Urban environment monitoring method based on satellite Internet of Things

Abstract

The invention discloses an urban environment monitoring method based on the satellite Internet of Things, and the method comprises the following steps: collecting environment data of each region of a city through employing a sensor network, and integrating the environment data into urban environment data; after preprocessing, data compression processing and decompression processing are carried out on the urban environment data, the data are transmitted to the data processing center; performing anomaly detection on the received data to generate an abnormal data report; for the abnormal data report, combining a preset environment threshold value, adopting a regression analysis algorithm to carry out environment trend prediction, and generating an environment change trend report; integrating the abnormal data report and the environment change trend report to generate an urban environment condition evaluation report; and based on the urban environment condition evaluation report, adjusting resource distribution of the environment data by adopting a resource scheduling algorithm, and generating an environment data processing scheme. According to the invention, the whole process optimization from data acquisition, transmission to analysis processing is realized, and the accuracy, real-time performance and scientificity of urban environment monitoring are effectively improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of environmental monitoring, and particularly relates to an urban environmental monitoring method based on satellite Internet of Things. Background Art

[0002] During the urban environmental monitoring process, the transmission and processing of data face multiple technical contradictions. First, the wireless communication between the sensor network and the satellite Internet of Things platform may experience signal attenuation or packet loss due to the complex urban terrain or electromagnetic interference, resulting in incomplete or delayed data transmission. Second, the bandwidth of the satellite link is limited, and when a large amount of environmental data is uploaded simultaneously from multiple regions, channel congestion may occur, affecting the data transmission efficiency. In addition, when the data processing center conducts in-depth analysis, insufficient computing resources may occur due to the large amount of data and complex algorithms, prolonging the data processing time.

[0003] More critically, the control center needs to judge the urban environmental situation in real time based on the results of the data processing center. However, due to potential problems in the data transmission and processing links, the information obtained by the control center may be lagged or inaccurate, thus affecting the timeliness and accuracy of decision-making.

[0004] In view of the above problems, there is an urgent need to propose an urban environmental monitoring method based on satellite Internet of Things to achieve efficient and reliable data transmission and processing, so as to ensure the real-time and accuracy of the urban environmental monitoring system. Summary of the Invention

[0005] To solve the above technical problems, the present invention proposes an urban environmental monitoring method based on satellite Internet of Things to solve the problems existing in the above prior art.

[0006] To achieve the above object, the present invention provides an urban environmental monitoring method based on satellite Internet of Things, including the following steps:

[0007] Collect environmental data from various regions of the city using a sensor network and integrate it into urban environmental data;

[0008] After preprocessing, data compression processing and decompression processing of the urban environmental data, transmit it to the data processing center;

[0009] At the data processing center, perform anomaly detection on the received data and generate an anomaly data report;

[0010] For the anomaly data report, combine the preset environmental thresholds and use a regression analysis algorithm to predict the environmental trend and generate an environmental change trend report;

[0011] Integrate the anomaly data report and the environmental change trend report to generate an urban environmental condition assessment report;

[0012] Based on the urban environmental status assessment report, a resource scheduling algorithm is used to adjust the resource allocation for environmental data and generate an environmental data processing plan.

[0013] Optionally, the process of preprocessing the urban environmental data includes:

[0014] Send the urban environmental data to the satellite Internet of Things platform. At the satellite Internet of Things platform, perform data cleaning and format conversion processing on the urban environmental data to remove invalid data and noise interference and obtain standardized data.

[0015] Optionally, the process of data compression processing on the standardized data includes:

[0016] Transmit the standardized data to the ground gateway station via a satellite link, monitor the channel status in real time, and determine whether there is a congestion phenomenon; if the channel is congested, use a preset data compression algorithm to compress the standardized data and re-transmit the compressed data to the ground gateway station.

[0017] Optionally, the process of decompression processing on the compressed data includes:

[0018] Use a preset decompression algorithm to decompress the received compressed data, compare and verify the decompressed original data with a preset data format. If the data formats are consistent, mark the original data as available, package and encapsulate the available original data according to a preset forwarding rule, and send the encapsulated data to the data processing center via a preset transmission protocol.

