Smart city informatization management system based on big data

By collecting air quality and meteorological data in real time in the smart city information management system and using deep learning models to predict, the problem of insufficient timeliness and analysis accuracy of existing systems in environmental monitoring data is solved, and air pollution is achieved Timely warning and response have improved environmental protection efficiency.

CN118967406AInactive Publication Date: 2024-11-15武汉慧友佳华电子有限公司

Patent Information

Application Number
CN202411113158.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-14
Publication Date
2024-11-15
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing smart city information management system has problems such as untimely data acquisition, inaccurate analysis, and slow early warning response in terms of environmental monitoring, which is difficult to meet the requirements of modern smart cities for efficient, accurate and intelligent environmental management, especially in the air. Pollutant concentration and meteorological data processing.

Method used

A smart city information management system based on big data was designed. The data acquisition module collects air quality and meteorological data in real time, combines the deep learning model to predict environmental quality, timely detect and warning of environmental pollution events, and use the early warning and response module. Automatically trigger early warning mechanisms and emergency plans to provide scientific basis to support environmental protection and governance.

Benefits of technology

It has achieved comprehensive, accurate, real-time monitoring and early warning of urban air environmental quality, improved the efficiency and effectiveness of environmental protection and governance, and can deal with air quality problems in a timely manner to ensure residents' health and urban ecological safety.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118967406A_ABST
    Figure CN118967406A_ABST
Patent Text Reader

Abstract

The invention discloses a smart city information management system based on big data, and relates to the technical field of smart city management, and the system comprises a data collection module which is used for deploying an air quality environment monitoring sensor and meteorological parameter monitoring equipment in a city area, and collecting environment and meteorological data in real time. The air quality and meteorological data in the environment are collected in real time through the data collection module, the collected data are accurately analyzed through the big data analysis model and the early warning and response module, timely early warning response is carried out, advanced technologies such as the Internet of Things, big data processing and deep learning are integrated, and the system is convenient to use. According to the invention, comprehensive, accurate and real-time monitoring and early warning of the urban air environment quality are realized, the efficiency and effect of environmental protection and treatment are effectively improved, corresponding measures can be taken in time according to the air pollutant concentration and meteorological data, the air quality problem of the smart city can be processed in time, and the air quality of the smart city is ensured. And the resident health and the urban ecological safety are guaranteed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of smart city management, and in particular to a smart city information management system based on big data. Background Art

[0002] Smart city refers to the integration of various fields of the city through information technology and Internet technology, so as to achieve intelligent, efficient and sustainable development in urban management, social services and economic operation. The core of this concept is to establish a highly information-based urban platform, using advanced technologies such as big data, artificial intelligence, and 5G communications to achieve comprehensive grasp and effective management of all aspects of urban information. Smart city information management is a comprehensive concept, which involves the use of modern information technology and communication technology to sense, analyze and integrate key information of the core system of urban operation, and make intelligent responses accordingly, so as to improve the level of intelligence and refinement of urban management, as well as the inclusiveness and convenience of social services.

[0003] With the in-depth advancement of smart city construction, environmental quality, as one of the important indicators of urban sustainable development, has an increasingly urgent need for monitoring and management. However, the existing smart city information management system still has certain defects in environmental monitoring. The existing smart city information management system has problems such as untimely data acquisition, inaccurate analysis, and slow early warning response during environmental monitoring. It is difficult to meet the requirements of modern smart cities for efficient, accurate, and intelligent environmental management. It is difficult to take corresponding measures in time for air pollutant concentrations and meteorological data, resulting in the difficulty of timely handling of urban air quality problems. Therefore, it is necessary to propose a smart city information management system based on big data to solve the problems in the existing technology. Summary of the invention

[0004] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide a smart city information management system based on big data. It can collect air quality environmental data of various areas of the city in real time, combine meteorological data and historical data, predict environmental change trends through big data analysis models, and timely discover and warn of environmental pollution incidents, providing a scientific basis for environmental protection and governance.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a smart city information management system based on big data, the system comprising:

[0006] Data collection module, used to deploy air quality environment monitoring sensors and meteorological parameter monitoring equipment in urban areas to collect environmental and meteorological data in real time;

[0007] The data storage and processing module is used to receive environmental data from the data acquisition module and provide a data basis for big data analysis;

[0008] Big data analysis model, using deep learning big data analysis technology, based on historical data and real-time meteorological data, to build an environmental quality prediction model to predict the trend of environmental quality changes;

[0009] The early warning and response module is used to automatically trigger the early warning mechanism, send information and call the emergency plan based on the prediction results of the big data analysis model;

[0010] The visualization display module is used to provide a user interface to display real-time data, forecast and warning information in the form of charts and maps.

