Real-time monitoring method of ecological environment data based on big data processing

Abstract

The present invention relates to the field of data processing technology, and specifically to a real-time monitoring method for ecological environment data based on big data processing. Determine the abnormal index and abnormal curve segment of the index data of the sensor at the current location in different time periods; determine the correlation between the index data of the sensor at the current monitoring location in this time period and the index data of other sensors in the corresponding time period of this time period; determine the atmospheric pollution index at the current monitoring location at this moment; dynamically control the atmospheric pollution index through multiple types of single sensors at a certain monitoring location at a certain moment and sensors adjacent to them and the direction of pollution diffusion; output warning information. This method can analyze the contribution of the index data of multiple sensors at different monitoring locations in the area to be tested to the atmospheric pollution situation, and dynamically adjust the atmospheric pollution index at a certain monitoring location in combination with the direction of pollution diffusion, reduce the impact of environmental factors on sensor detection, and improve the accuracy of atmospheric pollution situation judgment.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a real-time monitoring method for ecological environment data based on big data processing. Background Art

[0002] The monitoring methods of ecological environment data in related technologies often use a variety of sensors to build an air pollution monitoring system, monitor air indicators through the air pollution monitoring system, and input the obtained multiple indicator data into a fixed data model, integrate the multi-dimensional data, and output the air pollution situation, set an air pollution level threshold, and output an alarm message when the obtained air pollution level exceeds the threshold.

[0003] However, since most of the air pollution monitoring sensors are set in outdoor environments and the sensor detection range is limited, there may be errors in the data collected by the sensor at a certain location under the influence of the environment. At this time, using the above fixed data model to judge the air pollution situation at the current location is prone to errors. For example, an increase in wind speed may cause errors in the detection values ​​of the temperature sensor and the humidity sensor at a certain location. Therefore, it is urgent to develop a real-time monitoring method for ecological environment data based on big data processing to solve the above problems. Summary of the invention

[0004] In order to solve the technical problem that the sensor monitoring error caused by environmental impact leads to inaccurate judgment of air pollution, the purpose of the present invention is to provide a real-time monitoring method of ecological environment data based on big data processing. The technical solution adopted is as follows:

[0005] The present invention provides a method for real-time monitoring of ecological environment data based on big data processing, the method comprising:

[0006] Step 101, obtaining environmental monitoring data of multiple sensors at multiple monitoring positions in a test area, establishing a plane rectangular coordinate system for the environmental monitoring data, and drawing an environmental monitoring data curve, wherein the environmental monitoring data includes time data and index data corresponding to the time data, and the horizontal axis of the plane rectangular coordinate system represents time, and the vertical axis represents the index;

[0007] Step 102, for a certain sensor, in response to the abnormal index of the indicator data of the sensor in a certain period of time at the current position being greater than the abnormal threshold, determining that the curve segment corresponding to the period of time is an abnormal curve segment;

[0008] Step 103, determining the correlation between the index data of the sensor of the current monitoring position in the time period and the index data of other sensors in the corresponding time period of the time period;

[0009] Step 104, determining the air pollution index of the current monitoring location at the moment according to the index data of the multiple sensors at the current monitoring location at a certain moment and the correlation between the index data of the multiple sensors at the current monitoring location;

[0010] Step 105, determining the original pollution diffusion direction and the pollution diffusion index corresponding to the original pollution diffusion direction according to the air pollution indexes of multiple monitoring locations in the test area at a certain moment, taking the original pollution diffusion direction corresponding to the maximum pollution diffusion index as the target pollution diffusion direction, and adjusting the air pollution index based on the target pollution diffusion direction to obtain an adjusted air pollution index;

[0011] Step 106, in response to the adjusted air pollution index being greater than the warning threshold, outputting warning information, the warning information including the adjusted air pollution index greater than the warning threshold and the monitoring location corresponding to the adjusted air pollution index greater than the warning threshold.

[0012] In some embodiments, step 102 includes:

[0013] The environmental monitoring data curve of each sensor among the multiple sensors is divided into a plurality of curve segments by using an APCA algorithm, wherein the curve segments include index data of different time periods;

[0014] For a certain sensor, the abnormal index of the indicator data of the sensor at the current monitoring location in different time periods is determined based on the difference in the indicator data of the sensor at the current monitoring location in different time periods, and the difference between the environmental monitoring data of the sensor at the current monitoring location and the sensors at other monitoring locations in similar time periods;

[0015] In response to the abnormal index of the indicator data of the sensor at the current position in a certain period of time being greater than the abnormal threshold, it is determined that the curve segment corresponding to the period of time is an abnormal curve segment.

[0016] In some embodiments, the abnormal index of the indicator data of the sensor at the current location in different time periods is determined according to the following formula:

[0017]

[0018] In the formula, Indicates the current monitoring position of a certain sensor in the j The abnormal index within a period of time, Indicates the type of sensor at the current monitoring location. j The average value of the indicator data within a period of time, Indicates the mean value of all indicator data in the environmental monitoring curve of this sensor at the current monitoring location, Indicates the type of sensor at the current monitoring location. jThe variance of the indicator data within a period, The multiple curve segments of the environmental monitoring curves of the sensor at all monitoring locations are the same as the first curve segment of the sensor at the current monitoring location. j The average of the duration of the corresponding time period of each time period, the multiple curve segments of the environmental monitoring curves of the sensor of the type at all monitoring locations corresponding to the first curve segment of the environmental monitoring curve of the sensor at the current monitoring location j The time period corresponds to the central time data of multiple curve segments of the environmental monitoring curve of this type of sensor at all monitoring locations and the j The time period corresponding to the curve segment closest to the central time data of each time period, Indicates the type of sensor at the current monitoring location. j The duration of a period, Indicates the type of sensor at the current monitoring location. j The maximum value of the indicator data in the period, Indicates the number of sensors of this type at other monitoring locations except the current monitoring location. j The average value of the indicator data in the corresponding period. j Indicates the sequence number of the time period.