[0019] Optionally, in the data processing center, the process of performing anomaly detection on the received data and generating an anomaly data report includes:

[0020] Use a time series algorithm to preprocess the received data and extract time series features; identify outliers in the time series features through an anomaly detection algorithm; if anomaly data is detected, classify the anomaly data according to the anomaly type classification rule; for the classified anomaly data, extract the corresponding time node information; associate the anomaly type with the time node information to form an anomaly data record, and generate an anomaly data report based on the anomaly data record.

[0021] Optionally, for the anomaly data report, in combination with a preset environmental threshold, the process of using a regression analysis algorithm to predict the environmental trend and generate an environmental change trend report includes:

[0022] Obtain an abnormal data report, extract the abnormal values and the corresponding time points from it; according to the preset environmental threshold, determine whether the abnormal values exceed the threshold line; for the abnormal values that exceed the threshold line, use the regression method to analyze the change trend of the parameter values and generate a trend line; combine the trend line to predict the predicted values of the parameter values in the future time period; associate the predicted values with the abnormal value classification values to generate an environmental change trend report.

[0023] Optionally, based on the urban environmental status assessment report, the process of adjusting the resource allocation for environmental data using a resource scheduling algorithm to generate an environmental data processing solution includes:

[0024] Obtain the environmental data in the environmental change trend report, extract the corresponding priority values and resource amounts; sort the resource amounts according to the priority values to determine the resource allocation order; if the resource amount is lower than the preset threshold, use the scheduling method to preferentially allocate resources to process high-priority environmental data; generate an environmental data processing solution through the adjusted resource allocation results.

[0025] The present invention also provides a computer device, including a memory, a processor, and a computer program stored on the memory, and the processor executes the computer program to implement the steps of the method.

[0026] The present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method are implemented.

[0027] The present invention also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the method are implemented.

[0028] Compared with the prior art, the present invention has the following advantages and technical effects:

[0029] The present invention discloses a method for urban environmental monitoring based on satellite Internet of Things. This method collects urban environmental data through a sensor network and uses a satellite Internet of Things platform for data processing and transmission. Aiming at the problem of channel congestion in the data transmission process, the present invention uses a data compression algorithm to improve the transmission efficiency. In the data processing stage, the present invention uses time series analysis for anomaly detection and combines a regression analysis algorithm to predict the environmental change trend. In the face of insufficient computing resources, the present invention preferentially processes high-priority data through a resource scheduling algorithm. Finally, the present invention integrates various analysis reports to generate an urban environmental status assessment report, providing a scientific basis for urban environmental management decisions. This method realizes the full-process optimization from data collection, transmission to analysis and processing, effectively improving the accuracy, real-time performance and scientific nature of urban environmental monitoring. Brief Description of the Drawings

[0030] The accompanying drawings, which form a part of this application, are used to provide a further understanding of this application. The schematic embodiments and descriptions thereof of this application are used to explain this application and do not constitute an improper limitation of this application. In the accompanying drawings:

[0031] Figure 1 It is a flowchart of the urban environment monitoring method according to an embodiment of the present invention. Specific embodiments

[0032] It should be noted that, without conflict, the embodiments in this application and the features in the embodiments can be combined with each other. The following will refer to the accompanying drawings and combine the embodiments to detail this application.

[0033] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0034] Embodiment 1

[0035] As Figure 1 shown, in this embodiment, a method for monitoring the urban environment based on a satellite Internet of Things is provided, including the following steps:

[0036] Use a sensor network to collect environmental data of each area of the city and integrate it into urban environmental data;

[0037] After preprocessing, data compression processing and decompression processing of the urban environmental data, transmit it to the data processing center;

[0038] In the data processing center, perform anomaly detection on the received data and generate an anomaly data report;

[0039] For the anomaly data report, combine the preset environmental thresholds and use a regression analysis algorithm to predict the environmental trend and generate an environmental change trend report;

[0040] Integrate the anomaly data report and the environmental change trend report to generate an urban environmental condition assessment report;

[0041] Based on the urban environmental condition assessment report, use a resource scheduling algorithm to adjust the resource allocation for environmental data and generate an environmental data processing plan.