[0011] Furthermore, the environmental data collected by the data acquisition module include PM2.5, PM10, sulfur dioxide, nitrogen oxides, ozone and carbon monoxide pollutant concentrations, and the meteorological data collected by the data acquisition module include temperature, humidity, wind speed and wind direction data.

[0012] Furthermore, the specific execution steps of the data acquisition module include:

[0013] Air quality environmental monitoring sensors and meteorological parameter monitoring equipment will be deployed in key urban areas, including industrial areas, residential areas, major traffic arteries, and parks and green spaces, based on environmental monitoring needs and layout planning;

[0014] Initialize the configuration of each sensor, including setting the data collection frequency, data format, communication protocol, and data transmission target address;

[0015] Air quality environmental monitoring sensors begin to collect real-time concentration data of PM2.5, PM10, sulfur dioxide, nitrogen oxides, ozone, and carbon monoxide pollutants in the air;

[0016] Meteorological parameter monitoring equipment simultaneously collects data on temperature, humidity, wind speed and wind direction meteorological parameters;

[0017] The sensor performs preliminary processing on the collected raw data, and the processed data is encapsulated into data packets that comply with specific protocols and are ready for transmission;

[0018] The sensor transmits the encapsulated data packets to the data storage and processing module in real time through the preset wireless network communication technology.

[0019] Furthermore, the specific execution steps of the data storage and processing module include:

[0020] The data storage and processing module receives real-time environmental data from the data acquisition module through a high-bandwidth network interface;

[0021] For missing values ​​in the data, interpolation is used to fill them, statistical methods are used to identify and eliminate outliers, and the data is formatted;

[0022] Integrate data from different sensors and monitoring stations according to timestamp and location dimensions to form a unified data format;

[0023] Combine meteorological data and historical environmental data to build a complete data set.

[0024] Furthermore, the specific execution steps of the big data analysis model also include:

[0025] Introducing distributed storage technology to store cleaned and integrated data on multiple nodes, build indexes, and optimize query efficiency;

[0026] Standardize and normalize the data to eliminate the impact of different dimensions on model training. The formula is: Among them, x is the original data, μ is the mean of the data, σ is the standard deviation of the data, and x norm It is the standardized data;

[0027] Establish a meteorological database and a historical environmental database to store cleaned and integrated data, as well as statistical data and analysis results that may be needed subsequently.

[0028] Furthermore, the specific execution steps of the big data analysis model include:

[0029] Clean the received environmental data, remove outliers and missing values, and normalize and standardize the data;

[0030] Construct a feature matrix including historical environmental quality data and real-time meteorological data;

[0031] Select the LSTM deep learning model, process time series data, design the model architecture, including input layer, hidden layer, output layer, and determine the model's hyperparameters, including learning rate, batch size, and number of iterations;

[0032] Using historical environmental data and meteorological data as training sets, the model parameters are adjusted through the back propagation algorithm to minimize the prediction error. The mean square error MSE formula is: Where N is the number of samples, y i is the true value, is the predicted value;

[0033] Apply the Adam optimization algorithm to update the model weights.

[0034] Furthermore, the specific execution steps of the big data analysis model also include:

[0035] Use the test set to evaluate the trained model, calculate the error between the predicted value and the actual value, including prediction accuracy, recall rate, and F1 score indicators, check whether the model is overfitting or underfitting, and adjust the model structure and hyperparameters accordingly;

[0036] According to the evaluation results, adjust and optimize the model, including adjusting the network structure, increasing the amount of training data, and adjusting the learning rate;

[0037] Deploy the trained model to the actual environment and receive new environmental and meteorological data in real time;

[0038] Use models to predict future environmental quality.

[0039] Furthermore, the specific execution steps of the early warning and response module include:

[0040] Set warning thresholds for pollutants and meteorological parameters based on environmental protection standards and historical data;

[0041] Obtain the prediction results of environmental quality in the future from the big data analysis model;

[0042] Compare the forecast results of each monitoring point, each pollutant and meteorological parameter with their corresponding warning thresholds;

[0043] Once it is determined that an early warning is necessary, the system will release early warning information to relevant departments and the public through preset communication channels; the early warning information includes the type and concentration of pollutants, predicted future trends, warning levels, and recommended protective measures;

[0044] According to the warning level, the preset emergency plan is automatically called up, which includes measures such as strengthening monitoring frequency, limiting emission sources, evacuating people and starting air purification equipment.