[0019] In some embodiments, the corresponding time period of the other sensors in the time period is the time period corresponding to the curve segment whose central time data of multiple curve segments of the environment monitoring curve of the other sensors is closest to the central time data of the time period, and step 105 includes:

[0020] Determine the similarity between the index data of a certain sensor at the current monitoring position in a certain period of time and the index data of other sensors at the current monitoring position except the sensor in a corresponding period of time of the period of time according to the abnormal index of the index data of a certain sensor at the current monitoring position in a certain period of time and the index data of other sensors at the current monitoring position except the sensor in a corresponding period of time of the period of time;

[0021] Based on the similarity of all curve segments in the environmental monitoring curve of the sensor at the current monitoring location and the corresponding time periods in the environmental monitoring curves of other sensors at the current monitoring location except the sensor, the number of curve segments determined as abnormal curve segments in the environmental monitoring data curve of the sensor at the current monitoring location, and the average number of curve segments determined as abnormal curve segments in the environmental monitoring data curves of other sensors at the current monitoring location, the correlation between the index data of the sensor at the current monitoring location and the index data of other sensors is determined.

[0022] In some embodiments, the similarity between the index data of the sensor of the current monitoring position in the time period and the index data of other sensors of the current monitoring position except the sensor of the current monitoring position in the corresponding time period of the time period is determined according to the following formula:

[0023]

[0024] In the formula, Indicates the current monitoring position of a certain sensor in the j The indicator data in the time period is compared with other sensors in the current monitoring location in j The similarity index of the indicator data in the corresponding period, Indicates the number of other sensor types at the current monitoring location except this sensor. Indicates the type of sensor at the current monitoring location. j The abnormal index within a period of time, Indicates the current monitoring location. z The sensor is j The abnormal index of each period corresponds to the period. z Indicates the type and serial number of other sensors at the current monitoring location except this sensor.

[0025] In some embodiments, the correlation between the indicator data of the sensor at the current monitoring location and the indicator data of other sensors is determined according to the following formula:

[0026]

[0027] In the formula, Indicates the correlation index between the indicator data of a certain sensor at the current monitoring location and the indicator data of other sensors. It represents the average of the similarity indexes of all curve segments in the environmental monitoring curve of the sensor at the current monitoring location and the corresponding time periods in the environmental monitoring curves of other sensors at the current monitoring location. Indicates the minimum value of the similarity index between all curve segments in the environmental monitoring curve of the sensor at the current monitoring location and the corresponding time periods in the environmental monitoring curves of other sensors at the current monitoring location, represents the number of curve segments determined as abnormal curve segments in the environmental monitoring data curve of the sensor at the current monitoring location, represents the average value of the number of curve segments determined as abnormal curve segments in the environmental monitoring data curves of other sensors at the current monitoring location, i Indicates the type and serial number of the sensor currently monitoring the location.

[0028] In some embodiments, the air pollution index at the current monitoring location at that moment is determined according to the following formula:

[0029]

[0030] In the formula, Indicates kThe air pollution index of a monitoring location at a certain time, Indicates k The monitoring location at this moment h The indicator data of each sensor, Indicates k The number of sensors at each monitoring location, Indicates k The monitoring location h The correlation index of each sensor, Indicates k The mean value of the correlation index of all sensors at a monitoring location, h Indicates k The number of sensors at each monitoring location.

[0031] In some embodiments, step 105 includes:

[0032] The monitoring position corresponding to the maximum value of the air pollution index of multiple monitoring positions in the measured area at a certain moment is taken as the air pollution center, the air pollution center is taken as the starting point, and the direction in which the air pollution index of multiple monitoring positions in the measured area at a certain moment gradually decreases is taken as the original pollution diffusion direction, and the monitoring position corresponding to the maximum value of the air pollution index of multiple monitoring positions in the measured area at a certain moment and the monitoring position in the direction in which the air pollution index of multiple monitoring positions in the measured area at a certain moment gradually decreases are all valid monitoring points;

[0033] Determine the pollution diffusion index corresponding to the original pollution diffusion direction;

[0034] The original pollution diffusion direction corresponding to the maximum value of the pollution diffusion index is taken as the target pollution diffusion direction;

[0035] Adjust the air pollution index based on the target pollution diffusion direction.

[0036] In some embodiments, the pollution diffusion index corresponding to the original pollution diffusion direction is determined according to the following formula:

[0037]

[0038] In the formula, is the pollution diffusion index corresponding to the current original pollution diffusion direction, Indicates the number of effective monitoring points in the current original pollution diffusion direction, Represents the number of all monitoring locations adjacent to the current original pollution diffusion direction, q represents the air pollution index corresponding to the air pollution center, It indicates the air pollution index of the last valid monitoring point in the current original pollution diffusion direction.

[0039] In some embodiments, the air pollution index is adjusted based on the target pollution diffusion direction according to the following formula:

[0040]

[0041] In the formula, Indicates a moment l The atmospheric pollution index after the monitoring position corresponding to the sensor with abnormal curve segment is adjusted. Indicates the moment l The air pollution index at the monitoring location corresponding to the sensor with abnormal curve segment, Indicates the moment l The average value of the air pollution index corresponding to all the locations adjacent to the monitoring location corresponding to the sensor with an abnormal curve segment, Indicates the target pollution diffusion direction of the area to be tested, Indicates the direction from the center of atmospheric pollution to the l The direction of the monitoring position corresponding to the sensor with abnormal curve segment, express and The angle of express The cosine value of l Indicates the number of sensors with abnormal curve segments at a certain moment.