[0042] As an implementable method, it specifically includes the following steps:

[0043] S101. Use a sensor network to collect environmental data of each area of the city and integrate it into urban environmental data. The data includes air quality, temperature and humidity, and noise parameters, and transmit the data to the satellite Internet of Things platform through wireless communication technology.

[0044] Sensors are deployed in urban areas to collect air quality, temperature, humidity, and noise parameters for environmental data. The network connects the sensors and transmits the collected environmental data to the wireless communication module. The wireless communication module transmits the data to the satellite Internet of Things platform through a preset communication protocol. The satellite Internet of Things platform receives the environmental data and stores it in a preset database.

[0045] Implementable. Environmental sensors are deployed in urban areas. Common deployment locations include parks, main roads, residential areas, etc. The installation location and density of sensors need to be reasonably selected at different locations. For example, ten measurement points are set in a residential community, and five measurement points are set at the main road intersections to form an environmental monitoring network. Each measurement point is equipped with sensors for gas concentration, temperature, humidity, noise, etc. Among them, the gas sensor can detect the concentration of sulfur dioxide, nitrogen oxides, and particulate matter. The detection range of the temperature and humidity sensor is from minus twenty degrees Celsius to sixty degrees Celsius, and the relative humidity is from zero percent to one hundred percent. The wireless transmission uses narrowband Internet of Things technology, which has the characteristics of wide coverage and low power consumption. The data collected by the sensors is uploaded regularly through the wireless module. The sampling frequency is once every ten minutes during the day and once every thirty minutes at night. The communication protocol uses the lightweight message transmission protocol. The data includes the measurement point number, timestamp, measurement value, etc. After receiving the data, the satellite Internet of Things platform performs format conversion and quality inspection, and stores the qualified data in the time series database.

[0046] S102. On the satellite Internet of Things platform, for the received environmental data, perform data cleaning and format conversion processing to remove invalid data and noise interference, obtain standardized data, and ensure the integrity and availability of the data.

[0047] Implementable. After obtaining the environmental data from the satellite Internet of Things platform, first perform data cleaning and filtering. For example, for air quality data, there are outliers caused by sensor failures. For example, the concentration of carbon monoxide suddenly reaches 10,000 micrograms per cubic meter, which is obviously not in line with the actual situation, and this kind of data needs to be filtered out. In the temperature and humidity data, there may be numerical jumps caused by disconnection or instantaneous interference, such as the temperature jumping from 20 degrees Celsius to 40 degrees Celsius within one second. This unreasonable data also needs to be removed. Perform standardization processing on the cleaned data to uniformly convert data from different sources and different formats into a standard structure. For example, air quality data includes indicators such as particulate matter, sulfur dioxide, and nitrogen oxides. The unit of particulate matter concentration may be micrograms per cubic meter or milligrams per cubic meter, and it needs to be uniformly converted to micrograms per cubic meter. The temperature and humidity data may have a mixture of Celsius and Fahrenheit, and it needs to be unified to Celsius. After obtaining the standardized data, store it in a preset database.

[0048] S103. Transmit the standardized data to the ground gateway station via the satellite link. If channel congestion is detected, use a data compression algorithm to compress the data, reduce the data transmission volume, lower the channel load, and improve the transmission efficiency.

[0049] Obtain the standardized data using a preset communication protocol. Send the standardized data to the ground gateway station via the satellite link. Monitor the channel status in real time and determine whether there is congestion. If the channel is congested, process the standardized data using a preset data compression algorithm. Transmit the compressed data to the ground gateway station again.