[0045] Furthermore, the specific process of comparing the prediction results of each monitoring point, each pollutant and meteorological parameter with the corresponding warning threshold in the early warning and response module is as follows: let the pollutant set be P = {p1, p2, ..., p n}, for each pollutant p∈P, the prediction result R(p)>threshold(p), then the trigger warning T=true, and the warning level L=mapping two values ​​to level(R(p),threshold).

[0046] Furthermore, the specific execution steps of the visual display module include:

[0047] Obtain the latest real-time environmental data, forecast results and warning information from the data storage and processing module;

[0048] Design user-friendly graphical interfaces, including the layout and style of maps, charts, and dashboard elements, and determine how each data type is presented;

[0049] Use the data visualization library to convert the organized data into graphic elements on charts and maps to achieve dynamic data updates;

[0050] By adding interactive elements, including zooming, dragging, and filtering, users can view environmental data in different areas and time periods according to their needs, and highlight early warning information.

[0051] Compared with the existing technology, the smart city information management system based on big data has the following beneficial effects:

[0052] The present invention collects air quality and meteorological data in the environment in real time through the data acquisition module, and uses the big data analysis model and the early warning and response module to accurately analyze the collected data and make timely early warning responses. It integrates advanced technologies such as the Internet of Things, big data processing, and deep learning to achieve comprehensive, accurate, and real-time monitoring and early warning of urban air environment quality, effectively improving the efficiency and effectiveness of environmental protection and governance, and being able to take corresponding measures in a timely manner in response to air pollutant concentrations and meteorological data, so that air quality problems in smart cities can be dealt with in a timely manner, thereby ensuring the health of residents and the ecological safety of the city.

[0053] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0055] Figure 1 This is a structural diagram of a smart city information management system based on big data. DETAILED DESCRIPTION

[0056] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] Embodiment 1

[0058] A smart city information management system based on big data, the system comprising:

[0059] Data collection module, used to deploy air quality environment monitoring sensors and meteorological parameter monitoring equipment in urban areas to collect environmental and meteorological data in real time;

[0060] The environmental data collected by the data acquisition module include PM2.5, PM10, sulfur dioxide, nitrogen oxides, ozone and carbon monoxide pollutant concentrations, and the meteorological data collected by the data acquisition module include temperature, humidity, wind speed and wind direction data.

[0061] The specific execution steps of the data acquisition module include: deploying air quality environmental monitoring sensors and meteorological parameter monitoring equipment in key urban areas, including industrial areas, residential areas, major traffic arteries, and parks and green spaces according to environmental monitoring needs and layout planning. These sensors and equipment must have high precision, high stability, and remote communication capabilities; initializing the configuration of each sensor, including setting the data collection frequency (such as once every minute or every hour), data format, communication protocol (such as Wi-Fi, NB-IoT, LoRa, etc.), and data transmission target address (i.e., the receiving address of the data center);

[0062] Air quality environmental monitoring sensors begin to collect real-time concentration data of PM2.5, PM10, sulfur dioxide, nitrogen oxides, ozone and carbon monoxide pollutants in the air; meteorological parameter monitoring equipment simultaneously collects data on temperature, humidity, wind speed and wind direction meteorological parameters; the sensor performs preliminary processing on the collected raw data, such as removing noise, calibrating errors, calculating average values ​​or performing simple data fusion, to improve data quality. The processed data is encapsulated into data packets that comply with specific protocols and is ready for transmission;

[0063] The sensor transmits the encapsulated data packets to the data storage and processing module in real time through the preset wireless network communication technology (such as Wi-Fi, cellular network, low-power wide area network, etc.). During the transmission process, data encryption and transmission security may need to be considered to prevent the data from being intercepted or tampered with. The data acquisition module also needs to have a sensor status monitoring function, which can monitor the operating status of the sensor (such as power, communication status, data acquisition status, etc.) in real time, and promptly alarm or take corresponding maintenance measures when abnormalities are found.

