluation model is obtained;

[0056] Obtain the jump interval characteristics of the cloud computing collaborative blockchain platform monitoring and environmental protection parameters of the cloud computing collaborative blockchain platform edge computing gateway within the preset time and input them into the trained cloud computing collaborative blockchain platform monitoring and environmental protection parameter boundary threshold evaluation model for evaluation, and obtain the cloud computing collaborative blockchain platform edge computing gateway cloud computing collaborative blockchain platform monitoring and environmental protection parameter boundary threshold of the unit timestamp;

[0057] Obtain the real-time cloud computing collaborative blockchain platform monitoring and environmental protection parameters of the cloud computing collaborative blockchain platform edge computing gateway. When the real-time cloud computing collaborative blockchain platform monitoring and environmental protection parameters are greater than the cloud computing collaborative blockchain platform monitoring and environmental protection parameter boundary threshold of the cloud computing collaborative blockchain platform edge computing gateway at the unit timestamp, adjust the real-time cloud computing collaborative blockchain platform monitoring and environmental protection parameters according to the cloud computing collaborative blockchain platform edge computing gateway at the unit timestamp, and obtain the cloud computing collaborative blockchain platform edge computing gateway after multimodal environmental protection parameter calculation configuration.

[0058] It should be noted that, in fact, since there is a peak in information transmission, there is a peak in the cloud computing collaborative blockchain platform monitoring and environmental protection parameters of the edge computing gateway of the cloud computing collaborative blockchain platform; since the edge computing gateway of the cloud computing collaborative blockchain platform uses multiple devices for control, the performance of the terminal equipment will degrade to a certain extent after a certain number of years of use (such as a decrease in the amount of information transmission per unit time), which leads to a peak in the cloud computing collaborative blockchain platform monitoring and environmental protection parameters of the edge computing gateway of the cloud computing collaborative blockchain platform. This method can be used to adjust the real-time cloud computing collaborative blockchain platform monitoring and environmental protection parameters through the boundary threshold of the cloud computing collaborative blockchain platform monitoring and environmental protection parameters of the edge computing gateway of the cloud computing collaborative blockchain platform at a unit timestamp, so that the human-machine edge computing gateway controls the cloud computing collaborative blockchain platform monitoring and environmental protection parameters in accordance with the predetermined requirements, thereby ensuring the stability of the edge computing gateway of the cloud computing collaborative blockchain platform.

[0059] Furthermore, in this method, the environmental information database is used to integrate the visualization information of seasonal fluctuation anomalies of multi-source data, and a graph neural network label is established based on the visualization information of seasonal fluctuation anomalies of multi-source data. The graph neural network label is used to establish an online monitoring algorithm for fluctuation anomalies of multi-source data, which specifically includes:

[0060] The environmental information database is used to integrate the visualization information of seasonal fluctuation anomalies of multi-source data, and the fluctuation anomaly types are classified using the visualization information of seasonal fluctuation anomalies of multi-source data. The visualization information of each fluctuation anomaly type is obtained, and the graph neural network label of each fluctuation anomaly type is established based on the visualization information of each fluctuation anomaly type.

[0061] The visualization information in the graph neural network label of each fluctuation anomaly type is input into the peak Spark calculation model to obtain the fluctuation anomaly unit period peak value in the unit time visualization information. It is also determined whether the fluctuation anomaly unit period peak value in the visualization information is equal to or exceeds the preset value, and the long short-term memory network is introduced;

[0062] When the fluctuation abnormality unit period peak value in the visualization information is equal to or exceeds the preset value, the fluctuation abnormality unit period peak value corresponding to the fluctuation abnormality type peak value information of the unit time visualization information is obtained as the relevant fluctuation abnormality unit period peak value; when the fluctuation abnormality unit period peak value in the visualization information is less than the preset value, the fluctuation abnormality unit period peak value corresponding to the fluctuation abnormality type peak value information of the unit time visualization information is used as the relevant fluctuation abnormality unit period peak value;

[0063] The relevant fluctuation anomaly unit period peak is input into the long short-term memory network, so that the input dimension is concentrated in the relevant fluctuation anomaly unit period peak, and the time step is obtained. An online monitoring algorithm for fluctuation anomalies of multi-source data is established based on the deep neural network, and the time step in the graph neural network label is input into the online monitoring algorithm for fluctuation anomalies of multi-source data for Dropout regularization.