[0050] Implementable. The preset communication protocol is selected to adopt the common satellite-ground communication standard for low-Earth orbit satellite Internet of Things, such as the short message communication protocol of the Beidou satellite navigation system, which has the characteristics of simple frame format and high transmission efficiency. The standardized data includes keyword fields such as environmental parameters, timestamps, and location information. The size of each piece of data is usually about several hundred bytes. The satellite link transmission adopts the multipath diversity technology, using multiple ground gateway stations to receive signals simultaneously, effectively improving the transmission reliability. For example, set up gateway stations in multiple regions such as Beijing, Shanghai, and Guangzhou to form a ground station network, which can ensure the continuity of data transmission. Even if the signal of a certain site deteriorates due to weather, other sites can still receive data normally. The channel status monitoring mainly focuses on indicators such as signal-to-noise ratio and bit error rate. When the signal-to-noise ratio is lower than the preset threshold (such as less than minus 10 decibels) or the bit error rate exceeds the preset threshold (such as greater than 1%), it is determined that the channel is congested. Taking an actual scenario as an example, when encountering severe convective weather, the channel quality drops significantly, and at this time, the data compression mechanism needs to be started. The data compression algorithm selects a lossless compression scheme, such as the differential coding compression algorithm customized for the characteristics of environmental monitoring data. This algorithm takes the difference between adjacent data points as the coding object. Since environmental parameters usually show continuous change characteristics, the difference is small and easy to compress. Actual measurements show that when compressing environmental data such as temperature and humidity, the compression ratio can reach three to five times, significantly reducing the amount of transmitted data. In the data retransmission stage, a selective retransmission mechanism is adopted. When the ground gateway station detects that a data packet is lost or the checksum is incorrect, only requests the retransmission of the incorrect data packet, rather than the entire data block. This method can effectively reduce the retransmission overhead and improve the transmission efficiency. For example, in a certain transmission process, it is found that the third data packet is damaged, and only this packet needs to be retransmitted, and other correctly received data packets do not need to be retransmitted.

[0051] S104. After the ground gateway station receives the compressed data, decompress the data to restore the original data content, and forward the decompressed data to the data processing center.

[0052] The received compressed data is decompressed using a preset decompression algorithm. The decompressed original data is compared and verified with a preset data format. If the data formats are consistent, the original data is marked as available. According to the preset forwarding rules, the original data in the available state is packaged and encapsulated. The encapsulated data is sent to the data processing center through a preset transmission protocol. After receiving the data, the data processing center performs data sharding and storage operations. Integrity verification is performed on the stored data to generate a data verification result.

[0053] Implementable, the decompression algorithm selected needs to correspond to the algorithm used during compression. Commonly, Huffman decoding or run-length decoding can be used. For example, for the telemetry data transmitted back by a spacecraft, if the Huffman compression algorithm is used, the receiving end needs to configure the corresponding Huffman decoding table, and the compressed binary data is restored to the original data by looking up the table. During the data format verification process, attention needs to be paid to the structural integrity and field standardization of the data. Taking meteorological satellite data as an example, the standard format includes fields such as timestamp, longitude and latitude, and meteorological elements. During verification, it is necessary to ensure that the data types, lengths, and value ranges of each field conform to the preset specifications. For example, the valid range of temperature data is between minus ninety degrees and sixty degrees, and data outside this range is marked as abnormal data. Marking the data as available is an important part of data quality control. Data packaging and encapsulation need to consider the classification and priority of the data. The data packet also needs to include control information such as checksum and sequence number to ensure the reliability of data transmission. The selection of the transmission protocol needs to balance the requirements of real-time performance and reliability. For application scenarios with high real-time requirements, such as satellite navigation data transmission, the User Datagram Protocol can be used to ensure that the data arrives quickly. For scenarios with high reliability requirements, such as scientific experiment data transmission, the Transmission Control Protocol is used, and the data integrity is guaranteed through the retransmission mechanism. The sharding storage strategy needs to consider the access characteristics of the data. For example, for meteorological observation data, it can be sharded according to time and space dimensions, and the data in the same time period and adjacent areas is stored in the same shard, which is convenient for subsequent spatio-temporal analysis. The size of each shard can be set to 64 megabytes, which not only ensures storage efficiency but also facilitates data management. The data integrity verification adopts a multi-level verification mechanism. First, the check value of the data packet is calculated through cyclic redundancy check and compared with the check value carried during transmission. Secondly, the continuity of the data is checked to ensure the integrity of the data sequence. Finally, through data redundancy backup, cross-verification is performed between the primary and backup data to generate the final verification result.