[0064] The data storage and processing module is used to receive environmental data from the data acquisition module, clean, integrate and store the data, and introduce the meteorological database and historical environmental database to provide a data basis for big data analysis;

[0065] The specific execution steps of the data storage and processing module include: the data storage and processing module receives real-time environmental data from the data acquisition module through a high-bandwidth network interface; for missing values ​​in the data, interpolation methods (such as linear interpolation, mean interpolation, etc.) are used to fill them, and statistical methods (such as Z-score detection, IQR (interquartile range) method) are used to identify and eliminate outliers; data is formatted to ensure that all data types and formats are unified for subsequent processing;

[0066] Integrate data from different sensors and monitoring stations according to timestamp and location dimensions to form a unified data format; merge meteorological data and historical environmental data to build a complete data set. Introduce distributed storage technology (such as Hadoop HDFS, Ceph, etc.) to store the cleaned and integrated data on multiple nodes to ensure data security and scalability, build indexes, and optimize query efficiency;

[0067] The data storage and processing module receives data packets from sensors and performs integrity verification and analysis to confirm the correctness and integrity of the data. If there is a problem during data transmission (such as packet loss, data error, etc.), the data storage and processing module will send a retransmission request to the sensor to ensure complete data reception. The data storage and processing module stores the received environmental data and meteorological data in a high-performance database system for subsequent analysis and processing. At the same time, in order to ensure the security and recoverability of the data, regular data backup and disaster recovery planning are also required.

[0068] Standardize and normalize the data to eliminate the impact of different dimensions on model training. The formula is: Among them, x is the original data, μ is the mean of the data, σ is the standard deviation of the data, and x norm It is standardized data; establish a meteorological database and a historical environmental database to store the cleaned and integrated data, as well as the statistical data and analysis results that may be needed later.

[0069] Embodiment 2

[0070] Big data analysis model, using deep learning big data analysis technology, based on historical data and real-time meteorological data, to build an environmental quality prediction model to predict the trend of environmental quality changes;

[0071] The specific execution steps of the big data analysis model include: cleaning the received environmental data, removing outliers and missing values, normalizing and standardizing the data to ensure that data of different dimensions can be processed in the same model; constructing a feature matrix, including historical environmental quality data (such as pollutant concentrations in the past few hours) and real-time meteorological data (such as current temperature, humidity, wind speed, etc.); selecting a deep learning model of the long short-term memory network LSTM to process time series data, designing the model architecture, including the input layer, hidden layer (possibly including multiple layers), and output layer, and determining the model's hyperparameters, including learning rate, batch size, and number of iterations;

[0072] Using historical environmental data and meteorological data as training sets, the model parameters are adjusted through the back propagation algorithm to minimize the prediction error. The mean square error MSE formula is: Where N is the number of samples, y i is the true value, It is the predicted value that updates the model weights using the Adam optimization algorithm.

[0073] The construction formula of the long short-term memory network LSTM deep learning model in the big data analysis model includes: t =σ(W xi x t +W hi h t-1 +b i ), f t =σ(W xf x t +W hf h t-1 +b f ), o t =σ(W xo x t +W ho h t-1 +b o ), h t =o t ⊙tanh(C t ), where i t is the input gate, f t It's the forget gate, t is the output gate, C t is the cell state, x t is the input, h t-1 is the hidden state of the previous moment, σ is the sigmoid function, and ⊙ is element-wise multiplication.

[0074] Use the test set to evaluate the trained model, calculate the error between the predicted value and the actual value, including prediction accuracy, recall rate, and F1 score indicators, check whether the model is overfitting or underfitting, and adjust the model structure and hyperparameters accordingly;

[0075] Based on the evaluation results, the model is adjusted and optimized, including adjusting the network structure, increasing the amount of training data, and adjusting the learning rate to improve the model's prediction accuracy and generalization ability; the trained model is deployed to the actual environment to receive new environmental data and meteorological data in real time; and the model is used to predict future environmental quality.

[0076] Embodiment 3

[0077] The early warning and response module is used to automatically trigger the early warning mechanism, send information and call the emergency plan based on the prediction results of the big data analysis model;

[0078] According to the prediction results of the big data analysis model, the warning threshold is set. When the prediction results exceed the warning threshold, the warning mechanism is automatically triggered, and warning information is sent to relevant departments and the public through the preset communication channels. The emergency plan is automatically called according to the warning level and the corresponding governance measures are initiated;

[0079] The specific execution steps of the early warning and response module include: setting early warning thresholds for pollutants and meteorological parameters according to environmental protection standards and historical data. These thresholds can be fixed or dynamically adjusted according to factors such as seasons and weather conditions; obtaining the prediction results of environmental quality in the future from the big data analysis model; comparing the prediction results of each monitoring point, each pollutant and meteorological parameter with their corresponding early warning thresholds. The specific comparison process is: let the pollutant set be P = {p1, p2, …, p n}, for each pollutant p∈P, the prediction result R(p)>threshold(p), then the trigger warning T=true, and the warning level L=mapping two values ​​to level(R(p),threshold);