[0064] It should be noted that the fluctuation anomaly visualization information includes data such as crack fluctuation anomaly visualization, corrosion fluctuation anomaly visualization, and fluctuation anomaly visualization after burning. Since the visualization information in the graph neural network label of each fluctuation anomaly type may contain at least two fluctuation anomaly types, such as crack fluctuation anomaly, corrosion fluctuation anomaly, etc., during training, graph neural network labels of multiple fluctuation anomaly types should be input into the deep neural network for training. When label information of at least two fluctuation anomaly types appears in a visualization during training, it will be interfered with. Using this method to fuse the long short-term memory network can make the input dimension concentrated in the relevant fluctuation anomaly unit period peak, and can suppress the interference of multi-scale fluctuation anomaly unit period peak on the multi-source data fluctuation anomaly online monitoring algorithm, thereby improving the evaluation accuracy of the algorithm.

[0065] Furthermore, in this method, the multi-source data fluctuation anomaly online monitoring algorithm is used to monitor the HiWooSCADA visualization information of the multi-source data online, and the fluctuation anomaly unit period peak data of the multi-source data at different altitudes and topography is obtained. The environmental damage risk is judged based on the fluctuation anomaly unit period peak data of the multi-source data at different altitudes and topography, and the environmental damage risk judgment information is generated, specifically including:

[0066] Input the HiWoo SCADA visualization information of multi-source data into the multi-source data fluctuation anomaly online monitoring algorithm for online monitoring, obtain the peak data of multi-source data fluctuation anomaly per unit time period at different altitudes and topography, and preset the environmental damage risk judgment level standard;

[0067] The environmental damage risk judgment level is divided into the environmental damage risk judgment level of the fluctuation abnormality unit period peak data of multi-source data at different altitudes and topography by using the environmental damage risk judgment level standard. The environmental damage risk judgment level of the fluctuation abnormality unit period peak data of multi-source data at different altitudes and topography is obtained, and the production and pollution emission information of the key environmental protection marked locations with fluctuation abnormality in multi-source data is integrated;

[0068] Environmental damage risk judgment information is generated by using the environmental damage risk judgment level of the peak value per unit period of the fluctuation abnormality of multi-source data at different altitudes and topography, the production and pollution emission information of the key environmental protection marked locations with fluctuation abnormality of multi-source data, and the peak value per unit period of the fluctuation abnormality of multi-source data at different altitudes and topography.

[0069] It should be noted that the standards for environmental damage risk judgment levels can be set based on the type of fluctuation anomaly and the size of the fluctuation anomaly. The environmental damage risk judgment levels include low environmental damage risk judgment levels, medium environmental damage risk judgment levels, high environmental damage risk judgment levels, etc.

[0070] Furthermore, in this method, environmental remediation measures with different funding and technologies are set based on environmental damage risk assessment information, including:

[0071] By integrating the production and pollution emission information of key environmental protection marked locations with abnormal fluctuations in multi-source data through environmental damage risk judgment information, and establishing fixed-point pollution sources based on the production and pollution emission information of key environmental protection marked locations with abnormal fluctuations in multi-source data, the pollution trajectory is tracked through the fixed-point pollution sources, and the pollution area of multi-source data is integrated;

[0072] The structural information of the common residential population is obtained through the pollution area of multi-source data, and a heat map of the common residential population structure is established. The structural information of the common residential population is input into the heat map for visualization, and the visualization results of the population distribution from deep to shallow are obtained;

[0073] Based on the visualization results of population distribution from deep to shallow, environmental remediation measures with different funds and technologies are set in key environmental protection marked locations, and the environmental remediation measures with different funds and technologies are output.

[0074] It should be noted that since the types of diseases in the polluted area may be limited, this method can be used to formulate more reasonable environmental remediation measures with different funds and technologies.

[0075] Furthermore, in this method, environmental optimization process processing is carried out based on environmental remediation measures with different funds and technologies, specifically including:

[0076] Obtain the distribution characteristic information of disease types in pollution areas per unit time and the production and pollution emission information of environmental protection key marked locations with abnormal fluctuations in high-risk enterprises. Calculate the correlation coefficient between the areas where disease types in each pollution area are located and the production and pollution emission information of environmental protection key marked locations with abnormal fluctuations in multi-source data based on the distribution characteristic information of disease types in pollution areas per unit time and the production and pollution emission information of environmental protection key marked locations with abnormal fluctuations in multi-source data.

[0077] Generative adversarial networks are introduced, and weight matrices are set through them. The working area processing of disease types in pollution areas is initialized by the correlation coefficients between the areas where disease types in each pollution area are located and the production and pollution emission information of key environmental protection marked locations with abnormal fluctuations in multi-source data, and the environmental optimization process area of each disease type in pollution area is obtained;

[0078] Determine whether the correlation coefficient between the production and pollution emission information of the area where the disease type in the pollution area is located and the environmental protection key marked location with abnormal fluctuations in multi-source data is greater than the preset correlation coefficient. When the correlation coefficient between the production and pollution emission information of the area where the disease type in the pollution area is located and the environmental protection key marked location with abnormal fluctuations in multi-source data is not greater than the preset correlation coefficient, output the environmental optimization process area for each disease type in the pollution area;

[0079] When the correlation coefficient between the production and pollution emission information in the areas where the disease types in the pollution area are located and the environmental protection key marked locations with abnormal fluctuations in multi-source data is greater than the preset correlation coefficient, the environmental optimization process areas of each disease type in the pollution area will be screened until the correlation coefficient between the production and pollution emission information in the areas where the disease types in the pollution area are located and the environmental protection key marked locations with abnormal fluctuations in multi-source data is no greater than the preset correlation coefficient.