[0042] The present invention has the following beneficial effects:

[0043] The real-time monitoring method of ecological environment data based on big data processing provided by the present invention first obtains environmental monitoring data of multiple sensors at multiple monitoring positions in the area to be tested, establishes a plane rectangular coordinate system for the environmental monitoring data, and draws an environmental monitoring data curve, wherein the environmental monitoring data includes time data and index data corresponding to the time data; then, for a certain sensor, in response to the abnormal index of the index data of the sensor in a certain period of time at the current position being greater than the abnormal threshold, determines that the curve segment corresponding to the period of time is an abnormal curve segment, and grasps the abnormal situation; determines the correlation between the index data of the sensor in the current monitoring position in the period of time and the index data of other sensors in the corresponding period of time in the period of time, and grasps the contribution of the index data of the sensor in the period of time to the judgment of the atmospheric pollution situation; determines the atmospheric pollution situation at the current monitoring position at that moment according to the index data of multiple sensors at the current monitoring position at a certain moment and the correlation between the index data of multiple sensors at the current monitoring position. The pollution index is calculated by comprehensively considering the index data of multiple sensors at the current monitoring position to improve the comprehensiveness of the judgment of the atmospheric pollution situation; further, according to the atmospheric pollution index of multiple monitoring positions in the measured area at a certain moment, the original pollution diffusion direction and the pollution diffusion index corresponding to the original pollution diffusion direction are determined, and the original pollution diffusion direction corresponding to the maximum pollution diffusion index is used as the target pollution diffusion direction, and the atmospheric pollution index is adjusted based on the target pollution diffusion direction to obtain the adjusted atmospheric pollution index, and the atmospheric pollution index is dynamically regulated by multiple types of single sensors at a certain monitoring position at a certain moment and sensors adjacent to it and the pollution diffusion direction, thereby further improving the accuracy of the atmospheric pollution situation judgment; finally, in response to the adjusted atmospheric pollution index being greater than the warning threshold, the warning information is output, and the warning information includes the adjusted atmospheric pollution index greater than the warning threshold and the monitoring position corresponding to the adjusted atmospheric pollution index greater than the warning threshold, so as to facilitate the staff to take prevention and control measures in time. This method can analyze the contribution of the index data of multiple sensors at different monitoring positions in the measured area to the atmospheric pollution situation, and dynamically adjust the atmospheric pollution index of a certain monitoring position in combination with the pollution diffusion direction, thereby reducing the influence of environmental factors on sensor detection and improving the accuracy of atmospheric pollution situation judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or 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. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1A method flow chart of a method for real-time monitoring of ecological environment data based on big data processing provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. 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.

[0047] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0048] The following is a detailed description of the specific scheme of the real-time monitoring method of ecological environment data based on big data processing provided by the present invention in conjunction with the accompanying drawings. Figure 1 , the method comprising:

[0049] Step 101, obtain environmental monitoring data of multiple sensors at multiple monitoring locations in the area to be tested, establish a plane rectangular coordinate system for the environmental monitoring data, and draw an environmental monitoring data curve. The environmental monitoring data includes time data and indicator data corresponding to the time data. The horizontal axis of the plane rectangular coordinate system represents time, and the vertical axis represents the indicator.

[0050] The environmental monitoring data of multiple sensors at multiple monitoring locations in the area to be tested is the basis for subsequent judgment of air pollution. The indicators that change over time can be obtained through sensors. In order to determine the abnormal detection data of the sensors in the future, the environmental monitoring data establishes a plane rectangular coordinate system and draws the environmental monitoring data curve. The sensors include PM2.5 concentration detectors, nitrogen dioxide concentration detectors, air pressure detectors, temperature sensors, humidity sensors and wind speed sensors. The indicator data include PM2.5 concentration, nitrogen dioxide concentration, air pressure, temperature, humidity and wind speed.

[0051] In some implementations, the unit of time data in the environmental monitoring data is min; the PM2.5 concentration detector detects the PM2.5 concentration, and the vertical axis is the PM2.5 concentration (Pm), and the unit is ; The nitrogen dioxide concentration detection instrument detects the nitrogen dioxide concentration, and the vertical axis is the nitrogen dioxide concentration ( ), the unit is ; The air pressure detector detects the air pressure, the vertical axis is the air pressure (Pm), the unit is P ( ); The temperature sensor detects the temperature, the vertical axis is temperature (C), the unit is ; The humidity sensor detects humidity, and the vertical axis is humidity (R) ( ), the unit is ; The wind speed sensor detects the wind speed, the vertical axis is the wind speed (V), the unit is .

[0052] Due to factors such as unstable power supply of the sensor itself or changeable outdoor environment, the detection data of a certain sensor may differ from the actual state of the current location. For example, due to factors such as building obstruction, the wind speed at a certain location is faster, so that the air contacted by the chip on the temperature sensor is not in a stable state, causing the measured temperature in a certain period of time to be biased or unstable. Therefore, it is necessary to determine whether the sensor has an abnormal curve segment with abnormal detection data.

[0053] Step 102: for a certain sensor, in response to the abnormal index of the indicator data of the sensor in a certain period of time at the current position being greater than the abnormal threshold, determine that the curve segment corresponding to the period of time is an abnormal curve segment.