[0080] Once it is determined that an early warning is necessary, the system will issue early warning information to relevant departments and the public through preset communication channels (including text messages, APP push, official websites, social media, etc.); the early warning information includes the type of pollutants, concentration, predicted future trends, warning levels and recommended protective measures. According to the warning level, the preset emergency plan will be automatically called. The emergency plan includes measures such as strengthening monitoring frequency, limiting emission sources, evacuating people and starting air purification equipment.

[0081] Embodiment 4

[0082] The visualization display module is used to provide a user interface to display real-time data, forecast and warning information in the form of charts and maps. It provides a user interface to intuitively display real-time environmental data, forecast results, warning information, etc. in the form of charts and maps, supporting managers and the public to understand environmental conditions.

[0083] The specific execution steps of the visualization module include: obtaining the latest real-time environmental data, forecast results and warning information from the data storage and processing module, and organizing and formatting these data as necessary for display in the visualization interface; designing a user-friendly graphical interface, including the layout and style of maps, charts, and dashboard elements, and determining the display method for each data type, such as using a line chart to display the trend of pollutant concentration changes, and using a heat map and scatter plot to display regional pollution distribution, etc.;

[0084] Use data visualization libraries (such as D3.js, ECharts, Highcharts, etc.) to convert the sorted data into graphic elements on charts and maps, realize dynamic data updates, and ensure that charts and maps can reflect the latest environmental conditions in real time; add interactive elements, including zooming, dragging, and filtering, so that users can view environmental data in different areas and time periods according to their needs, and highlight warning information, such as using red borders, flashing effects, or alarm sounds to remind users;

[0085] The performance of the visualization interface is optimized to ensure smooth operation under high data volume, and technologies such as lazy loading and data paging are used to reduce the amount of data loaded at a single time.

[0086] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the same elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A smart city information management system based on big data, characterized in that: The system includes: Data collection module, used to deploy air quality environment monitoring sensors and meteorological parameter monitoring equipment in urban areas to collect environmental and meteorological data in real time; The data storage and processing module is used to receive environmental data from the data acquisition module and provide a data basis for big data analysis; Big data analysis model, using deep learning big data analysis technology, based on historical data and real-time meteorological data, to build an environmental quality prediction model to predict the trend of environmental quality changes; The early warning and response module is used to automatically trigger the early warning mechanism, send information and call the emergency plan based on the prediction results of the big data analysis model; The visualization display module is used to provide a user interface to display real-time data, forecast and warning information in the form of charts and maps.

2. According to the big data-based smart city information management system of claim 1, it is characterized in that: The environmental data collected by the data acquisition module include PM2.5, PM10, sulfur dioxide, nitrogen oxides, ozone and carbon monoxide pollutant concentrations, and the meteorological data collected by the data acquisition module include temperature, humidity, wind speed and wind direction data.

3. According to the big data-based smart city information management system of claim 1, it is characterized in that: The specific execution steps of the data acquisition module include: Air quality environmental monitoring sensors and meteorological parameter monitoring equipment will be deployed in key urban areas, including industrial areas, residential areas, major traffic arteries, and parks and green spaces, based on environmental monitoring needs and layout planning; Initialize the configuration of each sensor, including setting the data collection frequency, data format, communication protocol, and data transmission target address; Air quality environmental monitoring sensors begin to collect real-time concentration data of PM2.5, PM10, sulfur dioxide, nitrogen oxides, ozone, and carbon monoxide pollutants in the air; Meteorological parameter monitoring equipment simultaneously collects data on temperature, humidity, wind speed and wind direction meteorological parameters; The sensor performs preliminary processing on the collected raw data, and the processed data is encapsulated into data packets that comply with specific protocols and are ready for transmission; The sensor transmits the encapsulated data packets to the data storage and processing module in real time through the preset wireless network communication technology.

4. According to the big data-based smart city information management system of claim 1, it is characterized in that: The specific execution steps of the data storage and processing module include: The data storage and processing module receives real-time environmental data from the data acquisition module through a high-bandwidth network interface; For missing values ​​in the data, interpolation is used to fill them, statistical methods are used to identify and eliminate outliers, and the data is formatted; Integrate data from different sensors and monitoring stations according to timestamp and location dimensions to form a unified data format; Combine meteorological data and historical environmental data to build a complete data set.