[0054] S105. In the data processing center, an anomaly detection algorithm based on time series analysis is used to identify outliers in the received environmental data. If abnormal data is detected, the anomaly type and time node are marked, and an abnormal data report is generated.

[0055] Preprocess environmental data using time series algorithms to extract time series features. Identify outliers in the time series features through a preset anomaly detection model. If outliers are detected, classify the abnormal data according to the anomaly type classification rules. For the classified abnormal data, extract the corresponding time node information. Associate the anomaly type with the time node information to form an abnormal data record. Generate an abnormal data report based on the abnormal data record to record the details of the anomaly. Use data storage technology to save the abnormal data report to a preset database.

[0056] Implementable, the time series algorithm is the basis for processing environmental data. For example, in air quality monitoring, time series analysis is performed on indicators such as temperature, humidity, and carbon dioxide concentration. Taking temperature monitoring as an example, by collecting temperature data in the greenhouse every ten minutes, a continuous time series is formed, and characteristic parameters such as mean, standard deviation, and trend are extracted from it. The anomaly detection model analyzes based on time series features, and common methods include statistical methods and machine learning methods. The anomaly type classification rules classify the detected abnormal data, which can be divided into sudden anomalies, gradual anomalies, periodic anomalies, etc. The extraction of time node information is crucial for anomaly analysis. The abnormal data record associates the anomaly type with the time information to form a complete description of the abnormal event. The generation of the abnormal data report is to facilitate managers to quickly understand the abnormal situation. The report content includes the environmental background where the anomaly occurred, the specific performance of the abnormal data, possible cause analysis, and handling suggestions. Data storage uses a structured database to save the abnormal report. The stored content includes fields such as timestamp, device identifier, anomaly type, abnormal value, and duration. By establishing an indexing mechanism, specific time periods and specific types of abnormal records can be quickly retrieved, facilitating subsequent statistical analysis and equipment maintenance. By regularly analyzing the stored abnormal data, the operation rules of the equipment can be discovered, and possible faults can be predicted.

[0057] S106. For the abnormal data report, combined with the preset environmental threshold, use the regression analysis algorithm for trend prediction, calculate the change trend of environmental parameters in the future time period, and generate an environmental change trend report.

[0058] Implementable, obtain the abnormal data report, extract the abnormal values and the corresponding time points from it. According to the preset environmental threshold, judge whether the abnormal value exceeds the threshold line. For the abnormal values that exceed the threshold line, use the regression method to analyze the change trend of their parameter values. Extract the environmental values within the time period, calculate their change amounts and generate a trend line. Combine the trend line to predict the predicted values of the parameter values in the future time period. Associate the predicted values with the abnormal value classification values to generate an environmental change trend report. Use data storage technology to save the environmental change trend report to a preset database.

[0059] S107. According to the environmental change trend report, adopt a resource scheduling algorithm to allocate computing resources. If the computing resources are insufficient, preferentially allocate resources to process high-priority environmental data to ensure the timeliness of data processing.

[0060] Obtain the environmental data in the environmental change trend report, extract the corresponding priority values and resource amounts. Sort the resource amounts according to the priority values to determine the resource allocation order. If the resource amount is lower than the preset threshold, use the scheduling method to preferentially allocate resources to process high-priority environmental data. Extract the change amount and trend line from the environmental change trend report and calculate the predicted value. Associate the predicted value with the outlier and determine whether it exceeds the threshold line. According to the outlier that exceeds the threshold line, readjust the resource allocation using the calculation method. Generate a new environmental data processing plan based on the adjusted resource allocation result.