[0054] Step 1021 , dividing the environmental monitoring data curve of each sensor among the multiple sensors into a plurality of curve segments by using an APCA algorithm, wherein the curve segments include index data of different time periods.

[0055] Dividing the environmental monitoring data curve into multiple curve segments facilitates the subsequent determination of abnormal curve segments.

[0056] Step 1022, for a certain sensor, determine the abnormal index of the indicator data of the sensor at the current monitoring location in different time periods based on the difference in indicator data of the sensor at the current monitoring location in different time periods, and the difference between the environmental monitoring data of the sensor at the current monitoring location and the sensors at other monitoring locations in similar time periods.

[0057] The difference in index data of the sensor at the current monitoring location in different time periods and the difference between the environmental monitoring data of the sensor at the current monitoring location and the sensors at other monitoring locations in similar time periods may contain information such as abnormal detection data. The abnormal index of the index data of the sensor at the current location in different time periods determined thereby can reflect the possibility of the existence of abnormal detection data for the sensor at the current location.

[0058] In some embodiments, step 1022 is implemented by determining the abnormal index of the indicator data of the sensor at the current location in different time periods according to the following formula:

[0059]

[0060] In the formula, Indicates the current monitoring position of a certain sensor in the jThe abnormal index in a period of time can reflect the abnormality of the sensor at the current location in the j The possibility of abnormal curve segments in a period of time, Indicates the type of sensor at the current monitoring location. j The average value of the indicator data in a period of time reflects the current monitoring location of this sensor in the j The average of the indicator data within a period of time, It indicates the mean value of all indicator data in the environmental monitoring curve of the sensor at the current monitoring location. It can reflect the average of all indicator data in the environmental monitoring curve of the sensor at the current monitoring location and its value is not 0. Indicates the type of sensor at the current monitoring location. j The variance of the indicator data within a period reflects the variance of the sensor at the current monitoring location in the j The difference of indicator data within a period of time, The multiple curve segments of the environmental monitoring curves of the sensor at all monitoring locations are the same as the first curve segment of the sensor at the current monitoring location. j The average time length of the corresponding time period reflects the multiple curve segments of this sensor at all monitoring locations and the j The average duration of the corresponding time period of each time period, the multiple curve segments of the environmental monitoring curves of the sensor of all monitoring locations are the same as the first curve segment of the sensor of the current monitoring location. j The time period corresponds to the central time data of multiple curve segments of the environmental monitoring curve of this type of sensor at all monitoring locations and the j The time period corresponding to the curve segment with the closest central time data of each time period can make the index data detected by the sensors at different monitoring locations be at similar times, that is, in similar atmospheric environments, which are comparable, making the determination result of the abnormal index more accurate. Indicates the type of sensor at the current monitoring location. j The duration of a period and the value is not zero, Indicates the type of sensor at the current monitoring location. j The maximum value of the indicator data in the period, Indicates the number of sensors of this type at other monitoring locations except the current monitoring location. j The average value of the indicator data in the corresponding period. j Indicates the sequence number of the time period.

[0061] Indicates the type of sensor at the current monitoring location. jThe greater the degree of abnormality of the indicator data in a time period relative to the environmental monitoring curve of the sensor, the greater the deviation from the overall indicator data, the more uneven the indicator data changes in the time period, and the greater the possibility that the curve segment corresponding to the time period is abnormal. Indicates the sensor of the current monitoring location. j The difference between the index data of the time period and the index data of the corresponding section in the environmental monitoring curve of the sensor at other monitoring locations is the difference between the index data of the sensor at the current monitoring location and the corresponding section in the environmental monitoring curve of the sensor at other monitoring locations. j The maximum value of the indicator data in the period The more deviation from the mean , the sensor at the current monitoring location is j Duration within a period The shorter the time, the greater the difference in the indicator data change. The greater the difference between the sensor at the current monitoring location and the sensor at other monitoring locations, the greater the difference between the sensor at the current location and the sensor at other monitoring locations. j The greater the possibility that an abnormal curve segment may exist in a time period.

[0062] In some embodiments, a certain sensor at the current monitoring location may be placed in the j Abnormal index in a period Normalize to (0,1).

[0063] Step 1023: In response to the abnormal index of the indicator data of the sensor at the current position in a certain period of time being greater than the abnormal threshold, determine that the curve segment corresponding to the period of time is an abnormal curve segment.

[0064] The anomaly index is greater than the anomaly threshold, which means that the anomaly detection data in this period will have a great impact on the subsequent judgment of the air pollution situation and needs to be taken seriously. Therefore, the curve segment corresponding to this period is determined to be an abnormal curve segment.

[0065] In some embodiments, the abnormal threshold may be 0.5. If the abnormal index of a certain time period is greater than 0.5, the curve segment corresponding to the time period is an abnormal curve segment.

[0066] Air quality is reflected by multiple indicators. Each indicator has a different degree of influence on the current air quality and there is a certain correlation between multiple indicators, which jointly affect the current air pollution level. For example, when the wind speed is high, the air flow is accelerated, and particulate matter is not easy to accumulate in the air, which speeds up the "dilution" speed of pollutants, thereby reducing the PM2.5 value in the air; high wind speed will also reduce the water vapor content in the air, thereby reducing the relative humidity, and the reduced humidity is not conducive to the accumulation of particulate matter and the secondary reaction of pollutants, thereby affecting the degree of air pollution. Therefore, the correlation between multiple sensors, that is, multiple indicator data, and finding the indicator data with a greater degree of correlation with the rest of the indicator data, the greater the contribution of this indicator data to the subsequent judgment of air pollution, the more attention it needs to pay.