[0080] It should be noted that this method can be used to configure multi-source data for maintenance at key environmental protection marked locations, so that each protected area can respond quickly, and the environmental optimization process for the types of diseases in the polluted area is more reasonable.

[0081] In addition, using the edge computing gateway of the cloud computing collaborative blockchain platform to control the HiWoo SCADA visualization information of the cloud computing collaborative blockchain platform integrating multi-source data can also include the following steps:

[0082] The cloud computing collaborative blockchain platform edge computing gateway is used to obtain the flight route of the cloud computing collaborative blockchain platform per unit time, and the environmental information database is used to obtain the HiWoo SCADA visualization feature data information under each pollution source, and the HiWoo SCADA visualization feature data information under each pollution source is input into the graph neural network; the pollution source is used as the first graph node of the graph neural network, and the HiWoo SCADA visualization feature data information is used as the second graph node of the graph neural network. An adjacency matrix is established through the first graph node and the second graph node, and the adjacency matrix is input into the knowledge graph for storage; the pollution source information of the flight route of the cloud computing collaborative blockchain platform within a preset range within a preset time is obtained, and the pollution source information of the flight route of the cloud computing collaborative blockchain platform within a preset range within the preset time is input into the knowledge graph, and the HiWoo SCADA visualization evaluation feature data information of each timestamp is obtained; if the HiWoo SCADA visualization evaluation feature data information is greater than the preset HiWoo When the SCADA visualization feature threshold is reached, the corresponding time period is used as the environmental optimization process period of the cloud computing collaborative blockchain platform, and the corresponding time period is used as the environmental optimization process period of the cloud computing collaborative blockchain platform, and data collection is performed during the environmental optimization process period of the cloud computing collaborative blockchain platform to integrate HiWoo SCADA visualization information of multi-source data.

[0083] In addition, the method may further include the following steps: using the environmental information database to obtain the HiWoo SCADA visualization feature information of each sensor parameter set under each pollution source and the pollution source of the area where the cloud computing collaborative blockchain platform is located per unit time, and obtaining the HiWoo SCADA visualization feature information of each sensor parameter of the cloud computing collaborative blockchain platform through the HiWoo SCADA visualization feature information of each parameter set under the pollution source and the pollution source of the area where the cloud computing collaborative blockchain platform is located per unit time; obtaining the adjustable range of the sensor parameters of the sensor equipment of the cloud computing collaborative blockchain platform per unit time, and judging whether there is at least one sensor parameter among the sensor parameters that makes the HiWoo SCADA visualization feature information of the cloud computing collaborative blockchain platform greater than the preset HiWoo SCADA visualization feature threshold value; if there is at least one sensor parameter among the sensor parameters that makes the HiWoo SCADA visualization feature information of the cloud computing collaborative blockchain platform greater than the preset HiWoo SCADA visualization feature threshold value, then randomly outputting a sensor parameter that makes the HiWoo SCADA visualization feature information of the cloud computing collaborative blockchain platform greater than the preset HiWoo The data of the SCADA visualization feature threshold is used as the sensing parameter of the cloud computing collaborative blockchain platform; if there is no sensing parameter among the sensing parameters that makes the HiWoo SCADA visualization feature information of the cloud computing collaborative blockchain platform greater than the preset HiWoo SCADA visualization feature threshold, the data collection period of the cloud computing collaborative blockchain platform, the flight route of the cloud computing collaborative blockchain platform and the data collection point of the cloud computing collaborative blockchain platform are adjusted until at least one sensing parameter among the sensing parameters makes the HiWoo SCADA visualization feature information of the cloud computing collaborative blockchain platform greater than the preset HiWoo SCADA visualization feature threshold.

[0084] It should be noted that due to the influence of the environment, no matter how the sensing parameters are adjusted, there is no parameter that makes the HiWoo SCADA visualization feature information of the cloud computing collaborative blockchain platform greater than the preset HiWoo SCADA visualization feature threshold, so that the predetermined standard visualization cannot be obtained. The use of this method can further improve the rationality of data collection.