[0061] Implementable. The environmental change trend report usually includes environmental data such as temperature, humidity, and air quality. Each data has its priority and required resource amount. Through priority sorting, it can be ensured that the most urgent environmental problems are handled in a timely manner. In terms of resource allocation, assume that the preset resource threshold is fifteen units, and the total amount of resources such as the current device processing capacity and personnel configuration is twelve units, which is lower than the threshold. In this case, the scheduling system will give priority to ensuring the treatment of harmful gases with the first priority, allocate eight resource units for monitoring and treatment, and allocate the remaining four resource units to other environmental data processing. In the analysis of environmental change trends, the change amount extracted by the system shows that the concentration of harmful gases has been on the rise in the past 24 hours and is predicted to exceed the safety threshold within the next four hours. At this time, it is necessary to compare the current predicted value with the historical outliers and find that if the current resource allocation plan continues, the upward trend of the harmful gas concentration cannot be effectively controlled. According to the analysis result of exceeding the threshold, the resource allocation system will readjust the plan. After adjustment, the device processing capacity is increased to ten resource units, and at the same time, two personnel resource units are dispatched specifically to handle the harmful gas problem. The new environmental data processing plan will formulate a more detailed monitoring frequency and processing process according to the adjusted resource allocation.

[0062] In specific implementation, the environmental data processing solution includes optimizing the monitoring point locations, adjusting the sampling frequency, etc. For example, in the original solution, there were four harmful gas monitoring points and the sampling frequency was once per hour. After adjustment, the number of monitoring points increased to six, and the sampling frequency was increased to once every thirty minutes. At the same time, dedicated personnel were arranged for data analysis and equipment maintenance to ensure the processing effect. Such adjustments can improve the accuracy of environmental data collection and the timeliness of processing. During the resource scheduling process, the system dynamically adjusts resource allocation according to the changing trends of environmental data. If a certain environmental indicator shows a sharp deterioration trend, the system will immediately increase its priority and allocate resources from other non-urgent projects. This dynamic adjustment mechanism can ensure that environmental risks are promptly controlled while ensuring resource utilization efficiency. Through scientific resource allocation and dynamic adjustment, it is possible to ensure the handling of key environmental issues and achieve the optimal utilization of resources.

[0063] S108. The data processing center integrates the abnormal data report and the environmental change trend report to generate an urban environmental status assessment report and sends it to the control center for decision-making reference.

[0064] Feasible. In the analysis of abnormal environmental data, outliers usually include key indicators such as air quality index, water quality parameters, and noise levels. The change trend can be reflected by time-series data. For example, the sulfur dioxide concentration at a monitoring point has shown a fluctuating upward trend in the past three months and is predicted to reach 0.4 milligrams per cubic meter within the next week. When conducting correlation analysis, multiple dimensions need to be considered, such as the relationship between air quality in a certain area and surrounding industrial activities and meteorological conditions. When the predicted value shows that the future air quality index may exceed 200, a threshold alarm mechanism will be triggered. In terms of resource scheduling, the processing of high-priority data such as toxic gas concentration requires preferential allocation of computing resources, and the priority can be reflected by a weight coefficient. For example, a weight of 0.8 is assigned to the monitoring data of toxic gases. Cluster analysis can discover the distribution pattern of abnormal data. For example, air pollution events are grouped according to characteristics such as pollutant type, pollution degree, and duration. The long-term prediction model predicts future environmental changes by analyzing the periodicity and trend of historical data. The assessment of the environmental situation needs to integrate multi-dimensional information, including pollutant concentration, meteorological conditions, population distribution, etc. The assessment report should present key findings, such as a significant correlation between air quality and population density in a certain area, or an obvious upward trend in the concentration of a certain type of pollutant. The assessment results can provide a decision-making basis for urban management departments. For example, it is recommended to add monitoring points in areas where air quality frequently exceeds the standard, or adjust the production hours of industrial enterprises. By establishing an early warning mechanism, when the prediction model shows that environmental indicators may exceed the standard, early warning information is sent to relevant departments in a timely manner. For example, if the prediction shows that there may be heavy pollution weather in the next three days, industrial enterprises need to be notified in advance to take emission reduction measures. The assessment report should also include countermeasures and suggestions. For example, according to the pollutant dispersion model, it is recommended that surrounding residents take protective measures. Such an early warning and suggestion mechanism can effectively reduce environmental risks and improve the scientificity and accuracy of urban environmental management.