[0067] Step 103 : determining the correlation between the index data of the sensor at the current monitoring position in the time period and the index data of other sensors in corresponding time periods of the time period.

[0068] The correlation between the index data of the sensor at the current monitoring position in the time period and the index data of other sensors in the corresponding time periods in the time period can reflect the contribution of the index data of the sensor in the time period to the judgment of the air pollution situation.

[0069] In some embodiments, the corresponding time period of the other sensors in step 103 is the time period corresponding to the curve segment whose central time data of multiple curve segments of the environment monitoring curve of the other sensors is closest to the central time data of the time period.

[0070] In some embodiments, step 103 includes the following steps:

[0071] Step 1031, based on the abnormal index of the index data of a certain sensor at the current monitoring location in a certain time period and the index data of other sensors at the current monitoring location except the sensor in the corresponding time period of the time period, determine the similarity between the index data of the certain sensor at the current monitoring location in the time period and the index data of other sensors at the current monitoring location except the sensor in the corresponding time period of the time period.

[0072] The similarity between the index data of the sensor of the current monitoring position in the time period and the index data of other sensors of the current monitoring position except the sensor of the current monitoring position in the corresponding time period of the time period can reflect the similarity degree of index data anomalies between different types of sensors.

[0073] In some embodiments, step 1031 is implemented by determining the similarity between the index data of the sensor of the current monitoring position in the time period and the index data of other sensors of the current monitoring position except the sensor of the current monitoring position in the corresponding time period of the time period according to the following formula:

[0074]

[0075] In the formula, Indicates the current monitoring position of a certain sensor in the j The indicator data in the time period is compared with other sensors in the current monitoring location in j The similarity index of the indicator data in the corresponding time period reflects the current monitoring location in the j The similarity of abnormal indicator data between different types of sensors in a period of time, Indicates the number of other sensor types at the current monitoring location except this sensor. Indicates the type of sensor at the current monitoring location. j The abnormal index within a period of time, Indicates the current monitoring location. z The sensor is j The abnormal index of each period corresponds to the period. z Indicates the type and serial number of other sensors at the current monitoring location except this sensor. Indicated in j The difference between the abnormal index data of this sensor and other sensors except this sensor at the current monitoring location within a period of time. The value is not zero. The smaller the value, the closer the difference is. The larger it is, the higher the similarity is.

[0076] Step 1032, based on the similarity of all curve segments in the environmental monitoring curve of the sensor at the current monitoring location and the corresponding time periods in the environmental monitoring curves of other sensors at the current monitoring location except the sensor, the number of curve segments determined as abnormal curve segments in the environmental monitoring data curve of the sensor at the current monitoring location, and the average number of curve segments determined as abnormal curve segments in the environmental monitoring data curves of other sensors at the current monitoring location, determine the correlation between the index data of the sensor at the current monitoring location and the index data of other sensors at the current monitoring location.

[0077] The correlation between the index data of the sensor at the current monitoring location and the index data of other sensors is obtained, so as to understand the contribution of the index data of the sensor in the period to the judgment of the air pollution situation.

[0078] In some embodiments, step 1032 is implemented by determining the correlation between the indicator data of the sensor at the current monitoring location and the indicator data of other sensors according to the following formula:

[0079]

[0080] In the formula, The correlation index between the index data of a certain sensor at the current monitoring location and the index data of other sensors can reflect the contribution of the index data of this sensor in this period to the judgment of the air pollution situation. The average value of the similarity index of all curve segments in the environmental monitoring curve of the sensor at the current monitoring location and the corresponding time periods in the environmental monitoring curves of other sensors at the current monitoring location can reflect the overall situation of the similarity index of all curve segments in the environmental monitoring curve of the sensor at the current monitoring location and the corresponding time periods in the environmental monitoring curves of other sensors at the current monitoring location. The minimum value of the similarity index between all curve segments in the environmental monitoring curve of the sensor at the current monitoring location and the corresponding time periods in the environmental monitoring curves of other sensors at the current monitoring location can reflect the lower limit of the similarity index between all curve segments in the environmental monitoring curve of the sensor at the current monitoring location and the corresponding time periods in the environmental monitoring curves of other sensors at the current monitoring location. represents the number of curve segments determined as abnormal curve segments in the environmental monitoring data curve of the sensor at the current monitoring location, The larger the correlation index The smaller, represents the average value of the number of curve segments determined as abnormal curve segments in the environmental monitoring data curves of other sensors at the current monitoring location, and the value is not zero, The larger the correlation index The bigger, i Indicates the type and serial number of the sensor currently monitoring the location.

[0081] Indicates the similarity between the number of curve segments determined as abnormal curve segments in the environmental monitoring data curve of the sensor at the current monitoring location and the number of curve segments determined as abnormal curve segments in the environmental monitoring data curves of other sensors at the current monitoring location. The larger the value, the higher the similarity. The bigger, The difference between the average of the similarity indexes of all curve segments in the environmental monitoring curve of the sensor at the current monitoring location and the corresponding time periods in the environmental monitoring curves of other sensors at the current monitoring location and the minimum value of the similarity indexes of all curve segments in the environmental monitoring curve of the sensor at the current monitoring location and the corresponding time periods in the environmental monitoring curves of other sensors at the current monitoring location, and the value is not zero. The smaller the difference, the higher the correlation index. The bigger. The bigger, The smaller, The larger the correlation index is, the The bigger.

[0082] The air pollution situation is reflected by the index data of multiple sensors. Therefore, it is necessary to fuse the index data of multiple sensors at the current monitoring location at a certain moment based on the index data of multiple sensors at the current monitoring location at that moment and the correlation between the index data of multiple sensors at the current monitoring location, so as to determine the air pollution index at the current monitoring location at that moment.