5. According to the big data-based smart city information management system of claim 4, it is characterized in that: The specific execution steps of the big data analysis model also include: Introducing distributed storage technology to store cleaned and integrated data on multiple nodes, build indexes, and optimize query efficiency; Standardize and normalize the data to eliminate the impact of different dimensions on model training. The formula is: Among them, x is the original data, μ is the mean of the data, σ is the standard deviation of the data, and x norm It is the standardized data; Establish a meteorological database and a historical environmental database to store cleaned and integrated data, as well as statistical data and analysis results that may be needed subsequently.

6. According to the big data-based smart city information management system of claim 1, it is characterized in that: The specific execution steps of the big data analysis model include: Clean the received environmental data, remove outliers and missing values, and normalize and standardize the data; Construct a feature matrix including historical environmental quality data and real-time meteorological data; Select the LSTM deep learning model, process time series data, design the model architecture, including input layer, hidden layer, output layer, and determine the model's hyperparameters, including learning rate, batch size, and number of iterations; Using historical environmental data and meteorological data as training sets, the model parameters are adjusted through the back propagation algorithm to minimize the prediction error. The mean square error MSE formula is: Where N is the number of samples, y i is the true value, is the predicted value; Apply the Adam optimization algorithm to update the model weights.

7. The smart city information management system based on big data according to claim 6 is characterized in that: The specific execution steps of the big data analysis model also include: Use the test set to evaluate the trained model, calculate the error between the predicted value and the actual value, including prediction accuracy, recall rate, and F1 score indicators, check whether the model is overfitting or underfitting, and adjust the model structure and hyperparameters accordingly; According to the evaluation results, adjust and optimize the model, including adjusting the network structure, increasing the amount of training data, and adjusting the learning rate; Deploy the trained model to the actual environment and receive new environmental and meteorological data in real time; Use models to predict future environmental quality.

8. The smart city information management system based on big data according to claim 1 is characterized in that: The specific execution steps of the early warning and response module include: Set warning thresholds for pollutants and meteorological parameters based on environmental protection standards and historical data; Obtain the prediction results of environmental quality in the future from the big data analysis model; Compare the forecast results of each monitoring point, each pollutant and meteorological parameter with their corresponding warning thresholds; Once it is determined that an early warning is necessary, the system will release early warning information to relevant departments and the public through preset communication channels; the early warning information includes the type and concentration of pollutants, predicted future trends, warning levels, and recommended protective measures; According to the warning level, the preset emergency plan is automatically called up, which includes measures such as strengthening monitoring frequency, limiting emission sources, evacuating people and starting air purification equipment.

9. The smart city information management system based on big data according to claim 8 is characterized in that: The specific process of comparing the prediction results of each monitoring point, each pollutant and meteorological parameter with the corresponding warning threshold in the early warning and response module is as follows: Let the pollutant set be P = {p1, p2, ..., p n }, for each pollutant p∈P, the prediction result R(p)>threshold(p), then the trigger warning T=true, and the warning level L=mapping two values ​​to level(R(p),threshold).

10. The smart city information management system based on big data according to claim 1, characterized in that: The specific execution steps of the visual display module include: Obtain the latest real-time environmental data, forecast results and warning information from the data storage and processing module; Design user-friendly graphical interfaces, including the layout and style of maps, charts, and dashboard elements, and determine how each data type is presented; Use the data visualization library to convert the organized data into graphic elements on charts and maps to achieve dynamic data updates; By adding interactive elements, including zooming, dragging, and filtering, users can view environmental data in different areas and time periods according to their needs, and highlight early warning information.

Citation Information

Patent Citations

  • Internet of Things-oriented accumulated water level prediction method based on long-short-term memory network

    CN111222698A

  • Smart city regionalization management method and system based on multi-source data analysis

    CN116991916A

  • Digital management system based on smart city governance

    CN117010718A

  • Smart city air quality monitoring and early warning system

    CN117218817A

  • Flue gas pollution source collecting and monitoring system and method and readable storage medium

    CN117744704A

Cited By

  • Urban greening state monitoring method and system based on digital mirror image information

    CN119399009A

  • Closed space three-proofing system control method and device based on multiple sensors

    CN119668346A

  • Smart city environment monitoring method, terminal and environment monitoring system

    CN119721838A

  • Urban ecological management and control method and system based on smart city

    CN119893455A

  • Big data environmental protection management system and method based on smart park

    CN120087781A