[0065] Embodiment 2

[0066] This embodiment also provides a computer device, including a memory, a processor, and a computer program stored on the memory. The processor executes the computer program to implement the steps of the method.

[0067] Embodiment 3

[0068] This embodiment also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method are implemented.

[0069] Embodiment 4

[0070] This embodiment also provides a computer program product, including a computer program. When the computer program is executed by a processor, the steps of the method are implemented.

[0071] The above are only the preferred specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An urban environmental monitoring method based on satellite Internet of Things, characterized in that, It includes the following steps: Collect environmental data of each area in the city using a sensor network and integrate it into urban environmental data; After preprocessing, data compression processing, and decompression processing of the urban environmental data, transmit it to the data processing center; At the data processing center, perform anomaly detection on the received data and generate an anomaly data report; For the anomaly data report, combine the preset environmental thresholds and use the regression analysis algorithm to predict the environmental trend and generate an environmental change trend report; Integrate the anomaly data report and the environmental change trend report to generate an urban environmental status assessment report; Based on the urban environmental status assessment report, use the resource scheduling algorithm to adjust the resource allocation for environmental data and generate an environmental data processing plan.

2. The method according to claim 1, wherein: The process of preprocessing the urban environmental data includes: Send the urban environmental data to the satellite Internet of Things platform. At the satellite Internet of Things platform, perform data cleaning and format conversion processing on the urban environmental data, remove invalid data and noise interference, and obtain standardized data.

3. The method according to claim 2, wherein: The process of performing data compression processing on the standardized data includes: Transmit the standardized data to the ground gateway station through the satellite link, monitor the channel status in real time, and determine whether there is a congestion phenomenon; if the channel is congested, use the preset data compression algorithm to compress the standardized data and re-transmit the compressed data to the ground gateway station.

4. The method according to claim 3, wherein: The process of performing decompression processing on the compressed data includes: Use the preset decompression algorithm to decompress the received compressed data, compare and verify the decompressed original data with the preset data format. If the data formats are consistent, mark the original data as available, package and encapsulate the available original data according to the preset forwarding rules, and send the encapsulated data to the data processing center through the preset transmission protocol.

5. The method according to claim 1, wherein: At the data processing center, the process of performing anomaly detection on the received data and generating an anomaly data report includes: Use the time series algorithm to preprocess the received data and extract time series features; identify outliers in the time series features through the anomaly detection algorithm; if anomaly data is detected, classify the anomaly data according to the anomaly type classification rules; for the classified anomaly data, extract the corresponding time node information; associate the anomaly type with the time node information to form an anomaly data record, and generate an anomaly data report based on the anomaly data record.

6. The method according to claim 1, wherein: For the anomaly data report, the process of combining the preset environmental thresholds and using the regression analysis algorithm to predict the environmental trend and generate an environmental change trend report includes: Obtain an abnormal data report, and extract the abnormal values and the corresponding time points therein; according to the preset environmental threshold, determine whether the abnormal values exceed the threshold line; for the abnormal values that exceed the threshold line, use the regression method to analyze the change trend of the parameter values and generate a trend line; combine the trend line to predict the predicted values of the parameter values within the future time period; associate the predicted values with the abnormal value classification values to generate an environmental change trend report.

7. The method according to claim 1, wherein Based on the urban environmental status assessment report, the process of adjusting the resource allocation for environmental data by using the resource scheduling algorithm and generating an environmental data processing plan includes: Obtain the environmental data in the environmental change trend report, and extract the corresponding priority values and resource amounts; sort the resource amounts according to the priority values to determine the resource allocation order; if the resource amount is lower than the preset threshold, use the scheduling method to preferentially allocate resources to process the environmental data with high priority; generate an environmental data processing plan through the adjusted resource allocation result.

8. A computer device, comprising a memory, a processor, and a computer program stored on the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1-7.

Images