[0083] Step 104, determining the air pollution index of the current monitoring location at a certain moment according to the index data of the various sensors at the current monitoring location at a certain moment and the correlation between the index data of the various sensors at the current monitoring location.

[0084] The air pollution index at the current monitoring location at this moment can comprehensively consider the indicator data of various sensors at the current monitoring location to improve the comprehensiveness of the judgment of the air pollution situation.

[0085] In some embodiments, the air pollution index at the current monitoring location at that moment is determined according to the following formula to implement step 104:

[0086]

[0087] In the formula, Indicates k The air pollution index at a monitoring location at a certain time preliminarily reflects the k The air pollution situation at a monitoring location at a certain time, Indicates k The monitoring location at this moment h The indicator data of each sensor, Indicates k The number of sensors at each monitoring location, Indicates k The monitoring location h The correlation index of the sensor reflects the k The monitoring location h The contribution of each sensor to the judgment of air pollution conditions, Indicates k The average of the correlation indexes of all sensors at the monitoring location is not zero, reflecting the k The overall contribution of all sensors at each monitoring location to the judgment of air pollution conditions. h Indicates k The number of sensors at each monitoring location. Indicates k The monitoring location h The correlation index of the first sensor is k The difference in the mean of the correlation index of all sensors at the monitoring location, The bigger, The bigger, The smaller the air pollution index is, the The bigger.

[0088] From the above analysis, it can be seen that the atmospheric pollution situation at a certain monitoring location at a certain moment obtained only through the index data of multiple types of single sensors at a certain monitoring location at a certain moment is deviated from the actual pollution situation. In addition, due to the influence of environmental factors and gas flow, atmospheric pollution has a certain tendency to diffuse to the surroundings, that is, the atmospheric pollution concentration gradually decreases from the location with a higher pollution level along the pollution diffusion direction. Therefore, in order to adjust the detection results of the location and improve the accuracy of the atmospheric pollution situation judgment, step 105 is introduced to adjust the atmospheric pollution index through multiple types of single sensors at a certain monitoring location at a certain moment and sensors adjacent to them and the pollution diffusion direction.

[0089] Step 105, based on the atmospheric pollution index of multiple monitoring locations in the measured area at a certain moment, determine the original pollution diffusion direction and the pollution diffusion index corresponding to the original pollution diffusion direction, take the original pollution diffusion direction corresponding to the maximum pollution diffusion index as the target pollution diffusion direction, and adjust the atmospheric pollution index based on the target pollution diffusion direction to obtain an adjusted atmospheric pollution index.

[0090] On the basis of obtaining the atmospheric pollution index, we further consider the impact of pollution diffusion on the atmospheric pollution index, find the source and direction of pollution diffusion, and dynamically adjust the atmospheric pollution index through multiple types of single sensors at a certain monitoring location at a certain moment and the sensors adjacent to them as well as the pollution diffusion direction, so as to further improve the accuracy of atmospheric pollution situation judgment.

[0091] In some embodiments, step 105 includes:

[0092] Step 1051, take the monitoring position corresponding to the maximum value of the air pollution index of multiple monitoring positions in the measured area at a certain moment as the air pollution center, take the air pollution center as the starting point, and take the direction in which the air pollution index of multiple monitoring positions in the measured area at a certain moment gradually decreases as the original pollution diffusion direction, the monitoring position corresponding to the maximum value of the air pollution index of multiple monitoring positions in the measured area at a certain moment and the monitoring positions in the direction in which the air pollution index of multiple monitoring positions in the measured area at a certain moment gradually decreases are all valid monitoring points.

[0093] The air pollution center is the source of pollution diffusion. The original pollution diffusion direction is the possible direction of pollution diffusion obtained initially. This direction satisfies the gradual decrease of the air pollution index at a certain moment. Multiple monitoring locations that meet the above conditions are effective monitoring points.

[0094] Step 1052, determining the pollution diffusion index corresponding to the original pollution diffusion direction.

[0095] The air pollution index is adjusted by using multiple types of single sensors and adjacent sensors at a certain monitoring location at a certain moment.

[0096] In some embodiments, the pollution diffusion index corresponding to the original pollution diffusion direction is determined according to the following formula:

[0097]

[0098] In the formula, is the pollution diffusion index corresponding to the current original pollution diffusion direction, Indicates the number of effective monitoring points in the current original pollution diffusion direction, It indicates the number of all monitoring locations adjacent to the current original pollution diffusion direction and its value is not 0. q Indicates the air pollution index corresponding to the air pollution center, It indicates the air pollution index of the last valid monitoring point in the current original pollution diffusion direction.

[0099] Step 1053: The original pollution diffusion direction corresponding to the maximum value of the pollution diffusion index is used as the target pollution diffusion direction.

[0100] By analyzing the pollution diffusion index at the monitoring location, the true direction of pollution diffusion, that is, the target pollution diffusion direction, can be found.

[0101] Step 1054, adjusting the air pollution index based on the target pollution diffusion direction.

[0102] The air pollution index is adjusted by the target pollution diffusion direction, thereby realizing dynamic regulation of the air pollution index, so that the adjusted air pollution index can more accurately reflect the air pollution situation.