[0085] like Figure 2As shown, the second aspect of the present invention provides an environmental online monitoring system based on cloud computing and blockchain technology, which includes a remote data computing service center and a multimodal information integrated supervision platform. The remote data computing service center includes a multi-source data fluctuation anomaly online monitoring and environmental damage risk judgment method program based on HiWoo SCADA monitoring. When the multi-source data fluctuation anomaly online monitoring and environmental damage risk judgment method program based on HiWoo SCADA monitoring is executed by the multimodal information integrated supervision platform, the following steps are implemented:

[0086] Establish an edge computing gateway for the cloud computing collaborative blockchain platform, and use it to perform multimodal environmental protection parameter calculation configuration, obtain the edge computing gateway for the cloud computing collaborative blockchain platform after the multimodal environmental protection parameter calculation configuration, and use the edge computing gateway for the cloud computing collaborative blockchain platform to control the HiWoo SCADA visualization information of the cloud computing collaborative blockchain platform that integrates multi-source data;

[0087] The environmental information database is used to integrate the visualization information of seasonal fluctuation anomalies of multi-source data, and a graph neural network label is established based on the visualization information of seasonal fluctuation anomalies of multi-source data. The graph neural network label is then used to establish an online monitoring algorithm for multi-source data fluctuation anomalies.

[0088] The HiWoo SCADA visualization information of multi-source data is monitored online using a multi-source data fluctuation anomaly online monitoring algorithm to obtain the peak value data of the fluctuation anomaly per unit period of the multi-source data at different altitudes and terrains. The environmental damage risk is then judged based on the peak value data of the fluctuation anomaly per unit period of the multi-source data at different altitudes and terrains, generating environmental damage risk judgment information.

[0089] Based on the environmental damage risk assessment information, environmental remediation measures with different funds and technologies are set, and environmental optimization process processing is carried out based on the environmental remediation measures with different funds and technologies.

[0090] Furthermore, in this system, a cloud computing collaborative blockchain platform edge computing gateway is established, and multimodal environmental protection parameter calculation configuration is performed on the cloud computing collaborative blockchain platform edge computing gateway to obtain the cloud computing collaborative blockchain platform edge computing gateway after the multimodal environmental protection parameter calculation configuration, specifically including:

[0091] Establish an edge computing gateway for the cloud computing collaborative blockchain platform, test it, and obtain the jump interval characteristics of the cloud computing collaborative blockchain platform's environmental protection parameters in different seasons. Establish a boundary threshold assessment model for the environmental protection parameters of the cloud computing collaborative blockchain platform based on the Hadoop ecosystem model.

[0092] The cloud computing collaborative blockchain platform monitoring and procurement environmental protection parameter jump interval characteristics of the edge computing gateway of the cloud computing collaborative blockchain platform in different seasons are input into the cloud computing collaborative blockchain platform monitoring and procurement environmental protection parameter boundary threshold evaluation model for training, and the trained cloud computing collaborative blockchain platform monitoring and procurement environmental protection parameter boundary threshold evaluation model is obtained;

[0093] Obtain the jump interval characteristics of the cloud computing collaborative blockchain platform monitoring and environmental protection parameters of the cloud computing collaborative blockchain platform edge computing gateway within the preset time and input them into the trained cloud computing collaborative blockchain platform monitoring and environmental protection parameter boundary threshold evaluation model for evaluation, and obtain the cloud computing collaborative blockchain platform edge computing gateway cloud computing collaborative blockchain platform monitoring and environmental protection parameter boundary threshold of the unit timestamp;

[0094] Obtain the real-time cloud computing collaborative blockchain platform monitoring and environmental protection parameters of the cloud computing collaborative blockchain platform edge computing gateway. When the real-time cloud computing collaborative blockchain platform monitoring and environmental protection parameters are greater than the cloud computing collaborative blockchain platform monitoring and environmental protection parameter boundary threshold of the cloud computing collaborative blockchain platform edge computing gateway at the unit timestamp, adjust the real-time cloud computing collaborative blockchain platform monitoring and environmental protection parameters according to the cloud computing collaborative blockchain platform edge computing gateway at the unit timestamp, and obtain the cloud computing collaborative blockchain platform edge computing gateway after multimodal environmental protection parameter calculation configuration.

[0095] Furthermore, in this system, the environmental information database is used to integrate the visualization information of seasonal fluctuation anomalies of multi-source data, and a graph neural network label is established based on the visualization information of seasonal fluctuation anomalies of multi-source data. The graph neural network label is used to establish an online monitoring algorithm for multi-source data fluctuation anomalies, specifically including:

[0096] The environmental information database is used to integrate the visualization information of seasonal fluctuation anomalies of multi-source data, and the fluctuation anomaly types are classified using the visualization information of seasonal fluctuation anomalies of multi-source data. The visualization information of each fluctuation anomaly type is obtained, and the graph neural network label of each fluctuation anomaly type is established based on the visualization information of each fluctuation anomaly type.