[0103] In some embodiments, the air pollution index is adjusted based on the target pollution diffusion direction according to the following formula:

[0104]

[0105] In the formula, Indicates a moment l The adjusted air pollution index at the monitoring location corresponding to the sensor with abnormal curve segments reflects the adjusted air pollution situation. Indicates the moment l The air pollution index at the monitoring location corresponding to the sensor with an abnormal curve segment reflects the air pollution situation before adjustment. Indicates the moment lThe average value of the air pollution index corresponding to all the positions adjacent to the monitoring position corresponding to the sensor with an abnormal curve segment reflects the average value of the air pollution index at that moment. l The overall situation of air pollution corresponding to all the locations adjacent to the monitoring location corresponding to the sensor with abnormal curve segments, Indicates the target pollution diffusion direction of the area to be tested, Indicates the direction from the center of atmospheric pollution to the l The direction of the monitoring position corresponding to the sensor with abnormal curve segment, express and The angle of express The cosine value of is not zero, l Indicates the number of sensors with abnormal curve segments at a certain moment. Along the pollution diffusion direction, the faster the pollution index decreases, the greater the degree. Therefore, the angle The smaller it is, the smaller the reduction in the air pollution index is. Indicates the moment l The monitoring position corresponding to the sensor with abnormal curve segment and the l The difference between the atmospheric pollution corresponding to all adjacent positions corresponding to the monitoring position corresponding to the sensor with an abnormal curve segment is not zero. The smaller the angle The smaller the air pollution index before adjustment The larger the value, the higher the adjusted air pollution index. The bigger.

[0106] In some embodiments, the air pollution index may be Normalize to (0,1).

[0107] Step 106, in response to the adjusted air pollution index being greater than the warning threshold, outputting warning information, the warning information including the adjusted air pollution index greater than the warning threshold and the monitoring location corresponding to the adjusted air pollution index greater than the warning threshold.

[0108] If the adjusted air pollution index is greater than the warning threshold, it means that the air pollution situation at the monitoring location is not good and an early warning is needed so that it can be given special attention and staff can take prevention and control measures in a timely manner.

[0109] In some embodiments, the warning threshold may be 0.8.

[0110] In summary, the real-time monitoring method of ecological environment data based on big data processing provided by the present invention can analyze the contribution of index data of multiple sensors at different monitoring locations in the measured area to the atmospheric pollution situation, and dynamically adjust the atmospheric pollution index of a certain monitoring location in combination with the pollution diffusion direction, thereby reducing the impact of environmental factors on sensor detection and improving the accuracy of atmospheric pollution situation judgment.