[0097] The visualization information in the graph neural network label of each fluctuation anomaly type is input into the peak Spark calculation model to obtain the fluctuation anomaly unit period peak value in the unit time visualization information. It is also determined whether the fluctuation anomaly unit period peak value in the visualization information is equal to or exceeds the preset value, and the long short-term memory network is introduced;

[0098] When the fluctuation abnormality unit period peak value in the visualization information is equal to or exceeds the preset value, the fluctuation abnormality unit period peak value corresponding to the fluctuation abnormality type peak value information of the unit time visualization information is obtained as the relevant fluctuation abnormality unit period peak value; when the fluctuation abnormality unit period peak value in the visualization information is less than the preset value, the fluctuation abnormality unit period peak value corresponding to the fluctuation abnormality type peak value information of the unit time visualization information is used as the relevant fluctuation abnormality unit period peak value;

[0099] The relevant fluctuation anomaly unit period peak is input into the long short-term memory network, so that the input dimension is concentrated in the relevant fluctuation anomaly unit period peak, and the time step is obtained. An online monitoring algorithm for fluctuation anomalies of multi-source data is established based on the deep neural network, and the time step in the graph neural network label is input into the online monitoring algorithm for fluctuation anomalies of multi-source data for Dropout regularization.

[0100] Furthermore, in this system, an online monitoring algorithm for multi-source data fluctuation anomalies is used to monitor the HiWooSCADA visualization information of multi-source data online, and the peak data of the fluctuation anomalies per unit period of the multi-source data at different altitudes and topography are obtained. The environmental damage risk is judged based on the peak data of the fluctuation anomalies per unit period of the multi-source data at different altitudes and topography, and the environmental damage risk judgment information is generated, specifically including:

[0101] Input the HiWoo SCADA visualization information of multi-source data into the multi-source data fluctuation anomaly online monitoring algorithm for online monitoring, obtain the peak data of multi-source data fluctuation anomaly per unit time period at different altitudes and topography, and preset the environmental damage risk judgment level standard;

[0102] The environmental damage risk judgment level is divided into the environmental damage risk judgment level of the fluctuation abnormality unit period peak data of multi-source data at different altitudes and topography by using the environmental damage risk judgment level standard. The environmental damage risk judgment level of the fluctuation abnormality unit period peak data of multi-source data at different altitudes and topography is obtained, and the production and pollution emission information of the key environmental protection marked locations with fluctuation abnormality in multi-source data is integrated;

[0103] Environmental damage risk judgment information is generated by using the environmental damage risk judgment level of the peak value per unit period of the fluctuation abnormality of multi-source data at different altitudes and topography, the production and pollution emission information of the key environmental protection marked locations with fluctuation abnormality of multi-source data, and the peak value per unit period of the fluctuation abnormality of multi-source data at different altitudes and topography.

[0104] Furthermore, in this system, environmental remediation measures with different funds and technologies are set based on environmental damage risk assessment information, including:

[0105] By integrating the production and pollution emission information of key environmental protection marked locations with abnormal fluctuations in multi-source data through environmental damage risk judgment information, and establishing fixed-point pollution sources based on the production and pollution emission information of key environmental protection marked locations with abnormal fluctuations in multi-source data, the pollution trajectory is tracked through the fixed-point pollution sources, and the pollution area of multi-source data is integrated;

[0106] The structural information of the common residential population is obtained through the pollution area of multi-source data, and a heat map of the common residential population structure is established. The structural information of the common residential population is input into the heat map for visualization, and the visualization results of the population distribution from deep to shallow are obtained;

[0107] Based on the visualization results of population distribution from deep to shallow, environmental remediation measures with different funds and technologies are set in key environmental protection marked locations, and the environmental remediation measures with different funds and technologies are output.

[0108] Furthermore, in this system, environmental optimization process is carried out based on environmental remediation measures with different funds and technologies, including:

[0109] Obtain the distribution characteristic information of disease types in pollution areas per unit time and the production and pollution emission information of environmental protection key marked locations with abnormal fluctuations in high-risk enterprises. Calculate the correlation coefficient between the areas where disease types in each pollution area are located and the production and pollution emission information of environmental protection key marked locations with abnormal fluctuations in multi-source data based on the distribution characteristic information of disease types in pollution areas per unit time and the production and pollution emission information of environmental protection key marked locations with abnormal fluctuations in multi-source data.