[0111] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0112] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A real-time monitoring method for ecological environment data based on big data processing, characterized in that: The method comprises: Step 101, obtaining environmental monitoring data of multiple sensors at multiple monitoring positions in a test area, establishing a plane rectangular coordinate system for the environmental monitoring data, and drawing an environmental monitoring data curve, wherein the environmental monitoring data includes time data and index data corresponding to the time data, and the horizontal axis of the plane rectangular coordinate system represents time, and the vertical axis represents the index; Step 102, for a certain sensor, in response to the abnormal index of the indicator data of the sensor in a certain period of time at the current position being greater than the abnormal threshold, determining that the curve segment corresponding to the period of time is an abnormal curve segment; Step 103, determining the correlation between the index data of the sensor of the current monitoring position in the time period and the index data of other sensors in the corresponding time period of the time period; Step 104, determining the air pollution index of the current monitoring location at the moment according to the index data of the multiple sensors at the current monitoring location at a certain moment and the correlation between the index data of the multiple sensors at the current monitoring location; Step 105, determining the original pollution diffusion direction and the pollution diffusion index corresponding to the original pollution diffusion direction according to the air pollution indexes of multiple monitoring locations in the test area at a certain moment, taking the original pollution diffusion direction corresponding to the maximum pollution diffusion index as the target pollution diffusion direction, and adjusting the air pollution index based on the target pollution diffusion direction to obtain an adjusted air pollution index; Step 106, in response to the adjusted air pollution index being greater than the warning threshold, outputting warning information, the warning information including the adjusted air pollution index being greater than the warning threshold and the monitoring location corresponding to the adjusted air pollution index being greater than the warning threshold; The corresponding time period of the other sensors in this time period is the time period corresponding to the curve segment whose central time data of multiple curve segments of the environment monitoring curve of the other sensors is closest to the central time data of this time period, and the step 103 includes: Determine the similarity between the index data of a certain sensor at the current monitoring position in a certain period of time and the index data of other sensors at the current monitoring position except the sensor in a corresponding period of time of the period of time according to the abnormal index of the index data of a certain sensor at the current monitoring position in a certain period of time and the index data of other sensors at the current monitoring position except the sensor in a corresponding period of time of the period of time; Determine the correlation between the index data of the sensor at the current monitoring location and the index data of other sensors according to the similarity between all curve segments in the environmental monitoring curve of the sensor at the current monitoring location and the corresponding time periods in the environmental monitoring curves of other sensors at the current monitoring location except the sensor, the number of curve segments determined as abnormal curve segments in the environmental monitoring data curve of the sensor at the current monitoring location, and the average of the number of curve segments determined as abnormal curve segments in the environmental monitoring data curves of other sensors at the current monitoring location; According to the following formula, determine the similarity between the index data of the sensor of the current monitoring position in the time period and the index data of other sensors of the current monitoring position except the sensor of the current monitoring position in the corresponding time period of the time period: In the formula, Indicates the current monitoring position of a certain sensor in the j The indicator data in the time period is compared with other sensors in the current monitoring location in j The similarity index of the indicator data in the corresponding period, Indicates the number of other sensor types at the current monitoring location except this sensor. Indicates the type of sensor at the current monitoring location. j The abnormal index within a period of time, Indicates the current monitoring location. z The sensor is j The abnormal index of each period corresponds to the period. z Indicates the type and serial number of other sensors at the current monitoring location except this sensor; According to the following formula, the correlation between the indicator data of the sensor at the current monitoring location and the indicator data of other sensors is determined: In the formula, Indicates the correlation index between the indicator data of a certain sensor at the current monitoring location and the indicator data of other sensors. It represents the average of the similarity indexes of all curve segments in the environmental monitoring curve of the sensor at the current monitoring location and the corresponding time periods in the environmental monitoring curves of other sensors at the current monitoring location. Indicates the minimum value of the similarity index between all curve segments in the environmental monitoring curve of the sensor at the current monitoring location and the corresponding time periods in the environmental monitoring curves of other sensors at the current monitoring location, represents the number of curve segments determined as abnormal curve segments in the environmental monitoring data curve of the sensor at the current monitoring location, represents the average value of the number of curve segments determined as abnormal curve segments in the environmental monitoring data curves of other sensors at the current monitoring location, i Indicates the type and serial number of the sensor at the current monitoring location; According to the following formula, determine the air pollution index at the current monitoring location at this moment: In the formula, Indicates k The air pollution index of a monitoring location at a certain time, Indicates k The monitoring location at this moment h The indicator data of each sensor, Indicates k The number of sensors at each monitoring location, Indicates k The monitoring location h The correlation index of each sensor, Indicates k The mean value of the correlation index of all sensors at a monitoring location, h Indicates k The number of sensors at each monitoring location; Step 105 includes: The monitoring position corresponding to the maximum value of the air pollution index of multiple monitoring positions in the measured area at a certain moment is taken as the air pollution center, the air pollution center is taken as the starting point, and the direction in which the air pollution index of multiple monitoring positions in the measured area at a certain moment gradually decreases is taken as the original pollution diffusion direction, and the monitoring position corresponding to the maximum value of the air pollution index of multiple monitoring positions in the measured area at a certain moment and the monitoring position in the direction in which the air pollution index of multiple monitoring positions in the measured area at a certain moment gradually decreases are all valid monitoring points; Determine the pollution diffusion index corresponding to the original pollution diffusion direction; The original pollution diffusion direction corresponding to the maximum value of the pollution diffusion index is taken as the target pollution diffusion direction; Adjusting the air pollution index based on the target pollution diffusion direction; The pollution diffusion index corresponding to the original pollution diffusion direction is determined according to the following formula: In the formula, is the pollution diffusion index corresponding to the current original pollution diffusion direction, Indicates the number of effective monitoring points in the current original pollution diffusion direction, Represents the number of all monitoring locations adjacent to the current original pollution diffusion direction, q represents the air pollution index corresponding to the air pollution center, Indicates the air pollution index of the last valid monitoring point in the current original pollution diffusion direction; According to the following formula, the air pollution index is adjusted based on the target pollution diffusion direction: In the formula, Indicates a moment l The atmospheric pollution index after the monitoring position corresponding to the sensor with abnormal curve segment is adjusted. Indicates the moment l The air pollution index at the monitoring location corresponding to the sensor with abnormal curve segment, Indicates the moment l The average value of the air pollution index corresponding to all the locations adjacent to the monitoring location corresponding to the sensor with an abnormal curve segment, Indicates the target pollution diffusion direction of the area to be tested, Indicates the direction from the center of atmospheric pollution to the l The direction of the monitoring position corresponding to the sensor with abnormal curve segment, express and The angle of express The cosine value of l Indicates the number of sensors with abnormal curve segments at a certain moment.

2. The real-time monitoring method of ecological environment data based on big data processing according to claim 1 is characterized in that: Step 102 includes: The environmental monitoring data curve of each sensor among the multiple sensors is divided into a plurality of curve segments by using an APCA algorithm, wherein the curve segments include index data of different time periods; For a certain sensor, the abnormal index of the indicator data of the sensor at the current monitoring location in different time periods is determined based on the difference in the indicator data of the sensor at the current monitoring location in different time periods, and the difference between the environmental monitoring data of the sensor at the current monitoring location and the sensors at other monitoring locations in similar time periods; In response to the abnormal index of the indicator data of the sensor at the current position in a certain period of time being greater than the abnormal threshold, it is determined that the curve segment corresponding to the period of time is an abnormal curve segment.

3. The real-time monitoring method of ecological environment data based on big data processing according to claim 2 is characterized in that: According to the following formula, the abnormal index of the indicator data of the sensor at the current location in different time periods is determined: In the formula, Indicates the current monitoring position of a certain sensor in the j The abnormal index within a period of time, Indicates the type of sensor at the current monitoring location. j The average value of the indicator data within a period of time, Indicates the mean value of all indicator data in the environmental monitoring curve of this sensor at the current monitoring location, Indicates the type of sensor at the current monitoring location. j The variance of the indicator data within a period, The multiple curve segments of the environmental monitoring curves of the sensor at all monitoring locations are the same as the first curve segment of the sensor at the current monitoring location. j The average of the duration of the corresponding time period of each time period, the multiple curve segments of the environmental monitoring curves of the sensor of the type at all monitoring locations corresponding to the first curve segment of the environmental monitoring curve of the sensor at the current monitoring location j The time period corresponds to the central time data of multiple curve segments of the environmental monitoring curve of this type of sensor at all monitoring locations and the j The time period corresponding to the curve segment closest to the central time data of each time period, Indicates the type of sensor at the current monitoring location. j The duration of a period, Indicates the type of sensor at the current monitoring location. j The maximum value of the indicator data in the period, Indicates the number of sensors of this type at other monitoring locations except the current monitoring location. j The average value of the indicator data in the corresponding period. j Indicates the sequence number of the time period.

Images