[0110] Generative adversarial networks are introduced, and weight matrices are set through them. The working area processing of disease types in pollution areas is initialized by the correlation coefficients between the areas where disease types in each pollution area are located and the production and pollution emission information of key environmental protection marked locations with abnormal fluctuations in multi-source data, and the environmental optimization process area of each disease type in pollution area is obtained;

[0111] Determine whether the correlation coefficient between the production and pollution emission information of the area where the disease type in the pollution area is located and the environmental protection key marked location with abnormal fluctuations in multi-source data is greater than the preset correlation coefficient. When the correlation coefficient between the production and pollution emission information of the area where the disease type in the pollution area is located and the environmental protection key marked location with abnormal fluctuations in multi-source data is not greater than the preset correlation coefficient, output the environmental optimization process area for each disease type in the pollution area;

[0112] When the correlation coefficient between the production and pollution emission information in the areas where the disease types in the pollution area are located and the environmental protection key marked locations with abnormal fluctuations in multi-source data is greater than the preset correlation coefficient, the environmental optimization process areas of each disease type in the pollution area will be screened until the correlation coefficient between the production and pollution emission information in the areas where the disease types in the pollution area are located and the environmental protection key marked locations with abnormal fluctuations in multi-source data is no greater than the preset correlation coefficient.

[0113] The third aspect of the present invention provides a computer-readable storage medium, which includes a computer-readable remote data computing service center medium that includes a method program for online monitoring of multi-source data fluctuation anomalies and environmental damage risk judgment based on HiWoo SCADA monitoring. When the method program for online monitoring of multi-source data fluctuation anomalies and environmental damage risk judgment based on HiWoo SCADA monitoring is executed by a multimodal information comprehensive supervision platform, any step of the method for online monitoring of multi-source data fluctuation anomalies and environmental damage risk judgment based on HiWoo SCADA monitoring is implemented.

[0114] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. An environmental online monitoring method based on cloud computing and blockchain technology, characterized in that: The following steps are involved: S1: Establish an edge computing gateway for a cloud computing collaborative blockchain platform, and use the edge computing gateway for multimodal environmental protection parameter calculation configuration to obtain the edge computing gateway for the cloud computing collaborative blockchain platform after the multimodal environmental protection parameter calculation configuration, and use the edge computing gateway for the cloud computing collaborative blockchain platform to control the HiWoo SCADA visualization information of the cloud computing collaborative blockchain platform that integrates multi-source data; the multi-source data includes air quality, water quality, noise, and soil; S2: Using an environmental information database to integrate seasonal fluctuation anomaly visualization information of multi-source data, establishing a graph neural network label based on the seasonal fluctuation anomaly visualization information of multi-source data, and establishing an online monitoring algorithm for multi-source data fluctuation anomaly based on the graph neural network label; S3: Using the multi-source data fluctuation anomaly online monitoring algorithm to monitor the HiWoo SCADA visualization information of the multi-source data online, obtain the fluctuation anomaly unit time period peak data of the multi-source data at different altitudes and terrains, and perform environmental damage risk judgment based on the fluctuation anomaly unit time period peak data of the multi-source data at different altitudes and terrains, and generate environmental damage risk judgment information; S4: setting environmental remediation measures with different funds and technologies based on the environmental damage risk assessment information, and performing environmental optimization process processing based on the environmental remediation measures with different funds and technologies.

2. The environmental online monitoring method based on cloud computing and blockchain technology according to claim 1 is characterized in that: Said S2 comprises: Using an environmental information database to integrate seasonal fluctuation anomaly visualization information of multi-source data, and using the seasonal fluctuation anomaly visualization information of the multi-source data to classify the fluctuation anomaly types, obtaining visualization information of each fluctuation anomaly type, and establishing a graph neural network label for each fluctuation anomaly type based on the visualization information of each fluctuation anomaly type; Input the visualization information in the graph neural network label of each fluctuation anomaly type into the peak Spark calculation model, obtain the fluctuation anomaly unit period peak value in the unit time visualization information, and determine whether the fluctuation anomaly unit period peak value in the visualization information is equal to or exceeds the preset value, and introduce the long short-term memory network; If the fluctuation abnormality unit period peak value in the visualization information is equal to or exceeds a preset value, the fluctuation abnormality unit period peak value corresponding to the fluctuation abnormality type peak value information of the unit time visualization information is obtained as the relevant fluctuation abnormality unit period peak value; if the fluctuation abnormality unit period peak value in the visualization information is less than the preset value, the fluctuation abnormality unit period peak value corresponding to the fluctuation abnormality type peak value information of the unit time visualization information is used as the relevant fluctuation abnormality unit period peak value; The relevant fluctuation anomaly unit period peak is input into the long short-term memory network, so that the input dimension is concentrated in the relevant fluctuation anomaly unit period peak, and the time step is obtained. A multi-source data fluctuation anomaly online monitoring algorithm is established based on a deep neural network, and the time step is input into the multi-source data fluctuation anomaly online monitoring algorithm for Dropout regularization.

3. The environmental online monitoring method based on cloud computing and blockchain technology according to claim 1 is characterized in that: Said S1 comprises: Establish a cloud computing collaborative blockchain platform edge computing gateway, and use the cloud computing collaborative blockchain platform edge computing gateway to test the cloud computing collaborative blockchain platform edge computing gateway to obtain the cloud computing collaborative blockchain platform monitoring and environmental protection parameter jump interval characteristics in different seasons of the cloud computing collaborative blockchain platform edge computing gateway, and establish a cloud computing collaborative blockchain platform monitoring and environmental protection parameter boundary threshold evaluation model based on the Hadoop ecosystem model; Input the jump interval characteristics of the cloud computing collaborative blockchain platform monitoring and procurement environmental protection parameters in different seasons of the cloud computing collaborative blockchain platform edge computing gateway into the cloud computing collaborative blockchain platform monitoring and procurement environmental protection parameter boundary threshold evaluation model for training, and obtain the trained cloud computing collaborative blockchain platform monitoring and procurement environmental protection parameter boundary threshold evaluation model; Obtain the jump interval characteristics of the cloud computing collaborative blockchain platform monitoring and environmental protection parameters of the cloud computing collaborative blockchain platform edge computing gateway within a preset time and input them into the trained cloud computing collaborative blockchain platform monitoring and environmental protection parameter boundary threshold evaluation model for evaluation, and obtain the cloud computing collaborative blockchain platform edge computing gateway cloud computing collaborative blockchain platform monitoring and environmental protection parameter boundary threshold of the unit timestamp; Obtain the real-time cloud computing collaborative blockchain platform monitoring and environmental protection parameters of the cloud computing collaborative blockchain platform edge computing gateway. If the real-time cloud computing collaborative blockchain platform monitoring and environmental protection parameters are greater than the cloud computing collaborative blockchain platform monitoring and environmental protection parameter boundary threshold of the cloud computing collaborative blockchain platform edge computing gateway at the unit timestamp, adjust the real-time cloud computing collaborative blockchain platform monitoring and environmental protection parameters according to the cloud computing collaborative blockchain platform edge computing gateway at the unit timestamp, and obtain the cloud computing collaborative blockchain platform edge computing gateway after multimodal environmental protection parameter calculation configuration.

4. The environmental online monitoring method based on cloud computing and blockchain technology according to claim 1 is characterized in that: Said S3 comprises: Inputting the HiWoo SCADA visualization information of the multi-source data into the multi-source data fluctuation anomaly online monitoring algorithm for online monitoring, obtaining the peak data of the fluctuation anomaly per unit time period of the multi-source data at different altitudes and topography, and presetting the environmental damage risk judgment level standard; The environmental damage risk judgment level is divided into the environmental damage risk judgment level of the fluctuation abnormality unit period peak data of the multi-source data at different altitudes and topography by the environmental damage risk judgment level standard, and the environmental damage risk judgment level of the fluctuation abnormality unit period peak data of the multi-source data at different altitudes and topography is obtained, and the production and pollution emission information of the environmental protection key marked locations with abnormal fluctuation of the multi-source data is integrated; An environmental damage risk judgment is generated by using the environmental damage risk judgment level of the abnormal fluctuation unit period peak value of the multi-source data at different altitudes and topography, the production and pollution emission information of the key environmental protection marked locations with abnormal fluctuation of the multi-source data, and the abnormal fluctuation unit period peak value data of the multi-source data at different altitudes and topography, and generating environmental damage risk judgment information.

5. The environmental online monitoring method based on cloud computing and blockchain technology according to claim 1 is characterized in that: Said S4 comprises: The environmental damage risk judgment information is used to integrate the production and pollution emission information of environmental protection key marked locations with abnormal fluctuations in multi-source data, and establish a fixed pollution source based on the production and pollution emission information of environmental protection key marked locations with abnormal fluctuations in multi-source data, track the pollution trajectory through the fixed pollution source, and integrate the pollution area of multi-source data; Obtaining structural information of the common resident population through the contaminated area of the multi-source data, and establishing a heat map of the common resident population structure, inputting the structural information of the common resident population into the heat map of the common resident population structure for visualization, and obtaining a visualization result of the population distribution from deep to shallow; Environmental remediation measures with different funds and technologies are set in key environmental protection marked locations based on the visualization results of the population distribution from deep to shallow, and the environmental remediation measures with different funds and technologies are output.

6. The environmental online monitoring method based on cloud computing and blockchain technology according to claim 1 is characterized in that: Said S4 further includes: Obtaining distribution characteristic information of disease types in polluted areas per unit time and production and pollution emission information of key environmental protection marked locations with abnormal fluctuations in high-risk enterprises, and calculating correlation coefficients between the areas where disease types in each polluted area are located and the production and pollution emission information of key environmental protection marked locations with abnormal fluctuations in multi-source data based on the distribution characteristic information of disease types in polluted areas per unit time and the production and pollution emission information of key environmental protection marked locations with abnormal fluctuations in multi-source data; A generative adversarial network is introduced, and a weight matrix is set through the generative adversarial network. The working area processing of the disease types in the pollution area is initialized by the correlation coefficient between the areas where the disease types in each pollution area are located and the production and pollution emission information of the key environmental protection marked locations with abnormal fluctuations in multi-source data, and the environmental optimization process area of each disease type in the pollution area is obtained; Determine whether the correlation coefficient between the production and pollution emission information of the area where the disease type of the pollution area is located and the environmental protection key marked location where the multi-source data has abnormal fluctuations is greater than the preset correlation coefficient; if the correlation coefficient between the production and pollution emission information of the area where the disease type of the pollution area is located and the environmental protection key marked location where the multi-source data has abnormal fluctuations is not greater than the preset correlation coefficient, output the environmental optimization process area for each disease type of the pollution area; If the correlation coefficient between the production and pollution emission information of the area where the disease type in the pollution area is located and the environmental protection key marked location where there is abnormal fluctuation in multi-source data is greater than the preset correlation coefficient, the environmental optimization process area of each disease type in the pollution area will be screened until the correlation coefficient between the production and pollution emission information of the area where the disease type in the pollution area is located and the environmental protection key marked location where there is abnormal fluctuation in multi-source data is no greater than the preset correlation coefficient.

7. The environmental protection online monitoring system based on cloud computing and blockchain technology is characterized by: The system includes a remote data computing service center and a multimodal information integrated supervision platform. The remote data computing service center includes a multi-source data fluctuation anomaly online monitoring and environmental damage risk judgment method program based on HiWoo SCADA monitoring. When the multi-source data fluctuation anomaly online monitoring and environmental damage risk judgment method program based on HiWoo SCADA monitoring is executed by the multimodal information integrated supervision platform, the following steps are implemented: Establish an edge computing gateway for a cloud computing collaborative blockchain platform, and use the edge computing gateway for multimodal environmental protection parameter calculation configuration to obtain the edge computing gateway for the cloud computing collaborative blockchain platform after the multimodal environmental protection parameter calculation configuration, and use the edge computing gateway for the cloud computing collaborative blockchain platform to control the HiWoo SCADA visualization information of the cloud computing collaborative blockchain platform that integrates multi-source data; Using an environmental information database to integrate seasonal fluctuation anomaly visualization information of multi-source data, establishing a graph neural network label based on the seasonal fluctuation anomaly visualization information of multi-source data, and establishing an online monitoring algorithm for multi-source data fluctuation anomaly based on the graph neural network label; The multi-source data fluctuation anomaly online monitoring algorithm is used to monitor the HiWoo SCADA visualization information of the multi-source data online, obtain the fluctuation anomaly unit time period peak data of the multi-source data at different altitudes and topography, and perform environmental damage risk judgment based on the fluctuation anomaly unit time period peak data of the multi-source data at different altitudes and topography to generate environmental damage risk judgment information; Setting environmental remediation measures with different funds and technologies based on the environmental damage risk assessment information, and performing environmental optimization process processing based on the environmental remediation measures with different funds and technologies; An environmental information database is used to integrate seasonal fluctuation anomaly visualization information of multi-source data, and a graph neural network tag is established based on the seasonal fluctuation anomaly visualization information of multi-source data. An online monitoring algorithm for multi-source data fluctuation anomaly is established based on the graph neural network tag. Specifically, the algorithm includes: Using an environmental information database to integrate seasonal fluctuation anomaly visualization information of multi-source data, and using the seasonal fluctuation anomaly visualization information of the multi-source data to classify the fluctuation anomaly types, obtaining visualization information of each fluctuation anomaly type, and establishing a graph neural network label for each fluctuation anomaly type based on the visualization information of each fluctuation anomaly type; Input the visualization information in the graph neural network label of each fluctuation anomaly type into the peak Spark calculation model, obtain the fluctuation anomaly unit period peak value in the unit time visualization information, and determine whether the fluctuation anomaly unit period peak value in the visualization information is equal to or exceeds the preset value, and introduce the long short-term memory network; If the fluctuation abnormality unit period peak value in the visualization information is equal to or exceeds a preset value, the fluctuation abnormality unit period peak value corresponding to the fluctuation abnormality type peak value information of the unit time visualization information is obtained as the relevant fluctuation abnormality unit period peak value; if the fluctuation abnormality unit period peak value in the visualization information is less than the preset value, the fluctuation abnormality unit period peak value corresponding to the fluctuation abnormality type peak value information of the unit time visualization information is used as the relevant fluctuation abnormality unit period peak value; The relevant fluctuation anomaly unit period peak is input into the long short-term memory network, so that the input dimension is concentrated in the relevant fluctuation anomaly unit period peak, and the time step is obtained. A multi-source data fluctuation anomaly online monitoring algorithm is established based on a deep neural network, and the time step is input into the multi-source data fluctuation anomaly online monitoring algorithm for Dropout regularization.

Images